A remote configuration method and system for a wireless bridge

Abstract

The present invention relates to the field of network communication technology, and discloses a remote configuration method for a wireless bridge, including: configuring a wireless bridge device of a network to be connected; using a device authentication module in a network cloud center to allocate a fingerprint certificate of the wireless bridge device, defining a parameter threshold group of the wireless bridge device, constructing a simulation environment of the network to be connected, configuring a configuration performance reward function, a DQN reinforcement algorithm, and a bridge environment perception network of the simulation environment; constructing a parameter configuration mechanism for the wireless bridge device, deploying the parameter configuration mechanism to an AI analysis engine in the network cloud center, and obtaining a parameter configuration AI model; using the parameter configuration AI model to define a first configuration parameter of the wireless bridge device, calculating a network connection coefficient of the first configuration parameter, optimizing the first configuration parameter, obtaining a target configuration parameter, and executing remote configuration of the wireless bridge device through the target configuration parameter. The present invention can improve the network performance of the wireless bridge configuration.

Description

Technical Field

[0001] The invention relates to a remote configuration method and system of a wireless bridge, belonging to the technical field of network communication. Background Art

[0002] Remote configuration of a wireless bridge refers to the process of remotely accessing the management interface of a wireless bridge through the network to set and adjust it. This process usually does not require physical contact with the device and can be performed by the administrator at any location that can connect to the network where the bridge is located. Remote configuration of a wireless bridge does not require on-site operation, saving time and cost.

[0003] Remote configuration of wireless bridges usually involves manual settings through a web interface or command line interface. This method is intuitive but inefficient, lacks adaptability and real-time monitoring capabilities, and is susceptible to human errors, resulting in poor network performance of the wireless bridge configuration. Summary of the invention

[0004] The present invention provides a remote configuration method and system for a wireless bridge, the main purpose of which is to improve the network performance of the wireless bridge configuration.

[0005] To achieve the above object, the present invention provides a remote configuration method of a wireless bridge, comprising:

[0006] Obtaining the network connection requirements of the network to be connected in the network cloud center, defining the remote configuration requirements of the bridge of the network to be connected, and configuring the wireless bridge device of the network to be connected based on the network connection requirements and the remote configuration requirements of the bridge;

[0007] Acquire the bridge device information of the wireless bridge device, allocate the fingerprint certificate of the wireless bridge device by using the device authentication module in the network cloud center through the bridge device information, and collect the historical network data of the data storage module in the network cloud center, wherein the historical network data includes historical configuration data, historical performance indicator data and historical resource usage data;

[0008] Defining a parameter threshold group of the wireless bridge device, constructing a simulation environment of the network to be connected, wherein the simulation environment includes a state space and an action space, configuring a configuration performance reward function, a DQN reinforcement algorithm, and a bridge environment perception network of the simulation environment;

[0009] According to the parameter threshold group, the simulation environment, the configuration performance reward function, the DQN reinforcement algorithm and the bridge environment perception network, a parameter configuration mechanism of the wireless bridge device is constructed, and the parameter configuration mechanism is deployed to the AI ​​analysis engine in the network cloud center to obtain a parameter configuration AI model;

[0010] Collect real-time streaming data of the wireless bridge device, upload the real-time streaming data to the data storage module of the network cloud center using the fingerprint certificate, obtain the real-time streaming data to be analyzed, define the first configuration parameter of the wireless bridge device based on the real-time streaming data to be analyzed using the parameter configuration AI model, calculate the network connection coefficient of the first configuration parameter, optimize the first configuration parameter based on the network connection coefficient, obtain the target configuration parameter, and perform remote configuration of the wireless bridge device through the target configuration parameter.

[0011] Optionally, configuring the wireless bridge device of the network to be connected based on the network connection requirement and the bridge remote configuration requirement includes:

[0012] Obtaining the first version of the firmware of the network to be connected, and extracting the firmware source code of the first version of the firmware;

[0013] Determining network parameters of the firmware source code according to the network connection requirements and the bridge remote configuration requirements;

[0014] Identify the network protocol of the firmware source code, construct a network protocol support mechanism for the firmware source code based on the network protocol, and construct a security authentication mechanism for the firmware source code;

[0015] Modifying the firmware source code according to the network parameters, the network protocol support mechanism, and the security authentication mechanism to obtain a modified source code;

[0016] Configuring a cross-compilation environment for the initial version of the firmware, and cross-compiling the modified source code based on the cross-compilation environment to obtain a newly compiled firmware;

[0017] Testing the newly compiled firmware to obtain a firmware test result, and analyzing the firmware performance of the newly compiled firmware according to the firmware test result;

[0018] When the firmware performance meets the preset firmware performance standard, using the newly compiled firmware as the wireless bridge firmware for connecting to the network;

[0019] The wireless bridge firmware is integrated into a preset initial wireless bridge device to obtain the wireless bridge device of the network to be connected.

[0020] Optionally, allocating the fingerprint certificate of the wireless bridge device by using the device authentication module in the network cloud center according to the bridge device information includes:

[0021] Configuring zero-touch configuration of the wireless bridge device;

[0022] The bridge device information is transmitted to the network cloud center by using the zero-touch configuration to obtain target device information;

[0023] Based on the target device information, construct a unique device identity record of the target device information;

[0024] Constructing a dynamic fingerprint generation algorithm for the wireless bridge device;

[0025] According to the unique device identity record, constructing a dynamic fingerprint of the wireless bridge device using the dynamic fingerprint generation algorithm;

[0026] Using the dynamic fingerprint, sending a fingerprint authentication request to a device authentication module in the network cloud center;

[0027] When the fingerprint authentication request meets the preset authentication standard, the fingerprint certificate of the wireless bridge device is issued.

[0028] Optionally, constructing the dynamic fingerprint of the wireless bridge device using the dynamic fingerprint generation algorithm according to the unique device identity record includes:

[0029] Determine, based on the unique device identity record, a MAC address, a hardware identifier, a serial number of the device, device configuration information, and device status information of the wireless bridge device;

[0030] A timestamp and a random number identifying the wireless bridge device;

[0031] The dynamic fingerprint generation algorithm is used to construct the dynamic fingerprint of the wireless bridge device according to the MAC address, the hardware identifier, the serial number of the device, the device configuration information, the device status information, the timestamp and the random number, wherein the dynamic fingerprint generation algorithm:

[0032] ;

[0033] in, Indicates the dynamic fingerprint of the wireless bridge device. Indicates the MAC address. Represents the hardware identifier, Indicates the serial number of the device. Indicates device configuration information. Indicates device status information. Indicates the timestamp, Represents a random number.

[0034] Optionally, the constructing a simulation environment of the network to be connected includes:

[0035] Determining a network state variable of the network to be connected;

[0036] Defining state descriptions and state boundaries of the network state variables;

[0037] Constructing the state space of the network to be connected through the state description and the state boundary;

[0038] Determine the action type of the network to be connected;

[0039] defining an action representation and an action impact of the action type;

[0040] Constructing an action space of the network to be connected according to the action representation and the action impact;

[0041] Based on the state space and the action space, a simulation environment of the network to be connected is constructed.

