Online Intelligent Detection and Analysis Method and System for Standard Board Production Based on Industrial Internet of Things

Abstract

The embodiment of the present application provides an online intelligent detection and analysis method and system for standard board production based on the industrial Internet of Things. First, the first standard board production monitoring data is obtained, and multiple node graph construction knowledge patterns are determined to construct a state node graph. Subsequently, by injecting identification attribute information into the first standard board production monitoring data, multiple second standard board production monitoring data corresponding to different knowledge patterns are generated, and the corresponding feature extraction paths are determined based on the injected pattern identification information. After that, the production parameter trajectory vectors are extracted and then the node graphs are constructed respectively. Based on the construction result of the state node graph, the abnormal state links in the target standard board production monitoring process are estimated, thereby significantly improving the online intelligent detection and analysis level of standard board production.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial Internet of Things for home furnishing, and in particular, to an online intelligent detection and analysis method and system for standard board production based on the industrial Internet of Things. Background Art

[0002] In modern industrial production, especially in the field of home furnishing industrial manufacturing, the production process of standard boards involves the interaction of multiple complex processes and equipment. How to efficiently and accurately monitor this process and timely discover and handle abnormal states in production is crucial for improving production efficiency and product quality. Traditionally, the monitoring of standard board production mainly relies on manual inspections and offline data analysis. This method is not only inefficient but also difficult to comprehensively and real-time reflect the production status.

[0003] With the rapid development of industrial Internet of Things technology, more and more production equipment has been connected to the Internet of Things platform, enabling real-time collection and transmission of production data. This provides the possibility for online intelligent detection and analysis. However, the production monitoring data recorded in the industrial Internet of Things platform often has characteristics such as massive volume, heterogeneity, and high dimensionality. How to extract valuable information from these complex data remains a challenge. For example, related technologies rely too much on preset rules and models, making it difficult to adapt to the dynamic changes in the production process and fully exploit the potential value of the data. Summary of the Invention

[0004] In order to at least overcome the above deficiencies in the prior art, the purpose of the embodiments of the present application is to provide an online intelligent detection and analysis method and system for standard board production based on the industrial Internet of Things.

[0005] According to one aspect of the present application, an online intelligent detection and analysis method for standard board production based on industrial Internet of Things is provided. The method includes: obtaining first standard board production monitoring data recorded in the industrial Internet of Things platform for monitoring the production process of the target standard board, and determining a plurality of node graph construction knowledge patterns for constructing a state node graph for the first standard board production monitoring data; for the plurality of node graph construction knowledge patterns, injecting identification attribute information into the first standard board production monitoring data respectively to generate a plurality of second standard board production monitoring data; the second standard board production monitoring data in the plurality of second standard board production monitoring data corresponds to the node graph construction knowledge patterns in the plurality of node graph construction knowledge patterns respectively, and the identification attribute information in each second standard board production monitoring data includes pattern identification information reflecting the corresponding node graph construction knowledge pattern; determining a plurality of feature extraction paths associated with the plurality of second standard board production monitoring data according to the pattern identification information included in the plurality of second standard board production monitoring data; for each second standard board production monitoring data in the plurality of second standard board production monitoring data, extracting production parameter trajectory vectors respectively according to the associated feature extraction path to generate a set of production parameter trajectory vectors corresponding to each of the plurality of node graph construction knowledge patterns; constructing node graphs for the sets of production parameter trajectory vectors corresponding to the plurality of node graph construction knowledge patterns respectively to generate state node graph construction results corresponding to the plurality of node graph construction knowledge patterns respectively, and estimating an abnormal state link of the target standard board production monitoring process based on the state node graph construction results corresponding to the plurality of node graph construction knowledge patterns.

[0006] In the technical solutions provided by some embodiments of the present application, the embodiments of the present application first determine a plurality of node graph construction knowledge patterns. By injecting identification attribute information into the production monitoring data of the first standard board, a plurality of second standard board production monitoring data corresponding to different knowledge patterns are generated, realizing the refined classification and processing of data. According to the pattern identification information in the second standard board production monitoring data, the feature extraction path associated with the data can be accurately matched. This accurate matching ensures the pertinence and effectiveness of feature extraction, providing a high-quality data basis for the subsequent construction of the state node graph. For each second standard board production monitoring data, the present invention efficiently extracts the production parameter trajectory vector according to the associated feature extraction path, generating a set of production parameter trajectory vectors corresponding to a plurality of node graph construction knowledge patterns, which can comprehensively reflect the parameter changes and state transitions in the production process. By constructing a node graph for the set of production parameter trajectory vectors, a plurality of state node graph construction results are generated, which can intuitively display the state transitions and logical relationships in the production process. Based on the state node graph, the abnormal state link in the production monitoring process of the target standard board can be accurately estimated, and potential problems in production can be discovered in a timely manner. Thus, through the construction of a multi-mode state node graph, the accurate matching of the feature extraction path, the efficient extraction of the production parameter trajectory vector, and the intelligent construction of the state node graph and the accurate estimation of the abnormal state link, the online intelligent detection and analysis level of standard board production is significantly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the accompanying drawings required to be used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0008] Figure 1 It is a schematic flowchart of an online intelligent detection and analysis method for standard board production based on industrial Internet of Things provided by an embodiment of the present application;

[0009] Figure 2 It is a schematic block diagram of the architecture of an online intelligent detection and analysis system for standard board production based on industrial Internet of Things provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0010] The following description is provided to enable a person of ordinary skill in the art to implement and combine this application, and this description is provided in the context of a specific application scenario and its required environment. For a person of ordinary skill in the art, it is obvious that various changes can be made to the disclosed embodiments, and when not departing from the principles and scope of this application, the general principles defined in this application can be applied to other embodiments and application scenarios. Therefore, this application is not limited to the described embodiments, but should be given the broadest scope consistent with the claims.

[0011] Figure 1 FIG. 4 is a schematic flowchart of an online intelligent detection and analysis method for standard board production based on industrial Internet of Things provided by an embodiment of this application. The following provides a detailed introduction to the online intelligent detection and analysis method for standard board production based on industrial Internet of Things.

[0012] Step S110: Obtain the first standard board production monitoring data recorded in the industrial Internet of Things platform for the production monitoring process of the target standard board, and determine multiple node graph construction knowledge patterns for constructing a state node graph for the first standard board production monitoring data.

[0013] Specifically, the industrial Internet of Things platform is a network integrating various industrial devices and systems, which realizes the interconnection and interoperability between devices through Internet of Things technology, collects, analyzes, and processes a large amount of data in the industrial production process to improve production efficiency and optimize resource allocation. The target standard board production monitoring process refers to the monitoring of the production process of standard boards (such as boards in furniture manufacturing) in home furnishing industrial manufacturing, which may include, for example, monitoring of raw material input, processing of each process, quality inspection of finished products, etc.

[0014] The first standard board production monitoring data is data obtained from the industrial Internet of Things platform and records the production monitoring process of the target standard board, which may include various types of data such as raw material information, equipment operation status, production parameters, quality inspection results, etc. The node graph construction knowledge pattern is a knowledge pattern or rule for guiding how to construct a state node graph based on production monitoring data, which may include, for example, a single-process node graph construction knowledge pattern, a whole-batch node graph construction knowledge pattern, an associated device interaction node graph construction knowledge pattern, etc.

[0015] For example, in this embodiment, in home furnishing industrial manufacturing, such as the production of standard boards for furniture. The server obtains the first standard board production monitoring data of the target standard board production monitoring process from the industrial Internet of Things platform. These data contain information on each link from raw material input to the preliminary forming of the standard board. For example, the humidity and texture direction data of the raw material wood, the rotation speed and temperature of the processing equipment, and the operation time of each process.

[0016] Determine multiple node graph construction knowledge patterns for constructing a state node graph from the first standard board production monitoring data. For example, based on the characteristics of home manufacturing, a single-process node graph construction knowledge pattern can be used to analyze the monitoring data of a single process, such as the wood cutting process, to construct a state node graph. The whole-batch node graph construction knowledge pattern can be used to analyze the overall monitoring data of the production of a whole batch of standard boards. For example, for the overall process monitoring data of a batch of 100 standard boards from the start of production to the complete production, a state node graph can be constructed. The associated device interaction node graph construction knowledge pattern is applicable to analyzing the monitoring data related to the interaction between different devices to construct a state node graph. For example, it can be used for the monitoring data related to the transfer of standard boards between a cutting device and a grinding device. The multi-source data node graph construction knowledge pattern can be used to process the standard board production monitoring data from multiple data sources to construct a state node graph. For example, it can be used for the standard board production monitoring data integrated from multi-source data such as production equipment sensors, environmental monitoring sensors, and manual quality inspection records. The customized node graph construction knowledge pattern can be used to construct a state node graph for specific requirements. For example, it can be used to specifically analyze the monitoring data of the standard board surface treatment process and only focus on the usage amount and treatment time of specific chemical agents to construct a state node graph. These different node graph construction knowledge patterns help to comprehensively analyze the standard board production monitoring process from different perspectives.

[0017] Step S120: For the multiple node graph construction knowledge patterns, inject identification attribute information into the first standard board production monitoring data respectively to generate multiple second standard board production monitoring data. The second standard board production monitoring data among the multiple second standard board production monitoring data corresponds to the node graph construction knowledge patterns among the multiple node graph construction knowledge patterns respectively, and the identification attribute information in each second standard board production monitoring data includes pattern identification information reflecting the corresponding node graph construction knowledge pattern.

[0018] Specifically, the second standard board production monitoring data is the data generated after injecting identification attribute information into the first standard board production monitoring data. Each second standard board production monitoring data corresponds to a specific node graph construction knowledge pattern and contains pattern identification information reflecting this pattern.

[0019] The identification attribute information is the attribute information used to identify and distinguish different node graph construction knowledge patterns. For example, it can include the start identifier of the initial data segment, the end identifier of the initial data segment, the termination identifier, and the pattern identification information reflecting the node graph construction knowledge pattern, etc.

[0020] For example, in this embodiment, for the multiple node graph construction knowledge patterns determined above, the server starts to inject identification attribute information into the first standard board production monitoring data to generate multiple second standard board production monitoring data.

[0021] Taking the construction of a knowledge model with a single process node diagram as an example, if it is the monitoring data for the wood cutting process. Suppose the amount of monitoring data for the wood cutting process in the first standard board production monitoring data is not greater than the set quantity. The server injects pattern identification information reflecting the construction knowledge model of the single process node diagram, such as "wood cutting process pattern identification", at the front end of this data. Then, before the initial data segment of the wood cutting process monitoring data and after this identification information, an initial data segment start identification, such as "cutting process data segment start identification", is injected. At the back end of the wood cutting process monitoring data, an initial data segment end identification, like "cutting process data segment end identification", is injected, and a termination identification "cutting process data termination identification" is injected after the injected initial data segment end identification, thus generating the second standard board production monitoring data corresponding to the construction knowledge model of the single process node diagram.

[0022] Looking at the construction knowledge model of the whole batch node diagram again, if the amount of the whole batch production monitoring data included in the first standard board production monitoring data is large (greater than the set quantity). The server injects pattern identification information "whole batch production pattern identification" reflecting the construction knowledge model of the whole batch node diagram at the front end of the whole batch production monitoring data. Before the initial data segment of the whole batch production monitoring data and after this identification information, an initial data segment start identification "whole batch initial data segment start identification" is injected. At the back end of the production monitoring data of the initial single process (such as the process corresponding to the start of the production of the first batch of standard boards) in the whole batch production monitoring data, an initial data segment end identification "whole batch initial data segment end identification" is injected. Then, the remaining single process production monitoring data in the whole batch production monitoring data except for the initial single process production monitoring data is determined, and a data segment division identification, such as "whole batch data segment division identification", is injected between every two associated remaining single process production monitoring data, thus generating the second standard board production monitoring data corresponding to the construction knowledge model of the whole batch node diagram.

[0023] For the construction knowledge model of the associated equipment interaction node diagram, such as the monitoring data involving the interaction between the cutting equipment and the grinding equipment. The server obtains the corresponding identification attribute information for this model, including specific pattern identification information "cutting - grinding equipment interaction pattern identification", initial data segment start identification, initial data segment end identification, etc., and injects them into the corresponding part of the first standard board production monitoring data according to the corresponding rules to generate the corresponding second standard board production monitoring data.

[0024] The knowledge pattern construction of the multi-source data node graph and the customized node graph construction knowledge pattern also inject the corresponding identification attribute information into the first standard board production monitoring data according to their respective requirements and data characteristics, so as to generate their respective corresponding second standard board production monitoring data. The identification attribute information in each second standard board production monitoring data contains the pattern identification information reflecting the corresponding node graph construction knowledge pattern, which helps the subsequent steps to accurately process the data.

[0025] Step S130: Determine a plurality of feature extraction paths associated with the plurality of second standard board production monitoring data according to the pattern identification information included in the plurality of second standard board production monitoring data.

