Industrial Internet trust value sharing method, device, electronic device and storage medium

Abstract

The present application provides a method, device, electronic device and storage medium for sharing trust values ​​in the industrial Internet. The method includes: obtaining a motion node and a base station node in the industrial Internet; obtaining the path information and trust value of the motion node; inputting the path information into a pre-trained deep learning network model; calculating the predicted driving direction of the motion node through the reward function in the deep learning network; and sending the trust value of the motion node to the next base station node in the predicted driving direction based on the predicted driving direction. The motion node directly encrypts the trust value and sends it to the next base station node in the predicted driving direction, which reduces the time for sharing trust values ​​between different base station nodes, thereby improving the scalability of the trust management system of the industrial Internet.

Description

Technical Field

[0001] The present application relates to the technical field, and in particular to an industrial Internet trust value sharing method, device, electronic device and storage medium. Background Art

[0002] An appropriate trust sharing mechanism in the Industrial Internet can accurately share the trust values ​​of motion nodes and achieve global consistency of the trust values ​​of motion nodes.

[0003] However, in order for a moving node to share trust values ​​between different base station nodes, it needs to first establish a connection with the central system controller, and then complete the sharing of trust values ​​with the next base station node through soft switching, which increases the latency of trust value sharing and occupies the communication resources of existing base station nodes during the soft switching process. Summary of the invention

[0004] In view of this, the purpose of this application is to propose an industrial Internet trust value sharing method, device, electronic device and storage medium to solve or partially solve the above-mentioned technical problems.

[0005] Based on the above purpose, the first aspect of the present application provides an industrial Internet trust value sharing method, including:

[0006] Obtain motion nodes and base station nodes in the industrial Internet;

[0007] Obtaining path information and trust value of the moving node;

[0008] Inputting the path information into a pre-trained deep learning network model;

[0009] Obtaining a predicted driving direction of the motion node by calculating a reward function in the deep learning network;

[0010] The trust value of the moving node is sent to the next base station node in the predicted driving direction based on the predicted driving direction.

[0011] Based on the same inventive concept, the second aspect of the present application proposes an industrial Internet trust value sharing device, comprising:

[0012] A node acquisition module, configured to acquire motion nodes and base station nodes in the industrial Internet;

[0013] An information acquisition module, configured to acquire path information and a trust value of the moving node;

[0014] An information processing module, configured to input the path information into a pre-trained deep learning network model;

[0015] A direction prediction module, configured to calculate the predicted driving direction of the motion node through a reward function in the deep learning network;

[0016] The trust value sending module is configured to send the trust value of the moving node to the next base station node in the predicted driving direction based on the predicted driving direction.

[0017] Based on the same inventive concept, the third aspect of the present application proposes an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the first aspect when executing the program.

[0018] Based on the same inventive concept, the fourth aspect of the present application proposes a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to execute the method described in the first aspect.

[0019] From the above, it can be seen that the industrial Internet trust value sharing method, device, electronic device and storage medium provided by the present application can predict the driving direction of the moving node in the industrial Internet. According to the predicted driving direction of the moving node, the moving node directly encrypts the trust value and sends it to the next base station node in the predicted driving direction, thereby reducing the time for sharing trust values ​​between different base station nodes, thereby improving the scalability of the industrial Internet trust management system. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the present application or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 A flow chart of a trust value sharing method for the industrial Internet according to an embodiment of the present application;

[0022] Figure 2 A schematic diagram of a process for obtaining input for a deep learning network according to an embodiment of the present application;

[0023] Figure 3 A schematic diagram of the deep learning network training process of an embodiment of the present application;

[0024] Figure 4 A schematic diagram of the hardware structure of a trust value sharing device for the industrial Internet according to an embodiment of the present application;

[0025] Figure 5A schematic diagram of the hardware structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0026] In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0027] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should be the usual meanings understood by people with ordinary skills in the field to which the present application belongs. The "first", "second" and similar words used in the embodiments of the present application do not represent any order, quantity or importance, but are only used to distinguish different components. "Including" or "comprising" and similar words mean that the elements or objects appearing in front of the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0028] As described in the background technology, the existing industrial Internet trust sharing method uses a central system controller to share the trust value of vehicles across clusters and adopts a soft switching method. However, for a network with strong mobility and high latency sensitivity such as the Internet of Vehicles, it faces the following three weaknesses: (1) When a moving node needs to switch clusters, it must first establish a communication connection with the central controller and notify the target cluster. Before the controller establishes communication with the target cluster, the trust value of the moving node cannot be shared, resulting in higher communication delays and signaling overhead. (2) The location of the central controller is generally fixed. As the distance between the moving node and the controller increases, the effectiveness of trust sharing will significantly decrease, which limits the scalability of the Internet of Vehicles. (3) The use of soft switching allows the moving node to maintain a communication connection with the head node of the historical cluster before joining the new cluster, wasting the communication resources of the head node of the historical cluster.

