A blockchain-based expressway large-scale traffic data collaborative scheduling method and device, a terminal device, and a storage medium

Abstract

The application is suitable for the field of block chain, and provides a highway large-scale traffic data collaborative scheduling method based on block chain, which comprises the following steps: a server acquires a traffic state prediction model of each highway traffic data producer node on a highway traffic data block chain of a target area based on updated traffic event data training; based on the traffic state prediction model, a global traffic state prediction model of the target area is acquired; and based on the global traffic state prediction model and traffic live data uploaded by a user end node, a traffic state corresponding to the traffic live data is predicted. By using the method, the traffic state prediction model parameters of each highway traffic data producer node locally trained are transmitted through the traffic data block chain to construct the global traffic state prediction model, so that the accurate and effective large-scale highway traffic data collaborative scheduling is realized under the condition that the data of each highway traffic data producer node is not exported.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of blockchains, and particularly relates to a method and device for coordinating and scheduling large-scale highway traffic data based on a blockchain, a terminal device, and a storage medium. BACKGROUND

[0002] With the acceleration of urbanization, traffic congestion problems are becoming increasingly serious, posing a huge challenge to urban operation and resident travel. In order to effectively solve the problem of traffic congestion, it is necessary to analyze and optimize large-scale highway traffic data in real time to achieve the rational allocation and coordinated scheduling of traffic resources, so that the traffic system is safer, more efficient, and more convenient. Due to the wide popularity of intelligent devices, most modern cars are equipped with on-board units, sensing functions, global positioning system receivers, and dedicated short-range communication modules, which allow vehicles to communicate with each other and with the surrounding environment, such as roadside units, traffic signs, pedestrians, etc. Vehicles can detect traffic conditions and share them with other vehicles to improve the traffic system. For example, the GPS and speed of a vehicle can be used to suggest optimized route recommendations to minimize traffic congestion. In order to achieve the coordinated scheduling of large-scale highway traffic data, it is crucial to optimize the dissemination of highway traffic data and its secure storage and management, which is essential for establishing a reliable road traffic record history to ensure data integrity, data traceability and availability, and vehicle privacy.

[0003] However, existing highway traffic data scheduling methods have the following problems, making them difficult to be effectively applied in practice. First, most existing highway traffic data scheduling methods are centralized, and these technologies rely on a central cloud to store and manage collected highway traffic data. However, this centralized architecture is prone to privacy problems and has bandwidth limitations, which can lead to serious network congestion problems. The centralized architecture is also vulnerable to attacks due to its single point of failure vulnerability. Second, existing highway traffic data coordination technologies often ignore the data island problem. In fact, since these highway traffic data are generated by multiple independent individuals, these individuals are reluctant to share raw data for scheduling analysis in order to protect their own data privacy. This large-scale data island mode greatly increases the difficulty of highway traffic data coordination and scheduling, making it difficult to accurately and effectively conduct data analysis, thereby leading to ineffective scheduling strategies. Third, existing highway traffic data scheduling methods ignore the scalability problem of task modules. Most existing blockchain-based technologies face scalability limitations, such as high confirmation latency and high storage and computing costs, which hinder the practical application of the technology. SUMMARY

[0004] This application provides a method, apparatus, terminal equipment, and storage medium for collaborative scheduling of large-scale traffic data on highways based on blockchain.

[0005] In a first aspect, embodiments of this application provide a blockchain-based method for collaborative scheduling of large-scale highway traffic data, comprising: acquiring traffic state prediction models trained by each highway traffic data producer node on the highway traffic data blockchain of a target area based on updated traffic event data; acquiring a global traffic state prediction model of the target area based on the traffic state prediction model; and predicting the traffic state corresponding to the traffic real-time data based on the global traffic state prediction model and the real-time traffic data uploaded by the highway traffic data user terminal nodes.

[0006] In one possible implementation of the first aspect, the traffic state prediction model trained by each highway traffic data producer node based on updated traffic event data includes the following steps: acquiring updated traffic flow event data from the target highway traffic data producer; training a pre-existing traffic state prediction model using the updated traffic event data; and acquiring the updated traffic state prediction model.

[0007] In one possible implementation of the first aspect, the traffic state prediction model trained by each highway traffic data producer node based on updated traffic event data further includes the following steps:

[0008] The updated traffic state prediction model is encrypted using the first encryption function to obtain the encrypted prediction model.

