Digital quality management method and system, device, storage medium

Abstract

The disclosure provides a digital quality management method and system, equipment and storage medium, and belongs to the technical field of digital quality management. The method comprises the following steps: determining target quality relationships between each target data based on the correlation between a plurality of target data, wherein the plurality of target data are a plurality of entity information data in target product supply chain data; constructing a knowledge graph based on the plurality of target data and the target quality relationships between each target data; and analyzing and managing the target product quality based on the knowledge graph. The digital quality management method and system, equipment and storage medium provided by the disclosure can quickly locate the root cause of the problem when a quality problem occurs.

Description

TECHNICAL FIELD

[0001] The present disclosure belongs to the technical field of digital quality management, and more particularly to a digital quality management method and system, device, and storage medium. BACKGROUND

[0002] In today's competitive market environment, product quality is crucial to the survival and development of enterprises. Traditional quality management methods have many limitations, such as insufficient integration and analysis capabilities for target product supply chain data, and difficulty in comprehensively and accurately identifying quality influencing factors.

[0003] Existing technologies often fail to deeply explore the potential connections between various entity information data in the target product supply chain, making it difficult to quickly locate the root cause of the problem when quality problems occur, delaying the solution opportunity. SUMMARY

[0004] The purpose of the present disclosure is to provide a digital quality management method and system, device, and storage medium to quickly locate the root cause of the problem when quality problems occur.

[0005] In a first aspect, the present disclosure provides a digital quality management method, comprising:

[0006] determining a target quality relationship between each target data based on the correlation between a plurality of target data, the plurality of target data being a plurality of entity information data in target product supply chain data;

[0007] constructing a knowledge graph based on the plurality of target data and the target quality relationship between each target data;

[0008] analyzing and managing the quality of the target product based on the knowledge graph.

[0009] In a second aspect, the present disclosure provides a digital quality management system, comprising:

[0010] a quality relationship determination module configured to determine a target quality relationship between each target data based on the correlation between a plurality of target data, the plurality of target data being a plurality of entity information data in target product supply chain data;

[0011] a knowledge graph module configured to construct a knowledge graph based on the plurality of target data and the target quality relationship between each target data;

[0012] a quality management module configured to analyze and manage the quality of the target product based on the knowledge graph.

[0013] In a third aspect, the present disclosure provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the steps of the digital quality management method when running the computer program.

[0014] In a fourth aspect, the present disclosure provides a computer readable storage medium, which stores a computer program, and the computer program implements the steps of the digital quality management method when executed by a processor.

[0015] The digital quality management method and system, device, and storage medium provided by the embodiments of the present disclosure have the following beneficial effects: the embodiments of the present disclosure determine the target quality relationship by analyzing the correlation between the multiple entity information data in the target product supply chain, can accurately mine the key factors affecting product quality, and provide a clear direction for quality management. Then, the knowledge graph is constructed based on the multiple entity information data and the target quality relationship, the entities and relationships are displayed in an intuitive graphical structure, and the complex quality correlation is clearly presented. Finally, the target product quality is analyzed and managed by using the knowledge graph, when a quality problem occurs, the problem root can be quickly located by tracing and diagnosing along the relationship edge, so that measures can be taken to solve the problem in time, improve the product quality, and optimize the target product supply chain quality management process. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0017] Figure 1 A flowchart of a digital quality management method provided by an embodiment of the present disclosure is shown in FIG. 1.

[0018] Figure 2 A structural block diagram of a digital quality management system provided by an embodiment of the present disclosure is shown in FIG. 2.

[0019] Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure is shown in FIG. 3. DETAILED DESCRIPTION

[0020] In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular architectures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present disclosure. However, it will be apparent to those skilled in the art that the present disclosure can be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present disclosure with unnecessary detail.

[0021] For the purpose of the present disclosure, the technical solutions and advantages will be clearer, specific embodiments will be described below with reference to the accompanying drawings.

[0022] Reference is made to Figure 1 , Figure 1 The flowchart of the digital quality management method provided by an embodiment of the present disclosure is shown in the figure. The method comprises the following steps.