[0042] Optionally, configuring the performance reward function, the DQN reinforcement algorithm, and the bridge environment perception network of the simulation environment includes:

[0043] determining key performance indicators of the simulation environment;

[0044] defining reward rules for said key performance indicators;

[0045] According to the reward rule, construct a performance reward function of the key performance indicator;

[0046] Constructing a deep neural network of the simulated environment;

[0047] Configuring a DQN reinforcement algorithm for the simulation environment through the deep neural network;

[0048] Determining perceived environmental parameters of the simulated environment, and constructing an environmental perception device of the simulated environment based on the perceived environmental parameters;

[0049] Construct a bridge environment perception network of the environment perception device.

[0050] Optionally, configuring the DQN reinforcement algorithm of the simulation environment through the deep neural network includes:

[0051] identifying neural network parameters of the deep neural network;

[0052] Constructing a DQN initial reinforcement algorithm for the simulation environment according to the neural network parameters;

[0053] Based on the neural network parameters, the algorithm loss of the DQN initial reinforcement algorithm in the simulation environment is calculated using the following formula:

[0054] ;

[0055] in, represents the algorithm loss of the DQN initial reinforcement algorithm, Indicates The actual Q value of the simulated environment, Indicates The output Q value of the DQN initial reinforcement algorithm in the simulation environment, Indicates The environmental state in the simulated environment, represents the DQN initial reinforcement algorithm, Indicates The environmental actions in the simulated environment, represents the neural network parameters;

[0056] Based on the algorithm loss, the DQN initial reinforcement algorithm is optimized to obtain the DQN reinforcement algorithm of the simulation environment.

[0057] Optionally, defining the first configuration parameter of the wireless bridge device by using the parameter configuration AI model based on the real-time stream data to be analyzed includes:

[0058] Preprocessing the real-time stream data to be analyzed to obtain preprocessed real-time stream data;

[0059] Extracting decision configuration features of the preprocessed real-time stream data;

[0060] Based on the decision configuration features, using the parameter configuration AI model to analyze the initial configuration parameters of the wireless bridge device;

[0061] Calculating a network risk coefficient of the initial configuration parameters;

[0062] When the network risk coefficient meets a preset network risk threshold, the initial configuration parameter is used as the first configuration parameter of the wireless bridge device.

[0063] Optionally, calculating the network risk coefficient of the initial configuration parameter includes:

[0064] Identifying a parameter change risk factor of the initial configuration parameter;

[0065] Analyze the main effect coefficients and interaction effect coefficients of the parameter change risk factors;

[0066] Based on the main effect coefficient and the interaction effect coefficient, the interaction coefficient of the parameter change risk factor was calculated using the following formula:

[0067] ;

[0068] in, represents the interaction coefficient of the parameter change risk factor, represents the intercept term, Indicates The main effect coefficient of the risk factor for parameter change is Indicates The main effect coefficient of the risk factor for parameter change is Indicates Parameter change risk factor, Indicates Parameter change risk factor, Indicates The risk factor for parameter change and The interaction effect coefficient of the risk factor for parameter changes, represents the number of parameter change risk factors, represents the error term;

[0069] Determining the risk weight of the parameter change risk factor;

[0070] The network risk coefficient of the initial configuration parameters is calculated according to the interaction coefficient and the risk weight.

[0071] In order to solve the above problems, the present invention also provides a remote configuration system for a wireless bridge, the system comprising:

[0072] A wireless bridge device construction module is used to obtain the network connection requirements of the network to be connected in the network cloud center, define the remote configuration requirements of the bridge of the network to be connected, and configure the wireless bridge device of the network to be connected based on the network connection requirements and the remote configuration requirements of the bridge;

[0073] A fingerprint certificate issuing module is used to obtain the bridge device information of the wireless bridge device, allocate the fingerprint certificate of the wireless bridge device by using the bridge device information and the device authentication module in the network cloud center, and collect the historical network data of the data storage module in the network cloud center, wherein the historical network data includes historical configuration data, historical performance indicator data and historical resource usage data;

[0074] A simulation environment construction module, used to define a parameter threshold group of the wireless bridge device, construct a simulation environment of the network to be connected, wherein the simulation environment includes a state space and an action space, and configure a configuration performance reward function, a DQN reinforcement algorithm, and a bridge environment perception network of the simulation environment;

[0075] A parameter configuration model construction module is used to construct a parameter configuration mechanism for the wireless bridge device according to the parameter threshold group, the simulation environment, the configuration performance reward function, the DQN reinforcement algorithm, and the bridge environment perception network, and deploy the parameter configuration mechanism to the AI ​​analysis engine in the network cloud center to obtain a parameter configuration AI model;

[0076] The bridge remote configuration module is used to collect real-time streaming data of the wireless bridge device, upload the real-time streaming data to the data storage module of the network cloud center using the fingerprint certificate, obtain the real-time streaming data to be analyzed, and define the first configuration parameter of the wireless bridge device based on the real-time streaming data to be analyzed using the parameter configuration AI model, calculate the network connection coefficient of the first configuration parameter, optimize the first configuration parameter based on the network connection coefficient, obtain the target configuration parameter, and perform remote configuration of the wireless bridge device through the target configuration parameter.

[0077] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising:

[0078] at least one processor; and,

[0079] a memory communicatively connected to the at least one processor; wherein,

[0080] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to implement the remote configuration method of the wireless bridge described above.

[0081] In order to solve the above problem, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is executed by a processor in an electronic device to implement the above-mentioned remote configuration method of the wireless bridge.

[0082] Compared with the problems described in the background technology, the embodiments of the present invention can obtain the network connection requirements of the network to be connected in the network cloud center through accurate demand analysis, so as to ensure that the network planning matches the actual requirements and avoid waste or shortage of resources; further, the embodiments of the present invention can optimize the quality and coverage of the wireless signal and improve the overall network performance by defining the remote configuration requirements of the bridge of the network to be connected. Furthermore, the embodiments of the present invention can adjust the wireless signal strength and channel allocation according to the coverage requirements based on the network connection requirements and the remote configuration requirements of the bridge to optimize the coverage and signal quality of the wireless network by configuring the wireless bridge device of the network to be connected. Furthermore, the present invention uses the device authentication module in the network cloud center through the bridge device information to allocate the fingerprint certificate of the wireless bridge device to ensure that the wireless bridge device is a legitimate device in the network and protect the communication between the device and the network cloud center from being tampered with. Furthermore, the present invention can ensure the wireless bridge device by defining the parameter threshold group of the wireless bridge device. Run in the best state and discover potential problems in time. Next, the present invention helps the reinforcement learning agent learn how to optimize the configuration of the wireless bridge under different network conditions by configuring the configuration performance reward function of the simulation environment, the DQN reinforcement algorithm and the bridge environment perception network. The present invention constructs the parameter configuration mechanism of the wireless bridge device according to the parameter threshold group, the simulation environment, the configuration performance reward function, the DQN reinforcement algorithm and the bridge environment perception network, which can adapt to environmental changes and automatically adjust the configuration to optimize performance. Furthermore, the present invention can collect the real-time streaming data of the wireless bridge device by collecting and analyzing these real-time streaming data, so that the network administrator can better understand the network behavior, respond to problems quickly, and continuously optimize the network performance. Finally, the present invention optimizes the first configuration parameter to obtain the target configuration parameter. The remote configuration of the wireless bridge device can effectively optimize the configuration parameters of the wireless bridge device through the target configuration parameter, and improve the network performance through remote configuration. Therefore, the present invention can improve the network performance of the wireless bridge configuration. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] Figure 1 A schematic diagram of a flow chart of a remote configuration method of a wireless bridge provided by an embodiment of the present invention;

