Unified configuration method, system, server and medium for industrial heterogeneous network

Abstract

Embodiments of the present application relate to the field of industrial internet, and provide a unified configuration method and system of industrial heterogeneous network, a server and a medium. The method comprises: receiving network configuration requirement information input by a user in an application program through a northbound interface; performing model generation processing on the network configuration requirement information to obtain a unified information model; performing configuration information generation processing on the unified information model by using a converter to obtain configuration information corresponding to a configuration protocol; and sending the configuration information to a target device. The method can uniformly configure multiple heterogeneous network devices and improves the efficiency of configuring heterogeneous network devices.

Description

Technical Field

[0001] This application relates to the field of industrial internet technology, specifically to a unified configuration method, system, server, and medium for industrial heterogeneous networks. Background Technology

[0002] With the continuous development of information and manufacturing technologies, traditional production methods can no longer meet the ever-increasing demands, and traditional industries are moving towards automation and intelligence. Industrial automation and intelligence rely heavily on various data from the industrial site. To achieve data interconnection between industrial equipment, communication barriers between different types of devices must be broken down. However, industrial environments are characterized by a wide variety of equipment and diverse network protocols. Therefore, achieving bidirectional communication between heterogeneous networks is a fundamental prerequisite for realizing automated and intelligent manufacturing.

[0003] Communication between various heterogeneous industrial network devices is a key technology for realizing smart manufacturing. To achieve interconnection and interoperability of heterogeneous industrial networks, the first step is to configure and manage these networks. Different networks in a heterogeneous industrial network have different configuration requirements and require various configuration tools. Traditional network configuration methods often employ a one-to-one manual configuration approach, which is inefficient, highly repetitive, and fails to meet the diverse business needs of the Industrial Internet of Things (IIoT).

[0004] Current research on industrial heterogeneous network configuration, both domestically and internationally, mostly focuses on the research and development of configuration methods and systems for single types or categories of industrial networks. Furthermore, most of these studies only support one network configuration protocol, resulting in low efficiency when configuring heterogeneous network devices. Summary of the Invention

[0005] This application provides a unified configuration method, system, server, and medium for industrial heterogeneous networks, which can uniformly configure various heterogeneous network devices and improve the efficiency of heterogeneous network device configuration.

[0006] The first aspect of this application provides a unified configuration method for industrial heterogeneous networks, applied to a unified configuration system, the method comprising:

[0007] Receive network configuration requirements from the user in the application via the northbound interface;

[0008] The network configuration requirement information is processed to generate a unified information model.

[0009] A converter is used to process the unified information model to generate configuration information, thereby obtaining the configuration information corresponding to the configuration protocol.

[0010] The configuration information is sent to the target device.

[0011] In this example, network configuration requirements input by the user in the application are received through the northbound interface. The network configuration requirements are processed to generate a unified information model. A converter is then used to generate configuration information from the unified information model to obtain configuration information corresponding to the configuration protocol. This configuration information is then sent to the target device. Therefore, configuration information corresponding to the configuration protocol can be automatically generated based on the network configuration requirements input by the user and sent to the target device. After receiving the configuration information, the target device can perform configuration, thus facilitating the configuration of the target device and improving the efficiency of device configuration.

[0012] A second aspect of this application provides a unified configuration system for industrial heterogeneous networks, the system comprising:

[0013] The receiving unit is used to receive network configuration requirement information input by the user in the application through the northbound interface;

[0014] The processing unit is used to perform model generation processing on the network configuration requirement information to obtain a unified information model; and to use a converter to perform configuration information generation processing on the unified information model to obtain configuration information corresponding to the configuration protocol.

[0015] The sending unit is used to send the configuration information to the target device.

[0016] A third aspect of this application provides a server including a processor, an input device, an output device, and a memory, wherein the processor, input device, output device, and memory are interconnected, wherein the memory is used to store a computer program, the computer program including program instructions, and the processor is configured to invoke the program instructions to execute the step instructions as described in the first aspect of this application.

[0017] A fourth aspect of this application provides a computer-readable storage medium storing a computer program for electronic data interchange, wherein the computer program causes a computer to perform some or all of the steps described in the first aspect of this application.

[0018] A fifth aspect of this application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps described in the first aspect of this application. The computer program product may be a software installation package. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This application provides an architectural diagram of a unified configuration system for industrial heterogeneous networks.

[0021] Figure 2 This application provides a flowchart illustrating a unified configuration method for industrial heterogeneous networks.

[0022] Figure 3 This application provides a schematic diagram of a unified information model.

[0023] Figure 4 This is a schematic diagram of a key information extraction model provided in an embodiment of this application;

[0024] Figure 5 This application provides a schematic diagram of a BERT model structure as an embodiment;

[0025] Figure 6 This application provides a flowchart illustrating the process of an embedding layer.

[0026] Figure 7 This is a schematic diagram of the structure of a Transformer encoder provided in an embodiment of this application;

[0027] Figure 8 This application provides a schematic diagram of the structure of a TextCNN model for embodiments;

[0028] Figure 9 This application provides a schematic diagram of the structure of a converter.

[0029] Figure 10 This application provides a schematic diagram of an SNMP message format for an embodiment.

[0030] Figure 11 This application provides a schematic diagram of the framework of a unified information model for embodiments;

[0031] Figure 12 This application provides a schematic diagram of the structure of a server according to an embodiment of the present application.

[0032] Figure 13 This application provides a schematic diagram of the structure of a unified configuration system for industrial heterogeneous networks. Detailed Implementation

[0033] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0034] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0035] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described in this application can be combined with other embodiments.