[0023] S101: Determine the target quality relationship between each target data based on the correlation between the plurality of target data. The plurality of target data is a plurality of entity information data in the target product supply chain data.

[0024] In this embodiment, the target data is derived from a plurality of entity information data in the target product supply chain data. The target product supply chain involves links from raw material procurement, production and manufacturing, product transportation to sales, etc. Each link generates a large amount of entity information data, such as suppliers, production equipment, product batches, etc.

[0025] In this embodiment, if the plurality of target data belongs to numerical data, the Pearson correlation coefficient or the Spearman correlation coefficient can be used to calculate the correlation between the plurality of target data; if the plurality of target data belongs to category data, the chi-square test method can be used to calculate the correlation between the plurality of target data.

[0026] Through correlation analysis, the correlation value between each target data can be obtained, which reflects the closeness of the association between the data. For example, if it is found that the purity of raw materials is highly correlated with the stability of products, it can be determined that the purity of raw materials is an important factor affecting product quality.

[0027] In this embodiment, the target quality relationship is determined according to the calculated correlation value and in combination with a preset correlation threshold. The correlation threshold can be empirically set according to the needs of the actual scene.

[0028] When the correlation value is greater than the threshold, there is a target quality relationship between the corresponding two target data. The target quality relationship can be a causal relationship, an association relationship, etc. For example, there can be a causal relationship between the content of a certain component of raw materials and a certain performance of products, and there can be an association relationship between the running state of production equipment and the qualified rate of products.

[0029] S102: constructing a knowledge graph based on the plurality of target data and the target quality relationship between each target data.

[0030] In this embodiment, the knowledge graph represents a semantic network, and the knowledge graph can display entities and their relationships in a graphical structure.

[0031] In this embodiment, the entities corresponding to the plurality of target data are extracted.

[0032] For example, the supplier, product, production equipment, etc. are taken as node entities in the knowledge graph.

[0033] The target quality relationship is mapped to the knowledge graph as an edge connecting each entity node, thereby constructing the knowledge graph.

[0034] For example, if it is determined that the quality of raw materials provided by the raw material supplier affects the product quality, an edge representing this quality influence relationship is established between the supplier entity node and the product entity node.

[0035] S103: analyzing and managing the target product quality based on the knowledge graph.

[0036] In this embodiment, when the target product has a quality problem, the knowledge graph is used for diagnosis.

[0037] Starting from the target product entity, the relationship edge in the knowledge graph can be queried and reasoned to find out the factors that may cause the quality problem.

[0038] For example, if a performance indicator of the product is unqualified, the knowledge graph can be used to trace back to the entities such as raw materials, production equipment, production process, etc. used, analyze the attributes of these entities and their relationships, and find out the possible problem root.

[0039] From the above, it can be concluded that the embodiment can accurately mine the key factors affecting the product quality by analyzing the correlation between the plurality of entity information data in the target product supply chain to determine the target quality relationship, and provide a clear direction for quality management. Then, the knowledge graph is constructed based on the plurality of entity information data and the target quality relationship to display the entities and relationships in a direct graphical structure, and clearly present the complex quality correlation. Finally, the knowledge graph is used to analyze and manage the target product quality, when a quality problem occurs, the problem root can be quickly located by tracing and diagnosing along the relationship edge, so that measures can be taken to solve the problem in time, improve the product quality, and optimize the target product supply chain quality management process.

[0040] In one embodiment of the present disclosure, the target quality relationship between each target data is determined based on the correlation between the plurality of target data, comprising:

[0041] calculate the correlation between the plurality of target data based on distribution characteristics of the plurality of target data, to obtain a correlation value between the plurality of target data;

[0042] In response to the correlation value being greater than a preset correlation threshold, determine two target data corresponding to the correlation value;

[0043] determine a corresponding target quality relationship based on the types of the two target data.

[0044] In this embodiment, the target product supply chain covers multiple links from raw material procurement to sales, and the data types are diverse, including numerical types such as raw material purity and production equipment temperature, and category types such as supplier name and product batch. Directly based on a fixed calculation method will cause analysis deviation due to abnormal distribution of data or special circumstances,

[0045] Therefore, in this embodiment, for a plurality of target data, instead of directly applying conventional methods, the correlation is calculated according to their distribution characteristics.