[0009] In one possible implementation of the first aspect, before obtaining the global traffic state prediction model for the target area based on the traffic state prediction model, the following steps are included: decrypting the encrypted prediction model to obtain the model parameters of the updated traffic state prediction model; generating a new block on the highway traffic data blockchain based on the model parameters; verifying the new block to obtain a valid block; and adding the valid block to the highway traffic data blockchain to obtain a new highway traffic data blockchain.

[0010] In a possible implementation manner of the first aspect, the verifying the new block, obtaining a valid block, comprises the following steps: obtaining a master node corresponding to the new block, and sending a verification signal to the master node, so that the master node broadcasts the new block to a slave node; the slave node refers to a highway traffic data producer node other than the master node; when a first preset number of slave nodes verify that the new block passes, a voting start signal is sent to the slave nodes, so that the slave nodes vote for the new block; when any of the slave nodes receives a second preset number of voting pass signals, it is determined that the new block is valid.

[0011] In a possible implementation manner of the first aspect, the obtaining the global traffic state prediction model of the target area based on the traffic state prediction model comprises the following steps: analyzing model parameters of an updated traffic state prediction model in the valid block; obtaining a federated model based on traffic state prediction models generated by the highway traffic data producer nodes; and updating the federated model according to the model parameters of the updated traffic state prediction model to obtain an updated global traffic state prediction model.

[0012] In a possible implementation manner of the first aspect, the predicting the traffic state corresponding to the traffic live data based on the global traffic state prediction model and the traffic live data uploaded by the highway traffic data user end node comprises the following steps: inputting the traffic live data uploaded by the highway traffic data user end node into the global traffic state prediction model to predict the traffic state corresponding to the traffic live data.

[0013] In a possible implementation manner of the first aspect, the verifying the new block, obtaining a valid block, comprises the following steps: obtaining a master node corresponding to the new block, and sending a verification signal to the master node, so that the master node broadcasts the new block to a slave node; the slave node refers to a highway traffic data producer node other than the master node; when a first preset number of slave nodes verify that the new block passes, a voting start signal is sent to the slave nodes, so that the slave nodes vote for the new block; when any of the slave nodes receives a second preset number of voting pass signals, it is determined that the new block is valid.

[0014] In a third aspect, the embodiments of the present application provide a computer readable storage medium, the computer readable storage medium storing a computer program, the computer program being executed by a processor to implement the following steps: obtaining a traffic state prediction model of each highway traffic data producer node on a highway traffic data blockchain of a target area, the traffic state prediction model being trained based on updated traffic event data; obtaining a global traffic state prediction model of the target area based on the traffic state prediction model; and predicting a traffic state corresponding to traffic live data uploaded by a highway traffic data user end node based on the global traffic state prediction model and the traffic live data.

[0015] In a fifth aspect, the embodiments of the present application provide a computer program product, when the computer program product is run on a terminal device, the terminal device executes the highway large-scale traffic data collaborative scheduling method based on a blockchain according to any one of the first aspect.

[0016] It can be understood that the beneficial effects of the second aspect to the fourth aspect can be referred to the related description in the first aspect, which will not be repeated here.

[0017] The beneficial effects of the embodiments of the present application compared with the prior art are: the highway large-scale traffic data collaborative scheduling method based on a blockchain, the server obtains a traffic state prediction model of each highway traffic data producer node on a highway traffic data blockchain of a target area, the traffic state prediction model being trained based on updated traffic event data; a global traffic state prediction model of the target area is obtained based on the traffic state prediction model; and a traffic state corresponding to traffic live data uploaded by a highway traffic data user end node is predicted based on the global traffic state prediction model and the traffic live data. The method uses the highway traffic data blockchain to deliver the traffic state prediction model parameters trained locally by each highway traffic data producer node to construct a global traffic state prediction model, thereby ensuring accurate and effective large-scale highway traffic data collaborative scheduling of each highway traffic data producer node without data export. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0019] Figure 1 is a flowchart of the highway large-scale traffic data collaborative scheduling method based on a blockchain in an embodiment of the present application;

[0020] Figure 2 is a flowchart of the block validity verification step in an embodiment of the present application. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical scheme and advantages of the present application clearer, the present application will be further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0022] In one embodiment, as shown in Figure 1 , a highway large-scale traffic data collaborative scheduling method based on a blockchain is provided, comprising the following steps:

[0023] S101, obtaining a traffic state prediction model trained by each traffic data producer node on the traffic data blockchain of the target area based on updated traffic event data.