[0036] To better understand the unified configuration method for industrial heterogeneous networks provided in this application, the unified configuration method for industrial heterogeneous networks in existing solutions is first briefly introduced below. In existing solutions, regarding industrial network configuration methods, Chen Bing et al., addressing the shortcomings of manual configuration methods for time-sensitive networks, proposed a method for automatic TSN configuration based on the NETCONF network configuration protocol, which automatically collects network topology information and traffic requirements (see reference: Chen Bing, Zhou Haotian, Liu Tian et al. A TSN network configuration method based on NETCONF [J]. Information Technology and Standardization, 2023, (05): 46-52), which can automatically adapt to changes in network topology and traffic requirements. The centralized network configuration architecture and automatic configuration method based on the centralized network configuration entity CNC and the centralized user configuration entity CUC are described, and the effectiveness of the method is verified through prototype system implementation and testing. Chen Chunlin proposed a general management scheme for network device configuration based on NETCONF (see reference: Chen Chunlin. Design and implementation of a general device configuration management system based on NETCONF [D]. Southeast University, 2018). He designed a template-based configuration method, which realizes the unified encapsulation of configuration messages through configuration templates and the dynamic rendering of the configuration interface through interface templates. He also gave a detailed design and implementation scheme of the system in combination with the various requirements of the device configuration management system.

[0037] However, most of the research on industrial heterogeneous network configuration mentioned above focuses on the research of configuration methods and the development of configuration systems for a single type or class of industrial networks, and most of them only support one network configuration protocol, resulting in low efficiency when configuring heterogeneous network devices.

[0038] To address the aforementioned technical problems, this application provides a unified configuration method for industrial heterogeneous networks. This method can automatically generate configuration information corresponding to the configuration protocol based on network configuration requirements input by the user and send it to the target device. After receiving the configuration information, the target device performs the configuration, thereby facilitating the configuration of the target device and improving the efficiency of device configuration.

[0039] Figure 1 A schematic diagram of the architecture of a unified configuration system for industrial heterogeneous networks is shown. For example... Figure 1 As shown, the unified configuration system for industrial heterogeneous networks receives network configuration requirements (as shown in the diagram) input by the user plane through an application program (APP). In the control plane, the corresponding modules within the unified configuration system generate a unified information model. In the data plane, the unified information model is used to generate the final configuration information corresponding to the specified protocol, and this configuration information is then sent to the target devices. The target devices include network devices such as 5G / TSN industrial Ethernet and field devices such as TSN / WIA-PA / Modbus.

[0040] Specifically, the architecture is divided into user plane, control plane, and data plane from top to bottom. Centered on the control plane, the configuration architecture can be viewed as running north-south. The control plane interacts with the user plane and data plane through both the northbound interface and the configuration interface. The functions of each layer of the unified configuration architecture are as follows:

[0041] The user plane includes various software-defined network-based applications (APPs) that can obtain business configuration requirements and implement corresponding network management functions. By calling the northbound interface, user plane APPs can achieve information interaction and management with the control plane and data plane.

[0042] The control plane primarily consists of a unified configuration system. This system models user-input configuration requirements and generates configuration information through converters and the collaborative efforts of various configuration modules. This information is then distributed to the data plane via configuration tools. The control plane communicates with the data plane through a configuration interface and with the user plane through a northbound interface. The unified configuration system manages and configures devices in the data plane through the configuration interface.

[0043] The data plane is the part of the network responsible for forwarding data packets. It is separate from the control plane and only needs to perform matching and actions according to the instructions from the control plane. Figure 1 It consists of industrial network equipment such as 5G gateways and TSN switches, as well as industrial field equipment such as PLCs and TSN terminals.

[0044] The basic tasks of the two types of interfaces are as follows:

[0045] Northbound interface: Provides user-plane apps with an interface to access and manage the network, facilitating unified configuration of resources; that is, a service interface facing the user plane.

[0046] Configuration Interface: Provides interfaces for field devices and network devices that support management and configuration functions, and serves as an interface for exchanging configuration information between the control plane and the data plane.

[0047] Please see Figure 2 , Figure 2 This application provides a flowchart illustrating a unified configuration method for industrial heterogeneous networks. For example... Figure 2 As shown, this method is applied to a unified configuration system for industrial heterogeneous networks. The method includes:

[0048] S20. Receive network configuration requirements information entered by the user in the application through the northbound interface.

[0049] In this application, the user plane APP establishes a connection with the unified configuration of the industrial heterogeneous network in the control plane through the northbound interface, thereby enabling the acquisition of heterogeneous network configuration information and the dissemination of network configuration requirements. The northbound interface designed in this application realizes the functional interaction and information transmission between the user plane and the control plane in the unified configuration architecture of heterogeneous networks, based on the unified configuration of heterogeneous networks.

[0050] The northbound interface of the unified configuration system should meet the following requirements:

[0051] (1) It has configuration information query interface, configuration information distribution interface, configuration template management interface, device management interface, etc., which can meet the requirements of unified configuration of heterogeneous networks.

[0052] (2) To improve the flexibility and reusability of the system, the provided northbound interface should be easy for other software systems to call, so that other systems can flexibly and conveniently integrate the unified configuration system functions.

[0053] The northbound interface of the unified configuration system in this application is designed using standard HTTP interface methods, including GET and POST. Based on the defined functions of the interface, the corresponding logical functions within the unified configuration system are invoked by accessing the interface and passing request parameters, and response data is returned according to the interface definition. The design specifications of the northbound interface of the unified configuration system, based on the interface functional requirements, are shown in Table 1.

[0054] Table 1 Northbound Interface Design Specifications

[0055] Interface Name Resource Identifier Request method describe Configuration information query interface / api / getInfo GET Query configuration information Configuration information distribution interface / api / config POST Configuration information distribution Configure template management interface / api / template POST Management Configuration Template Device Management Interface / api / device POST Management equipment Algorithm result retrieval interface / api / algoResult GET Obtaining Algorithm Results

[0056] The configuration information query interface primarily queries existing configuration information on devices, serving as a reference for configuration modifications. The configuration information distribution interface is the system's main interface, responsible for distributing configuration information. The configuration template management interface manages configuration templates, providing users with a way to edit them. The device management interface manages device information, storing common device information for later use. The algorithm result acquisition interface interacts with the scheduling system. The scheduling system is independent of the unified configuration system but works collaboratively with it. It runs scheduling algorithms and provides results. The unified configuration system receives the algorithm calculation results from the scheduling system, generates configuration information, and returns it through this interface.