[0046] For example, for numerical data, if its distribution presents obvious non-normal characteristics, Pearson correlation coefficient cannot be simply used, and a method more suitable for non-normal distribution data such as Spearman correlation coefficient needs to be selected to accurately measure the correlation between variables; for category data, a suitable statistical method such as chi-square test needs to be reasonably selected according to its distribution to ensure that the calculated correlation can truly reflect the internal relationship between data, to obtain a correlation value between the plurality of target data.

[0047] In this embodiment, the preset correlation threshold is a preset correlation threshold, which is used as a standard for judging whether there is a quality relationship between two target data.

[0048] The calculated correlation value is compared with the preset correlation threshold. When the correlation value is greater than the preset correlation threshold, the two target data corresponding to the correlation value are determined. This means that the degree of association between the two data reaches a certain level.

[0049] After determining that there is a quality relationship between the two target data, the specific target quality relationship is determined according to the types of the two target data.

[0050] For example, if two target data are the content of a certain component of raw materials and a certain performance of a product, and their correlation value is greater than the threshold, it indicates that there is a causal relationship between them, that is, the change of the content of the raw material component can cause the change of the product performance; if the two target data are the running state of the production equipment and the qualified rate of the product, and the correlation is significant, it indicates that there is an association between them, that is, there is a certain relationship between the running state of the production equipment and the qualified rate of the product.

[0051] From the above, it can be concluded that the embodiment selects an adaptive correlation calculation method by dynamically analyzing the data distribution characteristics, effectively avoiding the analysis deviation of fixed algorithms in abnormal data scenarios, and improving the accuracy of quality relationship identification. Combined with the threshold determination mechanism, it can quickly filter out key influencing factors with high correlation degree, providing a clear direction for quality management.

[0052] In an embodiment of the present disclosure, the correlation between the plurality of target data is calculated based on the distribution characteristics of the plurality of target data, and the correlation value between the plurality of target data is obtained, including:

[0053] The correlation between the plurality of target data is calculated based on the first formula;

[0054] The first formula is:

[0055]

[0056] Wherein, represents the correlation value between the target data and the target data , represents the mean value of the target data , represents the mean value of the target data , represents the business weight factor corresponding to the target data at the same time, represents the distribution characteristic adjustment factor corresponding to the target data at the same time, represents the time series dynamic factor corresponding to the target data at the same time, represents the number of target data.

[0057] In the embodiment, it is assumed that we have two target data sequences and , and their time series are .

[0058] Consider the influence of the distribution characteristics of the data on the correlation. Different distribution characteristics may lead to inaccurate results of traditional correlation calculation methods, so the data needs to be adjusted.

[0059] First, calculate the skewness coefficients of the data sequences X and Y , and the kurtosis coefficients , .

[0060] For each data point i, the distribution characteristic adjustment factor is represented as:

[0061]

[0062] distribution feature adjustment factor The correlation deviation caused by the distribution difference can be adjusted, so that the correlation calculation under different distribution features is more reasonable. Therefore, the correlation calculation under different distribution features can be realized by only one calculation formula.

[0063] The target product supply chain data has time series characteristics, and the recent data has more reference value for the current quality status and correlation. Therefore, different weights need to be given to the data at different time points. Time series dynamic factor can be expressed as:

[0064]

[0065] wherein, is the maximum timestamp in the time series T, is a decay coefficient, which can be adjusted according to actual conditions to control the speed of time decay.

[0066] In the target product supply chain scenario, different data points have different influences on product quality. Business weight factor is used to reflect the relative importance of the i th data point in the entire business process. For example, in automobile manufacturing, the weight of engine-related data is higher than that of interior color data, because the engine has a more critical impact on the quality of the automobile. By giving corresponding weights to different data points, the contribution of important data to the correlation can be highlighted, so that the calculation result is more in line with the actual business logic.

