A product quality assessment method and system based on industrial Internet of Things

Abstract

The present invention provides a product quality assessment method and system based on the industrial Internet of Things. The method is executed by the industrial Internet of Things management platform, including: obtaining one or more links of the current production line based on the industrial Internet of Things perception control platform; for each of the one or more links: based on the link characteristics of the link, through the quality database, determine the first abnormality of the link and the link criticality; based on the link criticality and the first abnormality, determine the link monitoring level; based on the link monitoring level, determine the quality detection parameters, and issue the quality detection parameters to the quality inspection equipment of the industrial Internet of Things perception control platform; control the quality inspection equipment to perform quality inspection on the products of the link according to the quality detection parameters to obtain the product quality characteristics of the link; based on the link characteristics and product quality characteristics, generate quality update data to update the quality database. Through the above method and system, the production process can be optimized based on the product quality assessment of each link.

Description

Technical Field

[0001] This specification relates to the field of product quality assessment, and in particular to a product quality assessment method and system based on industrial Internet of Things. Background Art

[0002] In today's highly automated industrial production environment, common general production lines are often composed of multiple closely connected links, each of which is directly related to the quality and performance of the final product. Traditional quality monitoring methods often rely on manual inspection, which is not only time-consuming and labor-intensive, but also prone to human errors. Industrial Internet of Things technology, by integrating sensors, smart devices and data analysis systems, can monitor various parameters in the production process in real time, thereby achieving a comprehensive assessment of product quality.

[0003] Therefore, it is necessary to provide a product quality assessment method and system based on industrial Internet of Things, which helps to collect and analyze various data in the production process in real time and accurately, thereby optimizing the production process and improving production efficiency. Summary of the invention

[0004] One aspect of an embodiment of the present specification provides a product quality assessment method based on the Industrial Internet of Things, which is executed by an Industrial Internet of Things management platform, and the method includes: obtaining one or more links of the current production line based on the Industrial Internet of Things perception control platform; for each of the one or more links: based on the link characteristics of the link, determining the first abnormality and link criticality of the link through a quality database; based on the link criticality and the first abnormality, determining the link monitoring level; based on the link monitoring level, determining quality inspection parameters, and issuing the quality inspection parameters to the quality inspection equipment of the Industrial Internet of Things perception control platform; controlling the quality inspection equipment to perform quality inspection on the products of the link according to the quality inspection parameters to obtain the product quality characteristics of the link; based on the link characteristics and the product quality characteristics, generating quality update data to update the quality database.

[0005] Another aspect of an embodiment of the present specification provides a product quality assessment system based on the Industrial Internet of Things, the system comprising an Industrial Internet of Things user platform, an Industrial Internet of Things service platform, an Industrial Internet of Things management platform, an Industrial Internet of Things sensor network platform, and an Industrial Internet of Things perception control platform; the Industrial Internet of Things management platform is configured to: obtain one or more links of the current production line based on the Industrial Internet of Things perception control platform; for each of the one or more links: based on the link characteristics of the link, determine the first abnormality and link criticality of the link through a quality database; based on the first abnormality and the link criticality, determine the link monitoring level; based on the link monitoring level, determine quality detection parameters, and issue the quality detection parameters to the quality inspection equipment of the Industrial Internet of Things perception control platform; control the quality inspection equipment to perform quality detection on the products of the link according to the quality detection parameters to obtain the product quality characteristics of the link; based on the link characteristics and the product quality characteristics, generate quality update data to update the quality database.

[0006] In some embodiments of the present specification, based on the link characteristics, product quality characteristics, etc. of different links in the production line, the quality inspection parameters corresponding to each link are determined through the quality database to carry out targeted monitoring of the products in each link, which helps to ensure the stability and consistency of product quality and optimize the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0008] Figure 1 It is a system structure diagram of a product quality assessment system based on the industrial Internet of Things according to some embodiments of this specification;

[0009] Figure 2 is an exemplary flow chart of a product quality assessment method based on the industrial Internet of Things according to some embodiments of this specification;

[0010] Figure 3 is an exemplary schematic diagram of determining a first abnormality degree and a link criticality according to some embodiments of this specification;

[0011] Figure 4 It is an exemplary schematic diagram of determining quality detection parameters according to some embodiments of this specification. DETAILED DESCRIPTION

[0012] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0013] It should be understood that the "system", "device" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0014] Unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0015] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0016] In modern manufacturing, complex and efficient production lines are usually closely connected by multiple links, and each link will affect the quality of the final product. In order to ensure the stability and consistency of product quality, comprehensive quality monitoring of the production line becomes particularly critical. In view of this, some embodiments of this specification provide a product quality assessment method and system based on the industrial Internet of Things, which integrates sensors, equipment and network communication technology to achieve real-time data collection and product quality assessment of each link of the production line, thereby improving the overall production efficiency and quality level of the enterprise.

[0017] Figure 1 It is a system structure diagram of a product quality assessment system based on industrial Internet of Things as shown in some embodiments of this specification.

[0018] like Figure 1 As shown, the product quality assessment system 100 based on the industrial Internet of Things may include an industrial Internet of Things user platform 110, an industrial Internet of Things service platform 120, an industrial Internet of Things management platform 130, an industrial Internet of Things sensor network platform 140, and an industrial Internet of Things perception control platform 150.

[0019] The IIoT user platform 110 is a platform for implementing interaction between users and systems.

[0020] In some embodiments, the industrial Internet of Things user platform 110 can be configured as a user terminal. A user terminal can refer to one or more terminal devices used by a user. A user can refer to a person in charge of the product quality assessment system 100 based on the industrial Internet of Things, etc. For example, a user terminal can include a mobile phone, a tablet computer, a client, a web page, etc.

[0021] The industrial Internet of Things service platform 120 is a platform for service communication and service data processing and storage.

