A method and device for optimizing a traffic network based on a large model

Abstract

The application particularly relates to a method and device for optimizing a traffic network based on a large model. The method and device for optimizing the traffic network based on the large model collect traffic data, perform preprocessing, adopt a Transformer model framework, train the traffic data in a manner combining unsupervised learning and reinforcement learning to predict future traffic states, adopt a traffic flow prediction model based on an LSTM and a knowledge graph to intelligently adjust a traffic signal light control strategy by using a traffic signal light timing intelligent optimization algorithm based on a Grey Model model according to a traffic flow prediction value, optimize traffic flow distribution, and realize dynamic optimization of the traffic network. The method and device for optimizing the traffic network based on the large model can significantly improve the efficiency and safety of a city traffic network, an expressway and a public transportation system by intelligently adjusting the traffic signal light control strategy and optimizing the traffic flow distribution through real-time analysis of the traffic data to realize the dynamic optimization of the traffic network.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of large models, in particular to a method and device for optimizing a traffic network based on a large model. BACKGROUND

[0002] With the rapid development of urbanization, traffic congestion has become a common problem faced by major cities around the world. Traditional traffic management methods, such as timed signal control and manual scheduling, have been difficult to meet the growing demand for transportation.

[0003] In recent years, the rapid development of artificial intelligence technology, especially the application of large models, has provided a new solution for traffic network optimization. Large models have made significant achievements in image recognition, natural language processing, and other fields due to their powerful data processing capabilities and deep learning capabilities, and their application in traffic network optimization has shown great potential.

[0004] In order to optimize the traffic network, improve traffic efficiency, reduce congestion, and improve travel safety, the present application proposes a method and device for optimizing a traffic network based on a large model. SUMMARY

[0005] The present application provides a simple and efficient method and device for optimizing a traffic network based on a large model to overcome the shortcomings of the prior art.

[0006] The present application is achieved by the following technical solutions:

[0007] A method for optimizing a traffic network based on a large model, comprising the following steps:

[0008] Step S1, data collection and feature extraction

[0009] Collect traffic flow monitoring data, weather information, and custom special event information related to traffic, and preprocess the collected data, including missing value processing, normalization processing, and time window division of time series data;

[0010] Use the self-attention mechanism of the Transformer model framework to process sequence data, and combine unsupervised learning and reinforcement learning to train the preprocessed data to predict future traffic conditions;

[0011] Step S2, traffic flow prediction model based on LSTM and knowledge graph

[0012] Step S2.1, collect traffic flow data, including historical traffic flow, road tolls, points of interest POI, and meteorological data, design static and dynamic city traffic knowledge graphs combining road traffic information and external factors to capture semantic relationships between road traffic information and external factors;

[0013] Step S2.2, input the urban traffic knowledge graph into the relation evolution graph convolutional neural network RE-GCN, and use the relation evolution graph convolutional neural network RE-GCN to perform knowledge embedding on the knowledge graph;

[0014] Step S2.3, use the long short-term memory network LSTM to perform traffic flow prediction and capture the spatio-temporal relationship of the traffic flow data;

[0015] Step S2.4, fuse the traffic flow data and the extracted information in the urban traffic knowledge graph, and then input the spatio-temporal multi-graph convolution module for training to extract spatio-temporal features;

[0016] Step S2.5, output the traffic flow prediction value through the full connection layer of the traffic flow prediction model, and evaluate the performance of the traffic flow prediction model on the real traffic flow data set;

[0017] Step S3, according to the traffic flow prediction value, use the traffic signal timing intelligent optimization algorithm based on the Grey Model to intelligently adjust the traffic signal control strategy, optimize the traffic flow distribution, and realize the dynamic optimization of the traffic network.

[0018] In step S1, traffic data is collected from three data sources, namely, monitoring cameras, sensors and GPS, to obtain a comprehensive traffic network view;

[0019] The mean filling method is used to process the missing values in the data; the input data is normalized to make the feature values of different dimensions have the same scale; and the time series data is self-defined to be divided into appropriate time windows to provide context information;

[0020] Key features are extracted from the preprocessed data, including traffic flow, speed and accident information.