[0026] Specifically, the feature extraction path is a path or method for extracting feature information from the second standard board production monitoring data, and may include an interactive feature extraction path and a non-interactive feature extraction path, which are respectively used to process the associated device interactive production monitoring data and the non-associated device interactive production monitoring data.

[0027] For example, in this embodiment, the server determines a plurality of feature extraction paths associated with the plurality of second standard board production monitoring data according to the pattern identification information included in the plurality of second standard board production monitoring data.

[0028] For the second standard board production monitoring data containing the interactive task pattern, such as the second standard board production monitoring data corresponding to the associated device interactive node graph construction knowledge pattern (such as the monitoring data related to the interaction between the cutting device and the grinding device), the server determines the feature extraction path associated with it as the interactive feature extraction path for extracting features from the associated device interactive production monitoring data. Because in the manufacture of furniture standard boards, the interaction process between the cutting device and the grinding device has unique features that need to be extracted, such as the time interval for the cut standard board to be transferred to the grinding device, and the matching degree between the size of the standard board output by the cutting device and the preset receiving size of the grinding device.

[0029] For the second standard board production monitoring data of the non-interactive task pattern, such as the second standard board production monitoring data corresponding to the whole batch node graph construction knowledge pattern (the overall monitoring data of the whole batch of standard board production), the server determines the feature extraction path associated with it as the non-interactive feature extraction path for extracting features from the non-associated device interactive production monitoring data. In this case, more attention may be paid to the overall time consumption and raw material utilization rate in the process of the whole batch of standard board production, rather than the interactive features between devices.

[0030] Construct the second standard board production monitoring data corresponding to the knowledge pattern of the single-process node diagram. If it is the monitoring data of the wood cutting process, since it mainly focuses on the internal situation of the single process and belongs to the non-interactive task mode, the non-interactive feature extraction path is also adopted, mainly extracting features such as the wear rate of the cutting tool and the cutting accuracy. The second standard board production monitoring data corresponding to the knowledge pattern of the multi-source data node diagram may adopt the interactive feature extraction path for some parts (if it involves data sources related to device interaction) and the non-interactive feature extraction path for some parts (such as simple environmental monitoring data) according to the nature of different source data. The second standard board production monitoring data corresponding to the customized node diagram construction knowledge pattern also determines whether to adopt the interactive or non-interactive feature extraction path according to its customized content. For example, if the customization is about the special relationship monitoring data between two specific process devices, the interactive feature extraction path is adopted, otherwise the non-interactive feature extraction path is adopted.

[0031] Step S140: For each of the multiple second standard board production monitoring data, respectively extract the production parameter trajectory vectors according to the associated feature extraction path, and generate the production parameter trajectory vector sets corresponding to the multiple node diagram construction knowledge patterns.

[0032] Specifically, the production parameter trajectory vector is generated by extracting features from the second standard board production monitoring data, representing the vector of the production parameter changing with time, and is used to construct the state node diagram to reflect the state transition and parameter change in the production process.

[0033] For example, in this embodiment, for each of the multiple second standard board production monitoring data, the server respectively extracts the production parameter trajectory vectors according to the associated feature extraction path, and generates the production parameter trajectory vector sets corresponding to the multiple node diagram construction knowledge patterns.

[0034] Taking the second standard board production monitoring data corresponding to the knowledge pattern of the associated device interaction node diagram (monitoring data related to the interaction between the cutting device and the grinding device) as an example, when the feature extraction path associated with this data is the interactive feature extraction path, for each single-process production monitoring data therein (such as the monitoring data corresponding to each cutting operation of the cutting device and the monitoring data corresponding to each grinding operation of the grinding device), the server respectively determines the interactive link data of each single-process production monitoring data in this second standard board production monitoring data. For example, when the cutting device transfers the standard board to the grinding device, the interactive link data such as the stop time of the cutting device and the start preparation time of the grinding device at the moment of transfer. Then, feature representations are respectively performed on the determined interactive link data to generate the interactive link feature vectors corresponding to each single-process production monitoring data.

[0035] Based on the interaction device tags in each single-process production monitoring data, such as those of cutting equipment and grinding equipment, determine the interaction devices associated with each single-process production monitoring data, and perform feature representations on the interaction devices associated with each single-process production monitoring data respectively to generate interaction device feature vectors corresponding to each single-process production monitoring data. For example, for cutting equipment, its features may include the type of cutting tool, cutting power, etc.; for grinding equipment, its features may include the roughness of the grinding wheel, grinding speed, etc.

[0036] Perform state parameter feature representations on each single-process production monitoring data respectively to generate a set of state parameter feature vectors corresponding to each single-process production monitoring data. For example, state parameters such as cutting depth and cutting angle of cutting equipment, and grinding force and grinding time of grinding equipment are all represented as state parameter feature vectors.

[0037] Perform context feature representations on each single-process production monitoring data respectively to generate a set of context feature vectors corresponding to each single-process production monitoring data. For example, the ambient temperature and humidity around the cutting equipment during operation may affect the cutting effect, and these environmental factors constitute the context feature vectors; the noise level in the workshop during the operation of the grinding equipment also belongs to the context feature vectors.

[0038] Finally, based on the interaction link feature vectors, interaction device feature vectors, set of state parameter feature vectors, and set of context feature vectors corresponding to each single-process production monitoring data respectively, generate a set of production parameter trajectory vectors corresponding to the production monitoring data of the second standard board corresponding to the knowledge pattern for constructing the interaction node graph of the associated device.

[0039] For the production monitoring data of the second standard board corresponding to the knowledge pattern for constructing the whole batch of node graphs, when the feature extraction path associated with it is a non-interaction feature extraction path, the server performs state parameter feature representations on each data node (such as each process link in the production process of each standard board is regarded as a data node) respectively to generate a set of state parameter feature vectors corresponding to each data node. For example, for the wood drying process of each standard board, the state parameters may include drying time, drying temperature, etc.

[0040] Perform context feature representations on each data node respectively to generate a set of context feature vectors corresponding to each data node. For example, the ventilation situation in the warehouse during the wood drying process, etc.

[0041] Fuse the state parameter feature vectors and context feature vectors corresponding to the same data nodes to generate fused feature vectors corresponding to each data node respectively. Based on the fused feature vectors corresponding to each data node respectively, generate a set of production parameter trajectory vectors corresponding to the second standard board production monitoring data corresponding to the overall batch of node graph construction knowledge patterns.

[0042] For the second standard board production monitoring data corresponding to the single-process node graph construction knowledge pattern (such as the wood cutting process), the multi-source data node graph construction knowledge pattern, and the customized node graph construction knowledge pattern, similar production parameter trajectory vector extraction operations are also performed according to their respective associated feature extraction paths to generate their respective corresponding sets of production parameter trajectory vectors.

[0043] Step S150: Perform node graph construction on the sets of production parameter trajectory vectors corresponding to the multiple node graph construction knowledge patterns respectively to generate the state node graph construction results corresponding to the multiple node graph construction knowledge patterns respectively. Estimate the abnormal state link of the target standard board production monitoring process based on the state node graph construction results corresponding to the multiple node graph construction knowledge patterns respectively.

[0044] Specifically, the state node graph construction result is a graphical representation based on the set of production parameter trajectory vectors, reflecting the state transition and logical relationship in the production monitoring process, including the initial state node, the derived state node, the relationship between state nodes, etc.

[0045] The abnormal state link is a link that appears abnormal in the production monitoring process and causes the production process to deviate from the normal path. By estimating the abnormal state link, problems in the production process can be discovered in a timely manner, and corresponding measures can be taken to solve them to improve production efficiency and product quality.

[0046] For example, in this embodiment, the server performs node graph construction on the sets of production parameter trajectory vectors corresponding to the multiple node graph construction knowledge patterns respectively to generate the state node graph construction results corresponding to the multiple node graph construction knowledge patterns respectively, and estimates the abnormal state link of the target standard board production monitoring process based on the state node graph construction results corresponding to the multiple node graph construction knowledge patterns respectively.

[0047] Taking the set of production parameter trajectory vectors corresponding to the single-process node graph construction knowledge pattern (such as the wood cutting process) as an example, for this set of production parameter trajectory vectors, the server generates an initial state node based on the traversed set of production parameter trajectory vectors and the initial state node identifier corresponding to this set of production parameter trajectory vectors. For example, if the initial state is the start of the cutting equipment, then the initial state node is represented as "cutting equipment start".

[0048] Based on this initial state node and the set of traversed production parameter trajectory vectors, multiple stages of graph construction processing are carried out. First, each production parameter trajectory vector in the set of production parameter trajectory vectors is classified and marked, and a preliminary association relationship is established between the initial state node and the first production parameter trajectory vector in the set of production parameter trajectory vectors. This preliminary association relationship is based on the starting logic of the production process. For example, the first production parameter trajectory vector may be the initial rotation speed of the cutting device, and it has an association based on the production starting logic with the initial state node of the cutting device startup.

[0049] Then, analyze the attributes of the initial state node. If the initial state node represents the startup state of production (such as the startup of the cutting device), then search for the production parameter vectors related to the startup state in the set of production parameter trajectory vectors, and establish an advanced association relationship between the production parameter vectors and the initial state node, thereby initially constructing a mapping relationship based on production logic between the initial state node and some production parameter trajectory vectors. For example, parameters such as the magnitude of the current when the cutting device starts are associated with the startup state of the cutting device.

[0050] Based on the preliminary association relationship, analyze each associated production parameter trajectory vector to search for other production parameter trajectory vectors in the set of production parameter trajectory vectors that have a logical association with the associated production parameter trajectory vector, and gradually expand the initial state node based on the search results to continuously create a representation of intermediate state nodes on the basis of the initial state node, generating an intermediate state node structure. For example, after the cutting device starts, as the cutting progresses, the wear condition of the cutting tool has a logical association with the startup state of the cutting device, and through this association, intermediate state nodes such as "the tool starts to wear after the cutting device has been started for a period of time" are expanded.

[0051] Perform redundancy optimization on the intermediate state node structure to obtain an optimized intermediate state node structure. Determine the time information corresponding to each production parameter trajectory vector in the set of production parameter trajectory vectors. According to the time information, perform a time sorting on the association relationships in the intermediate state nodes in the optimized intermediate state node structure, and expand the intermediate state nodes according to the advancement of the time sorting sequence to obtain a derived state node structure carrying time sorting sequence information. For example, the wear degree of the tool is different at different time points after the cutting device starts, and different derived state nodes are constructed in chronological order.

[0052] Integrate the initial state node and multiple derived state nodes to generate a state node graph construction result corresponding to the set of production parameter trajectory vectors corresponding to the single-process node graph construction knowledge pattern.

[0053] Similar node graph construction operations are also performed on the production parameter trajectory vector sets corresponding to the whole batch node graph construction knowledge mode, associated device interaction node graph construction knowledge mode, multi-source data node graph construction knowledge mode, and customized node graph construction knowledge mode to generate their respective corresponding state node graph construction results.

[0054] Next, the server performs standardization processing on the state node graphs corresponding to each state node graph construction result to unify the representation of state nodes and the description format of the relationships between state nodes in the state node graphs. For example, device states, process states, etc. under different modes are represented by unified symbols or formats.

[0055] Analyze each state node in the standardized state node graph and the relationships between various state nodes, find the state nodes corresponding to each link in the production process. For each state node, determine the preceding node and the succeeding node of this state node in the production process, establish a complete node relationship mapping based on the production process sequence, and generate a state node graph structure carrying the production process mapping relationship. For example, in the production of standard furniture boards, the preceding node of the wood drying process may be the wood cutting process, and the succeeding node may be the board splicing process, and establish such a complete relationship mapping.

[0056] Based on the established node relationship mapping, extract the normal state link under normal production conditions from the state node graph, and analyze the characteristic patterns in the normal state link. Combine the key nodes, relationships, and characteristic patterns of the normal state link to construct a characteristic model for describing the normal state link.

[0057] Compare and analyze the actual state link in each state node graph with the characteristic model of the normal state link, and preliminarily screen out the candidate abnormal links in the state node graph. For example, if the time of the wood drying process in the actual state link far exceeds the time in the normal state link, it may be preliminarily screened as a candidate abnormal link.

[0058] For the preliminarily screened candidate abnormal links, verify them with reference to historical production monitoring data to generate the verified target abnormal links. For example, check the time data range of past similar wood drying processes. If the current abnormal situation is also determined to be abnormal in the historical data, then it is determined as the target abnormal link.

[0059] For the verified target abnormal link, perform root cause analysis in the graph structure of the state node graph, trace the abnormal state node where the abnormal state first appears in the target abnormal link, analyze the abnormal cause that leads to the abnormality of this abnormal state node, and at the same time evaluate the correlation relationship information between the target abnormal link and other state links. For example, if the target abnormal link is that the wood drying process takes too long, trace back to the possible cause of the drying equipment failure, and at the same time analyze whether this abnormal link will affect subsequent processes such as board splicing and other correlation relationships.

