CN117527479B

CN117527479B - Soft bus networking connection method, device, equipment and storage medium

Info

Publication number: CN117527479B
Application number: CN202410025617.2A
Authority: CN
Inventors: 胡伟; 范光彬; 董建涛; 李达; 郑韩; 赵成斌
Original assignee: Shenzhen Issmart Science And Technology Co ltd
Current assignee: Shenzhen Issmart Science And Technology Co ltd
Priority date: 2024-01-08
Filing date: 2024-01-08
Publication date: 2024-03-29
Anticipated expiration: 2044-01-08
Also published as: CN117527479A

Abstract

The invention relates to the technical field of Internet of things, and discloses a method, a device, equipment and a storage medium for connecting a soft bus networking, which are used for improving the connection efficiency of the soft bus networking connection. The method comprises the following steps: automatically discovering the target soft bus based on the device discovery mechanism to obtain a plurality of target devices and a device characteristic information set of each target device; analyzing networking connection constraint conditions to obtain networking connection constraint conditions and constructing an initial soft bus networking connection model; performing networking connection network environment analysis to obtain networking connection network environment data; constructing a plurality of networking connection prediction networks and monitoring performance states to obtain a plurality of prediction network performance parameter data; defining a network performance optimization target and carrying out optimization strategy analysis to obtain a target network optimization strategy; and carrying out network optimization processing to obtain a plurality of networking connection target networks, and carrying out dynamic model updating to obtain a target soft bus networking connection model.

Description

Soft bus networking connection method, device, equipment and storage medium

Technical Field

The present invention relates to the field of internet of things, and in particular, to a method, an apparatus, a device, and a storage medium for connecting a soft bus network.

Background

In today's increasingly complex and dynamic network environments, research into soft bus networking connectivity methods is becoming particularly important. The traditional hardware bus connection mode has a plurality of limitations in a large-scale distributed system, such as high hardware cost, poor expandability, insensitivity to network changes and the like. To overcome these problems, researchers have come to focus on soft bus networking connectivity methods that enable flexible, configurable device connectivity in a software-defined manner to accommodate changing network environments.

Challenges faced by existing schemes include problems with automatic discovery of devices, analysis of connection constraints, dynamic adaptation of the network environment, etc. In large-scale networks, the automatic discovery of devices becomes particularly complex, requiring efficient mechanisms to ensure that all devices in the network are effectively identified and integrated. In addition, due to the ever changing network environment, the stability and performance of the connection becomes a key concern, and a dynamic approach is needed to continuously optimize the connection model.

Disclosure of Invention

The invention provides a method, a device, equipment and a storage medium for connecting a soft bus networking, which are used for improving the connection efficiency of the soft bus networking connection.

The first aspect of the present invention provides a soft bus networking connection method, which includes: automatically discovering the target soft bus based on a preset device discovery mechanism to obtain a plurality of target devices, and extracting device characteristics of the plurality of target devices to obtain a device characteristic information set of each target device; respectively analyzing networking connection constraint conditions of the plurality of target devices according to the device characteristic information set to obtain networking connection constraint conditions of each target device, and performing soft bus networking connection on the plurality of target devices according to the networking connection constraint conditions to construct an initial soft bus networking connection model; acquiring networking transmission channel data of each target device, and carrying out networking connection network environment analysis on the initial soft bus networking connection model according to the networking transmission channel data to obtain networking connection network environment data; constructing a plurality of networking connection prediction networks corresponding to the initial soft bus networking connection model according to the networking connection network environment data, and respectively monitoring performance states of the networking connection prediction networks to obtain a plurality of prediction network performance parameter data; defining a network performance optimization target of each networking connection prediction network according to the plurality of prediction network performance parameter data, and respectively carrying out optimization strategy analysis on the network performance optimization targets to obtain a target network optimization strategy; and carrying out network optimization processing on the networking connection prediction networks according to the target network optimization strategy to obtain networking connection target networks, and carrying out model dynamic update on the initial soft bus networking connection model according to the networking connection target networks to obtain a target soft bus networking connection model.

With reference to the first aspect, in a first implementation manner of the first aspect of the present invention, the automatically discovering devices on the target soft bus based on a preset device discovery mechanism to obtain a plurality of target devices, and extracting device features of the plurality of target devices to obtain a device feature information set of each target device, where the automatically discovering devices includes: request monitoring is carried out on a target soft bus based on a preset device discovery mechanism, so that device discovery requests sent by a plurality of candidate devices are obtained; performing request analysis on the device discovery requests sent by the plurality of candidate devices to obtain a request identifier of each candidate device, and acquiring a device registration state corresponding to each candidate device according to the request identifier; matching target equipment discovery rules corresponding to the plurality of candidate equipment according to the equipment registration state, and screening the plurality of candidate equipment according to the target equipment discovery rules and the equipment registration state to obtain a plurality of target equipment; generating a corresponding target device list according to the plurality of target devices, and extracting device characteristics of the plurality of target devices according to the target device list to obtain a device characteristic information list; and performing feature information set conversion on the device feature information list to obtain a device feature information set of each target device.

With reference to the first aspect, in a second implementation manner of the first aspect of the present invention, the performing, according to the device feature information set, analysis of networking connection constraint conditions on the plurality of target devices to obtain networking connection constraint conditions of each target device, and performing soft bus networking connection on the plurality of target devices according to the networking connection constraint conditions, to construct an initial soft bus networking connection model, includes: performing feature clustering on the equipment feature information set to obtain N key features of each target equipment; acquiring networking connection standards of the target soft bus, and respectively defining a plurality of initial connection constraint conditions of the N key features; performing equipment matching on the plurality of initial connection constraint conditions and the plurality of target devices to obtain networking connection constraint conditions of each target device; and executing the soft bus networking connection operation according to the networking connection constraint condition, and constructing a corresponding initial soft bus networking connection model.

With reference to the first aspect, in a third implementation manner of the first aspect of the present invention, the obtaining networking transmission channel data of each target device, and performing networking connection network environment analysis on the initial soft bus networking connection model according to the networking transmission channel data, to obtain networking connection network environment data, includes: acquiring networking transmission channel data of each target device, wherein the networking transmission channel data comprises: bandwidth, delay, and packet loss rate; respectively carrying out data standardization processing on the networking transmission channel data to obtain a plurality of standard transmission channel data; performing data matrix conversion on the plurality of standard transmission channel data to obtain a target transmission channel matrix; performing association relation integration on the target transmission channel matrix and the initial soft bus networking connection model to obtain a target association relation; and according to the target association relation, carrying out networking connection network environment analysis on the initial soft bus networking connection model to obtain networking connection network environment data.