[0084] Figure 2 A functional module diagram of a remote configuration system for a wireless bridge provided by an embodiment of the present invention;

[0085] Figure 3 A schematic diagram of the structure of an electronic device of a remote configuration system of a wireless bridge provided by an embodiment of the present invention;

[0086] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0087] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0088] The embodiment of the present application provides a remote configuration method for a wireless bridge. The execution subject of the remote configuration method of the wireless bridge includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the remote configuration method of the wireless bridge can be executed by software or hardware installed in a terminal device or a server device. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0089] Embodiment 1:

[0090] Reference Figure 1 FIG. 1 is a flow chart of a remote configuration method of a wireless bridge provided by an embodiment of the present invention. In this embodiment, the remote configuration method of the wireless bridge includes:

[0091] S1. Obtain the network connection requirements of the network to be connected in the network cloud center, define the remote configuration requirements of the bridge of the network to be connected, and configure the wireless bridge device of the network to be connected based on the network connection requirements and the remote configuration requirements of the bridge.

[0092] The embodiment of the present invention can obtain the network connection requirements of the network to be connected in the network cloud center through accurate demand analysis, and ensure that the network planning matches the actual demand to avoid waste or shortage of resources. The network cloud center refers to a centralized network infrastructure that provides computing resources, storage resources, network services and other IT services, and the network to be connected refers to a local network or a remote network, which may be an internal enterprise network, a home network, an Internet of Things (IoT) device network, or any network that needs to establish a connection with the network cloud center through a wireless bridge device. The network connection requirements refer to a series of specific technical specifications and performance goals, which define the conditions that the network must meet to support specific applications, services or user groups.

[0093] Optionally, as an embodiment of the present invention, the obtaining of the network connection requirements of the network to be connected in the network cloud center may be obtained through network traffic analysis.

[0094] The embodiment of the present invention can optimize the quality and coverage of wireless signals and improve the overall network performance by defining the remote configuration requirements of the bridge of the network to be connected.

[0095] Optionally, as an embodiment of the present invention, the requirement for defining the remote configuration of the bridge of the network to be connected may be defined by business requirement analysis.

[0096] The embodiment of the present invention can adjust the wireless signal strength and channel allocation according to the coverage requirements based on the network connection requirements and the bridge remote configuration requirements to optimize the coverage and signal quality of the wireless network. The wireless bridge firmware refers to the software program embedded in the wireless bridge device, which controls the operation, function and performance of the device.

[0097] As an embodiment of the present invention, configuring the wireless bridge device of the network to be connected based on the network connection requirement and the bridge remote configuration requirement includes:

[0098] Obtaining the first version of the firmware of the network to be connected, and extracting the firmware source code of the first version of the firmware;

[0099] Determining network parameters of the firmware source code according to the network connection requirements and the bridge remote configuration requirements;

[0100] Identify the network protocol of the firmware source code, construct a network protocol support mechanism for the firmware source code based on the network protocol, and construct a security authentication mechanism for the firmware source code;

[0101] Modifying the firmware source code according to the network parameters, the network protocol support mechanism, and the security authentication mechanism to obtain a modified source code;

[0102] Configuring a cross-compilation environment for the initial version of the firmware, and cross-compiling the modified source code based on the cross-compilation environment to obtain a newly compiled firmware;

[0103] Testing the newly compiled firmware to obtain a firmware test result, and analyzing the firmware performance of the newly compiled firmware according to the firmware test result;

[0104] When the firmware performance meets the preset firmware performance standard, using the newly compiled firmware as the wireless bridge firmware for connecting to the network;

[0105] The wireless bridge firmware is integrated into a preset initial wireless bridge device to obtain the wireless bridge device of the network to be connected.

[0106] Among them, the initial version of firmware refers to software that includes the device's boot program, basic drivers and minimum functional support. The firmware source code refers to the original programming code of the initial version of the firmware, which is a set of instructions and data structures written by the developer during the firmware development process to control the operation and behavior of the device. The network parameters refer to a series of key settings used to configure and optimize the performance of network devices during network communication and data transmission, such as IP address, subnet mask, DNS server address, etc. The network protocol refers to a series of rules and conventions that define how data is formatted, transmitted, received and processed in the network. The series of technologies and methods ensure that the network protocol can effectively perform its intended functions. The security authentication mechanism refers to a series of security measures and protocols that are used to verify the identity of devices or users in the network to ensure that only authorized entities can access network resources and services. The modified source code refers to the code after the original source code is modified, optimized or new functions are added by the developer according to specific needs during the development of the network bridging device firmware. The cross-compilation environment refers to a set of specific software development tools and resources that allow developers to compile and build executable programs or firmware for another different architecture (such as ARM, MIPS, PowerPC, etc.) on one computer architecture (such as x86_64). The newly compiled firmware refers to the firmware version that is recompiled using the cross-compilation environment after modification, optimization or update. The firmware test results refer to the feedback and data obtained during a series of tests on the newly compiled firmware. The firmware performance refers to the various efficiencies and functional performances exhibited by the firmware when it runs on a specific hardware platform. The preset firmware performance standards refer to a set of performance indicators and thresholds defined at the beginning, which are used to measure whether the firmware meets the network connection requirements and the bridge remote configuration requirements. The wireless bridge firmware refers to the software program embedded in the wireless bridge device, which controls the operation, function and performance of the device. The initial wireless bridge device refers to the wireless bridge hardware that has not yet been configured or customized with firmware, and the wireless bridge device refers to the wireless bridge hardware that has been configured and customized.

[0107] Optionally, the security authentication mechanism for constructing the firmware source code may be constructed by using a secure communication protocol.

[0108] Optionally, cross-compiling the modified source code based on the cross-compiling environment to obtain a new compiled firmware may be compiled by using a cross-compiling tool chain.

[0109] S2. Obtain the bridge device information of the wireless bridge device, use the device authentication module in the network cloud center to allocate the fingerprint certificate of the wireless bridge device through the bridge device information, and collect the historical network data of the data storage module in the network cloud center, wherein the historical network data includes historical configuration data, historical performance indicator data and historical resource usage data.

[0110] It should be explained that the bridge device information refers to the relevant information of the wireless bridge device, including but not limited to the device's hardware identification (such as MAC address), device model, serial number, current firmware version, configuration parameters, network interface status and other information.

[0111] The present invention uses the bridge device information to utilize the device authentication module in the network cloud center to allocate the fingerprint certificate of the wireless bridge device to ensure that the wireless bridge device is a legitimate device in the network and to protect the communication between the device and the network cloud center from being tampered with.