[0029] An embodiment of the present application provides an industrial Internet trust value sharing method, which can be executed on a client with a corresponding motion node installed, or on a corresponding server.

[0030] like Figure 1 As shown, the method of this embodiment includes:

[0031] Step 101, obtain motion nodes and base station nodes in the industrial Internet.

[0032] In this step, the moving node can be an unmanned vehicle, aircraft or other means of transportation, or a vehicle, aircraft or other means of transportation equipped with an automatic driving system. The present application preferably uses an unmanned vehicle. The base station node can be a roadside fixed device for the access of the moving node. The present application preferably uses an RSU (Roadside Unit). The moving node is equipped with intelligent devices such as wireless sensors, and has communication, storage and computing capabilities; the moving nodes can communicate freely; the moving nodes are equipped with GPS (Global Positioning System), and the starting position and the end point are known. In this way, a data basis is provided for the subsequent use of deep learning networks to predict the driving direction of the moving node.

[0033] Step 102: Obtain the path information and trust value of the moving node.

[0034] In this step, since the moving node knows the starting position and the end point, but the moving node can reach the end point through multiple paths when encountering an intersection, it is necessary to determine the input of the deep learning network model based on the path information shared by the moving node in the communication process in the industrial Internet. In this way, a data basis is provided for the input of the subsequent deep learning network model.

[0035] Step 103: input the path information into a pre-trained deep learning network model.

[0036] In this step, the deep learning network model has a strong adaptability to the processing of image information, so it is necessary to convert the path information into image information that the deep learning network model is good at processing. In this way, a data basis is provided for the deep learning network model to predict the driving direction of the moving node.

[0037] Step 104: obtain the predicted driving direction of the motion node by calculating the reward function in the deep learning network.

[0038] In this step, the reward function in the deep learning network is used to calculate the reward values ​​corresponding to all driving directions when the moving node encounters an intersection, and the driving direction of the moving node is predicted based on the calculation results. The deep learning network's ability to accurately predict actions based on environmental interaction is used to improve the accuracy of driving direction prediction for multiple moving nodes under complex road conditions.

[0039] Step 105: Send the trust value of the moving node to the next base station node in the predicted driving direction based on the predicted driving direction.

[0040] In this step, in the distributed trust management system in the industrial Internet, the sharing of motion nodes between different base station nodes needs to be completed through the motion cluster to which the motion node belongs. Such a trust value sharing method not only has a time delay but also occupies the communication resources of the current motion cluster to which the motion node belongs. Sending the trust value of the motion node to the next base station node in the predicted driving direction according to the predicted driving direction of the motion node realizes point-to-point communication between the motion node and the base station node in the distributed trust management system, reduces the time for sharing trust values ​​between different base station nodes, and thus improves the scalability of the trust management system of the industrial Internet.

[0041] Through the above scheme, the driving direction of the moving node in the industrial Internet can be predicted. According to the predicted driving direction of the moving node, the moving node directly encrypts the trust value and sends it to the next base station node in the predicted driving direction, thereby reducing the time for sharing trust values ​​between different base station nodes, thereby improving the scalability of the industrial Internet trust management system.

[0042] In some embodiments, reference Figure 2 , step 103 specifically includes:

[0043] Step 1031, constructing a pixel map with color features according to the path information;

[0044] Step 1032: Use the pixel map as input of the deep learning network model.

[0045] In the above scheme, the input of the deep learning network model can be an RGB (Red Green Blue) pixel image.

[0046] Through the above scheme, the deep learning network model has a strong adaptability in processing image information, and the path information is converted into image information that the deep learning network model is good at processing. In this way, a data basis is provided for the deep learning network model to predict the driving direction of the moving node.

[0047] In some embodiments, the path information includes the current position and end point of the motion node, and accident information, obstacle information, and congestion information of the industrial Internet;

[0048] Step 1031 specifically includes:

[0049] Converting a map including the path information into the pixel map, wherein intersections in the map are marked as cross pixel points in the pixel map, and roads between adjacent intersections in the map are marked as line segments in the pixel map;

[0050] Setting the pixel point corresponding to the current position in the pixel map to a first color;

[0051] Setting the pixel point corresponding to the end point in the pixel map to a second color;

[0052] Setting the pixel corresponding to the accident information in the pixel map to a third color;

[0053] Setting the pixel point corresponding to the obstacle information in the pixel map to a fourth color;

[0054] The pixel corresponding to the congestion information in the pixel map is set to a fifth color.

