Product quality management method based on block chain and industry chain information full-process tracing

Abstract

The invention relates to the technical field of product quality evaluation, in particular to a product quality management method based on block chain and industry chain information full-process tracing. The method comprises the steps of obtaining basic information of a to-be-evaluated product based on an industrial chain information full-process tracing information platform, and determining a category of the to-be-evaluated product based on the basic information of the to-be-evaluated product; obtaining a non-appearance quality evaluation index corresponding to the category of the to-be-evaluated product based on the category of the to-be-evaluated product, and obtaining a non-appearance quality index of the to-be-evaluated product based on the basic information of the to-be-evaluated product and the non-appearance quality evaluation index, and obtaining an appearance image of the to-be-evaluated product in a chain on the block chain, the appearance image of the to-be-evaluated product and the appearance image of the standard sample product are compared and analyzed to obtain the graph comparison result, the appearance quality of the product can be evaluated based on the graph comparison result, and the product quality management efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of product quality assessment, and specifically to a product quality management method based on blockchain and full-process tracing of industrial chain information. Background Art

[0002] In today's increasingly competitive market environment, product quality management has become the key for enterprises to gain market competitive advantages. However, traditional product quality management methods have many shortcomings and are difficult to meet the needs of the current market. The existing technology has the following problems:

[0003] Unreliable traceability mechanism: Traditional product traceability methods rely on paper documents or centralized databases, which are easily tampered with or lost, resulting in unreliable traceability information. Once a product has quality problems, it is difficult to accurately trace it back to the source, causing serious reputation and economic losses to the company;

[0004] Inefficient quality certification and management: The traditional quality certification and management process is cumbersome and inefficient, and cannot meet the current market demand for rapid response and efficient management.

[0005] Therefore, there is an urgent need for a product quality management method based on blockchain and full-process traceability of industrial chain information to solve the above problems. Summary of the invention

[0006] The purpose of this invention is to provide a product quality management method based on blockchain and full-process traceability of industrial chain information: to solve the technical problem that traditional product quality certification methods often rely on paper documents or centralized databases, which are easily affected by human factors, making it difficult to ensure the accuracy and reliability of product quality test results.

[0007] The purpose of the present invention can be achieved through the following technical solutions: The product quality management method based on blockchain and full-process traceability of industrial chain information is applied to the full-process traceability information platform of industrial chain information. The method includes: Obtain basic information of the product to be evaluated based on the full-process traceability information platform of the industrial chain, and determine the category to which the product to be evaluated belongs based on the basic information of the product to be evaluated; Based on the category of the product to be evaluated, obtain the non-appearance quality evaluation index corresponding to the category of the product to be evaluated, and obtain the non-appearance quality index of the product to be evaluated based on the basic information of the product to be evaluated and the non-appearance quality evaluation index analysis; Obtain the appearance image of the product to be evaluated on the blockchain, perform comparative analysis based on the appearance image of the product to be evaluated and the appearance image of the standard sample product, and obtain image comparison results; The quality assessment results of the product to be assessed are generated based on the non-appearance quality index and the image comparison results.

[0008] Furthermore, it is characterized in that determining the category to which the product to be evaluated belongs based on the basic information of the product to be evaluated specifically includes the following process: The basic information of the product to be evaluated is used as sample points, and the sample points are combined into a data set ,in, represents a d-dimensional vector, ; n represents the number of sample points; Computational Dataset Any two sample points , The Euclidean distance ,in, ; Get the distance matrix and set the initial density radius threshold ; According to the distance matrix and Get the density of each sample point : ; According to the density of each sample Calculate the distance between the sample and the sample with greater density than itself ; The distance obtained and density Multiply to get a new variable , Follows a normal distribution and will fall within the interval Points outside of are called center points, where is the mean of the normal distribution, is the standard deviation of the normal distribution; perform k-means clustering on the center points: Step 1: Select the initial center point, each center point represents the mean of a category; Step 2: Calculate the distance between other samples and the center point, and assign samples according to the closest distance; Step 3: Recalculate the mean of each category; Step 4: Use the mean of step 3 as the center point and repeat step 1 until the minimum sum of squared errors is obtained. The category corresponding to the minimum sum of squared errors is recorded as the category to which the product to be evaluated belongs.

[0009] Furthermore, it is characterized in that obtaining the non-appearance quality index of the product to be evaluated based on the basic information of the product to be evaluated and the non-appearance quality evaluation index analysis specifically includes the following process: Based on the basic information of the product to be evaluated, the number of raw material types and the corresponding content of each raw material type in the product to be evaluated are obtained; based on the non-appearance quality evaluation index, the number of raw material types that should be in the product to be evaluated and the minimum content of each raw material type are obtained; the difference A between the number of raw material types in the product to be evaluated and the number of raw material types that should be in the product to be evaluated is calculated; and the number B of raw material types whose content corresponding to each raw material type in the product to be evaluated does not exceed the minimum content of each raw material type is calculated; Based on the basic information of the product to be evaluated, the number of processing steps of the product to be evaluated is obtained; based on the non-appearance quality evaluation index, the number of processing steps that the product to be evaluated should have is obtained; and the ratio C of the number of processing steps to the number of processing steps that should have is calculated; Based on the basic information of the product to be evaluated, the transportation time and storage time of the product to be evaluated are obtained; based on the non-appearance quality evaluation index, the maximum transportation time and maximum storage time of the product to be evaluated are obtained; the sum of the transportation time and the storage time is calculated; the sum of the maximum transportation time and the maximum storage time is calculated; and the ratio D of the two sums is calculated; Substitute the difference A, the number of types B, the proportion C and the ratio D into the calculation formula of the non-appearance quality index of the product to be evaluated to calculate the non-appearance quality index PGZ of the product to be evaluated. The calculation formula is as follows: ; in, , are weight coefficients, The value of is 2.72.