[0022] In some embodiments, the industrial Internet of Things service platform 120 can be configured as a single server or as a server group. The server group can be centralized or distributed, for example, the server can be a distributed system. In some embodiments, the server can be local or remote.

[0023] In some embodiments, the industrial Internet of Things service platform 120 may also be configured to include a database or a memory.

[0024] In some embodiments, the IIoT service platform 120 may exchange data with the IIoT user platform 110 and the IIoT management platform 130 .

[0025] The industrial Internet of Things management platform 130 is a platform configured in each factory for Internet of Things management.

[0026] In some embodiments, the industrial Internet of Things management platform 130 can be configured as a processor, such as a central processing unit, a microcontroller, an embedded processor (Embedded Processor), a graphics processing unit (Graphics Processing Unit, GPU), etc., or any combination thereof.

[0027] In some embodiments, the IIoT management platform 130 may exchange data with the IIoT service platform 120 and the IIoT sensor network platform 140 .

[0028] The industrial Internet of Things sensor network platform 140 refers to a sensor communication platform that realizes uploading of perception information and sending of control information. For example, the industrial Internet of Things sensor network platform 140 can be configured as a gateway, a data interface, etc.

[0029] The industrial Internet of Things perception control platform 150 refers to a functional platform for obtaining perception information and executing control instructions. In some embodiments, the industrial Internet of Things perception control platform 150 can be configured in a factory production line, a factory storage and logistics center, or a factory equipment monitoring room. In some embodiments, the industrial Internet of Things perception control platform 150 can include operating equipment, quality inspection equipment, monitoring equipment, etc. Among them, operating equipment is equipment used for production and manufacturing, which may include machine tools, manipulators, etc.; quality inspection equipment is equipment used for quality inspection, which may include laser rangefinders, mechanical testers, image detection equipment, etc.; monitoring equipment is equipment used to obtain the operating status and production status of operating equipment, which may include sensors, PLC systems, etc.

[0030] In some embodiments, the industrial Internet of Things sensor network platform 140 can exchange data with the industrial Internet of Things management platform 130 and the industrial Internet of Things perception control platform 150.

[0031] In some embodiments, the industrial Internet of Things management platform 130 can obtain one or more links of the current production line based on the industrial Internet of Things perception control platform 150; for each of the one or more links: based on the link characteristics of the link, determine the first abnormality and link criticality of the link through the quality database; based on the link criticality and the first abnormality, determine the link monitoring level; based on the link monitoring level, determine the quality inspection parameters, and issue the quality inspection parameters to the quality inspection equipment of the industrial Internet of Things perception control platform 150; control the quality inspection equipment to perform quality inspection on the products of the link according to the quality inspection parameters to obtain the product quality characteristics of the link; based on the product quality characteristics, generate quality update data to update the quality database. For more information about this section, please refer to Figure 2~Figure 4 and its related description.

[0032] It should be noted that the above description of the product quality assessment system based on the industrial Internet of Things is only for the convenience of description and cannot limit this specification to the scope of the embodiments. It is understandable that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine the various platforms or form a subsystem to connect with other platforms without deviating from this principle.

[0033] Figure 2 is an exemplary flow chart of a product quality assessment method based on the industrial Internet of Things according to some embodiments of this specification. Figure 2 As shown, the process 200 includes the following steps. In some embodiments, the process 200 can be executed by an industrial Internet of Things management platform.

[0034] In some embodiments, the industrial Internet of Things management platform can obtain one or more links of the current production line based on the industrial Internet of Things perception control platform; for each of the one or more links: based on the link characteristics of the link, determine the first abnormality and link criticality of the link through the quality database; based on the link criticality and the first abnormality, determine the link monitoring level; based on the link monitoring level, determine the quality inspection parameters, and issue the quality inspection parameters to the quality inspection equipment of the industrial Internet of Things perception control platform; control the quality inspection equipment to perform quality inspection on the products of the link according to the quality inspection parameters to obtain the product quality characteristics of the link; based on the product quality characteristics, generate quality update data to update the quality database.

[0035] Step 210: Obtain one or more links of the current production line based on the industrial Internet of Things perception control platform.

[0036] The current production line refers to the production line that currently needs to be evaluated for quality.

[0037] A link refers to a certain sequence or interrelated processing steps in a production line.

[0038] In some embodiments, the industrial Internet of Things management platform can obtain one or more links of the current production line through the industrial Internet of Things sensor network platform based on the industrial Internet of Things perception control platform.

[0039] Step 220, for each of the one or more links, execute steps 221 to 225.

[0040] When executing the following steps for each of the one or more links, the link is taken as the target link, and each of the one or more links will be taken as the target link in turn.

[0041] Step 221, based on the link characteristics of the link, determine the first abnormality degree and link criticality of the link through the quality database.

[0042] Link features refer to the processing features included in the link. In some embodiments, link features may include part features, assembly features, equipment features, etc. Among them, part features may include part name, part size, processing accuracy, etc., assembly features may include assembly sequence, assembly process, assembly accuracy, etc., and equipment features may include the equipment used, etc. Among them, the higher the value of processing accuracy, the higher the accuracy requirement for the processing process, and the higher the value of assembly accuracy, the higher the accuracy requirement for the assembly process.

[0043] In some embodiments, the industrial Internet of Things management platform can obtain the link characteristics of the target link by reading drawings (such as parts drawings, assembly drawings, process documents, etc.), and can also obtain the link characteristics input by the user through the industrial Internet of Things user platform.

[0044] For more information about part features and assembly features, see Figure 3 Related description.

[0045] The quality database is a database containing relevant data of multiple links of the historical production line. In some embodiments, the quality database may include the link ID of each link of the historical production line, the historical link characteristics of the link, the historical link characteristics of the previous link, the historical link characteristics of the next link, the historical quality characteristics and other field names and their corresponding data.