[0055] In the above scheme, a 25*25 pixel image can be used to simulate the traffic environment. The path information consists of 25 intersections and 20 T-junctions. Pixels have six corresponding RGB values. Black represents roads without congestion information, white represents obstacles in obstacle information, blue and green represent the current position and destination of the vehicle, and red represents accident information.

[0056] Through the above scheme, the path information is converted into image information that the deep learning network model is good at processing. In this way, a data basis is provided for the deep learning network model to predict the driving direction of the moving node.

[0057] In some embodiments, setting the pixel corresponding to the congestion information in the pixel map to a fifth color includes:

[0058] The depth of the fifth color is adjusted based on traffic flow information in the congestion information.

[0059] In the above scheme, three colors with different RGB values ​​may be used to represent the congestion degree in the congestion information of the road, and the congestion degree is quantified by the traffic flow information. As the color becomes darker, the congestion degree increases.

[0060] Through the above scheme, the congestion information in the path information is converted into color data that is easy for the deep learning network model to process, thereby improving the efficiency of the deep learning network model in predicting the driving direction of the moving node.

[0061] In some embodiments, step 104 specifically includes:

[0062] In response to determining that the moving node encounters an intersection, calculating a reward value corresponding to the reward function of the moving node in each driving direction;

[0063] The reward value is calculated according to the following formula:

[0064]

[0065] Among them, rewardt is the reward function, r barrier is the reward value for encountering the obstacle information, r accident To receive the reward value of the accident information, flow threshold To meet the traffic flow information of the normal driving speed of the moving node, r flow is the reward value when the traffic flow information meets the normal driving speed, r reach is the reward value when the moving node reaches the destination;

[0066] The driving direction corresponding to the maximum reward value is used as the predicted driving direction of the motion node.

[0067] In the above scheme, for the sake of driving safety and efficiency, the design of the reward value in the reward function of the deep learning network is concentrated on four aspects: avoiding sections where traffic accidents occur, avoiding sections with high vehicle density, avoiding obstacles, and reaching the destination. The relationship between the size of the reward value can be ranked as follows: barrier <r accident <r flow 0 <r reach In this way, the motion nodes of the Industrial Internet can improve driving efficiency while ensuring driving safety.

[0068] Through the above scheme, the accuracy of driving direction prediction of multiple motion nodes under complex road conditions is improved by utilizing the characteristics of deep learning networks that accurately predict actions based on environmental interactions.

[0069] In some embodiments, reference Figure 3 The training process of the deep learning network in step 103 includes:

[0070] Step 201, obtaining a plurality of training pixel images as a training set;

[0071] Step 202, obtaining an initial reward function corresponding to the training set;

[0072] Step 203, training the initial reward function in the deep learning network based on the training set;

[0073] Step 204: Use the trained initial reward function as the reward function.

[0074] In the above scheme, the deep learning network used to predict the driving direction of the moving node is mainly divided into three parts: environment observation, action space design and reward design. Environment observation: Environment observation is the input of the deep neural network. Action space: There are four actions in the action space of the moving node, up, down, left and right. Each moving node in the deep learning network is an agent, which comprehensively considers the current position of the moving node and the surrounding environment. The moving node selects different behaviors to interact with the environment and learns the best strategy. Reward design: The core of the deep learning network is to learn unfamiliar scenes through interaction with the environment, so as to obtain behavioral strategies that meet the set goals. The reward design can be completed using the reward function in the step 104 embodiment. In this process, the reward is the only feedback that the moving node can get from the environment.

[0075] Specifically, deep neural networks can be used to approximate the values ​​of Q-tables (tables formed by Q values ​​in reinforcement learning) to solve the problems of poor scalability and low dimensionality in the prediction of the direction of motion of moving nodes in the industrial Internet. Different weights can be defined for the training set to improve the training stability of the deep learning network model, and then the mean square error can be used to define the loss function in the training process, and finally the training of the deep learning network is completed by minimizing the loss function.

[0076] Through the above scheme, the trained deep neural network provides a model basis for predicting the driving direction of moving nodes in the industrial Internet.

[0077] In some embodiments, step 105 specifically includes:

[0078] Encrypting the trust value using an elliptic curve and a hash function to obtain an encrypted trust value;

[0079] The encrypted trust value is sent to the next base station node in the predicted driving direction.