[0024] Among them, the traffic data blockchain can be used on the highway, and the highway traffic data blockchain is composed of a chain composed of one after another blocks, each block containing each target traffic flow event data, and the target traffic flow event data containing a hash value, traffic event nature, traffic event description, traffic location, signature, data source and traffic event creation time.

[0025] It can be understood that the nodes existing on the highway traffic data blockchain can be divided into nodes processing data uploaded by highway traffic data producers and nodes processing data uploaded by highway traffic data user terminals; the highway traffic data producer can be a vehicle, a pedestrian, a signal lamp, etc., which can collect highway traffic data through sensors, cameras and other devices; the highway traffic data user terminal can be a traffic management department, a travel user, a traffic operator.

[0026] Specifically, each highway traffic data producer node trains the pre-trained traffic state prediction model based on the locally updated traffic event data to obtain an updated traffic state prediction model corresponding to the highway traffic data producer node; then the first encryption function is used to encrypt the updated traffic state prediction model to obtain an encrypted prediction model, and the encrypted prediction model is sent to the server.

[0027] S102, obtaining a global traffic state prediction model of the target area based on the traffic state prediction model.

[0028] Specifically, after receiving the encrypted prediction model, the server decrypts the encrypted prediction model to obtain the model parameters of the updated traffic state prediction model; based on the model parameters, it generates a new block on the highway traffic data blockchain; it verifies the new block to obtain a valid block; and it adds the valid block to the highway traffic data blockchain to obtain a brand new highway traffic data blockchain.

[0029] S103, based on the global traffic state prediction model and the real-time traffic data uploaded by the traffic data user terminal node, predicts the traffic state corresponding to the real-time traffic data.

[0030] Specifically, the real-time traffic data uploaded by user nodes on highways is input into the global traffic state prediction model to predict the traffic state corresponding to the real-time traffic data.

[0031] In this embodiment, the server obtains traffic state prediction models trained by each highway traffic data producer node on the highway traffic data blockchain of the target area based on updated traffic event data; based on the traffic state prediction models, it obtains a global traffic state prediction model for the target area; and based on the global traffic state prediction model and the real-time traffic data uploaded by the highway traffic data user nodes, it predicts the traffic state corresponding to the real-time traffic data. This method constructs a global traffic state prediction model by transmitting the parameters of the traffic state prediction models trained locally by each highway traffic data producer node through the highway traffic data blockchain, thereby ensuring accurate and effective large-scale highway traffic data collaborative scheduling for each highway traffic data producer node without requiring data to leave the database.

[0032] In one embodiment, the traffic state prediction model trained by each highway traffic data producer node based on the updated traffic event data further includes the following steps: encrypting the updated traffic state prediction model using a first encryption function to obtain an encrypted prediction model.

[0033] Specifically, it can be defined This is a collection of highway traffic data. For the first Traffic data for the highway ;definition This is a collection of highway traffic data sources. For the first One source of highway traffic data. ;definition A collection of highway traffic data producers. For the first A highway traffic data producer ;definition a highway traffic data user end set, a first highway traffic data user end, a second highway traffic data user end, ; define a function for obtaining , return the result of cleaning, encryption and hash processing; define a function for storing evidence on the chain, return the index and key on the blockchain; define a function for accessing , return the number of digital currencies or points paid; define a function for contribution , return the number of digital currencies or points obtained; define a highway traffic data sharing platform, which can be represented by the following formula: wherein , , , . In this embodiment, the server can use function to encrypt the traffic state prediction model to obtain an encrypted traffic state prediction model. Since the node obtains the traffic state prediction model according to the self-updated traffic flow event data locally, it is equivalent to decentralizing the traffic flow event data, which ensures the security of the traffic flow event data. At the same time, the traffic state prediction model obtained by the node is encrypted before being sent to the server, which further ensures the security of the traffic flow event data.

[0034] In an application embodiment, as shown, the encrypted prediction model is decrypted to obtain the model parameters of the updated traffic state prediction model, which includes the following steps:

[0035] S201, decrypt the encrypted prediction model to obtain the model parameters of the updated traffic state prediction model. Figure 2 S202, based on the model parameters, generate a new block on the traffic data blockchain.

[0036] Specifically, after decrypting the encrypted prediction model, the server parses the model parameters of the updated traffic state prediction model, and then generates a new block containing the model parameters according to the data format of the block.