[0067] From the above, it can be concluded that by introducing the business weight factor, the distribution feature adjustment factor and the time series dynamic factor, the accuracy and adaptability of the correlation calculation are improved. The business weight factor highlights the influence of key data, the distribution feature adjustment factor eliminates the deviation caused by the difference in data distribution, and the time series dynamic factor strengthens the timeliness of recent data. The combination of the three makes the correlation value more suitable for the application of target product supply chain quality management scenarios.

[0068] In an embodiment of the present disclosure, it further comprises:

[0069] A distributed storage network is constructed based on the supply chain data, wherein the network nodes in the distributed storage network are data in the supply chain data.

[0070] The corresponding data on the network nodes is encrypted to obtain supply chain ciphertext data.

[0071] In this embodiment, each data in the supply chain data is regarded as a network node of the distributed storage network. In the target product supply chain scenario, the supply chain data covers various links from raw material procurement information, equipment parameters in the production process, quality detection data to product sales records, etc. Each data becomes a node in the network, forming the basic architecture of the distributed storage network.

[0072] The supply chain data is stored in multiple nodes, which can improve the storage reliability of the data and avoid the risk of data loss due to failure of a single storage center. At the same time, distributed storage is beneficial to improve the access efficiency of data, different nodes can process data requests in parallel, reducing the burden of a single node, especially when processing a large amount of supply chain data, it can effectively improve the overall performance of the system.

[0073] For the data on each network node, an encryption algorithm is used for encryption operation. The encryption algorithm can be converted into ciphertext form. The encryption algorithm includes a symmetric encryption algorithm (such as AES) or an asymmetric encryption algorithm (such as RSA), and a suitable algorithm can be selected according to the sensitivity of the data and the actual demand.

[0074] The encrypted data is stored in the form of ciphertext on the network node, even if the data is stolen or the storage node is attacked during transmission, the attacker cannot obtain the real content of the data without the corresponding decryption key. The security of the supply chain data is enhanced, and the sensitive information of the enterprise, such as raw material procurement price, production process parameter, etc. is protected, to prevent economic loss or competitive disadvantage of the enterprise due to data leakage.

[0075] From the above, it can be concluded that the present embodiment provides a higher level of security guarantee for supply chain data from the aspects of storage architecture and data protection by constructing a distributed storage network and encrypting node data, ensuring the security and reliability of data in the target product supply chain management.

[0076] In an embodiment of the present disclosure, the target product quality is analyzed and managed based on the knowledge graph, including:

[0077] Based on the change rate of the target product quality data, the detection result of the target product quality is determined, and the detection result includes qualified and unqualified;

[0078] In response to the detection result of the target product quality being unqualified, a target path related to the target product quality is determined from the knowledge graph;

[0079] Based on the target path, the root cause affecting the target product quality is determined.

[0080] In this embodiment, quality data of the target product is continuously collected throughout its entire life cycle, including production, transportation, sales, etc. These data can be physical properties (such as strength, hardness), chemical indicators (such as ingredient content), appearance characteristics (such as dimensional accuracy), etc. By comparing the quality data at different time points, the change rate of the quality data is calculated to reflect the dynamic changes of product quality over time.

[0081] The qualified threshold of the quality data change rate can be set in advance according to the quality standards of the product, historical data, and industry experience. Compare the calculated quality data change rate of the target product with the qualified threshold. If the change rate is less than the threshold, it means that the product quality is relatively stable, and the detection result is determined to be qualified; otherwise, if the change rate is greater than or equal to the threshold, it indicates that the product quality may be abnormal, and the detection result is determined to be unqualified.

[0082] In this embodiment, when the quality detection result of the target product is unqualified, the target product is taken as the starting node in the knowledge graph. The knowledge graph contains various entities in the target product supply chain and their quality relationships. Search along the relationship chain in the knowledge graph to find a series of paths composed of entities and relationships related to the quality of the target product. These paths record various factors that affect product quality and their interactions throughout the process from raw material procurement to final production.