[0046] The link ID may represent the identifiers of multiple links of multiple production lines, and the historical quality features corresponding to the link may include the number of products corresponding to the link in the historical data, the number of abnormal products, etc. Among them, the number of abnormal products may be the sum of the number of defective products and the number of unqualified products. Defective products refer to products with poor quality but can flow into the next link for continued production, and unqualified products refer to products that cannot flow into the next link and are directly eliminated.

[0047] In some embodiments, the industrial Internet of Things management platform can build a quality database based on historical data. For example, the industrial Internet of Things management platform can retrieve historical data according to link ID, determine the link corresponding to each link ID and the historical link characteristics, historical quality characteristics, etc. of the previous and next links, and when multiple historical data are retrieved for the same link ID, the average of the multiple historical data can be taken, and the quality database can be built based on the link ID and the determined corresponding link and the historical link characteristics, historical quality characteristics, etc. of the previous and next links, where each link ID and its corresponding historical data correspond to a row in the quality database.

[0048] For more information about the quality database, see Figure 3 The corresponding description.

[0049] The first abnormality is an indicator that reflects the degree of abnormality of the products produced in a link.

[0050] Link criticality is an indicator that reflects the criticality of a link to the finished product.

[0051] In some embodiments, the industrial Internet of Things management platform can determine the first abnormality and link criticality of the target link based on the link characteristics of the target link and the previous and next links through the quality database. For example, the industrial Internet of Things management platform can construct a first feature vector based on the link characteristics of the target link and the previous and next links, match them through the quality database, use the first reference vector with the highest similarity as the first target vector, and obtain the first abnormality and link criticality of the target link through corresponding calculation methods based on the historical link characteristics and historical quality characteristics of the link corresponding to the first target vector.

[0052] Exemplarily, the first abnormality can be determined by the proportion of the number of abnormal products in the historical quality characteristics corresponding to the first target vector. The link criticality can be the result of weighted averaging the processing accuracy and assembly accuracy in the link characteristics of the target link, multiplied by the quality coefficient. The weight of the weighted average can be set by the technician based on historical data and prior knowledge. The quality coefficient can be positively correlated to the number of abnormal products in the historical quality characteristics corresponding to the first target vector.

[0053] The first reference vector is a vector generated based on the quality database. For example, the link corresponding to each link ID in the quality database and the historical link features of the previous and next links can be used as the first reference vector, and the corresponding historical quality features can be used as the label corresponding to the first reference vector. Similarity can be calculated based on cosine distance, Euclidean distance, etc.

[0054] It can be understood that when constructing the first reference vector and the first characteristic vector, when the corresponding link is the first link of the production line, the industrial Internet of Things management platform can set the (historical) link characteristics of the previous link to a null value; when the link is the last link of the production line, the industrial Internet of Things management platform can set the (historical) link characteristics of the latter link to a null value.

[0055] Step 222, determining the link monitoring level based on the link criticality and the first abnormality.

[0056] The link monitoring level is data that represents the intensity of monitoring of a link.

[0057] In some embodiments, the industrial Internet of Things management platform can determine the link monitoring level in a variety of ways based on the link criticality and the first abnormality. For example, the link monitoring level can be positively correlated with the link criticality and the first abnormality. Exemplarily, the industrial Internet of Things management platform can perform a weighted average of the link criticality and the first abnormality, and determine the corresponding link monitoring level based on the numerical range of the result after the weighted average. Among them, the weight of the weighted average, and the corresponding relationship between different numerical ranges and link monitoring levels can be set by technical personnel based on historical data and prior knowledge.

[0058] Step 223, based on the link monitoring level, determine the quality inspection parameters, and issue the quality inspection parameters to the quality inspection equipment of the industrial Internet of Things perception control platform.

[0059] Quality inspection parameters refer to the relevant parameters required for quality inspection of a link. For example, quality inspection parameters may include the equipment type and equipment operation parameters of the quality inspection equipment. For more information about the equipment type and equipment operation parameters of the quality inspection equipment, see Figure 4 Related description.

[0060] In some embodiments, the industrial Internet of Things management platform can determine the quality inspection parameters in a variety of ways based on the link monitoring level, and issue the quality inspection parameters to the quality inspection equipment of the industrial Internet of Things perception control platform. For example, the industrial Internet of Things management platform can obtain the corresponding quality inspection parameters by querying the first preset table based on the link monitoring level.

[0061] Among them, the first preset table can be constructed by technical personnel based on historical data or prior knowledge, including the correspondence between link monitoring levels and quality detection parameters.

[0062] For more information on determining quality test parameters, see Figure 4 and its related description.

[0063] Step 224, controlling the quality inspection equipment to perform quality inspection on the products of the link according to the quality inspection parameters, and obtaining the quality characteristics of the products of the link.

[0064] Product quality characteristics refer to the data obtained by testing the products in the process. For example, product quality characteristics may include product size data, image data, product quality data (such as product quantity, number of abnormal products, etc.), etc.

[0065] In some embodiments, the industrial Internet of Things management platform can control the quality inspection equipment, perform quality inspection on the products of the target link according to the equipment type and equipment operating parameters corresponding to the quality inspection equipment in the quality inspection parameters, and obtain the product quality characteristics of the target link.

[0066] Step 225, based on the link characteristics and product quality characteristics, generate quality update data to update the quality database.

[0067] The quality update data refers to the relevant data required to update the quality database. For example, the quality update data may include the update content required to update the quality database, such as the link characteristics of the target link, the product quality characteristics, etc.

[0068] In some embodiments, the industrial Internet of Things management platform can generate quality update data based on link characteristics and product quality characteristics, and update the quality database in a variety of ways. For example, the industrial Internet of Things management platform can generate new data records about the target link based on the link characteristics and product quality characteristics of the target link and store them in the quality database.