[0112] In detail, the method of allocating the fingerprint certificate of the wireless bridge device by using the device authentication module in the network cloud center through the bridge device information includes:

[0113] Configuring zero-touch configuration of the wireless bridge device;

[0114] The bridge device information is transmitted to the network cloud center by using the zero-touch configuration to obtain target device information;

[0115] Based on the target device information, construct a unique device identity record of the target device information;

[0116] Constructing a dynamic fingerprint generation algorithm for the wireless bridge device;

[0117] According to the unique device identity record, constructing a dynamic fingerprint of the wireless bridge device using the dynamic fingerprint generation algorithm;

[0118] Using the dynamic fingerprint, sending a fingerprint authentication request to a device authentication module in the network cloud center;

[0119] When the fingerprint authentication request meets the preset authentication standard, the fingerprint certificate of the wireless bridge device is issued.

[0120] Among them, the zero-touch configuration is an automated process that allows the device to configure itself and join the network without human intervention when it is first started. The target device information refers to a set of data that the wireless bridge device needs to identify and record during the configuration process, including but not limited to the device's MAC address, serial number, manufacturer information, model, etc. The device authentication module refers to a component in the network cloud center, which is responsible for verifying the identity of the device and ensuring that only legal and trusted devices can access the network. The dynamic fingerprint generation algorithm refers to an algorithm that combines the device's hardware information, software configuration, network status and other dynamic parameters (such as timestamps, random numbers, etc.) to generate a unique fingerprint. The dynamic fingerprint refers to a data set generated by the dynamic fingerprint generation algorithm, which reflects the current status and identity of the device. The fingerprint authentication request refers to a message sent by the device to the device authentication module of the network cloud center, which contains the device's dynamic fingerprint and other necessary information. The authentication standard refers to a set of predefined rules and conditions for verifying the validity of the fingerprint authentication request. The fingerprint certificate refers to a digital certificate issued by the device authentication module to the authenticated device.

[0121] Further, constructing the dynamic fingerprint of the wireless bridge device using the dynamic fingerprint generation algorithm according to the unique device identity record includes:

[0122] Determine, based on the unique device identity record, a MAC address, a hardware identifier, a serial number of the device, device configuration information, and device status information of the wireless bridge device;

[0123] A timestamp and a random number identifying the wireless bridge device;

[0124] The dynamic fingerprint generation algorithm is used to construct the dynamic fingerprint of the wireless bridge device according to the MAC address, the hardware identifier, the serial number of the device, the device configuration information, the device status information, the timestamp and the random number, wherein the dynamic fingerprint generation algorithm:

[0125] ;

[0126] in, Indicates the dynamic fingerprint of the wireless bridge device. Indicates the MAC address. Represents the hardware identifier, Indicates the serial number of the device. Indicates device configuration information. Indicates device status information. Indicates the timestamp, Represents a random number.

[0127] Among them, the MAC address refers to the physical address of the network device, the hardware identifier refers to the unique identifier of one or more hardware components of the device, the serial number of the device refers to a unique number assigned to each device by the manufacturer, the device configuration information includes the network settings, security parameters, service options and other information of the device, the device status information refers to the current operating status of the device, including but not limited to power status, connection status, resource utilization and other status, the timestamp refers to an exact date and time mark used to record the moment when an event occurs, and the random number refers to a randomly generated number within a specific range, which is used to increase the uniqueness and unpredictability of the fingerprint, thereby improving security.

[0128] It should be explained that the data storage module refers to the component in the network cloud center that is responsible for collecting, storing and managing data, and the historical configuration data refers to the record of configuration changes made to wireless bridge devices or other network devices in the past period of time. These data may include snapshots of configuration information such as network settings, device parameters, security policies, access control lists (ACLs), etc. The historical performance indicator data refers to the quantitative data of recorded network or device performance, such as transmission rate, delay, packet loss rate, throughput, error rate, etc. The historical resource usage data refers to the usage record of network or device resources (such as CPU usage, memory usage, disk space usage, network bandwidth usage, etc.), which are used to analyze the health status and performance trends of the network. These data help identify resource bottlenecks and optimize resource allocation.

[0129] S3. Define a parameter threshold group of the wireless bridge device, construct a simulation environment of the network to be connected, wherein the simulation environment includes a state space and an action space, configure a configuration performance reward function, a DQN reinforcement algorithm, and a bridge environment perception network of the simulation environment.

[0130] The present invention can ensure that the wireless bridge device operates in the best state and discover potential problems in time by defining the parameter threshold group of the wireless bridge device. The parameter threshold group refers to a set of predefined value ranges used to indicate the parameter values ​​of the wireless bridge device in normal and abnormal operating states.

[0131] In detail, the construction of the simulation environment of the network to be connected includes:

[0132] Determining a network state variable of the network to be connected;

[0133] Defining state descriptions and state boundaries of the network state variables;

[0134] Constructing the state space of the network to be connected through the state description and the state boundary;

[0135] Determine the action type of the network to be connected;

[0136] defining an action representation and an action impact of the action type;

[0137] Constructing an action space of the network to be connected according to the action representation and the action impact;

[0138] Based on the state space and the action space, a simulation environment of the network to be connected is constructed.

[0139] Among them, the network state variables refer to parameters or indicators used to describe the state of the network at a certain moment. These variables can be quantitative indicators of network performance, such as bandwidth utilization, delay, packet loss rate, connection status and other indicators. The state description refers to how to combine network state variables into a meaningful representation. The state boundary refers to the effective range of the network state variable. The state space refers to the set consisting of all possible state descriptions. The action type refers to the operations that can be performed in the network simulation environment. These operations can be operations such as changing network configuration, adjusting resource allocation, starting or stopping services, etc. The action representation refers to how to encode or describe the action type. The action impact refers to the impact on the network state after executing an action. The action space refers to the set consisting of all possible action representations. The simulation environment refers to a virtual test platform that simulates the configuration, behavior and performance of the actual network.

[0140] The present invention helps the reinforcement learning agent learn how to optimize the configuration of the wireless bridge under different network conditions by configuring the configuration performance reward function of the simulation environment, the DQN reinforcement algorithm and the bridge environment perception network.

[0141] In detail, the configuration of the simulation environment includes:

[0142] determining key performance indicators of the simulation environment;

[0143] defining reward rules for said key performance indicators;

[0144] According to the reward rule, construct a performance reward function of the key performance indicator;

[0145] Constructing a deep neural network of the simulated environment;

[0146] Configuring a DQN reinforcement algorithm for the simulation environment through the deep neural network;

[0147] Determining perceived environmental parameters of the simulated environment, and constructing an environmental perception device of the simulated environment based on the perceived environmental parameters;

[0148] Construct a bridge environment perception network of the environment perception device.

[0149] Among them, the key performance indicators refer to a series of quantitative indicators used to measure the performance of a network or system, the reward rules refer to a series of rules set to guide the reinforcement learning algorithm to learn to optimize the network configuration. Exemplarily, the reward rules can be rules such as improving bandwidth utilization or reducing latency will obtain positive rewards, increasing packet loss rate or reducing signal strength will obtain negative rewards, etc. The performance reward function refers to a function that calculates the reward value based on the current network state and the actions taken, the deep neural network refers to a neural network structure that contains multiple hidden layers and can learn high-level features of data, the DQN reinforcement algorithm refers to an algorithm that combines deep learning and reinforcement learning, the perceived environmental parameters refer to data collected from the environment for influencing decisions, the environmental perception device refers to a device that can monitor and collect environmental data, such as a sensor, and the bridge environmental perception network refers to a network composed of multiple environmental perception devices that work together to collect and transmit data for use by wireless bridge devices to better adapt to environmental changes.