[0037]

[0038] ​​​

[0039] S203, verifying the new block to obtain a valid block.

[0040] Specifically, the server obtains a primary node corresponding to the new block, and sends a verification signal to the primary node, so that the primary node broadcasts the new block to secondary nodes; the secondary nodes refer to expressway traffic data producer nodes other than the primary node; when more than a first preset number of secondary nodes verify that the new block passes, a voting start signal is sent to the secondary nodes, so that the secondary nodes vote on the new block; when any secondary node receives a second preset number of voting pass signals, it is determined that the new block is valid.

[0041] S204, adding the valid block to the traffic data block chain to obtain a new expressway traffic data block chain.

[0042] In this embodiment, the block chain is a linked list composed of blocks, each block containing a set of description data of traffic flow events (i.e. atomic data of the system) and a reference to the previous block, and consensus needs to be reached among members of the block chain network before a block can be added to the block chain. Only when a majority of nodes verify that the newly added block is valid can the new block be added to the block chain, thereby ensuring the privacy of the traffic flow event data.

[0043] In one embodiment, verifying the new block to obtain a valid block includes the following steps: obtaining a primary node corresponding to the new block, and sending a verification signal to the primary node, so that the primary node broadcasts the new block to secondary nodes; the secondary nodes refer to expressway traffic data producer nodes other than the primary node; when more than a first preset number of secondary nodes verify that the new block passes, a voting start signal is sent to the secondary nodes, so that the secondary nodes vote on the new block; when any secondary node receives a second preset number of voting pass signals, it is determined that the new block is valid.

[0044] Exemplarily, , , respectively represent the first block, the first verification message, the first voting message; respectively set , respectively represent the first primary node, the first secondary node; , represents that the primary node proposes a new block and broadcasts it to all secondary nodes; , represents that the secondary node verifies the received block and return a validation message ; , representing a sub-node voting block and return a voting message ; , , representing a judging block whether the block is valid, if more than 2 / 3 of the validation messages and voting messages are collected, the block is considered valid. The master node proposes a new highway traffic data block and broadcasts it to all sub-nodes ; after the sub-nodes receive the block , they perform validation, and if it passes, they return a validation message and broadcast it to all nodes; when the sub-nodes receive more than 2 / 3 of the validation messages, they vote, and if they agree, they return a voting message and broadcast it to all nodes; if the sub-nodes receive more than 2 / 3 of the voting messages, the block is considered valid and is added to the blockchain. For the confirmed valid block model, it will be merged into the server's global large model, and for the voting failed model, the model will not be federated. When the same highway traffic data producer's block is considered invalid for three consecutive times, it is considered malicious data, and the server will be punished, so that the highway traffic data producer cannot participate in block data aggregation and information acquisition for three consecutive times.

[0045] In an application embodiment, based on the traffic state prediction model, the global traffic state prediction model of the target area is obtained, including the following steps: analyzing the model parameters of the updated traffic state prediction model in the valid block; based on the traffic state prediction model generated by each highway traffic data producer node, a federated model is obtained; the federated model is updated according to the model parameters of the updated traffic state prediction model, and an updated global traffic state prediction model is obtained.

[0046] Among them, the federal modeling is based on the federal learning technology, and under the demand of meeting the compliance policy and data value protection of each participant, the service of model iteration and update is realized. Each participant of the federal model usually feeds back the encrypted model parameters of his own to the coordinator of the federal learning modeling, and then the coordinator aggregates each encrypted model parameter, and feeds back the aggregated parameter after aggregation to each participant for federal learning modeling. ​

[0047] Exemplarily, the server selects producers participating in model training according to factors such as geographical location, data quality, reputation of the highway traffic data producer, and trains the federated model; the parties train the traffic state prediction model locally, for example, a traffic management department of a city can use the traffic flow, road conditions, accident and other data collected by itself to train a model for predicting traffic congestion, an autonomous vehicle can use the road pass information obtained by itself to train its own model using a similar method, and share the model parameters, a road monitoring camera can use its own traffic condition information to train the model and share the model parameters; the parties send the encrypted model to the server after the trained model is encrypted locally using an encryption function.

[0048] The server aggregates all the received model parameters, and forms a new block based on the model parameters, and adds it to the block chain for aggregation and synchronization, so as to obtain a global traffic state prediction model based on the block chain.