[0057] S21. Perform model generation processing on the network configuration requirement information to obtain a unified information model.

[0058] Industrial heterogeneous network scenarios involve different network types and device types, with diverse network configuration methods. Therefore, industrial heterogeneous networks inevitably have network configuration information in different formats, necessitating a unified model for the input of industrial heterogeneous network configuration requirements. This paper abstracts three parts—basic device information, configuration protocol information, and device configuration information—for different network types and configuration methods in industrial heterogeneous networks. These are combined to form a unified information model, thereby standardizing the input of different network configuration requirements and achieving a unified input format for various heterogeneous network configuration needs.

[0059] The unified information model performs unified modeling for different configuration requirements, including basic device information, configuration protocol information, and device configuration information, such as... Figure 3 As shown. The basic device information mainly covers basic device parameters such as device type, IP address, and communication port, used to identify and describe some basic information about the device. The configuration protocol information includes the protocol type, protocol communication address, and possibly included protocol parameters. This configuration protocol information is needed for the subsequent converter to identify the device configuration protocol and perform the corresponding conversion. The device configuration information contains the specific configuration requirements for the device.

[0060] This application uses the BERT+TextCNN model (key information extraction model) to extract and model key information from user configuration requirements. The overall model is as follows: Figure 4 As shown, the overall architecture of the key information extraction model can be viewed as two main parts: BERT and TextCNN. The BERT model, proposed by Google in 2018, is a powerful pre-trained model that employs a multi-layer Transformer encoder. It can learn information from both sides of each word, combining contextual information to model the text, thus more comprehensively reflecting the semantics of the sentence and providing deep bidirectional language representation of the input configuration information. The output after training with the BERT model contains rich semantic knowledge. Therefore, this solution, for the task of configuration information text classification and extraction, adds a TextCNN model downstream of the BERT model to perform configuration information classification and extraction.

[0061] Specifically, the process of generating a unified information model from the network configuration requirement information may include the following steps:

[0062] S211. Preprocess the network configuration requirement information to obtain preprocessed network configuration requirement information;

[0063] Preprocessing may specifically include the following steps and methods:

[0064] S2111, Text format information of network configuration requirements;

[0065] S2112. Extract the network configuration requirement information from the text according to the file extraction method corresponding to the text format information to obtain the network configuration requirement information text.

[0066] S2113. Perform text preprocessing on the network configuration requirement information text to obtain preprocessed network configuration requirement information.

[0067] Given the diverse formats of network configuration requirement information input by users, this solution first determines the format in which the network configuration requirement information is saved, and then uses different methods to extract the network configuration requirement information from the file based on the saved format. After successfully extracting the user-input network configuration requirement information, text preprocessing is required to remove noise, stop words, and segment the text. The network configuration requirement information text is then cleaned, normalized, and transformed to facilitate subsequent tasks such as feature extraction and model training.

[0068] S212. Use the BERT model to extract features from the preprocessed network configuration requirement information to obtain a configuration information feature vector.

[0069] The preprocessed network configuration requirement information text is still not recognizable by the computer. Therefore, it needs to be encoded into a series of vectors that can be recognized by the computer. This application uses the BERT model to encode the network configuration requirement information text. The BERT model structure is as follows: Figure 5 As shown.

[0070] The BERT model consists of an embedding layer and an encoding layer. The preprocessed network configuration requirement information text is first input into the embedding layer to generate an embedding vector. Then, the multi-layer Transformer encoder of the BERT model's encoding layer performs parallel operations to extract the feature information of the embedding vector E and obtain the output feature vector.

[0071] Embedded layer

[0072] Embedded vector E i The token is generated by concatenating and summing three embedding vectors: the word vector (token) of the current configuration information text, the segment vector of the sentence containing the word, and the position vector of the word in the text. Then, CLS and SEP are added to each segment to create markers for the beginning and end of the text. Figure 6 As shown. [CLS] indicates the beginning of a sentence, and [SEP] indicates the end of a sentence.

[0073] The BERT model performs word embedding, segment embedding, and position embedding on the network configuration requirement information text, thereby converting it into a vector representation. Then, the three embedding vectors are summed to generate a single vector representation, which is used as the output of the embedding layer.

[0074] Input the configuration information text X into the BERT model, and calculate the formula as follows:

[0075] X = (x1, x2, ..., x) n ) T (Equation 1)

[0076] T i =TokenEmbedding(x i (Equation 2)

[0077] S i =SegmentEmbedding(x i (Equation 3)

[0078] P i =PositionEmbedding(x i (Equation 4)

[0079] E i =T i +S i +P i (Equation 5)

[0080] E = (E1, E2, ..., E n ) T (Equation 5)

[0081] Where, x i It is a word or character that makes up the configuration information text X. TokenEmbedding(·) embeds a single word in the input sequence, SegmentEmbedding(·) embeds the segment to which the word belongs, and PositionEmbedding(·) embeds the position of the word. i S represents the word embedding vector. i P represents the sentence tag embedding vector. i E represents the position embedding vector. i It is the final embedding vector of the i-th word in the input sequence, and E is the output of the embedding layer, which is an n×d vector. model The embedding vector dimension varies depending on the BERT model; in the BERT base, d... model It has 768 dimensions.

[0082] coding layer

[0083] The network configuration requirement information text is processed by the BERT embedding layer to obtain the embedding layer output E, which is then input into the encoding layer for preliminary text feature extraction. The BERT model's encoding layer uses a bidirectional, multi-layer Transformer encoder structure stacked together, as shown in the diagram. Figure 7 As shown.