[0069] In some embodiments, the industrial Internet of Things management platform can also merge similar data records to organize the quality database to avoid insufficient database space due to continuous storage of new data. Similar data records refer to data of the same type whose differences do not exceed the corresponding difference threshold, which can be preset manually. Data of the same type refers to data with the same field name.

[0070] In some embodiments of the present specification, by matching the link characteristics of each link of the current production line in the quality database, the link criticality, the first abnormality and the link monitoring level are determined in order to determine appropriate quality inspection parameters, and more targeted quality inspections are performed on the links to better update the quality database. This can provide more complete data references for the optimization of the overall production process of the production line and establish a product quality evaluation system.

[0071] It should be noted that the above description of the process 200 is only for example and illustration, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to the process 200 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0072] Figure 3 It is an exemplary schematic diagram for determining the first abnormality degree and the link criticality according to some embodiments of this specification.

[0073] In some embodiments, Figure 3 As shown, the industrial Internet of Things management platform can search in the quality database 320 based on the link feature 310 to determine the target knowledge base 330; through the target knowledge base 330, the first abnormality 351 and the link criticality 352 are determined. For relevant descriptions of link features, quality databases, first abnormality and link criticality, please refer to Figure 2 The corresponding description.

[0074] In some embodiments, the quality database 320 may include multiple knowledge bases. The format of each knowledge base is the same as that of the quality database, except that the amount of data contained is different and / or the historical data used when constructing it is different. For example, the knowledge base KA is constructed based on historical data in summer; the knowledge base KB is constructed based on historical data in winter. For another example, the knowledge base KA is constructed based on historical data of process A and process B; the knowledge base KB is constructed based on historical data of process C and process D.

[0075] The target knowledge base 330 is a knowledge base used for matching historical links.

[0076] In some embodiments, the industrial Internet of Things management platform can search multiple knowledge bases in the quality database based on the link characteristics of the target link to determine the target knowledge base. For example, the industrial Internet of Things management platform can determine the target knowledge base based on the link characteristics of the target link through the following steps (1) to (3):

[0077] Step (1) extracts a part of the link features as the features to be matched, takes the part of the features in the historical link features of the knowledge base that correspond to the features to be matched as the historical matching features, constructs a second feature vector based on the features to be matched, constructs a second reference vector based on the historical matching features, searches the quality database based on the second feature vector, and returns the number of matches of the second reference vector in each knowledge base (e.g., the number of vectors with similarity greater than a similarity threshold); wherein the features to be matched refer to the features in the link features that are used to match the historical links, such as the similarity of the part features in the link features that may indicate that the production processes have certain similarities, so the part name and the maximum size of the part in the part features of the link features can be selected as the features to be matched. It can be understood that each row of data in the knowledge base corresponds to a second reference vector.

[0078] Step (2) calculates the matching degree of each knowledge base, where the matching degree of a knowledge base is the ratio of the number of matches to the amount of data in the knowledge base. The amount of data in the knowledge base may be the total number of rows of data in the knowledge base.

[0079] Step (3) takes the knowledge base with the highest matching degree as the target knowledge base.

[0080] In some embodiments, the link feature may include at least one of a part feature and an assembly feature. For a description of the part feature and the assembly feature, see Figure 2 Related description.

[0081] In some embodiments, the industrial Internet of Things management platform can also determine the scale level of the knowledge base based on the processing accuracy of the part features of the target link and the assembly accuracy of the assembly features; and determine the target knowledge base based on the scale level of the knowledge base.

[0082] The knowledge base scale level is data that reflects the scale of the amount of data contained in the knowledge base. The higher the knowledge base scale level is, the more data the knowledge base contains.

[0083] In some embodiments, the industrial Internet of Things management platform can determine the knowledge base scale level based on the machining accuracy of the part features and the assembly accuracy of the assembly features of the target link. For example, the knowledge base scale level can be positively correlated with the machining accuracy of the part features and the assembly accuracy of the assembly features. For example, the knowledge base scale level can be determined based on the following formula (1):

[0084] R=(a j+b z) k(1)

[0085] Among them, R represents the scale level of the knowledge base, a and b are the weight coefficients of machining accuracy and assembly accuracy, respectively, with values ​​ranging from 0 to 1, and the sum of a and b is 1, j represents the machining accuracy of part features, z represents the assembly accuracy of assembly features, and k is the maximum amount of data in all knowledge bases contained in the quality database.

[0086] In some embodiments, the industrial Internet of Things management platform can determine the target knowledge base in a variety of ways based on the knowledge base scale. For example, the industrial Internet of Things management platform can use the steps (1) to (3) of determining the target knowledge base in the previous text, and replace step (3) with the following steps (3.1) to (3.3):

[0087] Step (3.1) selects one or more knowledge bases with a matching degree greater than a matching threshold as candidate knowledge bases. When there is only one candidate knowledge base, the subsequent steps can be skipped and the knowledge base can be directly determined as the target knowledge base.

[0088] Step (3.2) determines the scale level of the knowledge base based on the machining accuracy of the part features of the link features and the assembly accuracy of the assembly features. The determination method is described in the previous text.

[0089] Step (3.3) selects the candidate knowledge base with the data volume closest to the knowledge base scale level from multiple candidate knowledge bases as the target knowledge base.

[0090] In some embodiments of the present specification, by determining the knowledge base scale level according to the processing accuracy and assembly accuracy of the target link and then determining the target knowledge base, a target knowledge base that better matches the processing accuracy and assembly accuracy of the target link can be selected so as to subsequently determine a more accurate first abnormality degree, link criticality, etc. of the target link.

[0091] In some embodiments, the industrial Internet of Things management platform can determine the first abnormality and the criticality of the link through the target knowledge base based on the link characteristics. The method of determining the first abnormality and the criticality of the link through the target knowledge base based on the link characteristics is similar to the method of determining the first abnormality and the criticality of the link through the quality database based on the link characteristics, which can be referred to Figure 2 Related instructions.