[0083] For example, starting from the target product, the raw materials used are found through the "use" relationship, and the suppliers are found through the "supply" relationship between the raw materials and the suppliers. The relevant production equipment can also be found through the "production" relationship between the product and the production equipment, etc.

[0084] In this embodiment, the target path found is analyzed in detail, and each entity and relationship on the path is fully investigated. The attributes and states of each entity, as well as their interactions on product quality, are analyzed.

[0085] For example, check whether the quality indicators of the raw materials meet the requirements, whether the operating parameters of the production equipment are normal, whether the personnel's operation is standardized, whether the production process is reasonable, etc.

[0086] Through comprehensive evaluation and analysis of each factor on the target path, the root cause of affecting the quality of the target product is determined. The root cause can include raw material quality problems, production equipment failures, personnel operation errors, unreasonable production processes, etc. After determining the root cause, the enterprise can take targeted improvement measures, such as replacing raw material suppliers, repairing or upgrading production equipment, strengthening personnel training, optimizing production processes, etc., to improve product quality.

[0087] From the above, by combining the product quality data change rate and the associated information of the knowledge graph, a complete product quality analysis and management system is formed, which can quickly and accurately locate the root cause of quality problems, and provide strong support for enterprises to improve product quality and production efficiency.

[0088] In one embodiment of the present disclosure, the detection result of the target product quality is determined based on the change rate of the target product quality data, and the detection result includes qualified and unqualified, including:

[0089] In response to the change rate of the target product quality data being less than the change rate threshold, the target product quality is marked as qualified;

[0090] In response to the change rate of the target product quality data being greater than or equal to the change rate threshold, the target product quality is marked as unqualified.

[0091] In this embodiment, target product quality data at different time points can be collected, and the change rate of quality data between adjacent time points can be calculated. It is assumed that at time The value of a certain quality indicator of the product is At time The value of the indicator becomes The change rate r of the quality indicator in the time period can be expressed as:

[0092]

[0093] The change rate reflects the degree of change of the product quality indicator within a certain time.

[0094] In this embodiment, the change rate threshold can be determined based on product characteristics, historical data, etc., and the change rate threshold is a key standard for judging whether the product quality is qualified or not.

[0095] When the calculated change rate of the target product quality data is less than the pre-set change rate threshold, it indicates that the product quality indicator fluctuates within the normal range, and the product quality is relatively stable. At this time, the target product quality is marked as qualified, which means that the product in the current production or use process meets the expected requirements and can meet the relevant quality standards and use requirements.

[0096] If the change rate of the target product quality data is greater than or equal to the change rate threshold, it indicates that the change of the product quality indicator exceeds the normal range, and there is quality instability or potential quality problems. The target product quality is marked as unqualified. The enterprise needs to further check and analyze the product, find out the reason for the abnormal change rate of the quality data, and take corresponding improvement measures.

[0097] From the above, the embodiment based on the quality data change rate and threshold comparison method provides an objective judgment standard for product quality detection, which helps enterprises to discover product quality problems in time and ensures the stability and reliability of product quality.

[0098] In one embodiment of the present disclosure, further comprising:

[0099] determining the change rate threshold based on a second formula;

[0100] The second formula is:

[0101]

[0102] wherein, represents the change rate threshold, represents the production equipment state coefficient, represents the production batch coefficient, represents the time decay coefficient, represents the historical average change rate.

[0103] In the embodiment, the historical average change rate is an average change rate calculated based on a large amount of historical product quality data, reflecting the typical fluctuation of product quality indicators under normal production and use conditions. Collect the quality indicator data of n historical samples, for each sample i, calculate the change rate of its quality indicator in a certain time period , and then take the average value:

[0104] In the embodiment, the running state and performance of the production equipment directly affect the product quality. Equipment aging, failure or improper maintenance, etc. may cause the change rate of product quality indicators to increase. Therefore, the production equipment state coefficient is considered in the second formula. According to the running parameters (such as temperature, pressure, speed, etc.) and maintenance records of the equipment, the health state score of the equipment is predicted by a machine learning model (such as a neural network) .