[0060] Based on the abnormal cause and the correlation relationship information between the target abnormal link and other state links, determine the severity of each target abnormal link. For example, if the drying equipment failure causes the wood drying process to take too long, and if it seriously affects the production progress and quality of the entire batch of standard boards, then the severity is relatively high. If it can be remedied in time through some adjustment measures, the severity is relatively low. In this way, the abnormal state links in the production monitoring process of standard boards in the home furnishing industry manufacturing can be analyzed comprehensively and accurately, which helps to discover problems in time and take effective solutions, improving production efficiency and product quality.

[0061] Based on the above steps, the embodiment of the present application first determines multiple node graph construction knowledge patterns. By injecting identification attribute information into the first standard board production monitoring data, multiple second standard board production monitoring data corresponding to different knowledge patterns are generated, realizing the refined classification and processing of data. According to the pattern identification information in the second standard board production monitoring data, the feature extraction path associated with the data can be accurately matched. This accurate matching ensures the pertinence and effectiveness of feature extraction, providing a high-quality data basis for the subsequent construction of the state node graph. For each second standard board production monitoring data, the present invention efficiently extracts the production parameter trajectory vector according to the associated feature extraction path, generating a set of production parameter trajectory vectors corresponding to multiple node graph construction knowledge patterns, which can comprehensively reflect the parameter changes and state transitions in the production process. By constructing a node graph for the set of production parameter trajectory vectors, multiple state node graph construction results are generated, which can intuitively display the state transitions and logical relationships in the production process. Based on the state node graph, the abnormal state links in the production monitoring process of the target standard board can be accurately estimated, and potential problems in production can be discovered in time. Thus, through multi-mode state node graph construction, accurate matching of feature extraction paths, efficient extraction of production parameter trajectory vectors, and intelligent construction of state node graphs and accurate estimation of abnormal state links, the online intelligent detection and analysis level of standard board production is significantly improved.

[0062] In a possible implementation manner, step S110 includes:

[0063] Step S111: Generate a node graph construction knowledge pattern sequence based on the node graph construction instruction for the production monitoring data of the first standard board.

[0064] Step S112: Based on the hit instruction for the node graph construction knowledge pattern sequence, use the multiple node graph construction knowledge patterns hit by the hit instruction as the multiple node graph construction knowledge patterns for constructing the status node graph of the production monitoring data of the first standard board.

[0065] In this embodiment, for determining multiple node graph construction knowledge patterns for constructing the status node graph of the production monitoring data of the first standard board, when the server receives the node graph construction instruction for the production monitoring data of the first standard board, it starts to generate a node graph construction knowledge pattern sequence. This sequence includes various patterns that may be applicable to the production monitoring data of the home standard board, such as single-process node graph construction knowledge patterns for single processes like cutting, grinding, and assembling in furniture production, whole-batch node graph construction knowledge patterns considering the production situation of the entire batch of standard boards, associated device interaction node graph construction knowledge patterns focusing on the interaction between different devices such as cutting devices and grinding devices, multi-source data node graph construction knowledge patterns integrating multi-source data like device sensors and manual quality inspection data, and customized node graph construction knowledge patterns to meet special requirements. Then, when there is a hit instruction for this node graph construction knowledge pattern sequence, for example, when producing standard boards for a specific style of furniture, since the production process involves multiple complex processes and device interactions and has high requirements for quality stability, the hit instruction may select multiple patterns such as the associated device interaction node graph construction knowledge pattern, the whole-batch node graph construction knowledge pattern, and the single-process node graph construction knowledge pattern. These hit patterns become the multiple node graph construction knowledge patterns for constructing the status node graph of the production monitoring data of the first standard board.

[0066] In a possible implementation manner, step S120 includes:

[0067] Step S121: For each node graph construction knowledge pattern among the multiple node graph construction knowledge patterns, obtain the identification attribute information corresponding to the traversed node graph construction knowledge pattern.

[0068] Step S122: Inject the identification attribute information corresponding to the traversed node graph construction knowledge pattern into the production monitoring data of the first standard board to generate the production monitoring data of the second standard board corresponding to the traversed node graph construction knowledge pattern.

[0069] In this embodiment, for injecting identification attribute information into the first standard board production monitoring data respectively under multiple node graph construction knowledge modes to generate multiple second standard board production monitoring data, the server will operate on each mode in the multiple node graph construction knowledge modes. Taking the associated device interaction node graph construction knowledge mode as an example, the server will obtain the identification attribute information corresponding to this mode. These identification attribute information are specially set for identifying the monitoring data related to the associated device interaction, including the start identifier of the initial data segment indicating the start of device interaction, the completion identifier of the initial data segment indicating the end of the interaction part of the data, the termination identifier indicating the end of the entire data segment, and the mode identifier information that can clearly reflect that this is the associated device interaction node graph construction knowledge mode. Then, the server injects the obtained identification attribute information into the part related to the associated device interaction in the first standard board production monitoring data, such as the data part during the interaction between the cutting device and the grinding device, so as to generate the second standard board production monitoring data corresponding to the associated device interaction node graph construction knowledge mode. Similarly, for the whole batch node graph construction knowledge mode, the server obtains the corresponding identification attribute information, such as the start identifier of the whole batch production, the segmentation identifier of different stages within each batch, etc., and injects these identification attribute information into the part related to the whole batch production in the first standard board production monitoring data to generate the corresponding second standard board production monitoring data. The single process node graph construction knowledge mode, the multi-source data node graph construction knowledge mode, and the customized node graph construction knowledge mode also follow a similar method, obtaining their respective corresponding identification attribute information and injecting them into the corresponding parts of the first standard board production monitoring data to generate their respective corresponding second standard board production monitoring data. Each of the generated second standard board production monitoring data can clearly reflect the corresponding node graph construction knowledge mode through the identification attribute information therein, facilitating subsequent processing and analysis.

[0070] In a possible implementation manner, the multiple node graph construction knowledge modes include at least one of a single process node graph construction knowledge mode, a whole batch node graph construction knowledge mode, an associated device interaction node graph construction knowledge mode, a multi-source data node graph construction knowledge mode, or a customized node graph construction knowledge mode.

[0071] The node graph construction instance of the single-process node graph construction knowledge mode is used to construct a status node graph for single-process production monitoring data. The node graph construction instance of the whole-batch node graph construction knowledge mode is used to construct a status node graph for whole-batch production monitoring data. The node graph construction instance of the associated device interaction node graph construction knowledge mode is used to construct a status node graph for associated device interaction production monitoring data. The node graph construction instance of the multi-source data node graph construction knowledge mode is used to construct a status node graph for the standard board production monitoring data extracted from multi-source data. The node graph construction instance of the customized node graph construction knowledge mode is used to construct a customized status node graph for the standard board production monitoring data.

[0072] In this embodiment, during the production process of home furnishing standard boards, different node graph construction knowledge modes play important roles respectively. The single-process node graph construction knowledge mode focuses on a single production process. Taking the wood cutting process as an example. In furniture production, the cutting process has a key impact on the dimensional accuracy and quality of the standard board. The server collects various production monitoring data in the cutting process, such as the rotation speed of the cutting tool, the cutting depth, and the feeding speed of the wood. These single-process production monitoring data are the basis for constructing the status node graph. The server starts to construct the status node graph through the node graph construction instance of the single-process node graph construction knowledge mode. First, it sets the starting state of the cutting process as an initial node, such as "cutting process starts", which includes the basic parameters when the cutting equipment starts, such as the initial power of the equipment and the initial position of the tool. As the cutting process progresses, different monitoring data form different status nodes, such as "cutting depth reaches 3 cm" and "feeding speed stabilizes at 1 meter per minute", and these nodes are associated according to the production logic. For example, the change in cutting depth will affect the adjustment of the feeding speed. In this way, a single-process status node graph is constructed, which helps to analyze potential problems in a single cutting process, such as whether the abnormal change in cutting depth is related to tool wear or equipment failure.

[0073] The knowledge model for constructing the whole-batch node diagram mainly targets the whole-batch production monitoring data. Suppose the production quantity of a batch of household standard boards is 500 pieces. The server will obtain various data during the whole process from the input of raw materials to the output of finished products for this whole batch of standard boards, including time nodes at different production stages, overall raw material consumption, quality inspection results of the whole batch of products, etc. When constructing the status node diagram using the node diagram construction instance of the knowledge model for constructing the whole-batch node diagram, the initial node can be "the start of the whole-batch production", which contains basic information about the whole-batch production, such as the batch number of raw materials, the start time of the production plan, etc. As production progresses, different status nodes will be generated, such as "completing the cutting process of 200 standard boards" and "the whole batch of standard boards entering the assembly process". These nodes reflect the progress and status conversion of the whole-batch production. At the same time, by analyzing the relationships between different nodes, potential problems in the whole-batch production process can be discovered. For example, if after a certain time node, the unqualified rate of the quality inspection of the whole batch of products suddenly rises, it can be traced through the status node diagram which production link has problems, whether it is the problem of raw materials or the operation error of a certain process that affects the quality of the whole batch of products.

[0074] The knowledge model for constructing the associated equipment interaction node diagram is used to process the associated equipment interaction production monitoring data. In furniture production, there is a close interaction relationship between the cutting equipment and the grinding equipment. The server will collect relevant data when the cutting equipment transfers standard boards to the grinding equipment, such as the dimensional accuracy of the standard boards after cutting, the time interval of transfer, the synchronization status of the cutting equipment and the grinding equipment, etc. By constructing the status node diagram using the node diagram construction instance of the knowledge model for constructing the associated equipment interaction node diagram, the initial node may be "the start of the cutting-grinding equipment interaction", which contains the status information of the two equipment at the start of the interaction, such as the stop state of the cutting equipment and the ready-to-receive state of the grinding equipment. Then, as the interaction process progresses, status nodes such as "the standard board is successfully transferred from the cutting equipment to the grinding equipment" and "the grinding equipment adjusts the grinding parameters according to the size of the standard board" will be generated. The relationships between these nodes can reflect the coordination situation during the equipment interaction process. For example, if there is a node of "the grinding equipment frequently adjusts the grinding parameters", by analyzing the status node diagram, it can be traced whether the dimensional accuracy of the standard boards output by the cutting equipment is unstable, or whether there is a problem with the detection and adjustment mechanism of the grinding equipment itself, so as to timely solve the abnormal situation in the equipment interaction process and ensure the smooth progress of production.

[0075] The knowledge pattern of constructing a multi-source data node graph targets the production monitoring data of standard boards extracted from multi-source data. In home manufacturing, data sources are diverse, including sensor data on production equipment, environmental monitoring data, manual quality inspection data, etc. For example, sensor data may provide the operating parameters of the equipment, environmental monitoring data can reflect the impact of temperature and humidity in the production workshop on the quality of standard boards, and manual quality inspection data records the inspection results of workers on the appearance and structural quality of standard boards. When the server constructs a status node graph using the node graph construction instance of the knowledge pattern of constructing a multi-source data node graph, it integrates these data from different sources. The initial node can synthesize the initial information from multiple data sources, such as "Production starts, the equipment is operating normally, the temperature in the workshop is 25 degrees Celsius, the humidity is 50%, and the appearance inspection of the first batch of standard boards is qualified". As production progresses, changes in different-source data form different status nodes, such as "The equipment temperature rises by 5 degrees, the workshop humidity drops to 40%, and the structural inspection of a certain standard board is unqualified". By constructing such a status node graph, the mutual influence between multi-source data can be comprehensively analyzed. For example, whether the change in equipment operating parameters is related to the change in environmental conditions, and how these changes jointly affect the quality of standard boards, so as to achieve more comprehensive and accurate production monitoring.

[0076] The knowledge pattern of constructing a customized node graph is used to construct a customized status node graph for the production monitoring data of standard boards. Suppose when producing standard boards for high-end customized furniture, special attention needs to be paid to two indicators: the grain direction of the wood and the surface finish. The server will specifically construct a customized status node graph for the production monitoring data related to these two indicators. The initial node can be "Customized production starts, paying attention to the wood grain and surface finish", which includes the initial set values and requirements related to these two indicators. Then during the production process, the status nodes may be "The grain direction of the wood meets the design requirements, and the surface finish reaches the preliminary standard", "After the sanding process, the surface finish is further improved", etc. By constructing a customized status node graph, precise monitoring under special production requirements can be met, ensuring that standard boards meeting the requirements of high-end customization are produced. For example, it can promptly detect that the grain direction of the wood deviates in a certain process, or the surface finish fails to reach the expected target, so as to adjust the production process in a timely manner.

[0077] In a possible implementation manner, the identification attribute information corresponding to the traversed node graph construction knowledge pattern includes an initial data segment start identifier, an initial data segment end identifier, a termination identifier, and pattern identifier information reflecting the traversed node graph construction knowledge pattern.