[0150] Furthermore, configuring the DQN reinforcement algorithm of the simulation environment through the deep neural network includes:

[0151] identifying neural network parameters of the deep neural network;

[0152] Constructing a DQN initial reinforcement algorithm for the simulation environment according to the neural network parameters;

[0153] Based on the neural network parameters, the algorithm loss of the DQN initial reinforcement algorithm in the simulation environment is calculated using the following formula:

[0154] ;

[0155] in, represents the algorithm loss of the DQN initial reinforcement algorithm, Indicates The actual Q value of the simulated environment, Indicates The output Q value of the DQN initial reinforcement algorithm in the simulation environment, Indicates The environmental state in the simulated environment, represents the DQN initial reinforcement algorithm, Indicates The environmental actions in the simulated environment, represents the neural network parameters;

[0156] Based on the algorithm loss, the DQN initial reinforcement algorithm is optimized to obtain the DQN reinforcement algorithm of the simulation environment.

[0157] The neural network parameters are trainable parameters in the deep neural network, including weights and biases. The DQN initial reinforcement algorithm refers to the initial version of the deep Q-network. The algorithm loss refers to an indicator used to measure the performance of the DQN algorithm, which represents the difference between the predicted Q value and the actual Q value. The actual Q value refers to the difference between the predicted Q value and the actual Q value under the environment state. Environmental Action The true value of the output Q value refers to the environmental state Environmental Action The predicted value of The current state of the simulated environment, the environmental action refers to the Take actions in a simulated environment.

[0158] S4. According to the parameter threshold group, the simulation environment, the configuration performance reward function, the DQN reinforcement algorithm and the bridge environment perception network, a parameter configuration mechanism of the wireless bridge device is constructed, and the parameter configuration mechanism is deployed to the AI ​​analysis engine in the network cloud center to obtain a parameter configuration AI model.

[0159] The present invention constructs a parameter configuration mechanism for the wireless bridge device based on the parameter threshold group, the simulation environment, the configuration performance reward function, the DQN enhancement algorithm, and the bridge environment perception network, which is capable of adapting to environmental changes and automatically adjusting the configuration to optimize performance. Among them, the parameter configuration mechanism refers to a framework responsible for automatically adjusting and optimizing the working parameters of the wireless bridge device to adapt to the ever-changing network environment and performance requirements. Exemplarily, the parameter configuration mechanism integrates the parameter threshold group, the configuration performance reward function, the DQN enhancement algorithm, and the bridge environment perception network into the simulation environment for simulation training.

[0160] The present invention deploys the parameter configuration mechanism to the AI ​​analysis engine in the network cloud center, and obtains the parameter configuration AI model, which can realize efficient management and optimization of wireless networks and improve the automation level and intelligence of the network, wherein the AI ​​analysis engine refers to a software platform that integrates artificial intelligence algorithms and data processing capabilities, and the parameter configuration AI model refers to a specific model trained and deployed in the AI ​​analysis engine. The tasks of the parameter configuration AI model include parameter prediction, decision making, and self-learning.

[0161] S5. Collect the real-time streaming data of the wireless bridge device, upload the real-time streaming data to the data storage module of the network cloud center using the fingerprint certificate, obtain the real-time streaming data to be analyzed, define the first configuration parameter of the wireless bridge device based on the real-time streaming data to be analyzed using the parameter configuration AI model, calculate the network connection coefficient of the first configuration parameter, optimize the first configuration parameter based on the network connection coefficient, obtain the target configuration parameter, and perform remote configuration of the wireless bridge device through the target configuration parameter.

[0162] The present invention can collect and analyze the real-time streaming data of the wireless bridge device, so that network administrators can better understand network behavior, quickly respond to problems, and continuously optimize network performance. The real-time streaming data includes key indicators such as signal strength, bandwidth usage, interference level, device temperature, and connection stability.

[0163] It should be explained that the real-time stream data to be analyzed refers to the data that needs to be pre-analyzed after the real-time stream data is uploaded to the data storage module of the network cloud center.

[0164] Optionally, based on the real-time streaming data to be analyzed, the first configuration parameter of the wireless bridge device defined by the parameter configuration AI model can be dynamically adjusted based on the real-time streaming data and the prediction of the AI ​​model to optimize network performance and efficiency.

[0165] In detail, based on the real-time stream data to be analyzed, defining the first configuration parameter of the wireless bridge device using the parameter configuration AI model includes:

[0166] Preprocessing the real-time stream data to be analyzed to obtain preprocessed real-time stream data;

[0167] Extracting decision configuration features of the preprocessed real-time stream data;

[0168] Based on the decision configuration features, using the parameter configuration AI model to analyze the initial configuration parameters of the wireless bridge device;

[0169] Calculating a network risk coefficient of the initial configuration parameters;

[0170] When the network risk coefficient meets a preset network risk threshold, the initial configuration parameter is used as the first configuration parameter of the wireless bridge device.

[0171] Among them, the pre-processed real-time streaming data refers to the real-time streaming data after a series of data pre-processing steps, which include but are not limited to data cleaning, formatting, standardization and conversion to ensure the quality and consistency of the data for subsequent analysis. The decision configuration features are data elements extracted from the pre-processed real-time streaming data that have an important impact on the configuration parameter decision of the wireless bridge device. These features usually include signal strength, bandwidth utilization, delay, packet loss rate, interference level, channel status, physical obstacles, temperature, power, hardware fault indication and other features. The initial configuration parameters refer to the preliminary configuration settings recommended by the AI ​​model for the wireless bridge device after analyzing the decision configuration features. These parameters may include wireless channels, transmission power, modulation methods and bandwidth allocation. The network risk coefficient refers to the parameter used to evaluate the risks that configuration parameter changes may bring to network stability, performance and security. The network risk threshold refers to the threshold used to decide whether to adopt the initial configuration parameters recommended by the AI ​​model. The first configuration parameter refers to the configuration parameter that is finally determined and applied to the wireless bridge device after AI model analysis and network risk assessment.

[0172] Further, the calculating of the network risk coefficient of the initial configuration parameters includes:

[0173] Identifying a parameter change risk factor of the initial configuration parameter;

[0174] Analyze the main effect coefficients and interaction effect coefficients of the parameter change risk factors;

[0175] Based on the main effect coefficient and the interaction effect coefficient, the interaction coefficient of the parameter change risk factor was calculated using the following formula:

[0176] ;

[0177] in, represents the interaction coefficient of the parameter change risk factor, represents the intercept term, Indicates The main effect coefficient of the risk factor for parameter change is Indicates The main effect coefficient of the risk factor for parameter change is Indicates Parameter change risk factor, Indicates Parameter change risk factor, Indicates The risk factor for parameter change and The interaction effect coefficient of the risk factor for parameter changes, represents the number of parameter change risk factors, represents the error term;

[0178] Determining the risk weight of the parameter change risk factor;

[0179] The network risk coefficient of the initial configuration parameters is calculated according to the interaction coefficient and the risk weight.