[0105] For example: real-time acquisition of various parameters in the running process of the equipment, such as temperature, pressure, speed, vibration frequency, etc.; collection of maintenance records of the equipment, including maintenance time, maintenance content, replacement of parts, etc. Clean and standardize the data, normalize the data to the range of 0-1. Input the processed data into the trained convolutional neural network model to predict the health state score of the equipment , the value range is 0-1, the lower the score, the worse the equipment state. Then:

[0106]

[0107] wherein, is an adjustable coefficient for controlling the degree of influence of the equipment state on the threshold.

[0108] In this embodiment, there may be process adjustments, personnel operation differences and other factors between different production batches, which can cause the product quality index change rate to be different. Therefore, the production batch coefficient is considered in the second formula. The product quality data of each production batch is analyzed, and the dispersion degree (such as variance ) of the product quality index within the batch is calculated and compared with the average dispersion degree of all batches.

[0109]

[0110] wherein, is an adjustable coefficient for controlling the degree of influence of the production batch difference on the threshold.

[0111] In this embodiment, over time, the reference value of early historical data on the current product quality change gradually decreases. An exponential decay function or the like can be used to calculate the time decay coefficient according to the interval between the data collection time and the current time, which decreases as the time interval increases.

[0112] In this embodiment, the historical average change rate is calculated according to the historical product quality data. Then, the current production equipment state is evaluated to obtain , the quality dispersion of the current production batch is analyzed to obtain , and the data timeliness is considered to determine . Finally, the four parameters are substituted into the second formula to calculate the change rate threshold. The actual change rate of the target product quality data is compared with the threshold, and if it is less than the threshold, the product quality is marked as qualified, and if it is greater than or equal to the threshold, it is marked as unqualified, thereby realizing effective detection and management of product quality.

[0113] Figure 2 Corresponding to the digital quality management method of the above embodiment, Figure 2 is a structural block diagram of a digital quality management system provided by an embodiment of the present disclosure. For ease of illustration, only parts related to the embodiments of the present disclosure are shown. Referring to , the digital quality management system 20 includes a quality relationship determination module 21, a knowledge graph module 22, and a quality management module 23.

[0114] The quality relationship determining module 21 is configured to determine a target quality relationship between each target data based on a correlation between a plurality of target data, the plurality of target data being a plurality of entity information data in the target product supply chain data.

[0115] The knowledge graph module 22 is configured to construct a knowledge graph based on the plurality of target data and the target quality relationship between each target data.

[0116] The quality management module 23 is configured to analyze and manage the target product quality based on the knowledge graph.

[0117] In an embodiment of the present disclosure, the quality relationship determining module 21 is specifically configured to:

[0118] calculate the correlation between the plurality of target data based on a distribution feature of the plurality of target data, to obtain a correlation value between the plurality of target data;

[0119] determine two target data corresponding to the correlation value in response to the correlation value being greater than a preset correlation threshold value;

[0120] determine a corresponding target quality relationship based on a type of the two target data.

[0121] In an embodiment of the present disclosure, the quality relationship determining module 21 is specifically further configured to:

[0122] calculate the correlation between the plurality of target data based on a first formula;

[0123] The first formula is:

[0124]

[0125] wherein, denotes a correlation value between target data and target data , denotes a mean value in target data , denotes a mean value in target data , denotes a business weight factor corresponding to the target data at the same moment, denotes a distribution feature adjustment factor corresponding to the target data at the same moment, denotes a time sequence dynamic factor corresponding to the target data at the same moment, denotes a number of target data. In an embodiment of the present disclosure, the digital quality management system 20 further comprises an encryption module specifically configured to:

[0126] In an embodiment of the present disclosure, the digital quality management system 20 further comprises an encryption module specifically configured to:

[0127] ​​A distributed storage network is constructed based on the supply chain data, wherein a network node in the distributed storage network is data in the supply chain data;

[0128] The corresponding data on the network node is encrypted to obtain supply chain ciphertext data.

[0129] In an embodiment of the present disclosure, the quality management module 23 is specifically configured to:

[0130] determine a detection result of the target product quality based on a change rate of the target product quality data, the detection result including pass and fail;

[0131] In response to the detection result of the target product quality being fail, determine a target path related to the target product quality from the knowledge graph;

[0132] determine a root cause affecting the target product quality based on the target path.