[0092] In some embodiments, Figure 3 As shown, the industrial Internet of Things management platform can determine the production structure map 312 based on the link characteristics 310 of one or more links; based on the production structure map 312, through the quality model 340 corresponding to the target knowledge base, determine the first abnormality 351 and the link criticality 352 of the link.

[0093] The production structure map 312 is a map reflecting the overall production structure of the current production line.

[0094] In some embodiments, the industrial Internet of Things management platform can construct a production structure map based on the link characteristics of one or more links. For example, the nodes of the production structure map can correspond to the links of the current production line, and the node characteristics can be the link characteristics of the corresponding links. There is an edge between the nodes corresponding to the two links with the previous and next production relationship, and the edge characteristics can be the direction of the edge, which is the direction from the previous link of the production line to the next link.

[0095] The quality model 340 is a model for determining the first abnormality and the criticality of a link. In some embodiments, the quality model may be a machine learning model. For example, the quality model may be a graph neural network model (GNN). In some embodiments, the input of the quality model may be a production structure map, and the output may include the first abnormality and criticality of one or more links determined based on one or more nodes.

[0096] In some embodiments, different knowledge bases correspond to different quality models. For example, the training samples of the quality models of different knowledge bases are different. For example, when training a quality model corresponding to a knowledge base, only the historical data of the knowledge base is used as a training sample. Therefore, the model parameters of the quality models corresponding to different knowledge bases may be different.

[0097] In some embodiments, taking the training of the quality model corresponding to the target knowledge base as an example: the quality model corresponding to the target knowledge base can be obtained based on a large number of training samples with training labels.

[0098] The training samples can be sample production structure maps generated based on historical records. For example, they can be generated from link features of one or more sample links of a production line in the target knowledge base. The generation method is similar to that of the production structure map. Please refer to the relevant instructions above.

[0099] The training label can be the first abnormality and criticality of one or more links corresponding to the sample production structure map. The first abnormality in the training label is determined in the same way as Figure 2 The method of determining the first abnormality degree is similar to that in Figure 2 The corresponding description.

[0100] In some embodiments, the link criticality of each sample link in the training label can be determined based on the difference between the number of abnormal products in the sample link and the number of defective products in the previous link of the sample link. For example, the link criticality of the sample link can be positively correlated to the difference between the number of abnormal products in the sample link and the number of defective products in the previous link of the sample link.

[0101] In some embodiments, the industrial Internet of Things management platform can input a large number of sample production structure maps from the target knowledge base into the initial quality model, construct a loss function based on the output of the initial quality model and the training labels corresponding to the sample production structure maps, and iteratively update the initial quality model based on the loss function; when the value of the loss function meets the iteration completion condition, the training is completed and a trained quality model is obtained. The iteration completion condition may include the convergence of the loss function, the number of iterations reaching a threshold, etc.

[0102] In some embodiments, the industrial Internet of Things management platform can input the production structure map into the quality model corresponding to the target knowledge base, and determine the first abnormality degree and link criticality corresponding to the target link from the first abnormality degree and link criticality of one or more links output by the quality model.

[0103] In some embodiments of the present specification, by constructing a production structure map and then determining the first abnormality degree and link criticality of one or more links through the quality model corresponding to the target knowledge base, the first abnormality degree and link criticality of the determined target link can be made more in line with the actual situation and more meaningful for reference, so as to subsequently determine more accurate link monitoring levels and quality detection parameters.

[0104] In some embodiments, the output of the quality model may also include link monitoring levels of one or more links.

[0105] In some embodiments, when the output of the quality model includes link monitoring levels of one or more links, the industrial Internet of Things management platform can add the link monitoring levels of one or more links corresponding to the sample production structure map in the training label. The link monitoring levels of one or more links in the training label can be determined based on the first abnormality and link criticality of one or more links in the training label. The determination method is similar to the method of determining the link monitoring level based on the first abnormality and link criticality. See Figure 2 The specific training process is similar to the previous one, please refer to the previous one for related instructions.

[0106] In some embodiments, the industrial Internet of Things management platform can input the production structure map into the quality model corresponding to the target knowledge base, and determine the link monitoring level corresponding to the target link from the link monitoring levels of one or more links output by the quality model.

[0107] In some embodiments of the present specification, by adding the link monitoring level of one or more links to the output of the quality model, the link monitoring level can be determined more efficiently and accurately based on the quality model, so as to subsequently determine more appropriate quality detection parameters.

[0108] Different knowledge bases may be constructed from different types of historical data. In some embodiments of the present specification, by determining the target knowledge base from the quality database, a knowledge base that is more suitable for the target link can be obtained; matching based on the target knowledge base to determine the first abnormality degree and link criticality of the target link can increase the reliability of the first abnormality degree and link criticality of the target link.

[0109] Figure 4 It is an exemplary schematic diagram of determining quality detection parameters according to some embodiments of this specification.

[0110] In some embodiments, Figure 4 As shown, the quality inspection parameters 440 include at least a quality assessment algorithm 442, a device type 444 of the quality inspection device, and device operating parameters 446; the industrial Internet of Things management platform 130 can determine the quality assessment algorithm 442 based on the link monitoring level 410; determine the device type 444 and the device operating parameters 446 based on the quality assessment algorithm 442; control the quality inspection device to perform quality inspection on the products of the link according to the quality inspection parameters 440 to obtain the initial product characteristics 450 of the link; based on the quality assessment algorithm 442, process the initial product characteristics 450 to obtain product quality characteristics 460.

[0111] The quality assessment algorithm 442 is an algorithm for quantitatively assessing product features. In some embodiments, the quality assessment algorithm may include the type of data collected and the granularity of the collected data. The type of data collected refers to the type of data that needs to be collected; the granularity of the collected data reflects the degree of detail of the collected data, for example, the higher the data collection frequency and the higher the accuracy of the collected data, the higher the granularity of the collected data.