[0084] The Transformer encoder is mainly composed of three parts: multi-head attention mechanism, residual connection and layer normalization, and feedforward neural network. After the configuration information embedding vector E is input into the encoding layer, it first extracts feature vectors through multi-head self-attention mechanism, then passes through residual connection and layer normalization to prevent overfitting of the model and accelerate the convergence speed of the model, and then passes through feedforward neural network to further extract features and enhance the expressive ability of the model.

[0085] 1) Multi-head self-attention mechanism

[0086] To better capture the contextual relationships of the input configuration information text and learn expressions with multiple meanings, the embedding layer output E is connected to a self-attention mechanism.

[0087] Each configuration information word vector E in the embedded layer output vector sequence E i The mapping is represented by a query vector (query, q), a key vector (key, k), and a value vector (value, v). The query vector q represents the query relationship of a given element in the input configuration information sequence to all other positions; the key vector k represents possible answers used to match the query vector; and the value vector v represents the information associated with the key vector, which is the actual feature to be extracted. The steps for calculating the self-attention mechanism are as follows:

[0088] First, perform a linear transformation on the embedding layer output E to obtain the Q, K, and V matrices, which are the matrices corresponding to the q, k, and v vectors. The specific formula is as follows:

[0089] Q = EW Q (Equation 6)

[0090] K = EW K (Equation 7)

[0091] V = EW V (Equation 8)

[0092] Among them, W Q W K W V This is a weight matrix, with dimension d. model ×d model Using a mean of 0 and a standard deviation of The algorithm is initialized using a normal distribution and continuously updated during training.

[0093] After performing a linear mapping to obtain matrices Q, K, and V, the output of the self-attention mechanism is obtained from these three matrices as follows:

[0094]

[0095] Here, Softmax(·) is the normalization exponential function. After being processed by Softmax(·), the row vector elements are proportionally compressed to [0,1], and the sum of the compressed vector elements is 1. The self-attention mechanism outputs X. attention The dimension is n×d model Each row represents the self-attention vector of the corresponding word in the input configuration information, which has been fused with information from other position words.

[0096] Obtain the single-head self-attention output X attention Then, by setting the number of attention heads h (i.e., the number of heads), and concatenating the self-attention matrices horizontally, an additional weight matrix is ​​multiplied by this matrix and projected onto the original dimension d of the model. model Thus, the output of the multi-head self-attention mechanism is obtained, and the calculation formula is as follows:

[0097]

[0098] MultiHead(Q,K,V)=Concat(head1,head2,…,head h W O (Equation 11)

[0099] Among them, head i W represents the output of a single-head self-attention mechanism. i Q , W represents the i-th head. Q W K W V Weight matrix, W O This represents the additional weight matrix, with dimensions (h·d). model )×d model Concat(·) represents the concatenation function.

[0100] 2) Residual connectivity and layer normalization

[0101] Residual connections add the input and output, thus passing information from the previous layer to the next. Layer normalization normalizes the output of each sub-layer before it is applied to prevent gradient vanishing and gradient exploding problems. The specific calculation formula is as follows:

[0102] X out=LayerNorm(E+MultiHead(Q,K,V)) (Equation 12)

[0103] MultiHead(Q,K,V) is the output of the multi-head self-attention mechanism, and LayerNorm(·) is the layer normalization function.

[0104] 3) Feedforward Neural Network

[0105] The feedforward neural network takes the output of the multi-head self-attention mechanism, after residual connections and layer normalization, as input, and maps it to a new representation vector through two linear transformations and a nonlinear activation function. The specific formula is as follows:

[0106] X hidden =ReLU(X) out W1+b1)W2+b2 (Equation 13)

[0107] Where W1 and W2 are the weight matrices for two different linear transformations, and W1 has a dimension of d. model ×n, W2 dimension is n×d model b1 and b2 are two bias vectors with dimensions n and d, respectively. model ReLU is the modified linear unit activation function.

[0108] The BERT model employs a multi-layer encoder, with each layer using the structure described above. The output of the previous encoder serves as the input to the next, and through multiple layers of encoding, preliminary feature extraction is performed on the configuration information text to obtain the output feature vector T, which has dimensions of n×d. model This vector contains configuration information and textual context relationships, and contains rich semantic knowledge, reflecting the semantics of the sentence more comprehensively.

[0109] S213. The TextCNN model is used to classify the feature vector of the configuration information to obtain the label classification result corresponding to the network configuration requirement information;

[0110] Among them, ERT, as a pre-trained model, can learn semantic information from word context. The output after training with the BERT model contains rich semantic knowledge, which cannot be fully utilized. Therefore, an additional output layer needs to be added to the BERT model after pre-training to adapt to different downstream tasks and new text data. For the task of classifying configuration information into text in this solution, a TextCNN model needs to be added after the BERT model to perform configuration information classification and extraction.

[0111] TextCNN is a variant of the CNN model, an algorithm that uses convolutional neural networks for text classification. The TextCNN model is as follows: Figure 8As shown, the TextCNN model consists of embedding layers, convolutional layers, pooling layers, and fully connected layers.

[0112] Embedded layer

[0113] This scheme uses a model combining BERT and TextCNN. Therefore, the BERT model embeds and encodes the input configuration information to obtain the word feature vector T = {T1, T2, ..., T}. n This replaces the original embedding layer of the TextCNN model.

[0114] Convolutional layer

[0115] The convolutional layer obtains the feature matrix c = {c1, c2, ..., c3} by performing convolution operations on the sentence matrix generated by the embedding layer using convolutional kernels of different sizes. n Let the convolution kernel w have dimensions h×d. model This scheme sets up three types of convolution kernels, namely 2×d model 3×d model 4×d model 2, 3, and 4 represent the number of words covered by the convolution kernel, respectively. The convolution kernel is then compared with the i-th window T in the configuration information word feature vector matrix T. i:i+h-1 The word vectors within the range are convolved to obtain feature c. i The formula for convolution operation is as follows:

[0116] c i =ReLU(w·T) i:i+h-1 +b) (14)

[0117] c′={c1,c2,…,c n-h+1} (15)

[0118] Among them, c i Let be the i-th element of the convolution result, be a scalar, w be the convolution kernel, and T be the scalar. i:i+h-1 is a segment of the input word feature matrix, where the symbol · represents the matrix dot product, b is the bias term, is a scalar, and ReLU is the activation function. The convolution kernel w is convolved with the word vectors within all windows of the word vector matrix T to obtain the feature map c′, where c′ has a dimension of 1×(n-h+1).