[0133] In an embodiment of the present disclosure, the quality management module 23 is specifically further configured to:

[0134] In response to the change rate of the target product quality data being less than a change rate threshold, mark the target product quality as pass;

[0135] In response to the change rate of the target product quality data being greater than or equal to the change rate threshold, mark the target product quality as fail.

[0136] In an embodiment of the present disclosure, the quality management module 23 is specifically further configured to:

[0137] determine the change rate threshold based on a second formula;

[0138] The second formula is:

[0139]

[0140] wherein, denotes the change rate threshold, denotes a production equipment state coefficient, denotes a production batch coefficient, denotes a time attenuation coefficient, denotes a historical average change rate.

[0141] Referring to Figure 3 , Figure 3 is a schematic block diagram of an electronic device provided by an embodiment of the present disclosure. As shown in Figure 3The electronic device 300 in the embodiment shown can include one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processor 301, the input device 302, the output device 303, and the memory 304 can communicate with each other through a communication bus 305. The memory 304 is configured to store a computer program including program instructions. The processor 301 is configured to execute the program instructions stored in the memory 304. The processor 301 is configured to invoke the program instructions to perform the functions of the modules / units in the above-described system embodiments, for example Figure 2 The functions of the modules 21 to 23 shown.

[0142] It should be understood that, in the embodiments of the present disclosure, the processor 301 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0143] The input device 302 can include a touchpad, a fingerprint collection sensor (for collecting fingerprint information and direction information of a fingerprint of a user), a microphone, etc., and the output device 303 can include a display (LCD, etc.), a speaker, etc.

[0144] The memory 304 can include read-only memory and random access memory, and provide instructions and data for the processor 301. A portion of the memory 304 can also include non-volatile random access memory. For example, the memory 304 can also store device type information.

[0145] In specific implementations, the processor 301, the input device 302, and the output device 303 described in the embodiments of the present disclosure can perform the implementation manners described in the first and second embodiments of the digital quality management method provided by the embodiments of the present disclosure, and can also perform the implementation manners of the electronic device described in the embodiments of the present disclosure, which will not be described here.

[0146] In another embodiment of the present disclosure, a computer readable storage medium is provided, which stores a computer program. The computer program includes program instructions, which, when executed by a processor, implement all or part of the processes of the above-mentioned embodiment methods. The computer program can also instruct related hardware to complete the above-mentioned processes. The computer program can be stored in a computer readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or some intermediate form. The computer readable medium can include any entity or system capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0147] The computer readable storage medium can be an internal storage unit of the electronic device, such as a hard disk or a memory of the electronic device. The computer readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the computer readable storage medium can include both the internal storage unit and the external storage device of the electronic device. The computer readable storage medium is used to store the computer program and other programs and data required by the electronic device. The computer readable storage medium can also be used to temporarily store data that has been output or will be output.

[0148] Those skilled in the art can appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be realized by electronic hardware, computer software or a combination of both. In order to clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been described in general terms in the above description. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present disclosure.

[0149] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic device and the units described above can refer to the corresponding processes in the above-mentioned method embodiments, which will not be described here.

[0150] In several embodiments provided in the present application, it should be understood that the disclosed electronic device and method can be implemented in other manners. For example, the embodiments of the system described above are merely illustrative. For example, the division of the units is only a logical function division. There can be another division manner for the actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed coupling or direct coupling or communication connection between the units can be indirect coupling or communication connection through some interfaces, or can be in electrical, mechanical or other forms.

[0151] The units described as separated components can or can not be physically separated, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purposes of the embodiments of the present disclosure.

[0152] In addition, each functional unit in the various embodiments of the present disclosure can be integrated in one processing unit, or each unit can exist physically as a separate unit, or two or more units can be integrated in one unit. The integrated unit can be implemented in the form of hardware, or in the form of a software functional unit.