[0112] In some embodiments, the quality assessment algorithm may further include an algorithm type, wherein the algorithm type refers to an algorithm type used to process data, for example, the algorithm type may be to screen unqualified products according to conditions.

[0113] In some embodiments, the algorithm type may include an extreme value averaging method, a data fitting method, and the like.

[0114] For example, to measure the flatness of a part, the algorithm type can be: the probe measures the height of multiple measurement points on the same plane, and the result of subtracting the minimum height from the maximum height is the flatness. For another example, using a more complex data fitting method to measure flatness can include the following steps:

[0115] (1) Collect images of the surface of the object to be measured at multiple angles;

[0116] (2) Extracting feature points of each image and performing plane fitting on the feature points in the same coordinate system, such as by using the least squares method, random sampling consensus method, etc.;

[0117] (3) Calculate the flatness based on the plane obtained after fitting.

[0118] For more information on initial product features, see Figure 4 and its related description.

[0119] In some embodiments, the industrial Internet of Things management platform can determine the quality assessment algorithm in a variety of ways based on the link monitoring level. For example, the industrial Internet of Things management platform can determine the algorithm level of the quality assessment algorithm based on the link monitoring level, and different algorithm levels can correspond to different types of collected data.

[0120] Exemplarily, the algorithm level of the quality assessment algorithm can correspond one-to-one to the link monitoring level. For example, the algorithm level and the link monitoring level both contain 10 levels, among which the higher the level of the quality assessment algorithm, the more data types it can collect, the higher the granularity of the collected data, and the more complex the algorithm type. The quality assessment algorithm corresponding to each algorithm level can be preset manually.

[0121] For more information about link monitoring levels and link characteristics, please refer to Figure 2 and its related description.

[0122] In some embodiments, the industrial Internet of Things management platform can obtain monitoring data 420 based on the link monitoring level 410; determine the second abnormality 430 of the link based on the monitoring data 420; and determine the quality assessment algorithm 442 based on the second abnormality 430.

[0123] Monitoring data 420 is real-time monitoring data of a link. For example, the monitoring data may include production speed, equipment operation status, dimension data, image data, etc.

[0124] In some embodiments, the industrial Internet of Things management platform can obtain monitoring data based on the link monitoring level. Exemplarily, the industrial Internet of Things management platform can determine the monitoring data type and monitoring data granularity by querying the second preset table based on the link monitoring level; based on the monitoring data type and monitoring data granularity, the monitoring data can be obtained through the monitoring equipment and quality inspection equipment of the industrial Internet of Things perception control platform, such as obtaining the production speed and equipment operation status of the target link through the monitoring equipment, and obtaining dimension data, image data, etc. through the quality inspection equipment. The definition of monitoring data type and monitoring data granularity is similar to the definition of acquisition data type and acquisition data granularity, and the details can be referred to the relevant description in the previous text.

[0125] The second preset table can be constructed by a person skilled in the art based on experience, and includes the correspondence between different link monitoring levels and monitoring data types and monitoring data granularity. For example, the higher the link monitoring level, the more corresponding monitoring data types and the higher the monitoring data granularity.

[0126] The second abnormality degree is an indicator that reflects the degree of abnormality of the monitoring data of a link.

[0127] In some embodiments, the second abnormality degree may be positively correlated with the abnormal data ratio of the monitoring data. When the monitoring device detects that the value of any data type of a certain monitoring data exceeds the corresponding normal value range, the monitoring data is regarded as abnormal data, and the normal value range can be preset by the technician. Exemplarily, the industrial Internet of Things management platform can determine the second abnormality degree according to the following formula (2):

[0128] m=c n(2)

[0129] Wherein, m represents the second abnormality, c is the conversion coefficient, and n represents the abnormal data ratio of the monitoring data. The conversion coefficient is a coefficient to make the comparison between the first abnormality and the second abnormality more realistic, and can be set according to actual conditions.

[0130] In some embodiments, the industrial Internet of Things management platform can determine the quality assessment algorithm in a variety of ways based on the second abnormality. For example, the industrial Internet of Things management platform can determine the quality assessment algorithm by querying the third preset table based on the value range of the second abnormality. Among them, the third preset table is a table that corresponds different value ranges of the second abnormality to different quality assessment algorithms. Exemplarily, the third preset table can be expressed as: {second abnormality 1%~20%, quality assessment algorithm A; second abnormality 21%~40%, quality assessment algorithm B;...}. Among them, the higher the second abnormality, the more complex the corresponding quality assessment algorithm can be set, and the more complex the quality assessment algorithm can be reflected in the more types of collected data, the higher the granularity of collected data, and the higher the algorithm level.

[0131] In some embodiments of the present specification, the quality assessment algorithm is determined by the link monitoring level, so that the assessment process is more targeted and accurate, which helps to quickly identify the key links in the production line, thereby improving the efficiency of product quality assessment.

[0132] In some embodiments, the industrial Internet of Things management platform can also adjust the quality assessment algorithm of one or more links based on the resource allocation of the server to determine the target assessment algorithm.

[0133] Since different links correspond to quality assessment algorithms of different complexity, the server resources called when using quality assessment algorithms of different complexity are also different. For example, suppose there are 20 servers to support product quality assessment at each link. In the case of 10 links in a production line, if all 10 links use the most complex quality assessment algorithm, the load on hardware resources is too large, which may cause mutual resource occupation, etc., affecting quality assessment. Therefore, when determining the quality assessment algorithms for multiple links, server resources can be allocated in combination with the load capacity of the server.

[0134] For more information about the server, see Figure 1 and its related description.

[0135] The target evaluation algorithm refers to the quality evaluation algorithm corresponding to one or more links that are finally determined.