[0180] Among them, the parameter change risk factor refers to changes in the configuration parameters of wireless bridge devices that may lead to increased network risks. These factors may include parameters such as the frequency of configuration parameter changes, the magnitude of changes, and parameter types (such as security and performance related). The main effect coefficient refers to the independent influence of a single parameter change risk factor on network risk. The interaction effect coefficient refers to the additional influence of two or more parameter change risk factors on network risk when they act together. The interaction coefficient refers to the effect of the interaction between two parameter change risk factors on network risk. The intercept term refers to the baseline value of the network risk coefficient when all parameter change risk factors are 0. The error term refers to the random variation or measurement error that the model cannot explain. The risk weight refers to the weight assigned to each parameter change risk factor, reflecting the importance of the risk factor in the entire network risk. The network risk coefficient refers to a comprehensive indicator used to quantify the network risk brought about by the change of wireless bridge device configuration parameters.

[0181] It should be explained that the network connection coefficient refers to an indicator used to measure the impact of network configuration parameters on network connection quality. In detail, the network connection coefficient can be obtained by statistically analyzing indicators such as signal strength, bandwidth, delay, and reliability.

[0182] Finally, the present invention optimizes the first configuration parameters to obtain target configuration parameters. The remote configuration of the wireless bridge device can effectively optimize the configuration parameters of the wireless bridge device by using the target configuration parameters, and improve the network performance through remote configuration. The target configuration parameters refer to a set of configuration parameters determined after the optimization process, which are intended to achieve the best performance of the wireless bridge device and the optimized operation of the network. The remote configuration refers to the process of remotely accessing the management interface of the wireless bridge device through the network to set, modify or monitor the configuration parameters of the device.

[0183] Compared with the problems described in the background technology, the embodiments of the present invention can obtain the network connection requirements of the network to be connected in the network cloud center through accurate demand analysis, so as to ensure that the network planning matches the actual requirements and avoid waste or shortage of resources; further, the embodiments of the present invention can optimize the quality and coverage of the wireless signal and improve the overall network performance by defining the remote configuration requirements of the bridge of the network to be connected. Furthermore, the embodiments of the present invention can adjust the wireless signal strength and channel allocation according to the coverage requirements based on the network connection requirements and the remote configuration requirements of the bridge to optimize the coverage and signal quality of the wireless network by configuring the wireless bridge device of the network to be connected. Furthermore, the present invention uses the device authentication module in the network cloud center through the bridge device information to allocate the fingerprint certificate of the wireless bridge device to ensure that the wireless bridge device is a legitimate device in the network and protect the communication between the device and the network cloud center from being tampered with. Furthermore, the present invention can ensure the wireless bridge device by defining the parameter threshold group of the wireless bridge device. Run in the best state and discover potential problems in time. Next, the present invention helps the reinforcement learning agent learn how to optimize the configuration of the wireless bridge under different network conditions by configuring the configuration performance reward function of the simulation environment, the DQN reinforcement algorithm and the bridge environment perception network. The present invention constructs the parameter configuration mechanism of the wireless bridge device according to the parameter threshold group, the simulation environment, the configuration performance reward function, the DQN reinforcement algorithm and the bridge environment perception network, which can adapt to environmental changes and automatically adjust the configuration to optimize performance. Furthermore, the present invention can collect the real-time streaming data of the wireless bridge device by collecting and analyzing these real-time streaming data, so that the network administrator can better understand the network behavior, respond to problems quickly, and continuously optimize the network performance. Finally, the present invention optimizes the first configuration parameter to obtain the target configuration parameter. The remote configuration of the wireless bridge device can effectively optimize the configuration parameters of the wireless bridge device through the target configuration parameter, and improve the network performance through remote configuration. Therefore, the present invention can improve the network performance of the wireless bridge configuration.

[0184] Embodiment 2:

[0185] like Figure 2 , which is a functional module diagram of a remote configuration system for a wireless bridge provided by an embodiment of the present invention.

[0186] The remote configuration system 200 of the wireless bridge of the present invention can be installed in an electronic device. According to the functions to be implemented, the remote configuration system 200 of the wireless bridge can include a wireless bridge device construction module 201, a fingerprint certificate issuing module 202, a simulation environment construction module 203, a parameter configuration model construction module 204 and a bridge remote configuration module 205. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0187] In this embodiment, the functions of each module / unit are as follows:

[0188] The wireless bridge device construction module 201 is used to obtain the network connection requirements of the network to be connected in the network cloud center, define the bridge remote configuration requirements of the network to be connected, and configure the wireless bridge device of the network to be connected based on the network connection requirements and the bridge remote configuration requirements;

[0189] The fingerprint certificate issuing module 202 is used to obtain the bridge device information of the wireless bridge device, allocate the fingerprint certificate of the wireless bridge device through the bridge device information using the device authentication module in the network cloud center, and collect the historical network data of the data storage module in the network cloud center, wherein the historical network data includes historical configuration data, historical performance indicator data and historical resource usage data;

[0190] The simulation environment construction module 203 is used to define the parameter threshold group of the wireless bridge device, construct the simulation environment of the network to be connected, wherein the simulation environment includes a state space and an action space, and configure the configuration performance reward function, the DQN reinforcement algorithm and the bridge environment perception network of the simulation environment;

[0191] The parameter configuration model building module 204 is used to build a parameter configuration mechanism for the wireless bridge device according to the parameter threshold group, the simulation environment, the configuration performance reward function, the DQN reinforcement algorithm and the bridge environment perception network, and deploy the parameter configuration mechanism to the AI ​​analysis engine in the network cloud center to obtain a parameter configuration AI model;

[0192] The bridge remote configuration module 205 is used to collect real-time streaming data of the wireless bridge device, upload the real-time streaming data to the data storage module of the network cloud center using the fingerprint certificate, obtain the real-time streaming data to be analyzed, and define the first configuration parameter of the wireless bridge device based on the real-time streaming data to be analyzed using the parameter configuration AI model, calculate the network connection coefficient of the first configuration parameter, optimize the first configuration parameter based on the network connection coefficient, obtain the target configuration parameter, and perform remote configuration of the wireless bridge device through the target configuration parameter.

[0193] In detail, each module described in the remote configuration system 200 of the wireless bridge described in the embodiment of the present invention adopts the same technical means as the remote configuration method of the wireless bridge described in the accompanying drawings when used, and can produce the same technical effects, which will not be repeated here.

[0194] An embodiment of the present invention provides an electronic device for implementing a remote configuration method of a wireless bridge.

[0195] See also Figure 3 As shown, the electronic device may include a processor 30, a memory 31, a communication bus 32 and a communication interface 33, and may also include a computer program stored in the memory 31 and executable on the processor 30, such as a remote configuration method program for a wireless bridge.

[0196] In some embodiments, the processor may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and a combination of various control chips, etc. The processor is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes various functions of the electronic device and processes data by running or executing programs or modules stored in the memory (for example, executing a remote configuration program of a wireless bridge, etc.), and calling data stored in the memory.

[0197] The memory includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory may be an internal storage unit of an electronic device, such as a mobile hard disk of the electronic device. In other embodiments, the memory may also be an external storage device of an electronic device, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Further, the memory may also include both an internal storage unit of the electronic device and an external storage device. The memory may be used not only to store application software and various types of data installed in the electronic device, such as the code of a remote configuration program based on a wireless bridge, but also to temporarily store data that has been output or is to be output.