[0119] Pooling layer

[0120] Since feature maps generated by convolutional kernels of different sizes have different dimensions, pooling layers are needed to process the feature maps c output by the convolutional layers to obtain feature vectors of fixed length. This scheme uses 1-max pooling, selecting the maximum value in each feature map as the representative value of that feature map, thereby compressing each feature map. Based on this, the pooling results of all convolutional kernels are concatenated to obtain a global feature vector composed of the maximum eigenvalue. The calculation formula is as follows:

[0121]

[0122] Where max(·) is the function for finding the maximum value, and c′ i The feature map generated for the i-th convolutional kernel. Let m be the i-th largest eigenvalue, where m is the number of feature maps. For splicing operations, The feature is a global feature with a dimension of 1×m.

[0123] Fully connected layer and output layer

[0124] After feature extraction and merging through convolutional and pooling layers, the softmax activation function is used in the fully connected layer to calculate the predicted probability and obtain the final configuration information classification result. The specific calculation formula is as follows:

[0125]

[0126] Where y is the final output of the model, representing the probability distribution of each category, with a dimension of 1×k, where k is the number of categories, and W o Here is the weight matrix of the fully connected layer, with dimensions m×k. Here, is the global feature after pooling, · is the vector dot product, and b o As the bias term, with a dimension of 1×k, the softmax function converts the output value into a relative probability to obtain the classification result of network configuration requirement information.

[0127] S214. Extract key configuration information from the network configuration requirement information based on the label classification results;

[0128] S215. Configure the key configuration information into the corresponding positions in the preset unified information template to obtain the unified information model.

[0129] After processing by the BERT and TextCNN models, the categories of network configuration requirement information are obtained. Based on the predefined unified information model, the corresponding categories and parameters are filled into the unified information model, thereby realizing the establishment of the unified information model from user input configuration information.

[0130] S22. The unified information model is processed by a converter to generate configuration information, thereby obtaining the configuration information corresponding to the configuration protocol.

[0131] The converter's main function is to transform the unified information model into a configuration method supported by user equipment; it is the core of achieving unified configuration. The converter's structure is as follows: Figure 9As shown, the converter takes the previously established unified information model as input and outputs configuration information in the configuration protocol format supported by the device. The converter internally includes a model parsing module and a configuration information conversion module. The model parsing module is responsible for parsing the unified information model and extracting key information such as configuration protocol information and device configuration information. The configuration information conversion module includes conversion modules for configuration protocols such as CLI, SNMP, NETCONF, and OPC UA, responsible for converting the information extracted from the model into configuration information in the corresponding format. After conversion by the converter, the unified information model generates configuration information in the corresponding format, which is then distributed to the device through the configuration tools integrated within the system.

[0132] The specific method for using a converter to process the unified information model to generate configuration information and obtain the configuration information corresponding to the configuration protocol may include the following steps:

[0133] S221. The model parsing module is used to extract information from the unified information model to obtain configuration protocol information and device configuration information;

[0134] S222. Determine the configuration protocol template based on the configuration protocol information;

[0135] S223. Using the configuration protocol template and the device configuration information, configuration information generation processing is performed to obtain the configuration information corresponding to the configuration protocol.

[0136] The configuration protocol templates include CLI configuration protocol template, SNMP configuration protocol template, Netconf configuration protocol template, OPC UA configuration protocol template, private protocol configuration protocol template, and default configuration protocol template.

[0137] In a specific implementation, when the configuration protocol template is a CLI configuration protocol template, the configuration information corresponding to the configuration protocol can be generated using the following method.

[0138] Command Line Interface (CLI) is not strictly a configuration protocol, but it is still the most common configuration method for traditional devices, and some devices even only support CLI. Therefore, the converter in this solution provides conversion for CLI commands. The conversion steps of the CLI module are as follows:

[0139] A1. Extract key information such as protocol type and device IP address from the unified information model. If the protocol type is CLI, use this module to convert the configuration information.

[0140] A2. Select different CLI configuration information generation templates according to requirements. Configuration commands vary between different devices and manufacturers. To enable the converter to transform a unified information model into a CLI configuration format, it is first necessary to unify the commonly used configuration commands of different devices within the configuration system, and provide open editing interfaces for less frequently used configuration commands so that users can edit and save them as command templates for future use. Furthermore, formatted configuration templates can be abstracted from the configuration commands. Based on different configuration functions, the required corresponding configuration commands are abstracted, and wildcards are left where configuration data is needed. When the converter determines which configuration commands need to be called, it replaces the wildcards in the configuration template with the data to be configured, thus completing the construction of the configuration commands.

[0141] A3. After selecting the template, perform model conversion. The following is a brief introduction to the model conversion of the CLI configuration information template. The generated template and converted configuration commands for a manufacturer's TSN terminal VLAN configuration commands are shown below:

[0142] Generate template: vlan bridge vlan add dev*vid*pvid

[0143] Configuration command: vlan bridge vlan add dev swp1 vid 100pvid

[0144] For this template, the CLI module will extract specific configuration information from the unified information model, such as {swp1:100}, and fill it into the configuration template to replace the wildcard *, thereby generating configuration commands.

[0145] A4. Output the generated configuration command. After outputting the configuration command, the configuration information is generated based on the configuration command to obtain the configuration information corresponding to the configuration protocol.