[0153] The above is merely specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto, and any skilled person in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present disclosure, and these modifications or replacements should be covered in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

1. A method of digital quality management, characterized by, Comprise: Correlation between multiple target data is calculated based on distribution characteristics of multiple target data, and correlation value between multiple target data is obtained; Wherein, the correlation between multiple target data is calculated based on the first formula; The first formula is: wherein, represents a correlation value between target data and target data , represents a mean value in target data , represents a mean value in target data , represents a service weight factor corresponding to target data at the same time, represents a distribution characteristic adjustment factor corresponding to target data at the same time, represents a time series dynamic factor corresponding to target data at the same time, represents a number of target data; For each data point i, the distribution characteristic adjustment factor is represented as: wherein, the skewness coefficient of the target data , the skewness coefficient of the target data , the kurtosis coefficient of the target data , the kurtosis coefficient of the target data ; Time series dynamic factors is represented as: wherein, is the maximum timestamp in the time series T, is the decay coefficient; In response to the correlation value being greater than a preset correlation threshold, two target data corresponding to the correlation value are determined; Based on the type of the two target data, the corresponding target quality relationship is determined, and the multiple target data are multiple entity information data in target product supply chain data; Based on the multiple target data and the target quality relationship between each target data, a knowledge graph is constructed; Based on the knowledge graph, target product quality is analyzed and managed.

2. The digital quality management method of claim 1, wherein, Also include: Based on the supply chain data, a distributed storage network is constructed, wherein the network nodes in the distributed storage network are data in the supply chain data; The corresponding data on the network node is encrypted to obtain supply chain ciphertext data.

3. The digital quality management method of claim 1, wherein, The knowledge graph is used to analyze and manage the target product quality, including: Based on the change rate of target product quality data, the detection result of the target product quality is determined, and the detection result includes qualified and unqualified; In response to the detection result of the target product quality being unqualified, a target path related to the target product quality is determined from the knowledge graph; Based on the target path, the root cause affecting the target product quality is determined.

4. The digital quality management method of claim 3, wherein, The change rate of target product quality data is used to determine the detection result of the target product quality, and the detection result includes qualified and unqualified, including: In response to the change rate of target product quality data being less than a change rate threshold, the target product quality is marked as qualified; In response to the change rate of target product quality data being greater than or equal to the change rate threshold, the target product quality is marked as unqualified.

5. The digital quality management method of claim 4, wherein, Also include: The change rate threshold is determined based on a second formula; The second formula is: wherein, denotes a rate of change threshold, denotes a production equipment status coefficient, denotes a production batch coefficient, denotes a time decay coefficient, denotes a historical average rate of change.

6. A digital quality management system characterized by, Comprise: The quality relationship determination module is used to Correlation between multiple target data is calculated based on distribution characteristics of multiple target data, and correlation value between multiple target data is obtained; Wherein, the correlation between multiple target data is calculated based on the first formula; The first formula is: wherein, represents a correlation value between target data and target data , represents a mean value in target data , represents a mean value in target data , represents a service weight factor corresponding to target data at the same time, represents a distribution characteristic adjustment factor corresponding to target data at the same time, represents a time series dynamic factor corresponding to target data at the same time, represents a number of target data; For each data point i, the distribution characteristic adjustment factor is represented as: wherein, the skewness coefficient of the target data the skewness coefficient of the target data the kurtosis coefficient of the target data the kurtosis coefficient of the target data the kurtosis coefficient of the target data​​​ Time series dynamic factors is represented as: wherein, is the maximum timestamp in the time series T, is a decay coefficient; In response to the correlation value being greater than a preset correlation threshold, two target data corresponding to the correlation value are determined; Based on the type of the two target data, the corresponding target quality relationship is determined, and the multiple target data are multiple entity information data in target product supply chain data; The knowledge graph module is used to construct a knowledge graph based on the multiple target data and the target quality relationship between each target data; The quality management module is used to analyze and manage the target product quality based on the knowledge graph.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, The processor executes the computer program to realize the steps of the method of any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, the computer-readable storage medium comprising: The computer program is executed by the processor to realize the steps of the method of any one of claims 1 to 5.

Images