[0049] In an application embodiment, the traffic live data uploaded by the user end node of the highway traffic data is input into the global traffic state prediction model to predict the traffic state corresponding to the traffic live data, including:

[0050] Specifically, when the global traffic state prediction model performs the prediction function, the trained traffic state prediction model is applied to the actual traffic scene, the real-time traffic live data or future traffic live data is input, and the prediction result is output and displayed to the user or decision maker.

[0051] Exemplarily, the collected massive heterogeneous traffic information data comes from different channels and platforms, such as sensors, satellite navigation, smart phones, social media, etc., including road network structure, traffic flow data, traffic event data, weather data, etc. Using the established global highway traffic data model, hidden features and patterns in the data can be effectively extracted, a complex and accurate traffic prediction paradigm can be automatically established, and dynamic updating and optimization can be realized with the iteration of the global model, so as to accurately realize real-time monitoring and dynamic evaluation of various indicators such as traffic flow, speed, travel time, and prediction and early warning of traffic conditions in the future. Using the global highway traffic data model in the block chain, each node performs data collaborative scheduling. Each block chain node can obtain the highway traffic data of other nodes from the block chain according to its own authority and demand, and perform decryption and verification. Decryption is realized by the function , which returns the original data . Verification is realized by the function , which returns the original data the authenticity and integrity of the data. If the verification is passed, the node can use the utility function to evaluate the utility value of and use it according to its own goals. If the node is a highway traffic data consumer , it can also optimize the scheduling of and use the utility function to pay the corresponding digital currency or points to the highway traffic data producers . All blockchain nodes follow the above step three to reach consensus and merge, and ensure the security, credibility and efficiency of the blockchain network .

[0052] In this embodiment, the server can provide optimized traffic scheduling schemes for various nodes according to different goals and needs based on the prediction results of the global traffic model, promoting the intelligentization and sustainable development of urban traffic systems. For public transportation operators, they can adjust the frequency, interval, and stop sites of buses, subways, and other vehicles based on real-time and predicted highway traffic data to improve operational efficiency and passenger satisfaction; for private car owners, they can choose the best travel time, route, and parking lot based on real-time and predicted highway traffic data to save time and fuel consumption; for government departments, they can develop reasonable traffic policies, plans, and management measures such as limiting, shunting, and expanding capacity based on real-time and predicted highway traffic data to identify and solve traffic problems and challenges, reduce urban traffic pollution and congestion, improve urban traffic efficiency and safety, and enhance the travel experience and quality of life of urban residents. In addition, with the continuous generation and accumulation of massive highway traffic data, it is necessary to regularly update the parameters and weights of the global traffic prediction model to maintain the effectiveness and adaptability of the model. Through the use of test sets or cross-validation methods, the prediction performance of the model can be evaluated, such as accuracy, error, and reliability. If the performance of the model does not meet expectations or there are problems such as overfitting or underfitting, the model structure can be adjusted, features can be added or reduced, and learning rates can be changed to optimize the model.

[0053] It should be understood that although the steps in the flowcharts involved in the above embodiments are shown in sequence according to the arrows, the steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, the execution of the steps is not strictly limited in sequence, and the steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts involved in the above embodiments can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of the steps or stages is not necessarily sequential, but can be alternately or alternately executed with at least part of other steps or steps or stages in other steps.

[0054] Based on the same inventive concept, the embodiments of the present application also provide a device for implementing the above-mentioned highway large-scale traffic data collaborative scheduling based on blockchain. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more highway large-scale traffic data collaborative scheduling device embodiments based on blockchain provided below can refer to the limitations of the highway large-scale traffic data collaborative scheduling method based on blockchain described above, and will not be repeated here.

[0055] In one embodiment, a device for highway large-scale traffic data collaborative scheduling based on blockchain is provided, and the device comprises:

[0056] a model obtaining module configured to obtain a traffic state prediction model trained by each highway traffic data producer node based on updated traffic event data on a highway traffic data blockchain of a target area;

[0057] a global model obtaining module configured to obtain a global traffic state prediction model of the target area based on the traffic state prediction model;

[0058] a prediction module configured to predict a traffic state corresponding to traffic live data uploaded by the highway traffic data user end node based on the global traffic state prediction model and the traffic live data.