With reference to the first aspect, in a fourth implementation manner of the first aspect of the present invention, the constructing a plurality of networking connection prediction networks corresponding to the initial soft bus networking connection model according to the networking connection network environment data, and performing performance state monitoring on the plurality of networking connection prediction networks to obtain a plurality of predicted network performance parameter data respectively, includes: performing data preprocessing on the networking connection network environment data to obtain target connection network environment data; inputting the target connection network environment data into a preset bidirectional long-short-time memory network, extracting forward hidden features from the target connection network environment data through a forward long-short-time memory network in the bidirectional long-short-time memory network to obtain forward hidden features, extracting backward hidden features from the target connection network environment data through a backward long-short-time memory network in the bidirectional long-short-time memory network to obtain backward hidden features, and carrying out feature fusion on the forward hidden features and the backward hidden features to obtain target fusion features; performing networking division and prediction on the initial soft bus networking connection model according to the target fusion characteristics to obtain a plurality of networking connection prediction networks; and respectively monitoring the performance states of the plurality of networking connection prediction networks to obtain a plurality of prediction network performance parameter data.

With reference to the first aspect, in a fifth implementation manner of the first aspect of the present invention, the defining a network performance optimization objective of each networking connection prediction network according to the plurality of prediction network performance parameter data, and performing an optimization policy analysis on the network performance optimization objective to obtain a target network optimization policy respectively includes: performing performance parameter comprehensive analysis on the plurality of predicted network performance parameter data to obtain a plurality of performance parameter comprehensive analysis indexes; defining a network performance optimization target of each networking connection prediction network according to the comprehensive analysis indexes of the plurality of performance parameters; respectively carrying out optimization strategy analysis on the network performance optimization targets to obtain an initial network optimization strategy of each networking connection prediction network; carrying out global strategy group initialization on the initial network optimization strategy of each networking connection prediction network through a preset global optimization algorithm to obtain a plurality of candidate network optimization strategies; performing policy fitness analysis on the plurality of candidate network optimization policies respectively to obtain policy fitness data of each candidate network optimization policy; and carrying out policy optimization analysis on the plurality of candidate network optimization policies according to the policy fitness data to obtain a target network optimization policy.

With reference to the first aspect, in a sixth implementation manner of the first aspect of the present invention, performing network optimization processing on the plurality of networking connection prediction networks according to the target network optimization policy to obtain a plurality of networking connection target networks, and performing model dynamic update on the initial soft bus networking connection model according to the plurality of networking connection target networks to obtain a target soft bus networking connection model, where the method includes: according to the target network optimization strategy, performing network optimization operation generation on the plurality of networking connection prediction networks to obtain a network optimization operation set of each networking connection prediction network; according to the network optimization operation set, respectively carrying out network optimization processing on each networking connection prediction network to obtain a plurality of networking connection target networks; performing model dynamic update and performance verification on the initial soft bus networking connection model according to the networking connection target networks to obtain a performance verification result of the initial soft bus networking connection model; and carrying out feedback circulation on the initial soft bus networking connection model according to the performance verification result to obtain a target soft bus networking connection model.

The second aspect of the present invention provides a soft bus networking connection device, which includes: the extraction module is used for automatically discovering the device on the target soft bus based on a preset device discovery mechanism to obtain a plurality of target devices, and extracting the device characteristics of the plurality of target devices to obtain a device characteristic information set of each target device; the construction module is used for respectively analyzing networking connection constraint conditions of the plurality of target devices according to the device characteristic information set to obtain networking connection constraint conditions of each target device, and carrying out soft bus networking connection on the plurality of target devices according to the networking connection constraint conditions to construct an initial soft bus networking connection model; the analysis module is used for acquiring networking transmission channel data of each target device, and carrying out networking connection network environment analysis on the initial soft bus networking connection model according to the networking transmission channel data to obtain networking connection network environment data; the monitoring module is used for constructing a plurality of networking connection prediction networks corresponding to the initial soft bus networking connection model according to the networking connection network environment data, and respectively monitoring performance states of the networking connection prediction networks to obtain a plurality of prediction network performance parameter data; the definition module is used for defining a network performance optimization target of each networking connection prediction network according to the plurality of prediction network performance parameter data, and respectively carrying out optimization strategy analysis on the network performance optimization targets to obtain a target network optimization strategy; and the updating module is used for carrying out network optimization processing on the networking connection prediction networks according to the target network optimization strategy to obtain networking connection target networks, and carrying out model dynamic updating on the initial soft bus networking connection model according to the networking connection target networks to obtain a target soft bus networking connection model.

A third aspect of the present invention provides a soft bus networking connection device, including: a memory and at least one processor, the memory having instructions stored therein; the at least one processor invokes the instructions in the memory to cause the soft bus networking connection device to perform the soft bus networking connection method described above.

A fourth aspect of the present invention provides a computer readable storage medium having instructions stored therein which, when run on a computer, cause the computer to perform the soft bus networking connection method described above.

In the technical scheme provided by the invention, the device discovery mechanism is based on the device discovery mechanism to automatically discover the target soft bus to obtain a plurality of target devices and a device characteristic information set of each target device; analyzing networking connection constraint conditions to obtain networking connection constraint conditions and constructing an initial soft bus networking connection model; performing networking connection network environment analysis to obtain networking connection network environment data; constructing a plurality of networking connection prediction networks and monitoring performance states to obtain a plurality of prediction network performance parameter data; defining a network performance optimization target and carrying out optimization strategy analysis to obtain a target network optimization strategy; the invention can automatically discover the equipment on the target soft bus by a system based on a preset equipment discovery mechanism, thereby realizing the automation of equipment connection. By device feature extraction, the system is able to intelligently extract key feature information, including bandwidth, latency, etc., from the target devices, helping to model the performance features of each device more accurately. By analyzing the networking connection constraint conditions of the device characteristic information set, the system can intelligently determine the connection constraint conditions of each target device, and the stability and reliability of connection are improved. By analyzing the networking connection network environment and constructing a plurality of networking connection prediction networks, the system can more comprehensively understand the network environment, optimize the soft bus networking connection model and improve the overall system performance. By defining and analyzing the network performance optimization targets, the system can intelligently formulate an optimization strategy, and the adaptability and performance of the soft bus networking connection are improved. By analyzing the predicted network performance parameter data and applying the target network optimization strategy, the system can dynamically update the soft bus networking connection model, thereby realizing the real-time adaptation to the changed network environment. Through real-time performance monitoring and feedback circulation, the system can be continuously learned and optimized, has self-adaptability, can be better adapted to continuously changing network conditions, and further improves the connection efficiency of soft bus networking connection.