[0080] In the above scheme, considering the limitations of computing, storage and communication capabilities of the moving nodes and the high sensitivity to time delay, this embodiment uses a lightweight encryption mechanism based on elliptic curve encryption and encrypted hash functions to encrypt the trust value.

[0081] Through the above scheme, the security of point-to-point sharing of trust values ​​between the moving nodes and the base station nodes is guaranteed.

[0082] It should be noted that the method of the embodiment of the present application can be performed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present application, and the multiple devices will interact with each other to complete the described method.

[0083] It should be noted that the above describes some embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do 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.

[0084] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides an industrial Internet trust value sharing device.

[0085] refer to Figure 4 , the industrial Internet trust value sharing device comprises:

[0086] The node acquisition module 401 is configured to acquire motion nodes and base station nodes in the industrial Internet;

[0087] The information acquisition module 402 is configured to acquire the path information and trust value of the moving node;

[0088] The information processing module 403 is configured to input the path information into a pre-trained deep learning network model;

[0089] A direction prediction module 404 is configured to calculate the predicted driving direction of the motion node through the reward function in the deep learning network;

[0090] The trust value sending module 405 is configured to send the trust value of the moving node to the next base station node in the predicted driving direction based on the predicted driving direction.

[0091] In some embodiments, the information processing module 403 is specifically configured to:

[0092] A pixel map construction unit, configured to construct a pixel map with color features according to the path information;

[0093] An input unit is configured to use the pixel map as an input of the deep learning network model.

[0094] In some embodiments, the path information in the information processing module 403 includes the current position and end point of the motion node, and the accident information, obstacle information and congestion information of the industrial Internet; the pixel map construction unit is specifically configured as follows:

[0095] A map conversion unit, configured to convert a map including the path information into the pixel map, wherein intersections in the map are marked as crossing pixels in the pixel map, and roads between adjacent intersections in the map are marked as line segments in the pixel map;

[0096] A position setting unit, configured to set a pixel point corresponding to the current position in the pixel map to a first color;

[0097] An endpoint setting unit, configured to set the pixel point corresponding to the endpoint in the pixel map to a second color;

[0098] An accident setting unit is configured to set the pixel point corresponding to the accident information in the pixel map to a third color;

[0099] An obstacle setting unit is configured to set the pixel point corresponding to the obstacle information in the pixel map to a fourth color;

[0100] The congestion setting unit is configured to set the pixel point corresponding to the congestion information in the pixel map to a fifth color.

[0101] In some embodiments, the congestion setting unit is specifically configured to:

[0102] The depth of the fifth color is adjusted based on traffic flow information in the congestion information.

[0103] In some embodiments, the direction prediction module 404 is specifically configured to:

[0104] In response to determining that the moving node encounters an intersection, calculating a reward value corresponding to the reward function of the moving node in each driving direction;

[0105] The reward value is calculated according to the following formula:

[0106]

[0107] Among them, reward t is the reward function, r barrier is the reward value for encountering the obstacle information, r accident To receive the reward value of the accident information, flow threshold To meet the traffic flow information of the normal driving speed of the moving node, rflow is the reward value when the traffic flow information meets the normal driving speed, r reach is the reward value when the moving node reaches the destination;

[0108] The driving direction corresponding to the maximum reward value is used as the predicted driving direction of the motion node.

[0109] In some embodiments, the information processing module 403 further includes a training unit of the deep learning network; the training unit is specifically configured to:

[0110] Obtain multiple training pixel images as a training set;

[0111] Obtaining an initial reward function corresponding to the training set;

[0112] Training the initial reward function in the deep learning network based on the training set;

[0113] The trained initial reward function is used as the reward function.

[0114] In some embodiments, the trust value sending module 405 is specifically configured to:

[0115] Encrypting the trust value using an elliptic curve and a hash function to obtain an encrypted trust value;

[0116] The encrypted trust value is sent to the next base station node in the predicted driving direction.

[0117] For the convenience of description, the above device is described in terms of functions divided into various modules. Of course, when implementing the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0118] The device of the above-mentioned embodiment is used to implement the corresponding industrial Internet trust value sharing method in any of the above-mentioned embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0119] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the industrial Internet trust value sharing method described in any of the above embodiments is implemented.

[0120] Figure 5A more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment is shown, and the device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are connected to each other through the bus 1050 in the device.

[0121] The processor 1010 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0122] The memory 1020 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0123] The input / output interface 1030 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0124] The communication interface 1040 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired mode (such as USB, network cable, etc.) or a wireless mode (such as mobile network, WIFI, Bluetooth, etc.).

[0125] The bus 1050 includes a path that transmits information between the various components of the device (eg, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).