[0146] In a specific implementation, when the configuration protocol template is the SNMP configuration protocol template, the configuration information corresponding to the configuration protocol can be generated using the following method.

[0147] SNMP, based on the SGMP (Simple Gateway Monitoring Protocol), enables remote management of network devices that support this protocol, including device discovery, operational status monitoring, and device configuration modification. The conversion steps for the SNMP module are as follows:

[0148] B1. Extract key information such as protocol type and device IP address from the unified information model. If the protocol type is SNMP, use this module to convert the configuration information.

[0149] B2. SNMP has a standard protocol message format, so there's no need to select a template; simply encapsulate the configuration information according to the message format. SNMP defines five Protocol Data Units (PDUs) for exchange between the management process and the agent. The unified configuration system primarily uses SNMP to configure devices, therefore only the get and set operations from the five defined PDUs are needed.

[0150] SNMP message format is as follows Figure 10 As shown, the get / set variable section of an SNMP message consists of the variable's name and value. When performing a get operation to retrieve the variable value, only the variable name is entered, and the value is ignored. The value is entered only when performing a set operation. SNMP uses Object Identifiers (OIDs) to uniquely identify devices; therefore, when setting get / set variables, the variable name should be set to the object identifier of the parameter to be configured. For public MIBs supported by SNMP, commonly used public variable OIDs can be pre-configured within the unified configuration system for users to choose from. For private MIBs, an open editing interface can be provided to allow users to enter their own private MIB OIDs. The unified configuration system can bind the user-input variable name with the corresponding OID, allowing for convenient access via the variable name when using the OID later.

[0151] B3. Model conversion for SNMP message format. The SNMP module extracts specific configuration information from the Unified Information Model, such as {1.3.6.1.2.1.1.5:”test”}, and fills it into the get / set variable part of the SNMP message. It also fills in parameters such as community and PDU type according to the message format to generate a configuration message.

[0152] B4. Output the generated configuration message.

[0153] In a specific implementation, when configuring the protocol template as the Netconf configuration protocol template, the following method can be used to generate the configuration information corresponding to the configuration protocol.

[0154] Netconf (Network Configuration Protocol) is a network configuration protocol used to configure network devices and monitor their status. It was designed to replace the traditional CLI method for managing network devices, providing a more structured and automated configuration management approach. The conversion steps for the Netconf module are as follows:

[0155] C1. Extract key information such as protocol type and device IP address from the unified information model. If the protocol type is Netconf, use this module to convert the configuration information.

[0156] C2.Netconf has a standard protocol message format, so there's no need to select a template; simply encapsulate the configuration information according to the message format. The Netconf protocol can be divided into four layers, with the Netconf module primarily handling configuration information conversion at the operation layer. Netconf defines three operation objects at the operation layer: running, candidate, and startup. Different configuration libraries have different states, allowing users to choose flexibly. Furthermore, the operation layer defines a set of basic protocol operations based on XML-encoded parameters and RPC method calls, mainly including four aspects: value retrieval, configuration, locking, and session operations, while also supporting user-defined RPC operations. This solution primarily uses Netconf for device configuration operations; therefore, the Netconf module will utilize common value retrieval and configuration operations.

[0157] Table 2 Examples of Netconf Messages

[0158]

[0159]

[0160] As shown in Table 2, Netconf encodes request messages based on XML format, where... <rpc>The `<resource>` element is used to encapsulate RPC requests, and the RPC request itself contains edit operations at the operation layer. <edit-config>The encapsulation is as follows. The operation layer contains the operation object and some commonly used operation options such as default operation and error options. <config>The content layer within the `<netconf>` tag contains the configuration changes to be made, such as adding or modifying VLANs.

[0161] C3. Model conversion is performed on the Netconf message format. The Netconf module uses an open-source XML library to construct Netconf messages. First, the outer RPC layer is independent of user configuration requirements and is automatically generated by the program. Then, the inner operation layer encapsulates configuration operations. <edit-config>Operations, encapsulated when performing configuration queries <get-config>The specific configuration content of the operation, configuration object and content layer is entered by the user in the configuration requirements. Then, the specific configuration information is extracted from the unified information model, converted into XML tag format by the Netconf module, and finally encapsulated into Netconf configuration message.

[0162] C4. Output the generated configuration message.

[0163] In a specific implementation, when the configuration protocol template is an OPC UA configuration protocol template, the configuration information corresponding to the configuration protocol can be generated using the following method:

[0164] OPC UA (Open Platform Communications Unified Architecture) is an open platform communications unified architecture used to achieve interoperability and integration in industrial automation and control systems. Based on standardized communication protocols and data models, OPC UA aims to solve communication and integration problems between different vendors, devices, and systems. The conversion steps for OPC UA modules are as follows:

[0165] D1. Extract key information such as protocol type and device IP address from the unified information model. If the protocol type is OPC UA, use this module to convert the configuration information.

[0166] D2.OPC UA has a standard protocol message format, so there's no need to select a template; simply encapsulate the configuration information according to the message format. OPC UA messages are typically encoded in XML text or binary format. Since XML encoding is convenient for different applications and platforms to use XML parsers to interpret OPC UA messages, this solution primarily describes the conversion of configuration information in XML encoding format.

[0167] Based on the definition of OPC UAService in Part 4 of the OPC UA specification (OPC 10000-4:UA Part 4:Services) and the description of the data encoding mechanism in Part 6 of the OPC UA specification (OPC 10000-6:UA Part 6:Mappings), the request message body in the XML encoding format of OPC UA is shown in Table 3.

[0168] Table 3. Examples of OPC UA Request Messages

[0169]

[0170]

[0171] According to the OPC UA specification, in the OPC UA request message body above, ReadRequest is a fixed request tag, RequestHeader contains request header parameters, MaxAge is the maximum interval time, TimestampsToReturn is the return timestamp option, and NodesToWrite contains the nodes to be written. If it is to read nodes, it can be replaced with NodesToRead.