[0021] In step S3, the traffic signal timing intelligent optimization algorithm based on the Grey Model is used to intelligently adjust the traffic signal control strategy, and the steps are as follows:

[0022] Step S3.1, collect historical traffic flow data recorded in 15-minute units; use the cumulative generation method to perform a cumulative operation on the original data to form a new data sequence;

[0023] Step S3.2, establish a Grey Model(1,1) model, and fit the model parameters by the least squares method;

[0024] Step S3.3, comprehensively consider the actual delay, effective green time and saturation factors to establish a fitness function;

[0025] Step S3.4, the timing of traffic lights is optimized by using a genetic algorithm, a plurality of signal timing schemes are randomly generated as initial populations, and the fitness of each scheme is evaluated according to a set objective function;

[0026] Step S3.5, a new generation of populations is generated through roulette selection, crossover and mutation operations, and iteration is performed until a custom-defined termination condition is reached.

[0027] The intelligent optimization algorithm for traffic light timing based on the Grey Model model has a built-in adaptive learning mechanism, which can dynamically adjust the learning rate and model parameters according to real-time traffic conditions to adapt to changes in traffic flow.

[0028] An apparatus for optimizing a traffic network based on a large model, comprising a data collection and feature extraction module, a traffic flow prediction model, and an intelligent optimization algorithm module;

[0029] The data collection and feature extraction module is responsible for collecting traffic flow monitoring data, weather information, and custom special event information related to traffic, and preprocessing the collected data, including missing value processing, normalization processing, and time window division of time series data.

[0030] The self-attention mechanism of the Transformer model framework is used to process sequence data, and the preprocessed data is trained by combining unsupervised learning and reinforcement learning to predict future traffic conditions.

[0031] The traffic flow prediction model is responsible for traffic flow prediction based on LSTM and knowledge graph.

[0032] The intelligent optimization algorithm module is responsible for intelligently adjusting the traffic signal light control strategy based on the traffic flow prediction value using the intelligent optimization algorithm for traffic signal light timing based on the Grey Model model, optimizing traffic flow distribution, and achieving dynamic optimization of the traffic network.

[0033] The data collection and feature extraction module collects traffic data from three data sources: monitoring cameras, sensors, and GPS, to obtain a comprehensive view of the traffic network.

[0034] The missing values in the data are processed using the mean filling method; the input data is normalized to have the same scale for features with different dimensions; and the time series data is divided into appropriate time windows to provide context information.

[0035] Key features are extracted from the preprocessed data, including traffic flow, speed, and accident information.

[0036] The traffic flow prediction model performs traffic flow prediction, which is implemented as follows:

[0037] Step S2.1, collect traffic flow data, including historical traffic flow, road portal, point of interest POI and meteorological data, design static and dynamic urban traffic knowledge graph combining road traffic information and external factors, for capturing semantic relationship of road traffic information and external factors;

[0038] Step S2.2, knowledge embedding of knowledge graph using relation evolution graph convolutional neural network RE-GCN, inputting the urban traffic knowledge graph into the relation evolution graph convolutional neural network RE-GCN to realize knowledge embedding;

[0039] Step S2.3, using long short-term memory network LSTM for traffic flow prediction, capturing the spatio-temporal relationship of traffic flow data;

[0040] Step S2.4, fuse the traffic flow data with the information extracted from the urban traffic knowledge graph, and then input into the spatio-temporal multi-graph convolution module for training to extract spatio-temporal features;

[0041] Step S2.5, output the traffic flow prediction value through the full connection layer of the traffic flow prediction model, and evaluate the performance of the traffic flow prediction model on the real traffic flow data set.

[0042] The intelligent optimization algorithm module adopts a traffic signal lamp timing intelligent optimization algorithm based on a Grey Model model to intelligently adjust the traffic signal lamp control strategy, and the implementation steps are as follows:

[0043] Step S3.1, collect historical traffic flow data, record in 15 minutes units; use cumulative generation method to accumulate the original data once, form a new data sequence;

[0044] Step S3.2, establish a Grey Model(1,1) model, and fit the model parameters by least squares method;

[0045] Step S3.3, considering the actual delay, effective green time and saturation factor, establish the fitness function;

[0046] Step S3.4, adopt genetic algorithm to optimize the timing of traffic signal lamp, randomly generate several signal lamp timing schemes as initial population, evaluate the fitness of each scheme according to the set objective function;

[0047] Step S3.5, generate a new generation of population through roulette selection, crossover and mutation operations, iterate until the termination condition set by the user is reached.