Drawings

FIG. 1 is a schematic diagram of an embodiment of a method for connecting a soft bus network according to an embodiment of the present invention;

FIG. 2 is a flow chart of a networking connection constraint analysis and a soft bus networking connection in an embodiment of the present invention;

FIG. 3 is a flowchart illustrating analysis of networking connectivity network environment in accordance with an embodiment of the present invention;

FIG. 4 is a flow chart of constructing a networking connectivity prediction network and performance state monitoring in an embodiment of the present invention;

FIG. 5 is a schematic diagram of an embodiment of a soft bus networking device according to an embodiment of the present invention;

fig. 6 is a schematic diagram of an embodiment of a soft bus networking device according to an embodiment of the present invention.

Detailed Description

The embodiment of the invention provides a method, a device, equipment and a storage medium for connecting a soft bus networking, which are used for improving the connection efficiency of the soft bus networking connection. The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.

For easy understanding, the following describes a specific flow of an embodiment of the present invention, referring to fig. 1, and one embodiment of a method for connecting a soft bus network in an embodiment of the present invention includes:

s101, automatically discovering equipment on a target soft bus based on a preset equipment discovery mechanism to obtain a plurality of target equipment, and extracting equipment characteristics of the plurality of target equipment to obtain equipment characteristic information sets of each target equipment;

it is to be understood that the execution body of the present invention may be a soft bus networking connection device, and may also be a terminal or a server, which is not limited herein. The embodiment of the invention is described by taking a server as an execution main body as an example.

Specifically, request interception is performed on the target soft bus based on a preset device discovery mechanism. The server may actively listen for or respond to device discovery requests from surrounding devices. The requests contain identity information, attributes, or other relevant information of the device. Then, request parsing is performed on device discovery requests sent by the plurality of candidate devices. The purpose is to extract useful information from each request for subsequent processing. Request parsing will help determine the request identification, i.e., the identifier or unique identification of the device, for each candidate device. Meanwhile, according to the request identification, the server acquires the device registration state of each candidate device. This status information may tell the server device whether it has registered on the soft bus, is available or needs further processing. Using the device registration status, device screening is performed to obtain a plurality of target devices. Which candidate devices are suitable for connection to the soft bus and which are unsuitable are determined based on the device status. This facilitates screening out target devices. Once the target devices are screened out, the server will generate a corresponding list of target devices. The list will include all screened devices that will become candidates for connection to the soft bus. And extracting device characteristics of the target devices by using the target device list. Data about its characteristics, performance parameters and other relevant information is extracted from each target device. And finally, carrying out feature information set conversion on the device feature information list. The information extracted from the individual target devices is integrated together to create a set of device characteristic information for each target device. This set will include all information about the target device, such as device characteristics, registration status, performance parameters, etc.

S102, respectively analyzing networking connection constraint conditions of a plurality of target devices according to the device characteristic information set to obtain networking connection constraint conditions of each target device, and carrying out soft bus networking connection on the plurality of target devices according to the networking connection constraint conditions to construct an initial soft bus networking connection model;

specifically, feature clustering is performed according to the device feature information set. The device characteristic information of the target devices is classified and grouped to identify key characteristics of each target device. Feature clustering helps to simplify subsequent connection constraint analysis because different devices have different feature sets. And obtaining networking connection standards of the target soft bus. Criteria and rules that need to be met when connecting to the target device are determined. Different soft buses have different connection standards, so connection constraints need to be defined according to a particular soft bus standard. For example, if the target soft bus is a Zigbee network, the connection criteria include requirements of a maximum connection distance, a communication frequency, and connection stability. These criteria will be part of the connection constraints. A plurality of initial connection constraints are defined for each target device based on the N key features. These constraints will be defined based on the device's characteristic information and connection criteria. Different devices have different constraints depending on their characteristics and the connection requirements required. And performing equipment matching to obtain the networking connection constraint condition of each target equipment. This step will take into account the characteristic information of each target device, the initial connection constraints associated with it and the connection criteria of the soft bus, to determine the final connection constraints. And executing the soft bus networking connection operation according to the obtained connection constraint condition, and constructing a corresponding initial soft bus networking connection model. This model will include the connection constraints of each target device, as well as their connection relationship to the soft bus.

S103, acquiring networking transmission channel data of each target device, and carrying out networking connection network environment analysis on the initial soft bus networking connection model according to the networking transmission channel data to obtain networking connection network environment data;

it should be noted that, the network transmission channel data of each target device is obtained. This is basic information about each device communicating in the network, including bandwidth, delay, and packet loss rate. Such data helps to understand the quality and performance of each device's connection to the network. Data normalization is performed to ensure consistent metrics for the transmission channel data of different devices. This is a step necessary to compare and analyze the performance parameters of different devices. For example, if different devices use different units of bandwidth data (e.g., mbps, kbps, etc.), they need to be standardized to the same unit for efficient comparison and analysis. And then, carrying out data matrix conversion on the standard transmission channel data to obtain a target transmission channel matrix. The matrix comprises transmission channel data among different devices to form a multidimensional matrix, which is beneficial to comprehensively analyzing the connection performance among the devices. For example, if there are three target devices, a 3x3 matrix may be created, where each element represents the transmission channel performance between different devices. And carrying out association relation integration on the target transmission channel matrix and the initial soft bus networking connection model. The transmission channel data is combined with the device connection model to understand how the connection performance between different devices affects the whole soft bus network. For example, if the transmission channel data of a certain device indicates that there is a high delay between it and other devices, this can negatively impact the performance of the overall network. Such associations facilitate a better understanding of the network environment. And according to the target association relation, carrying out networking connection network environment analysis on the initial soft bus networking connection model so as to obtain data about the network environment. These data will include information about connection performance, network topology and potential bottlenecks. For example, analysis results show that a high latency connection of a certain device affects the real-time performance of the entire network or identifies potential network topology problems such as bottlenecks or excessive congestion.

S104, constructing a plurality of networking connection prediction networks corresponding to the initial soft bus networking connection model according to networking connection network environment data, and respectively monitoring performance states of the networking connection prediction networks to obtain a plurality of prediction network performance parameter data;

specifically, the networking connection network environment data is subjected to data preprocessing to obtain the target connection network environment data. The raw data is cleaned, normalized, or processed to ensure consistency and availability of the data. Data preprocessing may include outlier removal, filling in missing data, and the like. For example, if the network environment data includes information such as bandwidth, delay, packet loss rate, etc., the data preprocessing may include removing outliers that do not fit the actual situation, ensuring consistency and comparability of the data. The target connection network environment data is input into a preset bidirectional long and short time memory network (bidirectional LSTM). Bi-directional LSTM is a deep learning model for sequence data with forward and backward hidden layers for capturing long-term dependencies in the sequence data. The forward LSTM is used to extract forward hidden features and the backward LSTM is used to extract backward hidden features. For example, if the target link network environment data is a time series, the bidirectional LSTM may effectively capture the time dependence and extract forward and backward features regarding network performance. And carrying out feature fusion on the forward hidden features and the backward hidden features to obtain target fusion features. Feature fusion helps to integrate forward and backward information together to better describe the network environment. For example, the forward feature includes historical performance data of the network and the backward feature includes future performance predictions of the network. By fusing these features, past and future network performance may be comprehensively considered. And then, carrying out networking division and prediction on the initial soft bus networking connection model according to the target fusion characteristics to obtain a plurality of corresponding networking connection prediction networks. These predictive networks may be machine learning models that predict the connectivity and performance between different devices. For example, by inputting the target fusion feature into the predictive model, the connection state between different devices can be predicted, such as whether a connection needs to be established, an optimal connection manner, and so on. And monitoring performance states of the plurality of networking connection prediction networks to obtain a plurality of prediction network performance parameter data. These performance parameter data may be used to evaluate the accuracy and performance of each predicted network. For example, the performance parameter data may include prediction accuracy, recall, F1 score, etc. to evaluate the performance of each predicted network.