[0126] It should be noted that, although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040 and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.

[0127] The electronic device of the above-mentioned embodiment is used to implement the corresponding industrial Internet trust value sharing method in any of the above-mentioned embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0128] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the industrial Internet trust value sharing method as described in any of the above embodiments.

[0129] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0130] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the industrial Internet trust value sharing method as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0131] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application (including the claims) is limited to these examples. In line with the concept of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0132] In addition, to simplify the description and discussion, and in order not to make the embodiments of the present application difficult to understand, the known power supply / ground connection with the integrated circuit (IC) chip and other components may or may not be shown in the provided drawings. In addition, the device can be shown in the form of a block diagram to avoid making the embodiments of the present application difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform to be implemented in the embodiments of the present application (that is, these details should be fully within the scope of understanding of those skilled in the art). In the case of elaborating specific details (e.g., circuits) to describe exemplary embodiments of the present application, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details or when these specific details are changed. Therefore, these descriptions should be considered to be illustrative rather than restrictive.

[0133] Although the present application has been described in conjunction with specific embodiments of the present application, many replacements, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.

[0134] The embodiments of the present application are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application should be included in the scope of protection of the present application.

Claims

1. An industrial Internet trust value sharing method, characterized in that: include: Obtain motion nodes and base station nodes in the industrial Internet; Obtaining path information and trust value of the moving node; Inputting the path information into a pre-trained deep learning network model; Obtaining a predicted driving direction of the motion node by calculating a reward function in the deep learning network; The trust value of the moving node is sent to the next base station node in the predicted driving direction based on the predicted driving direction.

2. The method according to claim 1, characterized in that The step of inputting the path information into a pre-trained deep learning network model comprises: Constructing a pixel map with color features according to the path information; The pixel map is used as input of the deep learning network model.

3. The method according to claim 2, characterized in that The path information includes the current position and end point of the motion node, and accident information, obstacle information and congestion information of the industrial Internet; The step of constructing a pixel map with color features according to the path information includes: Converting a map including the path information into the pixel map, wherein intersections in the map are marked as cross pixel points in the pixel map, and roads between adjacent intersections in the map are marked as line segments in the pixel map; Setting the pixel point corresponding to the current position in the pixel map to a first color; Setting the pixel point corresponding to the end point in the pixel map to a second color; Setting the pixel corresponding to the accident information in the pixel map to a third color; Setting the pixel point corresponding to the obstacle information in the pixel map to a fourth color; The pixel corresponding to the congestion information in the pixel map is set to a fifth color.

4. The method according to claim 3, characterized in that The step of setting the pixel point corresponding to the congestion information in the pixel map to a fifth color includes: The depth of the fifth color is adjusted based on traffic flow information in the congestion information.

5. The method according to claim 4, characterized in that The step of calculating the predicted driving direction of the motion node by using the reward function in the deep learning network includes: In response to determining that the moving node encounters an intersection, calculating a reward value corresponding to the reward function of the moving node in each driving direction; The reward value is calculated according to the following formula: Among them, reward t is the reward function, r barrier is the reward value for encountering the obstacle information, r accident To receive the reward value of the accident information, flow threshold To meet the traffic flow information of the normal driving speed of the moving node, r flow is the reward value when the traffic flow information meets the normal driving speed, r reach is the reward value when the moving node reaches the destination; The driving direction corresponding to the maximum reward value is used as the predicted driving direction of the motion node.

6. The method according to claim 1, characterized in that The training process of the deep learning network includes: Obtain multiple training pixel images as a training set; Obtaining an initial reward function corresponding to the training set; Training the initial reward function in the deep learning network based on the training set; The trained initial reward function is used as the reward function.

7. The method according to claim 1, characterized in that The step of sending the trust value of the moving node to the next base station node in the predicted driving direction based on the predicted driving direction comprises: Encrypting the trust value using an elliptic curve and a hash function to obtain an encrypted trust value; The encrypted trust value is sent to the next base station node in the predicted driving direction.

8. An industrial Internet trust value sharing device, characterized in that: include: A node acquisition module, configured to acquire motion nodes and base station nodes in the industrial Internet; An information acquisition module, configured to acquire path information and a trust value of the moving node; An information processing module, configured to input the path information into a pre-trained deep learning network model; A direction prediction module, configured to calculate the predicted driving direction of the motion node through a reward function in the deep learning network; The trust value sending module is configured to send the trust value of the moving node to the next base station node in the predicted driving direction based on the predicted driving direction.

9. An electronic device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to cause a computer to execute the method according to any one of claims 1 to 7.

Images