[0048] The traffic signal lamp timing intelligent optimization algorithm based on the Grey Model model has a built-in adaptive learning mechanism, which can dynamically adjust the learning rate and model parameters according to real-time traffic conditions, so as to adapt to the changes of traffic flow.

[0049] An equipment for optimizing a traffic network based on a large model, characterized by comprising a memory and a processor; the memory is used for storing a computer program, and the processor is used for implementing the method steps when the computer program is executed.

[0050] A readable storage medium, characterized by: the readable storage medium has a computer program stored thereon, and the computer program is executed by a processor to implement the method steps.

[0051] The method and device for optimizing a traffic network based on a large model have the advantages that: by analyzing traffic data in real time, the control strategy of the traffic signal lamp is intelligently adjusted, the traffic flow distribution is optimized, the dynamic optimization of the traffic network is realized, and the efficiency and safety of the urban traffic network, the expressway and the public transportation system can be significantly improved. BRIEF DESCRIPTION OF DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced below. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0053] FIG. 1 is a schematic diagram of a traffic flow prediction method of the present application. Figure 1 FIG. 1 is a schematic diagram of a traffic flow prediction method of the present application.

[0054] FIG. 2 is a schematic diagram of an intelligent adjustment method of a traffic signal lamp control of the present application. Figure 2 FIG. 2 is a schematic diagram of an intelligent adjustment method of a traffic signal lamp control of the present application. DETAILED DESCRIPTION

[0055] In order to make the person skilled in the art better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be described in detail below. Obviously, the described embodiments are only some of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0056] The method for optimizing a traffic network based on a large model comprises the following steps:

[0057] Step S1, data collection and feature extraction

[0058] Collect traffic flow monitoring data, weather information and custom special event information related to traffic, preprocess the collected data, including missing value processing, normalization processing and time window division of time series data;

[0059] Adopt the self-attention mechanism of the Transformer model framework to process sequence data, and train the preprocessed data in a combination of unsupervised learning and reinforcement learning to predict future traffic conditions;

[0060] Step S2, traffic flow prediction model based on LSTM and knowledge graph

[0061] Step S2.1, collect traffic flow data, including historical traffic flow, road portal, point of interest POI and meteorological data, design static and dynamic urban traffic knowledge graph combining road traffic information and external factors, for capturing semantic relationship of road traffic information and external factors;

[0062] Step S2.2, input the city traffic knowledge graph into the relation evolution graph convolutional neural network RE-GCN, and use the relation evolution graph convolutional neural network RE-GCN to perform knowledge embedding on the knowledge graph;

[0063] Step S2.3, use the long short-term memory network LSTM to predict traffic flow, and capture the spatio-temporal relationship of traffic flow data;

[0064] Step S2.4, fuse the traffic flow data with the information extracted from the city traffic knowledge graph, and then input into the spatio-temporal multi-graph convolution module for training to extract spatio-temporal features;

[0065] Step S2.5, output the traffic flow prediction value through the full connection layer of the traffic flow prediction model, and evaluate the performance of the traffic flow prediction model on the real traffic flow data set;

[0066] Step S3, according to the traffic flow prediction value, adopt the traffic signal timing intelligent optimization algorithm based on Grey Model to intelligently adjust the traffic signal control strategy, optimize the traffic flow distribution, and realize the dynamic optimization of the traffic network.

[0067] In step S1, traffic data is collected from three data sources of monitoring cameras, sensors and GPS to obtain a comprehensive traffic network view;

[0068] The missing values in the data are processed by the mean filling method; the input data are normalized to have the same scale for different dimensional characteristic values; and the time series data are self-defined to be divided into appropriate time windows to provide context information;

[0069] Key features are extracted from the pre-processed data, including traffic flow, speed, and accident information.

[0070] In step S3, the traffic signal timing intelligent optimization algorithm based on Grey Model model is used to intelligently adjust the traffic signal control strategy, and the implementation steps are as follows:

[0071] Step S3.1, collect historical traffic flow data, record in 15 minutes unit; use cumulative generation method to accumulate the original data once, form new data sequence;

[0072] Step S3.2, establish Grey Model(1,1) model, fit model parameters by least square method;

[0073] Step S3.3, considering the actual delay, effective green time and saturation factor, establish fitness function;

[0074] Step S3.4, adopt genetic algorithm to optimize the timing of traffic signal, randomly generate several signal timing schemes as initial population, evaluate the fitness of each scheme according to the set objective function;

[0075] Step S3.5, generate new population through roulette selection, crossover and mutation operation, iterate until the termination condition is reached.