S105, defining a network performance optimization target of each networking connection prediction network according to the plurality of prediction network performance parameter data, and respectively carrying out optimization strategy analysis on the network performance optimization targets to obtain a target network optimization strategy;

specifically, performance parameter comprehensive analysis is performed on the plurality of predicted network performance parameter data to obtain a plurality of performance parameter comprehensive analysis indexes. The data of the different performance parameters is comprehensively analyzed as a set of metrics to more fully evaluate the performance of each predicted network. These metrics may include accuracy, recall, F1 score, etc. for measuring the performance of the predicted network. And defining a network performance optimization target of each networking connection prediction network according to the comprehensive analysis indexes of the plurality of performance parameters. These optimization objectives will be well defined to guide the direction of improvement in network performance. This may include increasing accuracy, decreasing false positive rates, increasing network efficiency, etc. And respectively carrying out optimization strategy analysis on the network performance optimization targets to obtain an initial network optimization strategy of each networking connection prediction network. This step involves determining how to improve each predicted network to achieve the network performance optimization objective. Each policy will be tuned and optimized according to specific performance objectives. And carrying out global strategy group initialization on the initial network optimization strategy of each networking connection prediction network through a preset global optimization algorithm so as to obtain a plurality of candidate network optimization strategies. The purpose of this step is to generate a set of candidate strategies for comparison and selection in subsequent analysis. These candidate strategies may represent different approaches and directions to achieve performance goals. And then, respectively carrying out strategy fitness analysis on the plurality of candidate network optimization strategies to obtain strategy fitness data of each candidate network optimization strategy. This step involves evaluating the adaptability and performance of each policy in the actual network environment. The fitness data may include information on performance, cost, feasibility, etc. of the policy. And carrying out policy optimization analysis on the plurality of candidate network optimization policies according to the policy fitness data so as to obtain a target network optimization policy. This step involves selecting the best performing policy to achieve the network performance optimization objective. Policy optimization analysis may consider different performance tradeoffs and constraints.

S106, carrying out network optimization processing on the networking connection prediction networks according to the target network optimization strategy to obtain networking connection target networks, and carrying out model dynamic update on the initial soft bus networking connection model according to the networking connection target networks to obtain a target soft bus networking connection model.

Specifically, according to a target network optimization strategy, performing network optimization operation generation on a plurality of networking connection prediction networks to obtain a network optimization operation set of each networking connection prediction network. The goal is to determine how to improve each predictive network to meet performance objectives. For example, if the target network optimization strategy is intended to improve the quality of real-time video streams, operations such as increasing bandwidth allocation to video streams, reducing packet loss rates, etc., are included in the set of network optimization operations. And then, according to the network optimization operation set, respectively carrying out network optimization processing on each networking connection prediction network so as to obtain a plurality of networking connection target networks. This step includes applying the previously generated set of operations to improve the performance of each predicted network. For example, for each predicted network, corresponding operations are performed according to a set of operations, such as adjusting bandwidth allocation, optimizing routing, reducing network latency, and the like. And carrying out model dynamic update and performance verification on the initial soft bus networking connection model according to the networking connection target networks. This step aims at integrating each optimized predictive network into the soft bus connection model and verifying the model performance. For example, for each target network, its connection configuration and performance parameters are compared to the initial connection model to ensure improved performance. And carrying out feedback circulation on the initial soft bus networking connection model according to the performance verification result to obtain a target soft bus networking connection model. This step includes using the performance verification results to further refine and optimize the connection model, thereby achieving better performance. For example, if the performance verification results show that the performance of a certain predictive network improves the quality of the video stream, this improvement will be fed back into the connection model to ensure better results in future connection decisions.

In the embodiment of the invention, the system can automatically discover the equipment on the target soft bus based on the preset equipment discovery mechanism, thereby realizing the automation of equipment connection. By device feature extraction, the system is able to intelligently extract key feature information, including bandwidth, latency, etc., from the target devices, helping to model the performance features of each device more accurately. By analyzing the networking connection constraint conditions of the device characteristic information set, the system can intelligently determine the connection constraint conditions of each target device, and the stability and reliability of connection are improved. By analyzing the networking connection network environment and constructing a plurality of networking connection prediction networks, the system can more comprehensively understand the network environment, optimize the soft bus networking connection model and improve the overall system performance. By defining and analyzing the network performance optimization targets, the system can intelligently formulate an optimization strategy, and the adaptability and performance of the soft bus networking connection are improved. By analyzing the predicted network performance parameter data and applying the target network optimization strategy, the system can dynamically update the soft bus networking connection model, thereby realizing the real-time adaptation to the changed network environment. Through real-time performance monitoring and feedback circulation, the system can be continuously learned and optimized, has self-adaptability, can be better adapted to continuously changing network conditions, and further improves the connection efficiency of soft bus networking connection.

In a specific embodiment, the process of executing step S101 may specifically include the following steps:

(1) Request monitoring is carried out on a target soft bus based on a preset device discovery mechanism, so that device discovery requests sent by a plurality of candidate devices are obtained;

(2) Carrying out request analysis on device discovery requests sent by a plurality of candidate devices to obtain a request identifier of each candidate device, and obtaining a device registration state corresponding to each candidate device according to the request identifier;

(3) Matching target equipment discovery rules corresponding to the candidate equipment according to the equipment registration state, and screening the candidate equipment according to the target equipment discovery rules and the equipment registration state to obtain a plurality of target equipment;

(4) Generating a corresponding target device list according to the plurality of target devices, and extracting device characteristics of the plurality of target devices according to the target device list to obtain a device characteristic information list;

(5) And performing feature information set conversion on the device feature information list to obtain a device feature information set of each target device.