[0078] Step S122 may include: when the number of single-process production monitoring data included in the first standard board production monitoring data is not greater than a set number, injecting pattern identification information reflecting the traversed node graph construction knowledge pattern at the front end of the first standard board production monitoring data.

[0079] Before the initial data segment of the first standard board production monitoring data and after the pattern identification information reflecting the traversed node graph construction knowledge pattern, inject the start identifier of the initial data segment.

[0080] Inject the end identifier of the initial data segment at the back end of the first standard board production monitoring data, and inject the termination identifier after the injected end identifier of the initial data segment to generate the second standard board production monitoring data corresponding to the traversed node graph construction knowledge pattern.

[0081] In another possible implementation manner, the identification attribute information corresponding to the traversed node graph construction knowledge pattern includes the start identifier of the initial data segment, the end identifier of the initial data segment, the data segment segmentation identifier, and the pattern identification information reflecting the traversed node graph construction knowledge pattern.

[0082] Step S122 may include: when the number of single-process production monitoring data included in the first standard board production monitoring data is greater than a set number, injecting pattern identification information reflecting the traversed node graph construction knowledge pattern at the front end of the first standard board production monitoring data.

[0083] Before the initial data segment of the first standard board production monitoring data and after the pattern identification information reflecting the traversed node graph construction knowledge pattern, inject the start identifier of the initial data segment.

[0084] Inject the end identifier of the initial data segment at the back end of the initial single-process production monitoring data in the first standard board production monitoring data.

[0085] Determine the remaining single-process production monitoring data in the first standard board production monitoring data except for the initial single-process production monitoring data, and inject the data segment segmentation identifier between every two associated remaining single-process production monitoring data to generate the second standard board production monitoring data corresponding to the traversed node graph construction knowledge pattern.

[0086] In this embodiment, during the production process of furniture standard boards, when it comes to injecting identification attribute information for different node graph construction knowledge patterns to generate corresponding second standard board production monitoring data, different injection methods need to be adopted according to the number of single-process production monitoring data.

[0087] Taking the construction of a knowledge model with a single process node diagram as an example, assume that this single process is the wood cutting process. If the number of production monitoring data regarding the wood cutting process in the first standard board production monitoring data is not greater than the set number, the server will inject identification attribute information according to specific rules. First, inject the pattern identification information reflecting the knowledge model construction of the single process node diagram at the front end of the first standard board production monitoring data (here it is the monitoring data related to the wood cutting process), such as "WOOD_CUTTING_SINGLE_PROCESS". This identification clarifies that this part of the data is related to the node diagram construction knowledge model of the wood cutting single process. Then, inject the start identifier of the initial data segment, such as "START_CUTTING_SEGMENT", after this pattern identification information and before the initial data segment of the wood cutting process monitoring data, which indicates the start of a valid data segment in the wood cutting process. Next, inject the end identifier of the initial data segment, like "END_CUTTING_SEGMENT", at the back end of the wood cutting process monitoring data, indicating the end of this initial data segment, and inject the termination identifier "TERMINATE_CUTTING_DATA" after the injected end identifier of the initial data segment. In this way, the identification attribute information is completely added to this part of the data, generating the second standard board production monitoring data corresponding to the knowledge model construction of the single process node diagram. This method helps to clearly define and identify this part of the data, providing convenience for subsequent processing. For example, when performing data extraction or constructing a state node diagram, it is possible to quickly locate the data segment related to the wood cutting process and clarify its start and end positions.

[0088] When the quantity of production monitoring data regarding the wood cutting process in the first standard board production monitoring data is greater than the set quantity, the operations of the server are different. Taking the construction of a knowledge model with a single process node diagram as an example, the server injects pattern identification information reflecting the construction knowledge model of the single process node diagram, such as "WOOD_CUTTING_SINGLE_PROCESS_LARGE_DATA", at the front end of the wood cutting process monitoring data. This identification corresponds to the single process wood cutting data in the case of a large data volume. Then, before the initial data segment of the wood cutting process monitoring data and after this pattern identification information, the start identification of the initial data segment "START_CUTTING_SEGMENT_LARGE" is injected. At the back end of the initial single process production monitoring data (such as the monitoring data of the first batch of cut wood) in the wood cutting process monitoring data, the end identification of the initial data segment "END_FIRST_CUTTING_SEGMENT" is injected. After that, the server determines the remaining single process production monitoring data in the wood cutting process monitoring data except for the initial single process production monitoring data, and injects a data segment division identification, such as "DIVIDE_CUTTING_SEGMENT", between every two associated remaining single process production monitoring data. In this way, a large amount of wood cutting process monitoring data is reasonably divided and identified, generating the second standard board production monitoring data corresponding to the construction knowledge model of the single process node diagram. The advantage of this is that when analyzing a large amount of subsequent cutting process data, different stages of data can be quickly located based on these identifications, facilitating data mining and analysis, such as analyzing the differences or trends in the wood cutting processes of different batches.

[0089] The same applies to the construction knowledge pattern of the whole batch of node diagrams. Suppose the whole batch is the monitoring data of the entire production process for manufacturing 1000 standard boards. If the number of single-process production monitoring data regarding a certain sub-process (such as the assembly process) in the whole batch production monitoring data is not greater than the set number, the server will inject pattern identification information reflecting the construction knowledge pattern of the whole batch of node diagrams at the front end of the monitoring data related to the assembly process, such as "WHOLE_BATCH_ASSEMBLY_PROCESS". Then, before the initial data segment of the assembly process monitoring data and after this identification, the initial data segment start identification "START_ASSEMBLY_SEGMENT" is injected, the initial data segment end identification "END_ASSEMBLY_SEGMENT" is injected at the back end, and finally the termination identification "TERMINATE_ASSEMBLY_DATA" is injected, thus generating the part related to the assembly process in the second standard board production monitoring data corresponding to the construction knowledge pattern of the whole batch of node diagrams. This helps to clearly identify the data part of the assembly process in the whole batch production monitoring data, facilitating subsequent analysis of the assembly process from the perspective of the whole batch, such as analyzing the impact of the assembly process on the quality of the whole batch of products.

[0090] When the number of single-process production monitoring data regarding a certain sub-process (such as the sanding process) in the whole batch production monitoring data is greater than the set number, the server injects pattern identification information reflecting the construction knowledge pattern of the whole batch of node diagrams at the front end of the monitoring data related to the sanding process, such as "WHOLE_BATCH_SANDING_PROCESS_LARGE_DATA". Before the initial data segment of the sanding process monitoring data and after this identification, the initial data segment start identification "START_SANDING_SEGMENT_LARGE" is injected, and the initial data segment end identification "END_FIRST_SANDING_SEGMENT" is injected at the back end of the initial single-process production monitoring data (such as the data of the first batch of sanded standard boards). Then, the remaining single-process production monitoring data is determined, and the data segment division identification "DIVIDE_SANDING_SEGMENT" is injected between every two associated remaining single-process production monitoring data, generating the part related to the sanding process in the second standard board production monitoring data corresponding to the construction knowledge pattern of the whole batch of node diagrams. This enables better data organization and analysis when dealing with a large amount of sanding process data, such as analyzing the contribution of sanding at different stages to the quality of the whole batch of standard boards or finding abnormal fluctuations during the sanding process.

[0091] In the knowledge model for constructing the interaction node diagram of associated devices, taking the interaction between the cutting device and the grinding device as an example. If the number of interaction monitoring data related to the standard board transmitted from the cutting device to the grinding device is not greater than the set number, the server injects mode identification information reflecting the knowledge model for constructing the interaction node diagram of associated devices, such as "CUTTING_SANDING_INTERACTION", at the front end of this part of the interaction monitoring data. Then, before the initial data segment and after this identifier, the start identifier of the initial data segment "START_INTERACTION_SEGMENT" is injected, and the end identifier of the initial data segment "END_INTERACTION_SEGMENT" is injected at the back end, and then the termination identifier "TERMINATE_INTERACTION_DATA" is injected to generate the corresponding second standard board production monitoring data. This helps to accurately identify the scope and nature of this part of the interaction data when analyzing the device interaction process.

[0092] When the number of interaction monitoring data related to the standard board transmitted from the cutting device to the grinding device is greater than the set number, the server injects mode identification information reflecting the knowledge model for constructing the interaction node diagram of associated devices, such as "CUTTING_SANDING_INTERACTION_LARGE_DATA", at the front end of this part of the interaction monitoring data. Before the initial data segment and after this identifier, the start identifier of the initial data segment "START_INTERACTION_SEGMENT_LARGE" is injected, and the end identifier of the initial data segment "END_FIRST_INTERACTION_SEGMENT" is injected at the back end of the initial interaction monitoring data (such as the interaction data for the first transmission of the standard board). The remaining interaction monitoring data is determined, and the data segment division identifier "DIVIDE_INTERACTION_SEGMENT" is injected between every two associated remaining interaction monitoring data to generate the corresponding second standard board production monitoring data. This can better manage and analyze a large amount of device interaction data, such as finding patterns or anomalies in the device interaction process.

[0093] For the knowledge pattern construction of the multi-source data node graph and the customized node graph, the injection of identification attribute information is also carried out according to similar principles. For the knowledge pattern construction of the multi-source data node graph, for example, when integrating device sensor data, environmental monitoring data, and manual quality inspection data, if the number of single-process production monitoring data corresponding to a certain type of data (such as temperature sensor data in device sensor data) is not greater than the set number, the server will inject the identification attribute information in the manner not greater than the set number mentioned above. If the data volume is greater than the set number, the identification attribute information will be injected in the corresponding manner greater than the set number, so as to generate the corresponding second standard board production monitoring data, which is convenient for the effective organization and analysis of multi-source data. For the knowledge pattern construction of the customized node graph, such as customizing the data on the usage amount and processing time of a certain special chemical agent in the surface treatment process of the standard board, if the number of this part of the data is not greater than the set number, the identification attribute information will be injected according to the corresponding rules; if it is greater than the set number, it will also be injected according to the corresponding rules to generate the second standard board production monitoring data corresponding to the customization requirements, which helps to accurately carry out customized production monitoring and analysis.

[0094] In a possible implementation manner, step S130 includes:

[0095] Step S131, for each second standard board production monitoring data among the multiple second standard board production monitoring data, when the node graph construction knowledge pattern reflected by the pattern identification information included in the traversed second standard board production monitoring data belongs to the interactive task pattern, determine the feature extraction path associated with the traversed second standard board production monitoring data as the interactive feature extraction path for extracting features from the associated device interactive production monitoring data;

[0096] Step S132, when the node graph construction knowledge pattern reflected by the pattern identification information included in the traversed second standard board production monitoring data belongs to the non-interactive task pattern, determine the feature extraction path associated with the traversed second standard board production monitoring data as the non-interactive feature extraction path for extracting features from the non-associated device interactive production monitoring data.

[0097] In this embodiment, during the production process of the home furnishing standard board, a plurality of second standard board production monitoring data have been generated as mentioned above, and now it is necessary to determine the associated feature extraction path. For each second standard board production monitoring data, the server will check the type of the node graph construction knowledge pattern reflected by the pattern identification information contained therein.

[0098] Taking the construction of the second standard board production monitoring data corresponding to the knowledge pattern of the associated device interaction nodes of the cutting equipment and the grinding equipment as an example, since this pattern belongs to the interaction task pattern, the server determines that the feature extraction path associated with this second standard board production monitoring data is the interaction feature extraction path used to extract features from the associated device interaction production monitoring data. In furniture production, this means paying attention to various interaction-related features during the interaction process between the cutting equipment and the grinding equipment. For example, the transfer speed and accuracy when the cutting equipment transfers the standard board to the grinding equipment, which involves whether the discharge speed of the cutting equipment matches the feeding speed of the grinding equipment, and whether the position of the standard board is accurate during the transfer process. It also includes the signal transmission situation during the interaction between the devices, such as whether the signal notifying the grinding equipment that the standard board is about to arrive sent by the cutting equipment is timely and accurate, and the response time of the grinding equipment after receiving the signal. In addition, the interaction feature extraction path will also pay attention to the impact of the cutting quality of the cutting equipment on the subsequent grinding work of the grinding equipment before transferring the standard board, such as the flatness of the cutting surface affecting the difficulty and effect of grinding, etc.

[0099] Looking at the second standard board production monitoring data corresponding to the knowledge pattern of the entire batch node diagram construction, this pattern belongs to the non-interaction task pattern. The server determines that the feature extraction path associated with this second standard board production monitoring data is the non-interaction feature extraction path used to extract features from the non-associated device interaction production monitoring data. For the entire batch production monitoring data, the server will focus on some overall features, such as the total consumption of raw materials during the production process of the entire batch of standard boards, which includes the total amount of wood used, the amount of auxiliary materials such as glue, etc. The total production duration is also an important feature, the time spent from the start of production of the first batch of standard boards to the completion of production of the last batch, which can reflect the production efficiency. In addition, the overall quality distribution of the entire batch of products is also the content to be extracted by the non-interaction feature extraction path. For example, the proportion of standard boards of different quality grades (such as high-quality, qualified, defective) in the entire batch of products, and the change trend of these proportions during the production process. For some macro environmental factors during the production process, such as the comprehensive impact of the average temperature and humidity in the entire production workshop during the entire batch production on the product quality, etc., are also extracted through the non-interaction feature extraction path.