[0076] The traffic signal timing intelligent optimization algorithm based on Grey Model model has built-in adaptive learning mechanism, which can dynamically adjust learning rate and model parameters according to real-time traffic conditions to adapt to the changes of traffic flow.

[0077] The traffic signal timing intelligent optimization algorithm based on Grey Model model can predict traffic flow in milliseconds and adjust traffic control strategy in real time.

[0078] The device for optimizing traffic network based on large model includes data collection and feature extraction module, traffic flow prediction model and intelligent optimization algorithm module;

[0079] The data collection and feature extraction module is responsible for collecting traffic flow monitoring data, weather information and custom special event information related to traffic, preprocessing the collected data, including missing value processing, normalization processing and time window division of time series data;

[0080] The self-attention mechanism of the Transformer model framework is used to process sequence data, and the pre-processed data is trained by combining unsupervised learning and reinforcement learning to predict future traffic conditions;

[0081] The traffic flow prediction model is responsible for traffic flow prediction based on LSTM and knowledge graph;

[0082] The intelligent optimization algorithm module is responsible for intelligently adjusting the traffic signal control strategy by using the traffic signal timing intelligent optimization algorithm based on the Grey Model, optimizing traffic flow distribution, and realizing dynamic optimization of the traffic network.

[0083] The data collection and feature extraction module collects traffic data from three data sources: surveillance cameras, sensors, and GPS, to obtain a comprehensive view of the traffic network;

[0084] The mean filling method is used to handle missing values in the data; the input data is normalized to have the same scale for different dimensional feature values; and the time series data is divided into appropriate time windows to provide context information;

[0085] Key features are extracted from the preprocessed data, including traffic flow, speed, and accident information.

[0086] The traffic flow prediction model performs traffic flow prediction, and the implementation steps are as follows:

[0087] Step S2.1, collect traffic flow data, including historical traffic flow, road tolls, points of interest POI, and meteorological data, combine road traffic information and external factors to design static and dynamic urban traffic knowledge graphs, which are used to capture the semantic relationships of road traffic information and external factors;

[0088] Step S2.2, use the relation evolution graph convolutional neural network RE-GCN to perform knowledge embedding of the knowledge graph, input the urban traffic knowledge graph into the relation evolution graph convolutional neural network RE-GCN to realize knowledge embedding;

[0089] Step S2.3, use the long short-term memory network LSTM to perform traffic flow prediction to capture the spatio-temporal relationship of traffic flow data;

[0090] Step S2.4, fuse the traffic flow data with the extracted information in the urban traffic knowledge graph, and then input it into the spatio-temporal multi-graph convolution module for training to extract spatio-temporal features;

[0091] Step S2.5, output the traffic flow prediction value through the full connection layer of the traffic flow prediction model, and evaluate the performance of the traffic flow prediction model on the real traffic flow data set.

[0092] The intelligent optimization algorithm module uses the traffic signal timing intelligent optimization algorithm based on the Grey Model to intelligently adjust the traffic signal control strategy, and the implementation steps are as follows:

[0093] Step S3.1, collect historical traffic flow data, record in 15 minutes units; use cumulative generation method to accumulate original data once, form new data sequence;

[0094] Step S3.2, establish Grey Model(1,1) model, fit model parameters by least square method;

[0095] Step S3.3, comprehensively consider actual delay, effective green time and saturation factor, establish fitness function;

[0096] Step S3.4, adopt genetic algorithm to optimize traffic signal timing, randomly generate several signal timing schemes as initial population, evaluate fitness of each scheme according to set target function;

[0097] Step S3.5, generate new generation population through roulette selection, crossover and mutation operation, iterate until reach self-defined set termination condition.

[0098] The intelligent optimization algorithm for traffic signal timing based on Grey Model model has built-in adaptive learning mechanism, which can dynamically adjust learning rate and model parameters according to real-time traffic conditions to adapt to changes in traffic flow.