Specifically, request monitoring is performed on the target soft bus based on a preset device discovery mechanism, so as to obtain device discovery requests sent by a plurality of candidate devices. The server will actively monitor the communication requests on the target soft bus to determine which devices are attempting to connect to the bus. And carrying out request analysis on the device discovery requests sent by the plurality of candidate devices to obtain the request identification of each candidate device. Request parsing is the interpretation and extraction of data in a request to determine the identity and attributes of a device. And then, the server acquires the device registration state corresponding to each candidate device according to the request identification. The device registration status indicates whether the device has registered as a legitimate device on the soft bus for communication. Once the device registration status is obtained, the server further matches target device discovery rules corresponding to the plurality of candidate devices according to the device registration status. The target device discovery rule is a preset rule for screening out target devices meeting specific requirements. Based on the target device discovery rules and the device registration status, the server performs device screening on the plurality of candidate devices, and obtains a plurality of target devices therefrom, wherein the devices meet specific conditions. The server generates a corresponding target device list, which contains basic information of the screened target devices, such as device types and unique identifiers. And extracting the device characteristics of each target device in the target device list. The purpose of this step is to obtain detailed characteristic information about each target device for subsequent network connection and decision making.

In a specific embodiment, as shown in fig. 2, the process of executing step S102 may specifically include the following steps:

s201, performing feature clustering on the device feature information set to obtain N key features of each target device;

s202, acquiring networking connection standards of a target soft bus, and respectively defining a plurality of initial connection constraint conditions of N key features;

s203, performing equipment matching on a plurality of initial connection constraint conditions and a plurality of target devices to obtain networking connection constraint conditions of each target device;

s204, performing soft bus networking connection operation according to networking connection constraint conditions, and constructing a corresponding initial soft bus networking connection model.

Specifically, feature clustering is performed on the device feature information set to obtain N key features of each target device. The characteristic information of the devices is grouped and classified to determine similarity and commonality between the devices. For example, if there is a set of sensor devices, their temperature measurement range, sampling frequency and accuracy are key features. And acquiring networking connection standards of the target soft bus, and respectively defining a plurality of initial connection constraint conditions of N key features. The connection criteria are rules that the server requires the device to follow, while the connection constraints are specific constraints based on key features of the device. For example, the connection standards include communication protocols, data transfer speeds, and power requirements. For key features, the following initial connection constraints may be defined: communication protocol: the device must support the MQTT communication protocol; data transmission speed: the data transmission speed of the device must not exceed 10Mbps; power supply requirements: the device must support a low power mode and have a standby power option. And then, performing device matching on the plurality of initial connection constraint conditions and the plurality of target devices to obtain networking connection constraint conditions of each target device. This step involves comparing the connection constraints with key features of the target device to determine which devices meet the connection criteria. For example, for one IoT server, the server would check the communication protocol, data transfer speed, and power requirements of each target device to ensure that they meet the connection standards. And executing the soft bus networking connection operation according to the networking connection constraint condition, and constructing a corresponding initial soft bus networking connection model. This includes connecting devices to the soft bus and configuring connection parameters to ensure that they meet connection standards and constraint conditions.

In a specific embodiment, as shown in fig. 3, the process of executing step S103 may specifically include the following steps:

s301, acquiring networking transmission channel data of each target device, wherein the networking transmission channel data comprises: bandwidth, delay, and packet loss rate;

s302, respectively carrying out data standardization processing on networking transmission channel data to obtain a plurality of standard transmission channel data;

s303, performing data matrix conversion on a plurality of standard transmission channel data to obtain a target transmission channel matrix;

s304, performing association relation integration on the target transmission channel matrix and the initial soft bus networking connection model to obtain a target association relation;

s305, carrying out networking connection network environment analysis on the initial soft bus networking connection model according to the target association relation to obtain networking connection network environment data.

Specifically, the networking transmission channel data of each target device is obtained, wherein the networking transmission channel data comprises key parameters such as bandwidth, delay, packet loss rate and the like. These parameters are critical to the performance of the network connection and thus accurate acquisition of the transmission channel data for each device is required. The bandwidth represents the available communication bandwidth, the delay represents the delay time of data transmission, and the packet loss rate represents the probability of data loss during transmission. These parameters will affect the quality and performance of the communication between the devices. And carrying out data standardization processing on the acquired networking transmission channel data. Normalization is to unify units, ranges, or metrics of different device transmission channel data for comparison and analysis. This may ensure that the data has a consistent benchmark in subsequent analyses. For example, if one device's bandwidth is in Mbps and the other device is in Kbps, normalization will translate them all into the same unit, such as Mbps, for comparison. Then, data matrix conversion is performed on the plurality of standard transmission channel data. This step involves organizing the transmission channel data into a data matrix, where each row represents a target device and each column represents a transmission channel parameter (e.g., bandwidth, delay, packet loss rate). For example, if there are 5 target devices and 3 transmission channel parameters, the data matrix would be a 5x3 matrix, where each row contains the transmission channel parameters for each device. And carrying out association relation integration on the target transmission channel matrix and the initial soft bus networking connection model. The transmission channel data is associated with the connection model to determine a connection relationship between each device and a communication path. For example, the connection model may define which devices need to communicate directly, which devices need to transmit data through the intermediate node, and which devices have better communication performance. And according to the target association relation, carrying out networking connection network environment analysis on the initial soft bus networking connection model. This step involves evaluating the various connection modes to determine which connection mode is best suited for the current network environment. For example, if the transmission channel data between some devices indicates that they can communicate directly, and communication between other devices requires the relay node, the analysis will determine the best connection to optimize the overall network performance.

In a specific embodiment, as shown in fig. 4, the process of executing step S104 may specifically include the following steps:

s401, carrying out data preprocessing on networking connection network environment data to obtain target connection network environment data;

s402, inputting the environment data of the target connection network into a preset bidirectional long-short-time memory network, extracting forward hidden features of the environment data of the target connection network through a forward long-short-time memory network in the bidirectional long-short-time memory network to obtain forward hidden features, extracting backward hidden features of the environment data of the target connection network through a backward long-short-time memory network in the bidirectional long-short-time memory network to obtain backward hidden features, and carrying out feature fusion on the forward hidden features and the backward hidden features to obtain target fusion features;

s403, carrying out networking division and prediction on the initial soft bus networking connection model according to the target fusion characteristics to obtain a plurality of corresponding networking connection prediction networks;

s404, monitoring performance states of the plurality of networking connection prediction networks respectively to obtain a plurality of prediction network performance parameter data.