[0136] In some embodiments, the IIoT management platform can judge the resource allocation of the server in a variety of ways. For example, the IIoT management platform can call the resource usage of the server through the IIoT service platform, and judge that the server resource allocation is sufficient in response to the resource usage not exceeding the usage threshold. The usage threshold can be preset by the technician based on experience.

[0137] In some embodiments, the industrial Internet of Things management platform can adjust the quality assessment algorithm of one or more links according to the resource allocation of the server and determine the target assessment algorithm. For example, the industrial Internet of Things management platform can pre-set the link priority for multiple links of the current production line. The smaller the link priority value, the more important the link; in response to insufficient resource allocation of the server, the link priority is sorted from large to small, and the quality assessment algorithm level is lowered in turn; each time the quality assessment algorithm level of a link is lowered, the server resource allocation is judged until the server resource allocation is sufficient, and the adjustment of the quality assessment algorithm is stopped, and the quality assessment algorithm of one or more links finally obtained is determined as the target assessment algorithm.

[0138] The link priority can be set by a person skilled in the art according to the current production line. For example, the link priority value of the rough processing stage can be large, and for another example, the link priority value of the surface treatment stage can be relatively large.

[0139] For more information about the algorithm levels of the quality assessment algorithm, please refer to the relevant description above.

[0140] In some embodiments of the present specification, by considering the resource allocation of the server, the quality assessment algorithm is flexibly adjusted to ensure that the assessment process can fully utilize the server resources, avoid waste or shortage of resources, and thus improve the assessment efficiency.

[0141] Equipment type refers to the type of quality inspection equipment.

[0142] The equipment operation parameters 446 refer to the parameters followed by the quality inspection equipment when working. For example, the equipment operation parameters may include data collection frequency, etc.

[0143] In some embodiments, the industrial Internet of Things management platform can determine the equipment type and equipment operating parameters of the quality inspection equipment in a variety of ways based on the quality assessment algorithm. For example, the industrial Internet of Things management platform can determine the equipment type that can collect data of the corresponding data type based on the data type collected by the quality assessment algorithm; and determine the data collection frequency of the corresponding quality inspection equipment based on the granularity of the collected data.

[0144] The initial product characteristics 450 refer to the unprocessed raw data collected by the quality inspection equipment. In some embodiments, the industrial Internet of Things management platform can perform quality inspection on the products of the link based on the quality inspection parameters through the quality inspection equipment of the industrial Internet of Things perception control platform to obtain the initial product characteristics of the link.

[0145] In some embodiments, the industrial Internet of Things management platform can process the initial product features in a variety of ways to obtain product quality features. For example, the industrial Internet of Things management platform can process the initial product quality features based on the algorithm type of the quality assessment algorithm and use the processed data as the product quality features. For example, the algorithm type can include a data cleaning algorithm for removing duplicate data.

[0146] For more information on product quality characteristics, see Figure 2 and its related description.

[0147] In some embodiments of the present specification, by comprehensively considering the link monitoring level, quality assessment algorithm, type of quality inspection equipment and its operating parameters, it has a high degree of flexibility and scalability, and can flexibly adjust the quality inspection parameters and quality assessment algorithm according to different production links and product requirements to adapt to product quality assessment requirements in different scenarios, thereby achieving accurate determination of quality inspection parameters and improving the accuracy and reliability of product quality inspection.

[0148] In some embodiments, the quality update data includes update parameters and update content. Figure 4 As shown, the industrial Internet of Things management platform can determine the update parameter 432 based on the difference characteristics between the first abnormality degree 351 and the second abnormality degree 430; determine the update content 470 based on the link characteristics 310 and the product quality characteristics 460; and update the update content 470 of the link to the target knowledge base 330 based on the update parameter 432.

[0149] The difference characteristic between the first abnormality degree and the second abnormality degree refers to the difference between the two.

[0150] Update parameters 432 refer to parameters followed when updating the target database. For example, update parameters may include update frequency, update detail level, etc. In some embodiments, update parameters may be positively correlated with difference characteristics, that is, the larger the difference characteristics, the higher the update frequency and the more detailed the update detail level. The update detail level may include brief, general, relatively detailed, detailed, etc. The more detailed the update detail level, the more data amount is updated at one time.

[0151] Update content 470 refers to the link content that needs to be updated to the target knowledge base. For example, the update content may include at least one of link characteristics and product quality characteristics.

[0152] In some embodiments, the industrial Internet of Things management platform can determine the update content of the target link in a variety of ways based on link characteristics and product quality characteristics, and update the update content to the target knowledge base based on the update parameters. For example, the industrial Internet of Things management platform can determine the similarity threshold based on the update detail level in the update parameters through the fourth preset table, determine the data that needs to be merged based on the link characteristics, product quality characteristics and the similarity threshold, and then determine the update content of the target link, and then update the update content to the target knowledge base according to the update frequency in the update parameters. Among them, the fourth preset table can be constructed by a person skilled in the art based on experience, and can include a corresponding relationship between the update detail level and the similarity threshold, and the higher the update detail level, the higher the similarity threshold.

[0153] Exemplarily, the industrial Internet of Things management platform determines the similarity threshold through the fourth preset table, forms a vector based on the link characteristics and product quality characteristics of the target link obtained this time, matches it in the target knowledge base, and averages the link characteristics and product quality characteristics with similarities exceeding the similarity threshold with the data obtained this time, and merges them into a new data as the update content of the target link, and updates the update content to the target knowledge base according to the update frequency. As an example only, when the update detail level is detailed, the similarity threshold is the highest. At this time, it may not be possible to match the link characteristics and product quality characteristics with similarities exceeding the similarity threshold. The industrial Internet of Things management platform can use all the data obtained this time as the update content. Among them, the similarity can be calculated based on cosine distance, Euclidean distance, etc.