[0100] If the knowledge pattern for constructing a single - process node diagram is for a relatively independent process such as the wood cutting process, it also belongs to the non - interactive task pattern. The server also determines that the feature extraction path associated with the second standard board production monitoring data corresponding to this pattern is a non - interactive feature extraction path. In this case, the server will focus on some features within the wood cutting process, such as the wear rate of the cutting tool, which can be determined by analyzing the change in the edge thickness of the cutting tool or the decrease in cutting accuracy over different time periods. The energy consumption of the cutting equipment is also an important feature. For example, when cutting woods of different hardnesses, the difference in the electricity consumption of the equipment, etc. In addition, the quality control indicators in the cutting process, such as the size accuracy distribution of the standard board after cutting, how many standard boards are within the allowable error range, and how many exceed the error range, etc., are all features extracted through the non - interactive feature extraction path.

[0101] For the second standard board production monitoring data corresponding to the knowledge pattern of constructing a multi - source data node diagram, if it contains a data part related to device interaction and the pattern identification information corresponding to this part of the data indicates an interactive task pattern, then an interactive feature extraction path is adopted for this part of the data. For example, in the multi - source data, there is data on the interaction between the cutting equipment and the quality inspection equipment. The interactive feature extraction path will focus on interactive features such as the speed at which the cutting equipment delivers the standard board to the inspection equipment, the recognition speed and accuracy of the inspection equipment for the standard board, etc. For other parts of the multi - source data, such as simple environmental monitoring data or the quality data of raw material batches at different time periods, if the corresponding pattern identification information indicates a non - interactive task pattern, a non - interactive feature extraction path is adopted. For example, extracting the long - term impact of temperature and humidity changes in the production workshop on the quality of standard boards from environmental monitoring data, and analyzing the impact of woods provided by different suppliers on product quality from the quality data of raw material batches.

[0102] The second standard board production monitoring data corresponding to the customized node graph construction knowledge pattern also determines the feature extraction path according to the task pattern reflected by its pattern identification information. If the customization focuses on the interaction between specific processes, for example, in the furniture surface treatment process, the interaction between the painting equipment and the drying equipment, and the pattern identification information indicates an interaction task pattern, then the interaction feature extraction path is adopted, focusing on the influence of the painting thickness and uniformity on the drying time and effect, as well as the feedback of the temperature and wind speed settings of the drying equipment on the painting effect and other interaction features. If the customization focuses on special indicators within a single process, such as the customization focuses on the two indicators of drying time and final wood moisture in the wood drying process, and the pattern identification information indicates a non-interaction task pattern, then the non-interaction feature extraction path is adopted, focusing on the variation law of the drying time under different power settings of the drying equipment, and the relationship between the final wood moisture and the drying time and other features. By accurately determining the feature extraction path according to different node graph construction knowledge patterns in this way, the server can effectively extract valuable features from the second standard board production monitoring data, providing accurate data support for subsequent operations such as production parameter trajectory vector extraction and state node graph construction.

[0103] In a possible implementation manner, step S140 includes: for each of the multiple second standard board production monitoring data, when the feature extraction path associated with the traversed second standard board production monitoring data is an interaction feature extraction path, for each single-process production monitoring data in the traversed second standard board production monitoring data, respectively determine the interaction link data of each of the single-process production monitoring data in the traversed second standard board production monitoring data, and respectively perform feature representation on the determined interaction link data to generate an interaction link feature vector corresponding to each single-process production monitoring data in the traversed second standard board production monitoring data.

[0104] Based on the interaction device labels corresponding to each single-process production monitoring data in the traversed second standard board production monitoring data, determine the interaction devices associated with each single-process production monitoring data in the traversed second standard board production monitoring data, and respectively perform feature representation on the interaction devices associated with each single-process production monitoring data to generate an interaction device feature vector corresponding to each single-process production monitoring data in the traversed second standard board production monitoring data.

[0105] Respectively perform state parameter feature representation on each single-process production monitoring data in the traversed second standard board production monitoring data to generate a set of state parameter feature vectors corresponding to each single-process production monitoring data in the traversed second standard board production monitoring data.

[0106] Perform context feature representation on each single-process production monitoring data in the traversed second standard board production monitoring data, and generate a set of context feature vectors corresponding to each single-process production monitoring data in the traversed second standard board production monitoring data.

[0107] Based on the set of interaction session feature vectors, interaction device feature vectors, state parameter feature vectors, and context feature vectors corresponding to each single-process production monitoring data in the traversed second standard board production monitoring data, generate a set of production parameter trajectory vectors corresponding to the traversed second standard board production monitoring data.

[0108] Alternatively, for each second standard board production monitoring data among the multiple second standard board production monitoring data, when the feature extraction path associated with the traversed second standard board production monitoring data is a non-interaction feature extraction path, perform state parameter feature representation on each data node in the traversed second standard board production monitoring data, and generate state parameter feature vectors corresponding to each data node in the traversed second standard board production monitoring data.

[0109] Perform context feature representation on each data node in the traversed second standard board production monitoring data, and generate context feature vectors corresponding to each data node in the traversed second standard board production monitoring data.

[0110] Fuse the state parameter feature vectors and the context feature vectors corresponding to the same data node to generate a set of fused feature vectors corresponding to each data node in the traversed second standard board production monitoring data.

[0111] Based on the set of fused feature vectors corresponding to each data node in the traversed second standard board production monitoring data, generate a set of production parameter trajectory vectors corresponding to the traversed second standard board production monitoring data.

[0112] In this embodiment, taking the second standard board production monitoring data corresponding to the knowledge pattern constructed by the associated device interaction node graph as an example, since it is associated with an interaction feature extraction path. In furniture production, assume there is second standard board production monitoring data related to the interaction process between a cutting device and a grinding device.

[0113] For each piece of single-process production monitoring data, such as the cutting operation process of a cutting device and the grinding operation process of a grinding device. First, determine the interaction link data of each piece of single-process production monitoring data during the entire interaction process. For the cutting operation process of the cutting device, the interaction link data may include the transfer speed when the cutting device transfers the cut standard board to the grinding device, the posture of the standard board during transfer (whether it is horizontal, inclined, etc.), and the stop state of the cutting device at the moment of transfer. For the grinding operation process of the grinding device, the interaction link data may include the initial detection data when receiving the standard board, such as the surface roughness of the detected standard board, the deviation between the actual size and the expected size of the standard board, etc., and the start parameters when starting grinding, such as the initial rotation speed of the grinding wheel, the initial setting value of the grinding pressure, etc. Then, perform feature representation on these determined interaction link data respectively to generate interaction link feature vectors corresponding to each piece of single-process production monitoring data. For example, represent the transfer speed of the cutting device in vector form, where the magnitude of the speed is the modulus of the vector and the transfer direction is the direction of the vector; for the initial detection data when the grinding device receives the standard board, encode information such as surface roughness and size deviation into vector form according to certain rules, so as to obtain the interaction link feature vector corresponding to each piece of single-process production monitoring data.

[0114] Based on the interaction device labels corresponding to each piece of single-process production monitoring data in the traversed second standard board production monitoring data, determine the interaction devices associated with each piece of single-process production monitoring data. For the cutting operation process, the associated interaction devices are the cutting device itself and the subsequent grinding device; for the grinding operation process, the associated devices are the grinding device and the previous cutting device. Perform feature representation on the interaction devices associated with each piece of single-process production monitoring data respectively to generate interaction device feature vectors corresponding to each piece of single-process production monitoring data. For the cutting device, the feature representation may include information such as the model of the cutting device, the specifications of the cutting tool (such as tool diameter, edge angle, etc.), the service life of the device, and the power range of the device, and convert this information into vector form. For the grinding device, it may include the model of the grinding wheel, the grit size of the grinding wheel, the maximum grinding pressure of the device, and the rotation speed range of the device, and also convert it into vector form, so as to obtain the interaction device feature vector corresponding to each piece of single-process production monitoring data.

[0115] For each single-process production monitoring data in the traversed second standard board production monitoring data, perform state parameter feature representation respectively to generate a set of state parameter feature vectors corresponding to each single-process production monitoring data. For the cutting operation process of the cutting equipment, the state parameters may include the dynamic changes of cutting depth, cutting angle, and cutting speed during the cutting process, and the real-time power of the equipment during cutting. These state parameters are converted into vector form according to a certain mathematical method. For example, the cutting depth and cutting angle can be combined into a two-dimensional vector, and the dynamic changes of cutting speed and real-time power can also be combined into a multi-dimensional vector to form a set of state parameter feature vectors corresponding to the cutting operation process. For the grinding operation process of the grinding equipment, the state parameters include the change of grinding wheel speed during grinding, the adjustment of grinding pressure, and the change of surface roughness of the standard board during grinding. Similarly, they are converted into vector form to construct a set of state parameter feature vectors corresponding to the grinding operation process.

[0116] For each single-process production monitoring data in the traversed second standard board production monitoring data, perform context feature representation respectively to generate a set of context feature vectors corresponding to each single-process production monitoring data. For the cutting operation process, the context features may include the ambient temperature and humidity in the workshop during cutting, because temperature and humidity may affect the physical properties of wood and thus affect the cutting effect; the noise level in the workshop may also affect the operation accuracy of the operator. After these environmental factors are quantified, they are converted into vector form to form a set of context feature vectors corresponding to the cutting operation process. For the grinding operation process of the grinding equipment, the context features may include the air dust content around during grinding, because dust may affect the grinding quality and the life of the equipment; the operating status of adjacent equipment (such as whether the nearby polishing equipment is operating and its operating parameters) may also affect the grinding operation. These factors are quantified into vector form to obtain a set of context feature vectors corresponding to the grinding operation process.

[0117] Finally, based on the interaction session feature vectors, interaction device feature vectors, set of state parameter feature vectors, and set of context feature vectors corresponding to each single-process production monitoring data in the traversed second standard board production monitoring data, generate a set of production parameter trajectory vectors corresponding to the traversed second standard board production monitoring data. For example, combine the above various types of vectors corresponding to the cutting operation process and the grinding operation process according to certain rules to form a comprehensive vector set, and this set can comprehensively describe the production parameter trajectory during the interaction process between the cutting equipment and the grinding equipment.

[0118] Next, look at the production monitoring data of the second standard board corresponding to the knowledge pattern of constructing the whole batch of node diagrams. Since it is associated with a non-interactive feature extraction path. In furniture production, the production process of a whole batch of standard boards involves multiple data nodes, such as raw material procurement, production operations of each process, quality inspection, etc.

[0119] For each data node in the traversed production monitoring data of the second standard board, perform state parameter feature representation respectively to generate state parameter feature vectors corresponding to each data node. For the data node of raw material procurement, the state parameters may include the type of wood, the moisture content of wood, the procurement quantity of wood, the credit rating of the supplier, etc., and convert this information into vector form. For the production operation data node of a certain process, such as the assembly process, the state parameters may include the number of assembly workers, the assembly speed, the defective rate during the assembly process, etc., and also convert them into vector form to obtain the state parameter feature vectors corresponding to each data node.

[0120] For each data node in the traversed production monitoring data of the second standard board, perform context feature representation respectively to generate context feature vectors corresponding to each data node. For the raw material procurement data node, the context features may include the market wood price fluctuation situation during procurement, the transportation distance, the transportation method (because these factors may affect the cost and the quality of raw materials), etc., and quantify these factors into vector form. For the assembly process data node, the context features may include the spatial layout of the assembly workshop (whether a reasonable layout may affect the assembly efficiency), the personnel flow situation in the workshop at that time (a large personnel flow may affect the stability of assembly), etc., and convert these factors into vector form to obtain the context feature vectors corresponding to each data node.

[0121] Fuse the state parameter feature vectors and context feature vectors corresponding to the same data node to generate fusion feature vectors corresponding to each data node in the traversed production monitoring data of the second standard board. For example, for the raw material procurement data node, fuse the state parameter feature vector representing the type of wood, moisture content, procurement quantity, and supplier credit rating with the context feature vector representing the market price fluctuation, transportation distance, and transportation method according to a certain weighted summation or other fusion rules to obtain the fusion feature vector corresponding to this data node. Perform the same operation for other data nodes.

[0122] Based on the fusion feature vectors corresponding to each data node in the traversed production monitoring data of the second standard board, generate a set of production parameter trajectory vectors corresponding to this traversed production monitoring data of the second standard board. This set can comprehensively consider the characteristics of each data node from the perspective of the whole batch and comprehensively describe the production parameter trajectory in the production process of the whole batch of standard boards.