[0172] D3. Model conversion is performed for OPC UA message format. The OPC UA module uses an open-source XML library to construct OPC UA messages. Tags such as RequestHeader and MaxAge are option parameters, which can usually be set to default values. The NodesToRead and NodesToWrite tags are used to perform read / write operations on nodes in OPC UA. Specific configuration parameters are extracted from the unified information model, such as {NodeId:”ns=2;i=1001”,Value=123.45}, and filled into the corresponding NodesToWrite tags to complete the construction of the OPC UA request message.

[0173] D4. Output the generated configuration message.

[0174] In a specific implementation, when configuring a private protocol template, the configuration information corresponding to the protocol can be generated using the following method:

[0175] To improve versatility, this solution provides an editing interface for proprietary protocols. For simple proprietary protocols, the proprietary protocol information can be edited through the configuration template management interface of the unified configuration system. The conversion steps for the proprietary protocol module are as follows:

[0176] E1. Extract key information such as protocol type and device IP address from the unified information model. If the protocol type is PRIVATE, use this module to convert the configuration information.

[0177] E2. Select different private protocol configuration information generation templates according to requirements. Here, the private protocol configuration information generation templates are edited by the user through the configuration template management interface of the unified configuration system. Similar to CLI templates, a formatted configuration template is abstracted from the private protocol configuration information, leaving wildcards where configuration data is required.

[0178] E3. After selecting the template, perform model conversion. Replace wildcards with specific configuration information extracted from the unified information model to complete the construction of private protocol configuration information.

[0179] E4. Output the generated configuration information.

[0180] In a specific implementation, when the configuration protocol template is the default configuration protocol template, the configuration information corresponding to the configuration protocol can be generated using the following method:

[0181] If the protocol type is not identified in the Unified Information Model (UNRECOG), or if some necessary parameters are missing, two methods are provided to resolve the issue.

[0182] F1. If the user's input configuration requirements match the protocol type in the converter and the necessary parameters are complete, the unified information model will be asked to re-identify the configuration. If any necessary parameters are missing, the user must complete the input configuration requirements before re-identification. If any necessary parameters are still missing, the unified configuration system will prompt the user that they are missing and require the user to manually enter them in the unified configuration system.

[0183] F2. If the user's input configuration requirements do not match the protocol type in the converter, the system will switch to the private protocol module, allowing the user to edit the configuration information and generate a template.

[0184] S23. Send the configuration information to the target device.

[0185] The unified information model (UMM) generates configuration messages in the corresponding protocol format after converting different configuration protocol formats using a converter. The next step is to distribute these messages to specific devices using configuration tools. The unified configuration system integrates configuration tools such as the Netconf client, OPC UA client, and SNMP Manager, which work in conjunction with the Netconf server and OPC UA server on the devices to perform configuration operations. Figure 11 As shown.

[0186] For devices supporting different configuration protocols, the corresponding configuration protocol tools are invoked to distribute configurations. For example, TSN switches use the Netconf protocol for configuration, allowing for functions such as gating list configuration and port enable status settings. The Netconf client integrated within the unified configuration system distributes the XML-formatted Netconf configuration information generated by the converter to the switch. The Netconf server deployed on the switch verifies and parses the configuration information, and performs functional configuration based on the parsed results. Industrial wireless networks primarily consist of three types of devices: industrial wireless gateways, industrial wireless routers, and field wireless nodes. For industrial wireless gateways, the unified configuration system establishes a connection with the OPC UA server within the industrial wireless gateway via an OPC UA client, sending the industrial wireless network configuration information to the gateway device. After receiving the configuration information, the industrial wireless gateway generates routing tables, superframe tables, and link tables. It then sends configuration information frames to the industrial wireless routers in the network. The industrial wireless routers send beacon frames and superframe configuration information to the field wireless nodes, which complete the superframe configuration task based on the configuration information.

[0187] For examples consistent with the above embodiments, please refer to... Figure 12 , Figure 12 A schematic diagram of a server structure provided in an embodiment of this application is shown in the figure. It includes a processor, an input device, an output device, and a memory. The processor, input device, output device, and memory are interconnected. The memory is used to store a computer program, which includes program instructions. The processor is configured to call the program instructions. The program includes instructions for performing the following steps.

[0188] Receive network configuration requirements from the user in the application via the northbound interface;

[0189] The network configuration requirement information is processed to generate a unified information model.

[0190] A converter is used to process the unified information model to generate configuration information, thereby obtaining the configuration information corresponding to the configuration protocol.

[0191] The configuration information is sent to the target device.

[0192] The above mainly describes the solutions of the embodiments of this application from the perspective of the method execution process. It is understood that, in order to achieve the above functions, the terminal includes the corresponding hardware structure and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments provided herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0193] This application embodiment can divide the terminal into functional units according to the above method example. For example, each function can be divided into a separate functional unit, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software functional unit. It should be noted that the unit division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0194] For those consistent with the above, please refer to Figure 13 , Figure 13 This application provides a schematic diagram of the structure of a unified configuration system for industrial heterogeneous networks. For example... Figure 13 As shown, the system includes:

[0195] The receiving unit 501 is used to receive network configuration requirement information input by the user in the application through the northbound interface;

[0196] Processing unit 502 is used to perform model generation processing on the network configuration requirement information to obtain a unified information model; and to use a converter to perform configuration information generation processing on the unified information model to obtain configuration information corresponding to the configuration protocol.

[0197] The sending unit 503 is used to send the configuration information to the target device.

[0198] In one specific implementation, regarding the process of generating a unified information model from the network configuration requirement information, the processing unit 502 is specifically used for:

[0199] The network configuration requirement information is preprocessed to obtain preprocessed network configuration requirement information;

[0200] The BERT model is used to extract features from the preprocessed network configuration requirement information to obtain a configuration information feature vector.