Specifically, the networking connection network environment data is subjected to data preprocessing to obtain the target connection network environment data. Data preprocessing is to clean, normalize, and prepare data to ensure its quality and consistency. This includes removing noise, processing missing data, and converting the data into a format that can be used for the model. The target connection network environment data is input into a preset bidirectional long and short time memory network (BiLSTM). BiLSTM is a deep learning neural network structure suitable for sequential data processing. In this process, forward and backward hidden feature extraction is performed on the target connection network environment data through the forward and backward parts of the BiLSTM. The forward hidden feature is information extracted from the data sequence through a forward long and short term memory network, which captures the time series characteristics and trends of the data. The backward hidden characteristic is information extracted by the backward long-short-time memory network, and the reverse sequence characteristic of the data is captured. And carrying out feature fusion on the forward hidden features and the backward hidden features to obtain target fusion features. Feature fusion may be achieved by simple stitching, weighted averaging, or more complex methods. The goal is to combine the forward and backward hidden features to obtain a more comprehensive and comprehensive feature representation. And carrying out networking division and prediction on the initial soft bus networking connection model according to the target fusion characteristics. This step involves applying the target fusion feature to the connection model to determine the manner of connection and communication path between the devices. This may help optimize network performance and resource utilization. And respectively monitoring performance states of the plurality of networking connection prediction networks to obtain a plurality of prediction network performance parameter data. Performance state monitoring is to evaluate the effect and performance of a connection prediction network to ensure that it is suitable for the actual network environment.

In a specific embodiment, the process of executing step S105 may specifically include the following steps:

(1) Performing performance parameter comprehensive analysis on the plurality of predicted network performance parameter data to obtain a plurality of performance parameter comprehensive analysis indexes;

(2) Defining a network performance optimization target of each networking connection prediction network according to the comprehensive analysis indexes of the plurality of performance parameters;

(3) Respectively carrying out optimization strategy analysis on the network performance optimization targets to obtain an initial network optimization strategy of each networking connection prediction network;

(4) Carrying out global strategy group initialization on the initial network optimization strategy of each networking connection prediction network through a preset global optimization algorithm to obtain a plurality of candidate network optimization strategies;

(5) Performing policy fitness analysis on the plurality of candidate network optimization policies respectively to obtain policy fitness data of each candidate network optimization policy;

(6) And carrying out policy optimization analysis on the plurality of candidate network optimization policies according to the policy fitness data to obtain a target network optimization policy.

Specifically, performance parameter comprehensive analysis is performed on the plurality of predicted network performance parameter data to obtain a plurality of performance parameter comprehensive analysis indexes. The different performance parameters are integrated together to obtain a comprehensive assessment of network performance. The analysis-by-synthesis metrics include the overall error rate, throughput, delay, availability, etc., which can help assess the overall performance of the network. And defining a network performance optimization target of each networking connection prediction network according to the comprehensive analysis indexes of the plurality of performance parameters. The goal is to set a clear performance goal for each network for subsequent optimization analysis. Network performance optimization objectives may include minimizing delay, maximizing throughput, minimizing packet loss rate, etc., depending on the requirements of the network and constraints. And respectively carrying out optimization strategy analysis on the network performance optimization targets to obtain an initial network optimization strategy of each networking connection prediction network. This step involves determining how to adjust the network parameters and settings to meet performance objectives. For example, if the performance goal is to minimize delay, the optimization strategy involves adjusting the data transmission path, reducing the number of data packet retransmissions, or increasing bandwidth, etc. And carrying out global strategy group initialization on the initial network optimization strategy of each networking connection prediction network through a preset global optimization algorithm. The global optimization algorithm may be a genetic algorithm, particle swarm optimization, or other optimization technique for searching for the optimal combination of strategies. And respectively carrying out policy fitness analysis on the plurality of candidate network optimization policies to obtain policy fitness data of each candidate network optimization policy. Policy fitness is the evaluation of the validity of each policy based on network performance objectives and actual performance data. And carrying out policy optimization analysis on the plurality of candidate network optimization policies according to the policy fitness data so as to obtain target network optimization policies. In this step, the algorithm will determine which policy combination best meets the performance objective to achieve the best performance of the network.

In a specific embodiment, the process of executing step S106 may specifically include the following steps:

(1) According to the target network optimization strategy, performing network optimization operation generation on a plurality of networking connection prediction networks to obtain a network optimization operation set of each networking connection prediction network;

(2) According to the network optimization operation set, respectively carrying out network optimization processing on each networking connection prediction network to obtain a plurality of networking connection target networks;

(3) Performing model dynamic update and performance verification on the initial soft bus networking connection model according to the networking connection target networks to obtain a performance verification result of the initial soft bus networking connection model;

(4) And carrying out feedback circulation on the initial soft bus networking connection model according to the performance verification result to obtain the target soft bus networking connection model.

Specifically, according to the target network optimization strategy, performing network optimization operation generation on the plurality of networking connection prediction networks to obtain a network optimization operation set of each networking connection prediction network. These operations may include adjusting connection parameters, path selection, routing algorithms, load balancing policies, and the like. A set of network optimization operations is a set of policies and rules for improving the performance of a connection prediction network to meet specific performance objectives. And respectively carrying out network optimization processing on each networking connection prediction network according to the network optimization operation set so as to obtain a plurality of networking connection target networks. An optimization operation is applied to each connection prediction network to improve its performance and efficiency. For example, if the set of optimization operations includes optimization of routing paths, the best path may be selected for each network to reduce latency and improve throughput. And carrying out model dynamic update and performance verification on the initial soft bus networking connection model according to the networking connection target networks. This includes reflecting the optimized network parameters and configuration information into the connection model to ensure that the model remains consistent with the actual network state. Performance verification is to evaluate the performance of the updated connection model in the actual network to determine whether the expected performance goal is achieved. And carrying out feedback circulation on the initial soft bus networking connection model according to the performance verification result to obtain a target soft bus networking connection model. If the performance verification results do not meet the expectations, the set of optimization operations may be adjusted and the connection model updated again until the performance goals are met.

The method for connecting the soft bus network in the embodiment of the present invention is described above, and the device for connecting the soft bus network in the embodiment of the present invention is described below, referring to fig. 5, where an embodiment of the device for connecting the soft bus network in the embodiment of the present invention includes:

the extracting module 501 is configured to automatically discover devices on the target soft bus based on a preset device discovery mechanism, obtain a plurality of target devices, and extract device features of the plurality of target devices to obtain a device feature information set of each target device;

a construction module 502, configured to perform a networking connection constraint condition analysis on the multiple target devices according to the device feature information set, obtain a networking connection constraint condition of each target device, and perform a soft bus networking connection on the multiple target devices according to the networking connection constraint condition, so as to construct an initial soft bus networking connection model;

an analysis module 503, configured to obtain networking transmission channel data of each target device, and perform networking connection network environment analysis on the initial soft bus networking connection model according to the networking transmission channel data, so as to obtain networking connection network environment data;

The monitoring module 504 is configured to construct a plurality of networking connection prediction networks corresponding to the initial soft bus networking connection model according to the networking connection network environment data, and monitor performance states of the networking connection prediction networks respectively to obtain a plurality of prediction network performance parameter data;

the definition module 505 is configured to define a network performance optimization objective of each networking connection prediction network according to the plurality of prediction network performance parameter data, and perform an optimization policy analysis on the network performance optimization objective respectively to obtain a target network optimization policy;

and an updating module 506, configured to perform network optimization processing on the plurality of networking connection prediction networks according to the target network optimization policy to obtain a plurality of networking connection target networks, and perform model dynamic updating on the initial soft bus networking connection model according to the plurality of networking connection target networks to obtain a target soft bus networking connection model.