[0059] The above-mentioned blockchain-based expressway large-scale traffic data collaborative scheduling device, the server obtains the traffic state prediction model of each expressway traffic data producer node based on the updated traffic event data in the target area of the expressway traffic data block chain; based on the traffic state prediction model, the global traffic state prediction model of the target area is obtained; based on the global traffic state prediction model and the traffic live data uploaded by the expressway traffic data user end node, the traffic state corresponding to the traffic live data is predicted. The method adopts the expressway traffic data block chain to deliver the traffic state prediction model parameters of each expressway traffic data producer node to construct the global traffic state prediction model, thereby ensuring that each expressway traffic data producer node realizes accurate and effective large-scale expressway traffic data collaborative scheduling without data out of the library.

[0060] Each module in the above-mentioned blockchain-based expressway large-scale traffic data collaborative scheduling device can be realized by software, hardware and their combinations. Each module can be embedded in or independent of the processor in the computer device in hardware form, or stored in the memory in the computer device in software form, so as to call and execute the operations of each module by the processor.

[0061] The above embodiments only express several embodiments of the present application, and the description is more specific and detailed, but it cannot be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A blockchain-based collaborative scheduling method for large-scale highway traffic data, wherein the method is applied to a server, characterized in that... The method includes: acquiring traffic state prediction models trained by each highway traffic data producer node on the highway traffic data blockchain of the target area based on updated traffic event data; Based on the traffic state prediction model, obtain the global traffic state prediction model for the target area; Based on the global traffic state prediction model and the real-time traffic data uploaded by the highway traffic data user terminal node, the traffic state corresponding to the real-time traffic data is predicted. The traffic state prediction model trained by each highway traffic data producer node based on the updated traffic event data includes the following steps: obtaining updated traffic flow event data from the target highway traffic data producer; training a pre-existing traffic state prediction model using the updated traffic event data; and obtaining the updated traffic state prediction model. The traffic state prediction model trained by each highway traffic data producer node based on the updated traffic event data further includes the following steps: encrypting the updated traffic state prediction model using a first encryption function to obtain an encrypted prediction model. Before obtaining the global traffic state prediction model for the target area based on the traffic state prediction model, the process includes the following steps: decrypting the encrypted prediction model to obtain the model parameters of the updated traffic state prediction model; generating a new block on the highway traffic data blockchain based on the model parameters; verifying the new block to obtain a valid block; and adding the valid block to the highway traffic data blockchain to obtain a new highway traffic data blockchain.

2. The blockchain-based collaborative scheduling method for large-scale highway traffic data as described in claim 1, characterized in that, The verification of the new block to obtain a valid block includes the following steps: obtaining a master node corresponding to the new block and sending a verification signal to the master node so that the master node broadcasts the new block to the slave nodes; the slave nodes refer to highway traffic data producer nodes other than the master node. When more than a first preset number of secondary nodes verify the new block, a voting start signal is sent to the secondary nodes so that the secondary nodes can vote on the new block. When any of the sub-nodes receives a second preset number of votes in favor, the new block is deemed valid.

3. The blockchain-based collaborative scheduling method for large-scale highway traffic data as described in claim 1, characterized in that, The step of obtaining the global traffic state prediction model for the target area based on the traffic state prediction model includes the following steps: parsing the model parameters of the updated traffic state prediction model in the effective block; Based on the traffic state prediction models generated by the traffic data producer nodes of each highway, a federated model is obtained. The federated model is updated based on the model parameters of the updated traffic state prediction model to obtain the updated global traffic state prediction model.

4. The blockchain-based collaborative scheduling method for large-scale highway traffic data as described in claim 1, characterized in that, The method of predicting the traffic state corresponding to the traffic real-time data based on the global traffic state prediction model and the traffic real-time data uploaded by the highway traffic data user terminal node includes the following steps: inputting the traffic real-time data uploaded by the highway traffic data user terminal node into the global traffic state prediction model to predict the traffic state corresponding to the traffic real-time data.

5. A blockchain-based large-scale highway traffic data collaborative scheduling device, applying the blockchain-based large-scale highway traffic data collaborative scheduling method as described in claim 1, characterized in that, The device includes: a model acquisition module, which is used to acquire traffic state prediction models trained by each highway traffic data producer node on the highway traffic data blockchain of the target area based on updated traffic event data. A global model acquisition module is used to acquire a global traffic state prediction model for the target area based on the traffic state prediction model. The prediction module is used to predict the traffic state corresponding to the real-time traffic data based on the global traffic state prediction model and the real-time traffic data uploaded by the highway traffic data user terminal node.

6. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1 to 4.

7. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 4.

Images