[0198] The communication bus may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory and at least one processor, etc.

[0199] The communication interface is used for communication between the above-mentioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the user interface may also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device and to display a visual user interface.

[0200] For example, although not shown, the electronic device may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor through a power management system, so that the power management system can realize functions such as charging management, discharging management, and power consumption management. The power source may also include any components such as one or more DC or AC power sources, recharging systems, power failure detection circuits, power converters or inverters, and power status indicators. The electronic device may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0201] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0202] The remote configuration program of the wireless bridge stored in the memory of the electronic device is a combination of multiple instructions, and when running in the processor, it can achieve:

[0203] Obtaining the network connection requirements of the network to be connected in the network cloud center, defining the remote configuration requirements of the bridge of the network to be connected, and configuring the wireless bridge device of the network to be connected based on the network connection requirements and the remote configuration requirements of the bridge;

[0204] Acquire the bridge device information of the wireless bridge device, allocate the fingerprint certificate of the wireless bridge device by using the device authentication module in the network cloud center through the bridge device information, and collect the historical network data of the data storage module in the network cloud center, wherein the historical network data includes historical configuration data, historical performance indicator data and historical resource usage data;

[0205] Defining a parameter threshold group of the wireless bridge device, constructing a simulation environment of the network to be connected, wherein the simulation environment includes a state space and an action space, configuring a configuration performance reward function, a DQN reinforcement algorithm, and a bridge environment perception network of the simulation environment;

[0206] According to the parameter threshold group, the simulation environment, the configuration performance reward function, the DQN reinforcement algorithm and the bridge environment perception network, a parameter configuration mechanism of the wireless bridge device is constructed, and the parameter configuration mechanism is deployed to the AI ​​analysis engine in the network cloud center to obtain a parameter configuration AI model;

[0207] Collect real-time streaming data of the wireless bridge device, upload the real-time streaming data to the data storage module of the network cloud center using the fingerprint certificate, obtain the real-time streaming data to be analyzed, define the first configuration parameter of the wireless bridge device based on the real-time streaming data to be analyzed using the parameter configuration AI model, calculate the network connection coefficient of the first configuration parameter, optimize the first configuration parameter based on the network connection coefficient, obtain the target configuration parameter, and perform remote configuration of the wireless bridge device through the target configuration parameter.

[0208] Specifically, the specific implementation method of the processor for the above instructions can refer to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, which will not be repeated here.

[0209] Furthermore, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or system that can carry the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0210] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement:

[0211] Obtaining the network connection requirements of the network to be connected in the network cloud center, defining the remote configuration requirements of the bridge of the network to be connected, and configuring the wireless bridge device of the network to be connected based on the network connection requirements and the remote configuration requirements of the bridge;

[0212] Acquire the bridge device information of the wireless bridge device, allocate the fingerprint certificate of the wireless bridge device by using the device authentication module in the network cloud center through the bridge device information, and collect the historical network data of the data storage module in the network cloud center, wherein the historical network data includes historical configuration data, historical performance indicator data and historical resource usage data;

[0213] Defining a parameter threshold group of the wireless bridge device, constructing a simulation environment of the network to be connected, wherein the simulation environment includes a state space and an action space, configuring a configuration performance reward function, a DQN reinforcement algorithm, and a bridge environment perception network of the simulation environment;

[0214] According to the parameter threshold group, the simulation environment, the configuration performance reward function, the DQN reinforcement algorithm and the bridge environment perception network, a parameter configuration mechanism of the wireless bridge device is constructed, and the parameter configuration mechanism is deployed to the AI ​​analysis engine in the network cloud center to obtain a parameter configuration AI model;

[0215] Collect real-time streaming data of the wireless bridge device, upload the real-time streaming data to the data storage module of the network cloud center using the fingerprint certificate, obtain the real-time streaming data to be analyzed, define the first configuration parameter of the wireless bridge device based on the real-time streaming data to be analyzed using the parameter configuration AI model, calculate the network connection coefficient of the first configuration parameter, optimize the first configuration parameter based on the network connection coefficient, obtain the target configuration parameter, and perform remote configuration of the wireless bridge device through the target configuration parameter.

[0216] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0217] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0218] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0219] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0220] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0221] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0222] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or systems stated in a system claim can also be implemented by one unit or system through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

Claims

1. A remote configuration method for a wireless bridge, characterized in that: The method comprises: Obtaining the network connection requirements of the network to be connected in the network cloud center, defining the remote configuration requirements of the bridge of the network to be connected, and configuring the wireless bridge device of the network to be connected based on the network connection requirements and the remote configuration requirements of the bridge; Acquire the bridge device information of the wireless bridge device, allocate the fingerprint certificate of the wireless bridge device by using the device authentication module in the network cloud center through the bridge device information, and collect the historical network data of the data storage module in the network cloud center, wherein the historical network data includes historical configuration data, historical performance indicator data and historical resource usage data; Defining a parameter threshold group of the wireless bridge device, constructing a simulation environment of the network to be connected, wherein the simulation environment includes a state space and an action space, configuring a configuration performance reward function, a DQN reinforcement algorithm, and a bridge environment perception network of the simulation environment; According to the parameter threshold group, the simulation environment, the configuration performance reward function, the DQN reinforcement algorithm and the bridge environment perception network, a parameter configuration mechanism of the wireless bridge device is constructed, and the parameter configuration mechanism is deployed to the AI ​​analysis engine in the network cloud center to obtain a parameter configuration AI model; Collect real-time streaming data of the wireless bridge device, upload the real-time streaming data to the data storage module of the network cloud center using the fingerprint certificate, obtain the real-time streaming data to be analyzed, define the first configuration parameter of the wireless bridge device based on the real-time streaming data to be analyzed using the parameter configuration AI model, calculate the network connection coefficient of the first configuration parameter, optimize the first configuration parameter based on the network connection coefficient, obtain the target configuration parameter, and perform remote configuration of the wireless bridge device through the target configuration parameter.

2. The remote configuration method of a wireless bridge as claimed in claim 1, characterized in that: The configuring the wireless bridge device of the network to be connected based on the network connection requirement and the bridge remote configuration requirement includes: Obtaining the first version of the firmware of the network to be connected, and extracting the firmware source code of the first version of the firmware; Determining network parameters of the firmware source code according to the network connection requirements and the bridge remote configuration requirements; Identify the network protocol of the firmware source code, construct a network protocol support mechanism for the firmware source code based on the network protocol, and construct a security authentication mechanism for the firmware source code; Modifying the firmware source code according to the network parameters, the network protocol support mechanism, and the security authentication mechanism to obtain a modified source code; Configuring a cross-compilation environment for the initial version of the firmware, and cross-compiling the modified source code based on the cross-compilation environment to obtain a newly compiled firmware; Testing the newly compiled firmware to obtain a firmware test result, and analyzing the firmware performance of the newly compiled firmware according to the firmware test result; When the firmware performance meets the preset firmware performance standard, using the newly compiled firmware as the wireless bridge firmware for connecting to the network; The wireless bridge firmware is integrated into a preset initial wireless bridge device to obtain the wireless bridge device of the network to be connected.