Through the cooperation of the components, the system can automatically discover the equipment on the target soft bus based on a preset equipment discovery mechanism, so that the automation of equipment connection is realized. By device feature extraction, the system is able to intelligently extract key feature information, including bandwidth, latency, etc., from the target devices, helping to model the performance features of each device more accurately. By analyzing the networking connection constraint conditions of the device characteristic information set, the system can intelligently determine the connection constraint conditions of each target device, and the stability and reliability of connection are improved. By analyzing the networking connection network environment and constructing a plurality of networking connection prediction networks, the system can more comprehensively understand the network environment, optimize the soft bus networking connection model and improve the overall system performance. By defining and analyzing the network performance optimization targets, the system can intelligently formulate an optimization strategy, and the adaptability and performance of the soft bus networking connection are improved. By analyzing the predicted network performance parameter data and applying the target network optimization strategy, the system can dynamically update the soft bus networking connection model, thereby realizing the real-time adaptation to the changed network environment. Through real-time performance monitoring and feedback circulation, the system can be continuously learned and optimized, has self-adaptability, can be better adapted to continuously changing network conditions, and further improves the connection efficiency of soft bus networking connection.

The above-mentioned fig. 5 describes the soft bus networking connection device in the embodiment of the present invention in detail from the point of view of modularized functional entities, and the following describes the soft bus networking connection device in the embodiment of the present invention in detail from the point of view of hardware processing.

Fig. 6 is a schematic structural diagram of a soft bus networking connection device according to an embodiment of the present invention, where the soft bus networking connection device 600 may have a relatively large difference due to different configurations or performances, and may include one or more processors (central processing units, CPU) 610 (e.g., one or more processors) and a memory 620, and one or more storage media 630 (e.g., one or more mass storage devices) storing application programs 633 or data 632. Wherein the memory 620 and the storage medium 630 may be transitory or persistent storage. The program stored on the storage medium 630 may include one or more modules (not shown), each of which may include a series of instruction operations on the soft bus networking connection device 600. Still further, the processor 610 may be configured to communicate with the storage medium 630 and execute a series of instruction operations in the storage medium 630 on the soft bus networking connection device 600.

The soft bus networking connection device 600 may also include one or more power supplies 640, one or more wired or wireless network interfaces 650, one or more input/output interfaces 660, and/or one or more operating systems 631, such as Windows Server, mac OS X, unix, linux, freeBSD, etc. It will be appreciated by those skilled in the art that the soft bus networking connection device structure shown in fig. 6 is not limiting of the soft bus networking connection device and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components.

The invention also provides a soft bus networking connection device, which comprises a memory and a processor, wherein the memory stores computer readable instructions, and when the computer readable instructions are executed by the processor, the processor executes the steps of the soft bus networking connection method in the above embodiments.

The present invention also provides a computer readable storage medium, which may be a non-volatile computer readable storage medium, and may also be a volatile computer readable storage medium, where instructions are stored in the computer readable storage medium, when the instructions are executed on a computer, cause the computer to perform the steps of the soft bus networking connection method.

It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. The soft bus networking connection method is characterized by comprising the following steps of:

automatically discovering the target soft bus based on a preset device discovery mechanism to obtain a plurality of target devices, and extracting device characteristics of the plurality of target devices to obtain a device characteristic information set of each target device; the method specifically comprises the following steps: request monitoring is carried out on a target soft bus based on a preset device discovery mechanism, so that device discovery requests sent by a plurality of candidate devices are obtained; performing request analysis on the device discovery requests sent by the plurality of candidate devices to obtain a request identifier of each candidate device, and acquiring a device registration state corresponding to each candidate device according to the request identifier; matching target equipment discovery rules corresponding to the plurality of candidate equipment according to the equipment registration state, and screening the plurality of candidate equipment according to the target equipment discovery rules and the equipment registration state to obtain a plurality of target equipment; generating a corresponding target device list according to the plurality of target devices, and extracting device characteristics of the plurality of target devices according to the target device list to obtain a device characteristic information list; performing feature information set conversion on the device feature information list to obtain a device feature information set of each target device;

Respectively analyzing networking connection constraint conditions of the plurality of target devices according to the device characteristic information set to obtain networking connection constraint conditions of each target device, and performing soft bus networking connection on the plurality of target devices according to the networking connection constraint conditions to construct an initial soft bus networking connection model;

acquiring networking transmission channel data of each target device, and carrying out networking connection network environment analysis on the initial soft bus networking connection model according to the networking transmission channel data to obtain networking connection network environment data;

constructing a plurality of networking connection prediction networks corresponding to the initial soft bus networking connection model according to the networking connection network environment data, and respectively monitoring performance states of the networking connection prediction networks to obtain a plurality of prediction network performance parameter data;

defining a network performance optimization target of each networking connection prediction network according to the plurality of prediction network performance parameter data, and respectively carrying out optimization strategy analysis on the network performance optimization targets to obtain a target network optimization strategy; the method specifically comprises the following steps: performing performance parameter comprehensive analysis on the plurality of predicted network performance parameter data to obtain a plurality of performance parameter comprehensive analysis indexes; defining a network performance optimization target of each networking connection prediction network according to the comprehensive analysis indexes of the plurality of performance parameters; respectively carrying out optimization strategy analysis on the network performance optimization targets to obtain an initial network optimization strategy of each networking connection prediction network; carrying out global strategy group initialization on the initial network optimization strategy of each networking connection prediction network through a preset global optimization algorithm to obtain a plurality of candidate network optimization strategies; performing policy fitness analysis on the plurality of candidate network optimization policies respectively to obtain policy fitness data of each candidate network optimization policy; performing policy optimization analysis on the plurality of candidate network optimization policies according to the policy fitness data to obtain a target network optimization policy;

Performing network optimization processing on the networking connection prediction networks according to the target network optimization strategy to obtain networking connection target networks, and performing model dynamic update on the initial soft bus networking connection model according to the networking connection target networks to obtain a target soft bus networking connection model; the method specifically comprises the following steps: according to the target network optimization strategy, performing network optimization operation generation on the plurality of networking connection prediction networks to obtain a network optimization operation set of each networking connection prediction network; according to the network optimization operation set, respectively carrying out network optimization processing on each networking connection prediction network to obtain a plurality of networking connection target networks; performing model dynamic update and performance verification on the initial soft bus networking connection model according to the networking connection target networks to obtain a performance verification result of the initial soft bus networking connection model; and carrying out feedback circulation on the initial soft bus networking connection model according to the performance verification result to obtain a target soft bus networking connection model.