[0201] The TextCNN model is used to classify the feature vector of the configuration information to obtain the label classification results corresponding to the network configuration requirement information;

[0202] Key configuration information is extracted from the network configuration requirement information based on the label classification results;

[0203] The key configuration information is configured into the corresponding positions in the preset unified information template to obtain the unified information model.

[0204] In one specific implementation, regarding the preprocessing of the network configuration requirement information to obtain preprocessed network configuration requirement information, the processing unit 502 is specifically used for:

[0205] Text format information of network configuration requirements;

[0206] The network configuration requirement information is extracted using the file extraction method corresponding to the text format information to obtain the network configuration requirement information text.

[0207] The network configuration requirement information text is preprocessed to obtain preprocessed network configuration requirement information.

[0208] In one specific implementation, the converter includes a model parsing module and a configuration information conversion module. Regarding the process of using the converter to generate configuration information from the unified information model to obtain configuration information corresponding to the configuration protocol, the processing unit 502 is specifically used for:

[0209] The model parsing module is used to extract information from the unified information model to obtain configuration protocol information and device configuration information.

[0210] Determine the configuration protocol template based on the configuration protocol information;

[0211] The configuration information is generated by using the configuration protocol template and the device configuration information to obtain the configuration information corresponding to the configuration protocol.

[0212] This application also provides a computer storage medium storing a computer program for electronic data interchange, which causes a computer to perform some or all of the steps of a unified configuration method for any of the industrial heterogeneous networks described in the above method embodiments.

[0213] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program that causes a computer to perform some or all of the steps of a unified configuration method for any of the industrial heterogeneous networks described in the above method embodiments.

[0214] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0215] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0216] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical or other forms.

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

[0218] Furthermore, the functional units in the various embodiments of the application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software program module.

[0219] If the integrated unit is implemented as a software program module and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0220] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage device, which may include: a flash drive, a read-only memory, a random access memory, a magnetic disk, or an optical disk, etc.

[0221] The embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application. < / config> < / rpc>

Claims

1. A method for unified configuration of an industrial heterogeneous network, characterized in that, The method is applied to a unified configuration system, and comprises the following steps: Receiving network configuration requirement information input by a user in an application through a northbound interface; Generating a unified information model from the network configuration requirement information; Generating configuration information corresponding to a configuration protocol from the unified information model by using a converter; Sending the configuration information to a target device; The method for generating a unified information model from the network configuration requirement information comprises the following steps: Preprocessing the network configuration requirement information to obtain preprocessed network configuration requirement information; Extracting features of the preprocessed network configuration requirement information by using a BERT model to obtain a configuration information feature vector; Classifying the configuration information feature vector by using a TextCNN model to obtain a label classification result corresponding to the network configuration requirement information; Extracting key configuration information from the network configuration requirement information according to the label classification result; Configuring the key configuration information into a corresponding position in a preset unified information template to obtain the unified information model; The converter comprises a model analysis module and a configuration information conversion module, and the method for generating configuration information corresponding to a configuration protocol from the unified information model by using a converter comprises the following steps: Extracting information from the unified information model by using the model analysis module to obtain configuration protocol information and device configuration information; Determining a configuration protocol template according to the configuration protocol information; Generating configuration information by using the configuration protocol template and the device configuration information to obtain configuration information corresponding to a configuration protocol.

2. The method of claim 1, wherein, The preprocessing of the network configuration requirement information to obtain preprocessed network configuration requirement information comprises the following steps: Text format information of the network configuration requirement information; Extracting text from the network configuration requirement information according to a file extraction method corresponding to the text format information to obtain network configuration requirement information text; Text preprocessing of the network configuration requirement information text to obtain preprocessed network configuration requirement information.

3. The method of claim 1, wherein, The configuration protocol template comprises a CLI configuration protocol template, an SNMP configuration protocol template, a Netconf configuration protocol template, an OPC UA configuration protocol template, a private protocol configuration protocol template, and a default configuration protocol template.

4. A unified configuration system of an industrial heterogeneous network, characterized by, The system comprises: A receiving unit configured to receive network configuration requirement information input by a user in an application through a northbound interface; A processing unit configured to generate a unified information model from the network configuration requirement information, and generate configuration information corresponding to a configuration protocol from the unified information model by using a converter; A sending unit configured to send the configuration information to a target device; In the aspect of generating a unified information model from the network configuration requirement information, the processing unit is specifically configured to: Preprocess the network configuration requirement information to obtain preprocessed network configuration requirement information; Extract features of the preprocessed network configuration requirement information by using a BERT model to obtain a configuration information feature vector; The TextCNN model is used to classify the configuration information feature vector, and a label classification result corresponding to network configuration requirement information is obtained. Key configuration information is extracted from the network configuration requirement information according to the label classification result; The key configuration information is configured to a corresponding position in a preset unified information template, and the unified information model is obtained; In the aspect of generating configuration information of the configuration protocol by using the converter to process the unified information model, the processing unit is specifically configured to: The model analysis module is used to extract information from the unified information model, and configuration protocol information and device configuration information are obtained; A configuration protocol template is determined according to the configuration protocol information; The configuration protocol template and the device configuration information are used to generate configuration information, and configuration information corresponding to the configuration protocol is obtained.

5. The method of claim 4, wherein, In the aspect of preprocessing the network configuration requirement information to obtain preprocessed network configuration requirement information, the processing unit is specifically configured to: Text format information of the network configuration requirement information; Text of the network configuration requirement information is extracted according to a file extraction method corresponding to the text format information, and network configuration requirement information text is obtained; The network configuration requirement information text is preprocessed to obtain preprocessed network configuration requirement information.

6. A server, characterized by The computer readable storage medium stores a computer program, and the computer program includes program instructions. The program instructions, when executed by a processor, cause the processor to execute the method according to any one of claims 1-3.

7. A computer readable storage medium characterized by The computer readable storage medium stores a computer program, and the computer program includes program instructions. The program instructions, when executed by a processor, cause the processor to execute the method according to any one of claims 1-3.

Images