3. The remote configuration method of a wireless bridge as claimed in claim 2, characterized in that: The method of allocating the fingerprint certificate of the wireless bridge device by using the device authentication module in the network cloud center through the bridge device information includes: Configuring zero-touch configuration of the wireless bridge device; The bridge device information is transmitted to the network cloud center by using the zero-touch configuration to obtain target device information; Based on the target device information, construct a unique device identity record of the target device information; Constructing a dynamic fingerprint generation algorithm for the wireless bridge device; According to the unique device identity record, constructing a dynamic fingerprint of the wireless bridge device using the dynamic fingerprint generation algorithm; Using the dynamic fingerprint, sending a fingerprint authentication request to a device authentication module in the network cloud center; When the fingerprint authentication request meets the preset authentication standard, the fingerprint certificate of the wireless bridge device is issued.

4. The remote configuration method of a wireless bridge as claimed in claim 3, characterized in that: The step of constructing the dynamic fingerprint of the wireless bridge device using the dynamic fingerprint generation algorithm according to the unique device identity record includes: Determine, based on the unique device identity record, a MAC address, a hardware identifier, a serial number of the device, device configuration information, and device status information of the wireless bridge device; A timestamp and a random number identifying the wireless bridge device; The dynamic fingerprint generation algorithm is used to construct the dynamic fingerprint of the wireless bridge device according to the MAC address, the hardware identifier, the serial number of the device, the device configuration information, the device status information, the timestamp and the random number, wherein the dynamic fingerprint generation algorithm: ； in, Indicates the dynamic fingerprint of the wireless bridge device. Indicates the MAC address. Represents the hardware identifier, Indicates the serial number of the device. Indicates device configuration information. Indicates device status information. Indicates the timestamp, represents a random number, and f represents a dynamic fingerprint generation algorithm.

5. The remote configuration method of a wireless bridge as claimed in claim 4, characterized in that: The step of constructing the simulation environment of the network to be connected includes: Determining a network state variable of the network to be connected; Defining state descriptions and state boundaries of the network state variables; Constructing the state space of the network to be connected through the state description and the state boundary; Determine the action type of the network to be connected; defining an action representation and an action impact of the action type; Constructing an action space of the network to be connected according to the action representation and the action impact; Based on the state space and the action space, a simulation environment of the network to be connected is constructed.

6. The remote configuration method of a wireless bridge as claimed in claim 5, characterized in that: The configuration of the simulation environment includes configuring a performance reward function, a DQN reinforcement algorithm, and a bridge environment perception network, including: determining key performance indicators of the simulation environment; defining reward rules for said key performance indicators; According to the reward rule, construct a performance reward function of the key performance indicator; Constructing a deep neural network of the simulated environment; Configuring a DQN reinforcement algorithm for the simulation environment through the deep neural network; Determining perceived environmental parameters of the simulated environment, and constructing an environmental perception device of the simulated environment based on the perceived environmental parameters; Construct a bridge environment perception network of the environment perception device.

7. The remote configuration method of a wireless bridge as claimed in claim 6, characterized in that: The DQN reinforcement algorithm of configuring the simulation environment through the deep neural network includes: identifying neural network parameters of the deep neural network; Constructing a DQN initial reinforcement algorithm for the simulation environment according to the neural network parameters; Based on the neural network parameters, the algorithm loss of the DQN initial reinforcement algorithm in the simulation environment is calculated using the following formula: ； in, represents the algorithm loss of the DQN initial reinforcement algorithm, Indicates The actual Q value of the simulated environment, Indicates The output Q value of the DQN initial reinforcement algorithm in the simulation environment, Indicates The environmental state in the simulated environment, represents the DQN initial reinforcement algorithm, Indicates The environmental actions in the simulated environment, represents the neural network parameters; Based on the algorithm loss, the DQN initial reinforcement algorithm is optimized to obtain the DQN reinforcement algorithm of the simulation environment.

8. The remote configuration method of a wireless bridge as claimed in claim 7, characterized in that: The method of defining the first configuration parameter of the wireless bridge device by using the parameter configuration AI model based on the real-time stream data to be analyzed includes: Preprocessing the real-time stream data to be analyzed to obtain preprocessed real-time stream data; Extracting decision configuration features of the preprocessed real-time stream data; Based on the decision configuration features, using the parameter configuration AI model to analyze the initial configuration parameters of the wireless bridge device; Calculating a network risk coefficient of the initial configuration parameters; When the network risk coefficient meets a preset network risk threshold, the initial configuration parameter is used as the first configuration parameter of the wireless bridge device.

9. The remote configuration method of a wireless bridge as claimed in claim 8, characterized in that: The calculating the network risk coefficient of the initial configuration parameter comprises: Identifying a parameter change risk factor of the initial configuration parameter; Analyze the main effect coefficients and interaction effect coefficients of the parameter change risk factors; Based on the main effect coefficient and the interaction effect coefficient, the interaction coefficient of the parameter change risk factor was calculated using the following formula: ； in, represents the interaction coefficient of the parameter change risk factor, represents the intercept term, Indicates The main effect coefficient of the risk factor for parameter change is Indicates Parameter change risk factor, Indicates Parameter change risk factor, Indicates The risk factor for parameter change and The interaction effect coefficient of the risk factor for parameter changes, represents the number of parameter change risk factors, represents the error term; Determining the risk weight of the parameter change risk factor; The network risk coefficient of the initial configuration parameters is calculated according to the interaction coefficient and the risk weight.

10. A remote configuration system for a wireless bridge, characterized in that: A system for executing a remote configuration method for a wireless bridge according to any one of claims 1 to 9, the system comprising: A wireless bridge device construction module is used to obtain the network connection requirements of the network to be connected in the network cloud center, define the remote configuration requirements of the bridge of the network to be connected, and configure the wireless bridge device of the network to be connected based on the network connection requirements and the remote configuration requirements of the bridge; A fingerprint certificate issuing module is used to obtain the bridge device information of the wireless bridge device, allocate the fingerprint certificate of the wireless bridge device by using the bridge device information and the device authentication module in the network cloud center, and collect the historical network data of the data storage module in the network cloud center, wherein the historical network data includes historical configuration data, historical performance indicator data and historical resource usage data; A simulation environment construction module, used to define a parameter threshold group of the wireless bridge device, construct a simulation environment of the network to be connected, wherein the simulation environment includes a state space and an action space, and configure a configuration performance reward function, a DQN reinforcement algorithm, and a bridge environment perception network of the simulation environment; A parameter configuration model construction module is used to construct a parameter configuration mechanism for the wireless bridge device according to the parameter threshold group, the simulation environment, the configuration performance reward function, the DQN reinforcement algorithm, and the bridge environment perception network, and deploy the parameter configuration mechanism to the AI ​​analysis engine in the network cloud center to obtain a parameter configuration AI model; The bridge remote configuration module is used to collect real-time streaming data of the wireless bridge device, upload the real-time streaming data to the data storage module of the network cloud center using the fingerprint certificate, obtain the real-time streaming data to be analyzed, and define the first configuration parameter of the wireless bridge device based on the real-time streaming data to be analyzed using the parameter configuration AI model, calculate the network connection coefficient of the first configuration parameter, optimize the first configuration parameter based on the network connection coefficient, obtain the target configuration parameter, and perform remote configuration of the wireless bridge device through the target configuration parameter.

Images