[0099] The device for optimizing traffic network based on large model includes a memory and a processor; the memory is used to store a computer program, and the processor is used to execute the computer program to realize the method steps described above.

[0100] The readable storage medium has a computer program stored thereon, and the computer program is executed by a processor to realize the method steps described above.

[0101] Compared with the prior art, the method and device for optimizing traffic network based on large model have the following characteristics:

[0102] (1) It can process and fuse data from different sources such as video monitoring, sensors, GPS, etc. to obtain a comprehensive view of the traffic network and realize multi-modal data fusion.

[0103] (2) It integrates adaptive learning mechanism, which can dynamically adjust learning rate and model parameters according to real-time traffic conditions to adapt to changes in traffic flow.

[0104] (3) It can predict traffic flow at millisecond level and adjust and optimize traffic control strategy in real time.

[0105] In terms of urban traffic network, by analyzing traffic flow and predicting congestion points, intelligent adjustment of signal control strategy can optimize traffic flow distribution and reduce congestion.

[0106] In terms of highway traffic, by predicting traffic flow and accident risk, real-time adjustment of speed limits and lane allocation can improve driving safety and efficiency.

[0107] For public transportation systems, by analyzing passenger flow and demand, the scheduling plan of buses and subways can be optimized to improve the efficiency of public transportation and passenger satisfaction.

[0108] The above-described embodiments are only one of the specific implementations of the present application, and any usual changes and substitutions made by those skilled in the art within the scope of the technical solutions of the present application should be included in the protection scope of the present application.

Claims

1. A method for optimizing a traffic network based on a large model, characterized in that: The method comprises the following steps: Step S1, data collection and feature extraction Collect traffic flow monitoring data, weather information and custom special event information related to traffic, and preprocess the collected data, including missing value processing, normalization processing and time window division of time series data; Use the self-attention mechanism of the Transformer model framework to process sequence data, and train the preprocessed data in a combination of unsupervised learning and reinforcement learning to predict future traffic conditions; Step S2, traffic flow prediction model based on LSTM and knowledge graph Step S2.1, collect traffic flow data, including historical traffic flow, road gate, point of interest POI and meteorological data, design static and dynamic urban traffic knowledge graph combining road traffic information and external factors to capture the semantic relationship of road traffic information and external factors; Step S2.2, input the city traffic knowledge graph into the relation evolution graph convolutional neural network RE-GCN, and use the relation evolution graph convolutional neural network RE-GCN to perform knowledge embedding on the knowledge graph; Step S2.3, use the long short-term memory network LSTM to predict traffic flow, and capture the spatio-temporal relationship of traffic flow data; Step S2.4, fuse the traffic flow data with the information extracted from the city traffic knowledge graph, and then input the spatio-temporal multi-graph convolution module for training to extract spatio-temporal features; Step S2.5, output the traffic flow prediction value through the full connection layer of the traffic flow prediction model, and evaluate the performance of the traffic flow prediction model on the real traffic flow data set; Step S3, according to the traffic flow prediction value, use the traffic signal timing intelligent optimization algorithm based on the Grey Model to intelligently adjust the traffic signal control strategy, optimize traffic flow distribution, and realize dynamic optimization of the traffic network.

2. The method for optimizing a traffic network based on a large model according to claim 1, characterized in that: In step S1, traffic data is collected from three data sources: monitoring cameras, sensors and GPS, to obtain a comprehensive view of the traffic network; The missing values in the data are processed using the mean filling method; the input data are normalized to have the same scale for feature values of different dimensions; and the time series data are divided into appropriate time windows to provide context information; Key features are extracted from the preprocessed data, including traffic flow, speed and accident information.

3. The method for optimizing traffic network based on large model according to claim 1, characterized in that: In step S3, the traffic signal timing intelligent optimization algorithm based on the Grey Model is used to intelligently adjust the traffic signal control strategy, and the steps are as follows: Step S3.1, collect historical traffic flow data recorded in 15-minute units; use the cumulative generation method to accumulate the original data once to form a new data sequence; Step S3.2, establish a Grey Model(1,1) model, and fit the model parameters by the least squares method; Step S3.3, consider the actual delay, effective green time and saturation factors to establish a fitness function; Step S3.4, the timing of traffic lights is optimized by using a genetic algorithm, a plurality of signal timing plans are randomly generated as an initial population, and the fitness of each plan is evaluated according to a set objective function; Step S3.5, a new generation population is generated through roulette selection, crossover and mutation operations, and iteration is performed until a custom-defined termination condition is reached.