[0123] For the production monitoring data of the second standard board corresponding to the knowledge model for constructing a single-process node diagram (such as the wood drying process), if the associated feature extraction path is non-interactive. For each data node in the wood drying process, such as the start of the drying equipment, the temperature and humidity control during drying, and the drying time.

[0124] Perform state parameter feature representation for each data node. For example, the state parameters of the drying equipment start data node may include the equipment power at startup and the initial temperature of the equipment, and convert them into vector form. The state parameters of the temperature and humidity control data node during drying are the actual temperature and humidity values and their fluctuations, which are also converted into vector form. Perform context feature representation for each data node, such as the ventilation situation in the workshop and the heat dissipation situation of surrounding equipment when the drying equipment starts, and convert them into vector form. Then fuse the state parameter feature vectors and context feature vectors of the same data node to obtain the fused feature vector corresponding to each data node. Finally, generate a set of production parameter trajectory vectors for the production monitoring data of the second standard board corresponding to the wood drying process based on these fused feature vectors.

[0125] For the production monitoring data of the second standard board corresponding to the multi-source data node diagram construction knowledge model and the customized node diagram construction knowledge model, the production parameter trajectory vectors are also extracted in a similar manner according to the associated feature extraction path (interactive feature extraction path or non-interactive feature extraction path) to generate their respective sets of production parameter trajectory vectors. Through such a comprehensive and detailed production parameter trajectory vector extraction process, the server can mine rich information from different production monitoring data of the second standard board, providing strong data support for subsequent node diagram construction and abnormal state link estimation operations.

[0126] In a possible implementation manner, the method is executed by a state node diagram construction model, and the training steps of the state node diagram construction model include:

[0127] Step A110, obtain the production monitoring data of the first template standard board and various prior state node diagrams corresponding to the production monitoring data of the first template standard board;

[0128] Step A120, for a preset plurality of node diagram construction knowledge models, inject identification attribute information into the production monitoring data of the first template standard board respectively to generate a plurality of second template standard board production monitoring data corresponding to the plurality of node diagram construction knowledge models. The identification attribute information in each second template standard board production monitoring data includes pattern identification information reflecting the corresponding node diagram construction knowledge model;

[0129] Step A130: Determine multiple feature extraction paths associated with the multiple second template standard board production monitoring data based on the pattern identification information included in each of the multiple second template standard board production monitoring data.

[0130] Step A140: For each of the multiple second template standard board production monitoring data, perform production parameter trajectory vector extraction respectively according to the associated feature extraction path, and generate a set of template production parameter trajectory vectors corresponding to each of the multiple node graph construction knowledge patterns.

[0131] Step A150: Perform node graph construction on the sets of template production parameter trajectory vectors corresponding to each of the multiple node graph construction knowledge patterns respectively, and generate prediction state node graphs corresponding to each of the multiple node graph construction knowledge patterns.

[0132] Step A160: Train the state node graph construction model based on the prediction state node graphs corresponding to each of the multiple node graph construction knowledge patterns and the multiple prior state node graphs, and generate a trained state node graph construction model.

[0133] In this embodiment, the server first obtains the first template standard board production monitoring data and multiple prior state node graphs corresponding to these data. The first template standard board production monitoring data contains various information in the home standard board production process. For example, in furniture production, it covers the monitoring data of each process from the selection of wood raw materials, cutting, sanding, assembly to the final surface treatment. The prior state node graph is constructed based on past experience or expert knowledge, reflecting the ideal state node relationships of each link in the standard board production process under normal production conditions. For example, in the normal cutting process, the ideal relationship between cutting depth, cutting speed and wood type will be clearly shown in the prior state node graph.

[0134] To construct a knowledge pattern for a preset multiple node graphs, the server begins to inject identification attribute information into the production monitoring data of the first template standard board to generate multiple second template standard board production monitoring data. For example, the preset node graph construction knowledge patterns include single-process node graph construction knowledge pattern, whole-batch node graph construction knowledge pattern, associated device interaction node graph construction knowledge pattern, etc. Taking the single-process node graph construction knowledge pattern as an example, if it is the wood cutting process, the server will inject the corresponding identification attribute information. The identification attribute information in each second template standard board production monitoring data contains pattern identification information reflecting the corresponding node graph construction knowledge pattern, such as the single-process pattern identification information "WOOD_CUTTING_SINGLE_PROCESS" for the wood cutting process, and at the same time, there are also identification information such as the start identifier of the initial data segment and the end identifier. For the whole-batch node graph construction knowledge pattern, if a batch is to produce 1000 standard boards, the server will inject identifiers for the data of each link in the whole-batch production process. The pattern identification information may be "WHOLE_BATCH_PRODUCTION", and add the corresponding start, end, etc. identifiers to generate the corresponding second template standard board production monitoring data. Under the associated device interaction node graph construction knowledge pattern, for example, the interaction between the cutting device and the grinding device, the pattern identification information such as "CUTTING_SANDING_INTERACTION" and other relevant identifiers will be injected to clarify the scope and nature of the interaction-related data.

[0135] Based on the pattern identification information included in each of the multiple second template standard board production monitoring data, the server determines multiple feature extraction paths associated with the multiple second template standard board production monitoring data. For example, for the second template standard board production monitoring data corresponding to the associated device interaction node graph construction knowledge pattern, since its pattern identification information indicates that it is related to device interaction, the determined feature extraction path associated with it is the interaction feature extraction path used to extract features from the associated device interaction production monitoring data. During the interaction between the cutting device and the grinding device, the interaction feature extraction path will focus on features related to the data of interaction links such as the speed at which the cutting device transfers the standard board to the grinding device and the attitude of the standard board. For the second template standard board production monitoring data corresponding to the whole-batch node graph construction knowledge pattern, the pattern identification information indicates a non-interaction task pattern, and the determined feature extraction path is the non-interaction feature extraction path used to extract features from the non-associated device interaction production monitoring data, which will focus on features such as the total consumption of raw materials and the total production duration during the whole-batch production process.

[0136] For each piece of production monitoring data of multiple second template standard plates, the server extracts production parameter trajectory vectors respectively according to the associated feature extraction paths, and generates sets of template production parameter trajectory vectors corresponding to multiple node graph construction knowledge patterns. Taking the production monitoring data of the second template standard plate corresponding to the associated device interaction node graph construction knowledge pattern as an example, for each piece of single-process production monitoring data therein, such as the cutting operation of the cutting device and the grinding operation of the grinding device. Determine the link data of the cutting operation in the interaction, such as the speed and stop state when transferring the standard plate, and perform feature representation to generate interaction link feature vectors; determine the associated cutting device and grinding device based on the interaction device tags, and perform feature representation on the devices to generate interaction device feature vectors; perform state parameter feature representation on the cutting operation, such as cutting depth, angle, speed change, etc. to generate a set of state parameter feature vectors, and perform context feature representation, such as workshop temperature, humidity, etc. to generate a set of context feature vectors. Finally, generate a set of template production parameter trajectory vectors corresponding to this piece of production monitoring data of the second template standard plate based on these vectors. For the production monitoring data of the second template standard plate corresponding to the whole batch of node graph construction knowledge patterns, perform state parameter feature representation and context feature representation respectively on each data node, such as raw material procurement, each process operation, etc., and generate a fused feature vector corresponding to each data node after fusion, and then generate a corresponding set of template production parameter trajectory vectors.

[0137] The server constructs node graphs respectively for the sets of template production parameter trajectory vectors corresponding to multiple node graph construction knowledge patterns, and generates prediction state node graphs corresponding to multiple node graph construction knowledge patterns respectively. Taking the set of template production parameter trajectory vectors corresponding to the single-process node graph construction knowledge pattern as an example, based on the vectors in the set and the corresponding initial state node identifier, such as the "start cutting" identifier for the cutting process, generate an initial state node. Then perform multi-stage graph construction processing, classify and label the vectors, and establish a preliminary association relationship between the initial state node and the first vector, such as associating the start of cutting with the cutting device start parameter vector. If the initial state node represents the production start state, search for vectors related to the start to further establish an advanced association relationship, such as the power vector at the start of cutting, etc. Based on the preliminary association relationship, analyze the logically associated other vectors of the associated vectors, expand the initial state node to create an intermediate state node structure, such as the tool wear state node during the cutting process. After redundant optimization of the intermediate state node structure, determine the time information of the vectors, sort and expand the association relationship of the intermediate state nodes according to the time to obtain a derived state node structure, and finally generate a prediction state node graph by synthesizing the initial state node and the derived state node. Similar operations are also performed on the sets of template production parameter trajectory vectors corresponding to other node graph construction knowledge patterns.

[0138] Finally, based on multiple node graphs, construct the predicted state node graph and multiple prior state node graphs corresponding to the knowledge patterns, and train the state node graph construction model to generate a trained state node graph construction model. For example, compare the predicted state node graph with the prior state node graph. If in the cutting process, there is a large deviation between the cutting depth shown in the predicted state node graph and the ideal cutting depth in the prior state node graph, the model will adjust its own parameters according to this difference, so that in subsequent construction, it can more accurately predict the state node graph. By comparing and adjusting the predicted results and prior results corresponding to the knowledge patterns of each node graph, continuously optimize the model, and finally obtain a trained state node graph construction model, which can more accurately construct the state node graph for the production monitoring data of household standard boards.

[0139] For example, in one possible implementation, step S150 includes:

[0140] Step S151, for each set of production parameter trajectory vectors, generate an initial state node based on the traversed set of production parameter trajectory vectors and the initial state node identifier corresponding to the traversed set of production parameter trajectory vectors. In this embodiment, first, taking the wood cutting process in furniture production as an example, assume that the corresponding set of production parameter trajectory vectors includes relevant vectors such as the startup parameters of the cutting equipment, the initial state of the tool, and the wood feeding speed. If the initial state node identifier is "cutting process start", then the server generates an initial state node based on this identifier and the relevant set of production parameter trajectory vectors. This initial state node includes information such as the initial power of the cutting equipment, the initial position of the tool, and the initial wood feeding speed, representing the state at the start of the wood cutting process;

[0141] Step S152, perform graph construction processing in multiple stages based on the initial state node and the traversed set of production parameter trajectory vectors to generate multiple derived state nodes;

[0142] Step S153, synthesize the initial state node and the multiple derived state nodes to generate a state node graph construction result corresponding to the traversed set of production parameter trajectory vectors. For example, in the example of the wood cutting process, combine the initial state node "cutting process start" and each node in the derived state node structure to form a complete state node graph construction result. This state node graph clearly shows the state transition of the wood cutting process from start to each stage and the logical relationship between different states, including the mutual influence relationship of each parameter at different time points, such as the changes and correlations of parameters such as power, feeding speed, tool rotation speed, and cutting depth during the cutting process over time.

[0143] For other production processes or for constructing a set of production parameter trajectory vectors corresponding to the knowledge model of the node diagram, such as in the case of furniture assembly processes, overall batch production monitoring, or associated equipment interaction, etc., similar steps are also taken for processing. Taking the furniture assembly process as an example, the initial state node may be "assembly process starts", and the set of production parameter trajectory vectors includes vectors such as the number of workers, the initial state of the assembly tools, and the initial placement of parts. According to the above-mentioned steps for diagram construction, first classify and label the vectors and establish a preliminary association relationship. For example, establish an association between the vector of the number of workers and the initial state node based on the logic that workers are in place when starting assembly; then analyze the attributes of the initial state node and find vectors related to startup to establish an advanced association relationship; then expand the initial state node based on the preliminary association relationship to create intermediate state nodes. For example, create an intermediate state node like "assembly process starts, the number of workers affects assembly efficiency, and the tool state affects assembly accuracy" according to the number of workers and the usage of assembly tools; after redundant optimization, determine the time information of each vector, expand the intermediate state nodes according to time sorting to obtain the derived state node structure, and finally synthesize the initial state node and the derived state node to obtain the construction result of the state node diagram for the assembly process. In the case of overall batch production monitoring, starting from the macroscopic perspective of the overall batch production, the initial state node may be "overall batch production starts", and the set of production parameter trajectory vectors includes vectors such as raw material batch information and the overall arrangement of each process. Similarly, construct the construction result of the state node diagram that reflects the state transition and logical relationship of the overall batch production process according to these steps. In terms of associated equipment interaction, taking the interaction between a cutting device and a grinding device as an example, the initial state node is "cutting - grinding device interaction starts", and the set of production parameter trajectory vectors includes vectors such as signal transmission between devices and the transfer state of standard plates. Through the above steps, construct the construction result of the state node diagram that can accurately reflect the state changes and logical relationships during the equipment interaction process. In this way, for different production situations and knowledge models of node diagram construction, the construction results of the state node diagram can be accurately constructed, providing an effective data basis for subsequent operations such as abnormal state link estimation.