[0154] In some embodiments of the present specification, by determining update parameters based on the difference characteristics of the first abnormality degree and the second abnormality degree, the update process is made more scientific and can accurately capture the target links with special circumstances, thereby updating the target knowledge base or quality database in a targeted manner and avoiding invalid or redundant update operations.

[0155] Some embodiments of the present specification also provide a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer runs the above-mentioned product quality assessment method.

[0156] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0157] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0158] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification.

[0159] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0160] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining the digits. Although the numerical domains and parameters used to confirm the breadth of the range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0161] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification is hereby incorporated by reference in its entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0162] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A product quality assessment method based on industrial Internet of Things, characterized in that: The method is executed by an industrial Internet of Things management platform, and the method includes: Obtain one or more links of the current production line based on the industrial Internet of Things perception control platform; For each of the one or more links: Based on the link characteristics of the link, determining the first abnormality degree and link criticality of the link through the quality database, the link characteristics are the processing characteristics included in the link, and the quality database is a database containing relevant data of multiple links of the historical production line; Determining the link monitoring level based on the link criticality and the first abnormality; Based on the link monitoring level, quality inspection parameters are determined, and the quality inspection parameters are issued to the quality inspection equipment of the industrial Internet of Things perception control platform, where the quality inspection parameters at least include a quality assessment algorithm, the equipment type of the quality inspection equipment, and equipment operation parameters; Controlling the quality inspection equipment to perform quality inspection on the products in the link according to the quality inspection parameters to obtain the product quality characteristics of the link; Based on the link characteristics and the product quality characteristics, quality update data is generated to update the quality database.

2. The product quality assessment method according to claim 1, characterized in that: The quality database includes a plurality of knowledge bases; the first abnormality degree and the criticality of the link are determined through the quality database based on the link characteristics of the link, including: Based on the link characteristics, searching in the quality database to determine a target knowledge base; The first abnormality degree and the link criticality are determined through the target knowledge base.

3. The product quality assessment method according to claim 1, characterized in that: The determining of quality detection parameters based on the link monitoring level includes: Determining the quality assessment algorithm based on the link monitoring level; Based on the quality assessment algorithm, determining the device type and the device operating parameters; The controlling the quality inspection device to perform quality inspection on the product of the link according to the quality inspection parameter to obtain the product quality characteristics of the link includes: Controlling the quality inspection equipment to perform quality inspection on the products of the link according to the quality inspection parameters to obtain initial product characteristics of the link; Based on the quality assessment algorithm, the initial product characteristics are processed to obtain the product quality characteristics.

4. The product quality assessment method according to claim 3, characterized in that: The determining of the quality assessment algorithm based on the link monitoring level includes: Based on the monitoring level of the link, obtain monitoring data; Based on the monitoring data, determining a second abnormality degree of the link; Based on the second abnormality degree, the quality assessment algorithm is determined.

5. The product quality assessment method according to claim 4, characterized in that: The quality update data includes update parameters and update content; the generating of the quality update data based on the link characteristics and the product quality characteristics to update the quality database includes: determining the update parameter based on the difference characteristics between the first abnormality degree and the second abnormality degree; Determining the update content based on the link characteristics and the product quality characteristics; Based on the update parameters, the update content of the link is updated to the target knowledge base.

6. A product quality assessment system based on industrial Internet of Things, characterized in that: The system includes an industrial Internet of Things user platform, an industrial Internet of Things service platform, an industrial Internet of Things management platform, an industrial Internet of Things sensor network platform, and an industrial Internet of Things perception control platform; the industrial Internet of Things management platform is configured as follows: Acquire one or more links of the current production line based on the industrial Internet of Things perception control platform; For each of the one or more links: Based on the link characteristics of the link, determining the first abnormality degree and link criticality of the link through the quality database, the link characteristics are the processing characteristics included in the link, and the quality database is a database containing relevant data of multiple links of the historical production line; Determining the link monitoring level based on the first abnormality and the link criticality; Based on the link monitoring level, quality inspection parameters are determined, and the quality inspection parameters are issued to the quality inspection equipment of the industrial Internet of Things perception control platform, where the quality inspection parameters at least include a quality assessment algorithm, the equipment type of the quality inspection equipment, and equipment operation parameters; Controlling the quality inspection equipment to perform quality inspection on the products in the link according to the quality inspection parameters to obtain the product quality characteristics of the link; Based on the link characteristics and the product quality characteristics, quality update data is generated to update the quality database.

7. The product quality assessment system according to claim 6, characterized in that: The quality database includes multiple knowledge bases; the industrial Internet of Things management platform is further configured as follows: Based on the link characteristics, searching in the quality database to determine a target knowledge base; The first abnormality degree and the link criticality are determined through the target knowledge base.

8. The product quality assessment system according to claim 6, characterized in that: The industrial Internet of Things management platform is further configured to: Determining the quality assessment algorithm based on the link monitoring level; Based on the quality assessment algorithm, determining the device type and the device operating parameters; Controlling the quality inspection equipment to perform quality inspection on the products of the link according to the quality inspection parameters to obtain initial product characteristics of the link; Based on the quality assessment algorithm, the initial product characteristics are processed to obtain the product quality characteristics.

9. The product quality assessment system according to claim 8, characterized in that: The industrial Internet of Things management platform is further configured to: Based on the monitoring level of the link, obtain monitoring data; Based on the monitoring data, determining a second abnormality degree of the link; Based on the second abnormality degree, the quality assessment algorithm is determined.

10. The product quality assessment system according to claim 9, characterized in that: The quality update data includes update parameters and update content; the industrial Internet of Things management platform is further configured as follows: determining the update parameter based on the difference characteristics between the first abnormality degree and the second abnormality degree; Determining the update content based on the link characteristics and the product quality characteristics; Based on the update parameters, the update content of the link is updated to the target knowledge base.

Images