4. The method for optimizing a traffic network based on a large model according to claim 3, characterized in that: The intelligent optimization algorithm for traffic light timing based on the Grey Model model has a built-in adaptive learning mechanism, which can dynamically adjust the learning rate and model parameters according to real-time traffic conditions to adapt to changes in traffic flow.

5. An apparatus for optimizing a traffic network based on a large model, characterized in that: It includes a data collection and feature extraction module, a traffic flow prediction model, and an intelligent optimization algorithm module. The data collection and feature extraction module is responsible for collecting traffic flow monitoring data, weather information, and custom special event information related to traffic, and preprocessing the collected data, including missing value processing, normalization processing, and time window division of time series data. The self-attention mechanism of the Transformer model framework is used to process sequence data, and unsupervised learning and reinforcement learning are combined to train the preprocessed data to predict future traffic conditions. The traffic flow prediction model is responsible for traffic flow prediction based on LSTM and knowledge graph; The traffic flow prediction model performs traffic flow prediction, and the implementation steps are as follows: Step S2.1, collect traffic flow data, including historical traffic flow, road checkpoints, points of interest POI, and meteorological data, design static and dynamic urban traffic knowledge graphs based on road traffic information and external factors, and use them to capture the semantic relationships between road traffic information and external factors; Step S2.2, use the relation evolution graph convolutional neural network RE-GCN to perform knowledge embedding, input the urban traffic knowledge graph into the relation evolution graph convolutional neural network RE-GCN, and realize knowledge embedding; Step S2.3, use the long short-term memory network LSTM to perform traffic flow prediction and capture the spatio-temporal relationship of traffic flow data; Step S2.4, fuse the traffic flow data with the information extracted from the urban traffic knowledge graph, and then input it into the spatio-temporal multi-graph convolution module for training to extract spatio-temporal features; Step S2.5, output the traffic flow prediction value through the fully connected layer of the traffic flow prediction model, and evaluate the performance of the traffic flow prediction model on the real traffic flow data set; The intelligent optimization algorithm module is responsible for intelligently adjusting the traffic signal control strategy based on the traffic flow prediction value, using the intelligent optimization algorithm for traffic signal timing based on the Grey Model model, optimizing traffic flow distribution, and realizing dynamic optimization of the traffic network.

6. The device for optimizing a traffic network based on a large model according to claim 5, characterized in that: The data collection and feature extraction module collects traffic data from three data sources: surveillance cameras, sensors, and GPS, to obtain a comprehensive view of the traffic network; The missing values in the data are processed using the mean filling method; the input data are normalized to have the same scale; and the time series data are divided into appropriate time windows to provide context information. Key features are extracted from the pre-processed data, including traffic flow, speed, and accident information.

7. The device for optimizing a traffic network based on a large model according to claim 5, characterized in that: The intelligent optimization algorithm module adopts a traffic signal timing intelligent optimization algorithm based on a Grey Model model to intelligently adjust the traffic signal control strategy, and the implementation steps are as follows: Step S3.1, collect historical traffic flow data, record in 15 minutes units; use the cumulative generation method to accumulate the original data once to form a new data sequence; Step S3.2, establish a Grey Model(1,1) model, and fit the model parameters by the least squares method; Step S3.3, comprehensively consider the actual delay, effective green time and saturation factors, and establish a fitness function; Step S3.4, use a genetic algorithm to optimize the timing of the traffic signal, randomly generate several signal timing schemes as the initial population, and evaluate the fitness of each scheme according to the set objective function; Step S3.5, generate a new generation of population through roulette selection, crossover and mutation operations, and iterate until the self-defined termination condition is reached.

8. The device for optimizing a traffic network based on a large model according to claim 6, characterized in that: The traffic signal timing intelligent optimization algorithm based on the Grey Model model has a built-in adaptive learning mechanism, which can dynamically adjust the learning rate and model parameters according to the real-time traffic conditions to adapt to the changes in traffic flow.

9. An apparatus for optimizing a traffic network based on a large model, the apparatus comprising: It comprises a memory and a processor; the memory is used to store a computer program, and the processor is used to execute the computer program to realize the method of any one of claims 1-4.

Images