[0144] For example, in a possible implementation manner, step S152 includes:

[0145] Step S1521, classify and label each production parameter trajectory vector in the production parameter trajectory vector set, and establish a preliminary association relationship between the initial state node and the first production parameter trajectory vector in the production parameter trajectory vector set. The preliminary association relationship is based on the starting logic of the production process. For example, in the wood cutting process, each vector is classified and labeled. For example, the starting power vector of the cutting equipment is labeled as "equipment starting parameter - power", and the initial position vector of the tool is labeled as "tool state - initial position", etc. Assume that the first vector in the production parameter trajectory vector set is the starting power vector of the cutting equipment. Since the cutting process starts with the equipment starting and power setting first, based on the starting logic of the production process, a preliminary association relationship is established between the initial state node "cutting process start" and this starting power vector;

[0146] Step S1522, analyze the attributes of the initial state node. If the initial state node represents the starting state of production, search for the production parameter vectors related to the starting state in the production parameter trajectory vector set, and establish an advanced association relationship between the production parameter vectors and the initial state node, thereby preliminarily constructing a mapping relationship based on the production logic between the initial state node and some production parameter trajectory vectors. For the wood cutting process, in addition to the starting power vector, the production parameter vectors related to the starting state may also include the starting current vector of the cutting equipment, the initial rotation speed vector of the tool, etc. Establish an advanced association relationship between these vectors and the initial state node "cutting process start", so that a mapping relationship based on the production logic is preliminarily constructed. For example, it can be clarified the relationship between the power, current of the equipment, and the rotation speed of the tool when the cutting process starts;

[0147] Step S1523: Based on the preliminary association relationship, analyze each associated production parameter trajectory vector to find other production parameter trajectory vectors in the set of production parameter trajectory vectors that have a logical association with the associated production parameter trajectory vector. And based on the search result, gradually expand the initial state node to continuously create a representation of an intermediate state node on the basis of the initial state node, generating an intermediate state node structure. The intermediate state node contains relevant information in the extended association relationship. For example, for the associated cutting equipment startup power vector, it is found through analysis that as the power is set, it will affect the feeding speed of the wood. Then the wood feeding speed vector has a logical association with the startup power vector. Based on this relationship, create an intermediate state node on the basis of the initial state node "cutting process startup". This intermediate state node may be represented as "cutting process startup, power setting affects feeding speed", which contains the association information between the startup power and the feeding speed. For other associated vectors, such as the initial rotation speed vector of the tool, it is found that it has a logical association with the cutting depth vector (the rotation speed affects the cutting depth), then create another intermediate state node "cutting process startup, tool rotation speed affects cutting depth". These intermediate state nodes together constitute the intermediate state node structure;

[0148] Step S1524: Perform redundancy optimization on the intermediate state node structure to obtain an optimized intermediate state node structure. For example, among the previously created intermediate state nodes, there may be two nodes respectively representing "cutting process startup, power setting affects feeding speed" and "cutting process startup, feeding speed is affected by both power and tool rotation speed". There is a repetitive part regarding the relationship between power and feeding speed here. Through redundancy optimization, remove the repetitive association relationships to obtain an optimized intermediate state node structure. For example, retain a structure like "cutting process startup, power setting affects feeding speed, tool rotation speed affects cutting depth", making the intermediate state node structure more concise, clear, and accurately reflecting the production logic relationship;

[0149] Step S1525: Determine the time information corresponding to each production parameter trajectory vector in the set of production parameter trajectory vectors. According to the time information, perform time sorting on the association relationships in the intermediate state nodes in the optimized intermediate state node structure, and expand the intermediate state nodes according to the advancement of the time sorting sequence to obtain a derived state node structure carrying time sorting sequence information.

[0150] In the wood cutting process, each vector has corresponding time information. For example, the time corresponding to the starting power vector of the cutting equipment is the moment t0 when the process starts. As time goes by, at the moment t1, the tool starts to cut into the wood, and at this time, the cutting angle vector of the tool comes into play. According to this time information, the correlation relationships in the optimized intermediate state node structure are sorted by time. First, the power setting affects the feeding speed (in the time period from t0 to t1), and then at the moment t1, the tool cuts into the wood, and the tool rotation speed affects the cutting depth. According to the advancement of this time sorting sequence, the intermediate state nodes are expanded to obtain a derived state node structure carrying time sorting sequence information such as "t0 - t1: The cutting process starts, and the power setting affects the feeding speed; t1: The tool cuts into the wood, and the tool rotation speed affects the cutting depth".

[0151] For example, in a possible implementation manner, step S150 further includes:

[0152] Step S154, standardize the state node diagrams corresponding to the construction results of each state node diagram to unify the representation methods of the state nodes and the description formats of the relationships between the state nodes in the state node diagrams. In this embodiment, in the production of household standard boards, for example, for the state node diagram of the wood cutting process, different engineers or systems may use different representation methods when constructing the node diagram. Some may describe the state nodes in detail with words, such as "The cutting equipment is in a high-speed cutting state, and the cutting depth is 3 cm", and some may use codes or specific symbols. Through standardization, these different representation methods are unified. For example, it is uniformly stipulated that the state nodes are represented by concise codes and numbers. For example, "CUT_01" represents a state of the cutting equipment, followed by specific parameter values. For the relationships between the state nodes, the format is also unified. For example, if it is a causal relationship, it is uniformly represented by an arrow plus a specific symbol, such as "→(C)" representing a causal relationship, where "C" represents the specific content of the causal connection. For example, "Power increase →(C) Cutting speed increase", where "Power increase" is the pre-node, "Cutting speed increase" is the post-node, and "Power increase causes the cutting speed to increase" is the specific description of the relationship. In this way, whether it is the state node diagram of the wood cutting process in the single-process node diagram construction knowledge mode, or the state node diagram of the production of the entire batch of standard boards in the whole-batch node diagram construction knowledge mode, or the interaction state node diagram of the cutting equipment and the grinding equipment in the associated equipment interaction node diagram construction knowledge mode, etc., they can all be presented in a unified format, facilitating subsequent analysis operations;

[0153] Step S155: Analyze each state node in the standardized state node diagram and the relationships between various state nodes. Specifically, search for the state nodes corresponding to each link in the production process. For each state node, determine its pre-node and post-node in the production process, establish a complete node relationship mapping based on the production process sequence, and generate a state node diagram structure carrying the production process mapping relationship. Then, taking the assembly process in furniture production as an example, in the standardized state node diagram, there are state nodes such as "parts sorting completed", "component assembly started", "assembly tools ready", etc. For the state node "component assembly started", through analysis, it is found that its pre-node is "parts sorting completed" because assembly can only start after parts sorting is completed; the post-node is "preliminary assembly completed" because after component assembly starts, a series of operations will lead to the state of preliminary assembly completion. Analyze each state node in this way to determine its pre-node and post-node relationships and establish a complete node relationship mapping based on the production process sequence. For example, in the state node diagram of the production of a batch of standard boards, for the state node "a batch of standard boards enter the grinding process", the pre-node is "a batch of standard boards complete the cutting process", and the post-node is "a batch of standard boards start the surface treatment process". Through such comprehensive analysis, a state node diagram structure carrying the production process mapping relationship is generated, which clearly shows the sequence of each link and the state transition relationship in the entire production process;

[0154] Step S156, based on the established node relationship mapping, extract the normal state link in the state node graph under normal production conditions, analyze the characteristic patterns in the normal state link, combine the key nodes, relationships, and the characteristic patterns of the normal state link to construct a characteristic model for describing the normal state link, and conduct a comparative analysis of the actual state link in each state node graph with the characteristic model of the normal state link to preliminarily screen out candidate abnormal links in the state node graph. Then, in the wood cutting process, the normal state link may be "Cutting equipment starts → (C) Cutting tool operates normally → (C) Wood feeding is stable → (C) Cutting depth and speed meet the standards → (C) Cutting is completed". Analyze the characteristic patterns in this normal state link. For example, for the key node "Cutting tool operates normally", its characteristic pattern may be that the rotation speed of the tool fluctuates within a certain range and the fluctuation amplitude is small; the characteristic pattern of "Wood feeding is stable" may be that the change rate of the feeding speed is within a certain threshold. Combine these key nodes, relationships, and characteristic patterns to construct a characteristic model for describing the normal state link. For the production of a batch of standard boards, the normal state link may involve the continuous normal operation of multiple processes, such as "Qualified raw material procurement → (C) Normal batch cutting process → (C) Normal batch grinding process → (C) Normal batch assembly process → (C) Qualified quality inspection of the whole batch of products". Analyze the characteristic patterns of the normal operation of each process. For example, the characteristic pattern of the normal batch cutting process may be that the cutting size deviation of the whole batch of standard boards is within the allowable range. Construct the characteristic model of the normal state link for the production of the whole batch of standard boards with this information. Then, in furniture production, if in the state node graph of the production of a certain batch of standard boards, the actual state link is "Qualified raw material procurement → (C) Excessive cutting size deviation of some standard boards in the whole batch cutting process → (C) Normal batch grinding process → (C) Normal batch assembly process → (C) Partial unqualified quality inspection of the whole batch of products", compared with the characteristic model of the normal state link, it is found that "Excessive cutting size deviation of some standard boards in the whole batch cutting process" does not conform to the characteristic of the normal cutting process in the normal state link (cutting size deviation within the allowable range), then the link containing this node may be preliminarily screened as a candidate abnormal link. For the associated equipment interaction state node graph, such as in the actual state link of the interaction between the cutting equipment and the grinding equipment, if "When the cutting equipment transfers the standard board to the grinding equipment, the transfer speed is unstable and exceeds the normal fluctuation range → (C) The grinding equipment frequently adjusts parameters when starting to grind", compared with the characteristic model of the normal interaction state link, this candidate abnormal link may be preliminarily screened as a candidate abnormal link;

[0155] Step S157: For the candidate abnormal links preliminarily screened, verify them with reference to historical production monitoring data to generate the verified target abnormal links. For the candidate abnormal links with excessive cutting size deviation in the cutting process mentioned above, the server will refer to the historical production monitoring data. If the historical data shows that under the same production conditions (such as the same raw materials, equipment settings, etc.), the cutting size deviation rarely exceeds a certain range under normal circumstances, but the current batch has exceeded the range, then this candidate abnormal link is verified as a target abnormal link. For the candidate abnormal links with unstable transfer speed in the interaction between the cutting equipment and the grinding equipment and the frequent parameter adjustment of the grinding equipment, check the similar equipment interaction situations in the historical data. It is found that the transfer speed is stable during normal interactions in the past and the grinding equipment rarely needs to adjust parameters frequently, then this link is also verified as a target abnormal link;

[0156] Step S158: For the verified target abnormal links, conduct root cause analysis in the graph structure of the state node diagram, trace back to the abnormal state node where the abnormal state first appears in the target abnormal link, analyze the abnormal cause that leads to the abnormality of this abnormal state node, and at the same time evaluate the association relationship information between the target abnormal link and other state links;

[0157] Step S159: Based on the abnormal cause and the association relationship information between the target abnormal link and other state links, determine the severity of each target abnormal link.

[0158] Finally, for the target abnormal link with excessive cutting size deviation in the cutting process, tracing in the state node graph structure, it is found that the abnormal state node where the abnormal state first appears may be "cutting tool wear". Analyzing the reasons for the abnormality of this abnormal state node, it may be that the cutting tool has not been replaced in time after being used for too long, or the hardness of the cut wood exceeds the expectation, resulting in accelerated tool wear. At the same time, evaluate the correlation information between this target abnormal link and other state links. For example, due to excessive cutting size deviation, it may lead to an increase in the workload of the subsequent grinding process, affecting the efficiency of the grinding process, and further may affect the production progress of the entire batch of products. Based on these abnormal reasons and correlation information, if this problem is not solved in time, it will lead to a large number of defective products in the entire batch, then the severity of this target abnormal link is relatively high. For the target abnormal link in the interaction between the cutting equipment and the grinding equipment, root cause analysis finds that the earliest abnormal state node may be the failure of the conveying device of the cutting equipment, resulting in unstable conveying speed. The abnormal reason may be that a certain component of the conveying device is damaged. This target abnormal link is closely related to the grinding process because the unstable conveying speed causes the grinding equipment to frequently adjust parameters, affecting the grinding quality and efficiency. If it continues, it will affect the quality of the entire batch of products, so the severity is also relatively high. Through such a comprehensive analysis, the server can accurately estimate the abnormal state links in the process of monitoring the production of target standard boards, so as to take effective measures for production optimization and problem solving.

[0159] Figure 2 The on-line intelligent detection and analysis system 100 for standard board production based on industrial Internet of Things shown in the figure includes: a processor 1001 and a memory 1003. Among them, the processor 1001 and the memory 1003 are connected, such as through a bus 1002. Optionally, the on-line intelligent detection and analysis system 100 for standard board production based on industrial Internet of Things may further include a transceiver 1004, and the transceiver 1004 can be used for data interaction between this server and other servers, such as data sending and / or data receiving, etc. It should be noted that in actual scheduling, the transceiver 1004 is not limited to one, and the structure of the on-line intelligent detection and analysis system 100 for standard board production based on industrial Internet of Things does not constitute a limitation to the embodiments of the present application.