2. The method of claim 1, wherein the performing a network connection constraint condition analysis on the plurality of target devices according to the device feature information set to obtain a network connection constraint condition of each target device, and performing a soft bus network connection on the plurality of target devices according to the network connection constraint condition, and constructing an initial soft bus network connection model includes:

Performing feature clustering on the equipment feature information set to obtain N key features of each target equipment;

acquiring networking connection standards of the target soft bus, and respectively defining a plurality of initial connection constraint conditions of the N key features;

performing equipment matching on the plurality of initial connection constraint conditions and the plurality of target devices to obtain networking connection constraint conditions of each target device;

and executing the soft bus networking connection operation according to the networking connection constraint condition, and constructing a corresponding initial soft bus networking connection model.

3. The method for soft bus networking connection according to claim 1, wherein the obtaining networking transmission channel data of each target device, and performing networking connection network environment analysis on the initial soft bus networking connection model according to the networking transmission channel data, to obtain networking connection network environment data, includes:

acquiring networking transmission channel data of each target device, wherein the networking transmission channel data comprises: bandwidth, delay, and packet loss rate;

respectively carrying out data standardization processing on the networking transmission channel data to obtain a plurality of standard transmission channel data;

Performing data matrix conversion on the plurality of standard transmission channel data to obtain a target transmission channel matrix;

performing association relation integration on the target transmission channel matrix and the initial soft bus networking connection model to obtain a target association relation;

and according to the target association relation, carrying out networking connection network environment analysis on the initial soft bus networking connection model to obtain networking connection network environment data.

4. The method for soft bus networking according to claim 1, wherein the constructing a plurality of networking prediction networks corresponding to the initial soft bus networking connection model according to the networking connection network environment data, and performing performance state monitoring on the plurality of networking prediction networks to obtain a plurality of prediction network performance parameter data respectively, comprises:

performing data preprocessing on the networking connection network environment data to obtain target connection network environment data;

inputting the target connection network environment data into a preset bidirectional long-short-time memory network, extracting forward hidden features from the target connection network environment data through a forward long-short-time memory network in the bidirectional long-short-time memory network to obtain forward hidden features, extracting backward hidden features from the target connection network environment data through a backward long-short-time memory network in the bidirectional long-short-time memory network to obtain backward hidden features, and carrying out feature fusion on the forward hidden features and the backward hidden features to obtain target fusion features;

Performing networking division and prediction on the initial soft bus networking connection model according to the target fusion characteristics to obtain a plurality of networking connection prediction networks;

and respectively monitoring the performance states of the plurality of networking connection prediction networks to obtain a plurality of prediction network performance parameter data.

5. A soft bus networking connection device, characterized in that the soft bus networking connection device comprises:

the extraction module is used for automatically discovering the device on the target soft bus based on a preset device discovery mechanism to obtain a plurality of target devices, and extracting the device characteristics of the plurality of target devices to obtain a device characteristic information set of each target device; the method specifically comprises the following steps: request monitoring is carried out on a target soft bus based on a preset device discovery mechanism, so that device discovery requests sent by a plurality of candidate devices are obtained; performing request analysis on the device discovery requests sent by the plurality of candidate devices to obtain a request identifier of each candidate device, and acquiring a device registration state corresponding to each candidate device according to the request identifier; matching target equipment discovery rules corresponding to the plurality of candidate equipment according to the equipment registration state, and screening the plurality of candidate equipment according to the target equipment discovery rules and the equipment registration state to obtain a plurality of target equipment; generating a corresponding target device list according to the plurality of target devices, and extracting device characteristics of the plurality of target devices according to the target device list to obtain a device characteristic information list; performing feature information set conversion on the device feature information list to obtain a device feature information set of each target device;

The construction module is used for respectively analyzing networking connection constraint conditions of the plurality of target devices according to the device characteristic information set to obtain networking connection constraint conditions of each target device, and carrying out soft bus networking connection on the plurality of target devices according to the networking connection constraint conditions to construct an initial soft bus networking connection model;

the analysis module is used for acquiring networking transmission channel data of each target device, and carrying out networking connection network environment analysis on the initial soft bus networking connection model according to the networking transmission channel data to obtain networking connection network environment data;

the monitoring module is used for constructing a plurality of networking connection prediction networks corresponding to the initial soft bus networking connection model according to the networking connection network environment data, and respectively monitoring performance states of the networking connection prediction networks to obtain a plurality of prediction network performance parameter data;

the definition module is used for defining a network performance optimization target of each networking connection prediction network according to the plurality of prediction network performance parameter data, and respectively carrying out optimization strategy analysis on the network performance optimization targets to obtain a target network optimization strategy; the method specifically comprises the following steps: performing performance parameter comprehensive analysis on the plurality of predicted network performance parameter data to obtain a plurality of performance parameter comprehensive analysis indexes; defining a network performance optimization target of each networking connection prediction network according to the comprehensive analysis indexes of the plurality of performance parameters; respectively carrying out optimization strategy analysis on the network performance optimization targets to obtain an initial network optimization strategy of each networking connection prediction network; carrying out global strategy group initialization on the initial network optimization strategy of each networking connection prediction network through a preset global optimization algorithm to obtain a plurality of candidate network optimization strategies; performing policy fitness analysis on the plurality of candidate network optimization policies respectively to obtain policy fitness data of each candidate network optimization policy; performing policy optimization analysis on the plurality of candidate network optimization policies according to the policy fitness data to obtain a target network optimization policy;

The updating module is used for carrying out network optimization processing on the networking connection prediction networks according to the target network optimization strategy to obtain networking connection target networks, and carrying out model dynamic updating on the initial soft bus networking connection model according to the networking connection target networks to obtain a target soft bus networking connection model; the method specifically comprises the following steps: according to the target network optimization strategy, performing network optimization operation generation on the plurality of networking connection prediction networks to obtain a network optimization operation set of each networking connection prediction network; according to the network optimization operation set, respectively carrying out network optimization processing on each networking connection prediction network to obtain a plurality of networking connection target networks; performing model dynamic update and performance verification on the initial soft bus networking connection model according to the networking connection target networks to obtain a performance verification result of the initial soft bus networking connection model; and carrying out feedback circulation on the initial soft bus networking connection model according to the performance verification result to obtain a target soft bus networking connection model.

6. A soft bus networking connection device, the soft bus networking connection device comprising: a memory and at least one processor, the memory having instructions stored therein;

The at least one processor invoking the instructions in the memory to cause the soft bus networking connection device to perform the soft bus networking connection method of any of claims 1-4.

7. A computer readable storage medium having instructions stored thereon, which when executed by a processor, implement the soft bus networking method of any of claims 1-4.