[0160] The processor 1001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logical blocks, modules, and circuits described in connection with the disclosure of this application. The processor 1001 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0161] The bus 1002 may include a path for transmitting information between the above components. The bus 1002 may be a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus 1002 may be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, Figure 2 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.

[0162] The memory 1003 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or it may also be an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media, other magnetic storage devices, or any other medium that can be used to carry or store program code and can be read by a computer, which is not limited here.

[0163] The memory 1003 is used to store the program code for implementing the embodiments of the present application, and is controlled by the processor 1001 to execute. The processor 1001 is used to execute the program code stored in the memory 1003 to implement the steps shown in the foregoing method embodiments.

[0164] In addition, an embodiment of the present application further provides a readable storage medium, in which computer-executable instructions are preset. When the processor executes the computer-executable instructions, the online intelligent detection and analysis method for standard board production based on the industrial Internet of Things as described above is implemented.

[0165] Similarly, it should be noted that, in order to simplify the description of the present application disclosure and thus help the understanding of one or more embodiments of the invention, in the foregoing description of the embodiments of the present application, sometimes multiple features are merged into one embodiment, drawing, or description thereof. Similarly, it should be noted that, in order to simplify the description of the present application disclosure and thus help the understanding of one or more embodiments of the invention, in the foregoing description of the embodiments of the present application, sometimes multiple features are merged into one embodiment, drawing, or description thereof.

Claims

1. An online intelligent detection and analysis method for standard board production based on industrial Internet of Things, characterized in that: The method comprises: obtaining first standard board production monitoring data recording the target standard board production monitoring process in an industrial Internet of Things platform, and determining a plurality of node graph construction knowledge patterns for constructing a state node graph for the first standard board production monitoring data; for the plurality of node graph construction knowledge patterns, injecting identification attribute information into the first standard board production monitoring data respectively to generate a plurality of second standard board production monitoring data; the second standard board production monitoring data in the plurality of second standard board production monitoring data respectively correspond to the node graph construction knowledge patterns in the plurality of node graph construction knowledge patterns, and the identification attribute information in each of the second standard board production monitoring data includes pattern identification information reflecting the corresponding node graph construction knowledge pattern; according to the plurality of second standard board production monitoring data The pattern identification information included in the production monitoring data is used to determine multiple feature extraction paths associated with the multiple second standard board production monitoring data; for each of the multiple second standard board production monitoring data, production parameter trajectory vector extraction is performed according to the associated feature extraction path to generate a set of production parameter trajectory vectors corresponding to the multiple node graph construction knowledge patterns; node graphs are constructed for the sets of production parameter trajectory vectors corresponding to the multiple node graph construction knowledge patterns to generate state node graph construction results corresponding to the multiple node graph construction knowledge patterns, and the abnormal state link of the target standard board production monitoring process is estimated based on the state node graph construction results corresponding to the multiple node graph construction knowledge patterns.

2. The online intelligent detection and analysis method for standard board production based on industrial Internet of Things according to claim 1 is characterized in that: The method of determining multiple node graph construction knowledge patterns for constructing a state node graph for the first standard board production monitoring data includes: generating a node graph construction knowledge pattern sequence based on a state node graph construction instruction for the first standard board production monitoring data; and based on a hit instruction for the node graph construction knowledge pattern sequence, using the multiple node graph construction knowledge patterns hit by the hit instruction as the multiple node graph construction knowledge patterns for constructing a state node graph for the first standard board production monitoring data.

3. The online intelligent detection and analysis method for standard board production based on industrial Internet of Things according to claim 1 is characterized in that: The method of constructing knowledge patterns for the multiple node graphs and injecting identification attribute information into the first standard plate production monitoring data respectively to generate multiple second standard plate production monitoring data includes: for each node graph construction knowledge pattern in the multiple node graph construction knowledge patterns, obtaining identification attribute information corresponding to the traversed node graph construction knowledge pattern; injecting the identification attribute information corresponding to the traversed node graph construction knowledge pattern into the first standard plate production monitoring data to generate second standard plate production monitoring data corresponding to the traversed node graph construction knowledge pattern.

4. The online intelligent detection and analysis method for standard board production based on industrial Internet of Things according to any one of claims 1 to 3, characterized in that: The multiple node graph construction knowledge patterns include at least one of a single-process node graph construction knowledge pattern, a whole batch node graph construction knowledge pattern, an associated device interaction node graph construction knowledge pattern, a multi-source data node graph construction knowledge pattern or a customized node graph construction knowledge pattern; the node graph construction instance of the single-process node graph construction knowledge pattern is used to construct a state node graph for single-process production monitoring data; the node graph construction instance of the whole batch node graph construction knowledge pattern is used to construct a state node graph for a whole batch of production monitoring data; the node graph construction instance of the associated device interaction node graph construction knowledge pattern is used to construct a state node graph for associated device interaction production monitoring data; the node graph construction instance of the multi-source data node graph construction knowledge pattern is used to construct a state node graph for standard board production monitoring data extracted from multi-source data; the node graph construction instance of the customized node graph construction knowledge pattern is used to construct a customized state node graph for standard board production monitoring data.

5. The online intelligent detection and analysis method for standard board production based on industrial Internet of Things according to claim 3 is characterized in that: The identification attribute information corresponding to the traversed node graph construction knowledge pattern includes an initial data segment start identifier, an initial data segment end identifier, an end identifier and a pattern identifier information reflecting the traversed node graph construction knowledge pattern; the identification attribute information corresponding to the traversed node graph construction knowledge pattern is injected into the first standard board production monitoring data to generate the second standard board production monitoring data corresponding to the traversed node graph construction knowledge pattern, including: when the number of single-process production monitoring data included in the first standard board production monitoring data is not greater than the set number, the pattern identifier information reflecting the traversed node graph construction knowledge pattern is injected into the front end of the first standard board production monitoring data; after the pattern identifier information reflecting the traversed node graph construction knowledge pattern and before the initial data segment of the first standard board production monitoring data, the initial data segment start identifier is injected; the initial data segment end identifier is injected into the back end of the first standard board production monitoring data, and the end identifier is injected after the injected initial data segment end identifier to generate the second standard board production monitoring data corresponding to the traversed node graph construction knowledge pattern.

6. The online intelligent detection and analysis method for standard board production based on industrial Internet of Things according to claim 3 is characterized in that: The identification attribute information corresponding to the traversed node graph construction knowledge pattern includes an initial data segment start identifier, an initial data segment end identifier, a data segment segmentation identifier, and a pattern identification information reflecting the traversed node graph construction knowledge pattern; the identification attribute information corresponding to the traversed node graph construction knowledge pattern is injected into the first standard board production monitoring data to generate the second standard board production monitoring data corresponding to the traversed node graph construction knowledge pattern, including: when the number of single-process production monitoring data included in the first standard board production monitoring data is greater than a set number, injecting the node graph construction reflecting the traversed knowledge pattern into the front end of the first standard board production monitoring data. The pattern identification information of the knowledge pattern; after the pattern identification information reflecting the traversed node graph to construct the knowledge pattern and before the initial data segment of the first standard board production monitoring data, the initial data segment start identifier is injected; at the back end of the initial single-process production monitoring data in the first standard board production monitoring data, the initial data segment end identifier is injected; the remaining single-process production monitoring data except the initial single-process production monitoring data in the first standard board production monitoring data is determined, and the data segment segmentation identifier is injected between every two associated remaining single-process production monitoring data to generate the second standard board production monitoring data corresponding to the knowledge pattern constructed by the traversed node graph.

7. The online intelligent detection and analysis method for standard board production based on industrial Internet of Things according to claim 1 is characterized in that: The determining of multiple feature extraction paths associated with the multiple second standard board production monitoring data includes: for each second standard board production monitoring data among the multiple second standard board production monitoring data, when the node graph construction knowledge pattern reflected by the pattern identification information included in the traversed second standard board production monitoring data belongs to the interactive task mode, determining that the feature extraction path associated with the traversed second standard board production monitoring data is an interactive feature extraction path used to extract features from the interactive production monitoring data of associated equipment; when the node graph construction knowledge pattern reflected by the pattern identification information included in the traversed second standard board production monitoring data belongs to the non-interactive task mode, determining that the feature extraction path associated with the traversed second standard board production monitoring data is a non-interactive feature extraction path used to extract features from the interactive production monitoring data of non-associated equipment.

8. The online intelligent detection and analysis method for standard board production based on industrial Internet of Things according to claim 7 is characterized in that: For each of the plurality of second standard board production monitoring data, production parameter trajectory vector extraction is performed respectively according to the associated feature extraction path, and a set of production parameter trajectory vectors corresponding to the plurality of node graph construction knowledge patterns are generated, including: for each of the plurality of second standard board production monitoring data, when the feature extraction path associated with the traversed second standard board production monitoring data is an interactive feature extraction path, for each single-process production monitoring data in the traversed second standard board production monitoring data, interactive link data of each single-process production monitoring data in the traversed second standard board production monitoring data is determined respectively, and the interactive link data of each single-process production monitoring data in the traversed second standard board production monitoring data is determined. The determined data of each interaction link are characterized respectively, and the interaction link feature vector corresponding to each single-process production monitoring data in the traversed second standard board production monitoring data is generated; based on the interaction device label corresponding to each single-process production monitoring data in the traversed second standard board production monitoring data, the interaction device associated with each single-process production monitoring data in the traversed second standard board production monitoring data is determined, and the interaction devices associated with each single-process production monitoring data are characterized respectively, and the interaction device feature vector corresponding to each single-process production monitoring data in the traversed second standard board production monitoring data is generated; for each single-process in the traversed second standard board production monitoring data The production monitoring data are represented by state parameter characteristics respectively, and a state parameter feature vector set corresponding to each single-process production monitoring data in the traversed second standard board production monitoring data is generated; each single-process production monitoring data in the traversed second standard board production monitoring data is represented by context characteristics respectively, and a context feature vector set corresponding to each single-process production monitoring data in the traversed second standard board production monitoring data is generated; based on the interaction link feature vector, interaction device feature vector, state parameter feature vector set and context feature vector set corresponding to each single-process production monitoring data in the traversed second standard board production monitoring data, a context feature vector set corresponding to the traversed second standard board production monitoring data is generated. A set of production parameter trajectory vectors corresponding to the data; or, for each second standard board production monitoring data in the multiple second standard board production monitoring data, when the feature extraction path associated with the traversed second standard board production monitoring data is a non-interactive feature extraction path, each data node in the traversed second standard board production monitoring data is respectively represented by state parameter features, and a state parameter feature vector corresponding to each data node in the traversed second standard board production monitoring data is generated; each data node in the traversed second standard board production monitoring data is respectively represented by context features, and a context feature vector corresponding to each data node in the traversed second standard board production monitoring data is generated;The state parameter feature vector and the context feature vector corresponding to the same data node are fused to generate a fused feature vector corresponding to each data node in the traversed second standard board production monitoring data; based on the fused feature vector corresponding to each data node in the traversed second standard board production monitoring data, a set of production parameter trajectory vectors corresponding to the traversed second standard board production monitoring data is generated. ; 9. The online intelligent detection and analysis method for standard board production based on industrial Internet of Things according to claim 1 is characterized in that: The method is executed by a state node graph construction model, and the training step of the state node graph construction model includes: obtaining first template standard plate production monitoring data and multiple prior state node graphs corresponding to the first template standard plate production monitoring data; constructing knowledge patterns for multiple preset node graphs, injecting identification attribute information into the first template standard plate production monitoring data respectively, and generating multiple second template standard plate production monitoring data corresponding to the multiple node graph construction knowledge patterns; the identification attribute information in each of the second template standard plate production monitoring data includes pattern identification information reflecting the corresponding node graph construction knowledge pattern; determining the multiple second template standard plate production monitoring data according to the pattern identification information respectively included in the multiple second template standard plate production monitoring data multiple feature extraction paths associated with production monitoring data; for each of the multiple second template standard plate production monitoring data, extracting production parameter trajectory vectors according to the associated feature extraction paths, generating sets of template production parameter trajectory vectors corresponding to the multiple node graph construction knowledge patterns; performing node graph construction on the sets of template production parameter trajectory vectors corresponding to the multiple node graph construction knowledge patterns, generating predicted state node graphs corresponding to the multiple node graph construction knowledge patterns; training the state node graph construction model according to the predicted state node graphs corresponding to the multiple node graph construction knowledge patterns and the multiple prior state node graphs, generating a trained state node graph construction model.

10. An online intelligent detection and analysis system for standard board production based on industrial Internet of Things, characterized in that: The online intelligent detection and analysis system for standard board production based on the industrial Internet of Things includes a processor and a machine-readable storage medium, wherein the machine-readable storage medium stores machine executable instructions, and the machine executable instructions are loaded and executed by the processor to implement the online intelligent detection and analysis method for standard board production based on the industrial Internet of Things as described in any one of claims 1 to 9.

Images