[0010] Furthermore, it is characterized in that before obtaining the appearance image of the product to be evaluated on the blockchain, the method also includes the following process: Step 1: Obtain the original color image of the product to be evaluated on the blockchain, convert the original color image to Lab space, retain the color component a and b channel images, and perform grayscale enhancement on the L channel image representing the brightness of the image; Step 2: Decompose the L channel image using an edge-preserving guided filter to obtain a structure image T and a texture image t; Step 3: Use a Gaussian filter to estimate the uneven illumination background of the structural image T and decompose the structural image into a background image S and an edge image E; Step 4: synthesize the edge image E and the texture image t into a new L1 channel image; Step 5, performing contrast enhancement processing on the L channel image to obtain an L2 channel image; Step six, the L2 and new L1 channel images and the color component a and b channel images are synthesized into a final enhanced image, which is recorded as the appearance image of the product to be evaluated.

[0011] Furthermore, it is characterized in that the contrast enhancement process is performed on the L channel image to obtain the L2 channel image using a linear enhancement method, a nonlinear enhancement method and a histogram enhancement method.

[0012] Furthermore, it is characterized in that, based on the appearance image of the product to be evaluated and the appearance image of the standard sample product, a comparative analysis is performed to obtain the image comparison result, which specifically includes the following process: The appearance image of the product to be evaluated and the appearance image of the standard sample product are respectively input into the graph neural network encoder to obtain the node vector representation of the appearance image of the product to be evaluated. Vector representation of the graph , node vector representation of the appearance image of the standard sample product Vector representation of the graph ; Calculate the node mutual information value L between the appearance image of the product to be evaluated and the appearance image of the standard sample product: ; in, The number of nodes representing the appearance image of the product to be evaluated, The number of nodes representing the appearance images of standard sample products, Represents the node vector representation Vector representation of the graph The number of elements in the adjacency matrix of Represents the node vector representation Vector representation of the graph The number of elements in the adjacency matrix of ; The node mutual information value L is recorded as the graph comparison result.

[0013] Furthermore, it is characterized in that generating the quality assessment result of the product to be assessed based on the non-appearance quality index and the image comparison result specifically includes the following process: Loading the non-appearance quality index threshold, determining whether the non-appearance quality index of the product to be evaluated exceeds the non-appearance quality index threshold, if so, the non-appearance quality of the product to be evaluated is unqualified, if not, the non-appearance quality of the product to be evaluated is qualified; The node mutual information value threshold is loaded to determine whether the node mutual information value exceeds the node mutual information value threshold. If so, the appearance quality of the product to be evaluated is qualified; if not, the appearance quality of the product to be evaluated is unqualified.

[0014] Furthermore, it is characterized in that, before performing comparative analysis based on the appearance image of the product to be evaluated and the appearance image of the standard sample product, the method further comprises preprocessing the appearance image of the product to be evaluated.

[0015] Compared with the existing solutions, the present invention achieves the following beneficial effects: The present invention obtains basic information of a product to be evaluated based on an information platform for tracing information throughout the entire industrial chain, determines the category to which the product to be evaluated belongs based on the basic information of the product to be evaluated, obtains a non-appearance quality evaluation index corresponding to the category to which the product to be evaluated belongs based on the category to which the product to be evaluated belongs, obtains a non-appearance quality index of the product to be evaluated based on the basic information of the product to be evaluated and the non-appearance quality evaluation index, and accurately evaluates the non-appearance quality of the product based on the non-appearance quality index, thereby ensuring the reliability of the traceability mechanism and further improving the accuracy of product quality evaluation.

[0016] Furthermore, the appearance image of the product to be evaluated on the blockchain is obtained, and a comparative analysis is performed based on the appearance image of the product to be evaluated and the appearance image of the standard sample product to obtain a picture comparison result. The quality of the product's appearance can be evaluated based on the picture comparison result, thereby improving the efficiency of product quality management. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0018] Figure 1 This is a workflow diagram of a product quality management method based on blockchain and full-process traceability of industrial chain information in an embodiment of the present invention; Figure 2 This is another workflow diagram of a product quality management method based on blockchain and full-process traceability of industrial chain information according to an embodiment of the present invention; Figure 3 This is a workflow diagram of another product quality management method based on blockchain and full-process traceability of industrial chain information in an embodiment of the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] In addition, the described features, structures or characteristics may be combined in one or more example embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the example embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, steps, etc. may be adopted. In other cases, well-known structures, methods, implementations or operations are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0021] This embodiment provides an information platform for full-process traceability of industrial chain information. The information platform for full-process traceability of industrial chain information is a comprehensive platform that integrates modern information technology, Internet of Things technology, and blockchain technology. The platform aims to achieve full-process information traceability of products from raw material procurement, production and processing, logistics distribution to sales terminals, ensure the authenticity and integrity of product information, and improve the efficiency and transparency of product quality management.

[0022] This embodiment provides a product quality management method based on blockchain and full-process traceability of industrial chain information. Figure 1 This is a workflow diagram of a product quality management method based on blockchain and full-process traceability of industrial chain information in an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps: Step S101: obtaining basic information of the product to be evaluated based on the full-process traceability information platform of the industrial chain information, and determining the category to which the product to be evaluated belongs based on the basic information of the product to be evaluated; Step S102: obtaining non-appearance quality evaluation indicators corresponding to the category of the product to be evaluated based on the category of the product to be evaluated, and obtaining a non-appearance quality index of the product to be evaluated based on the basic information of the product to be evaluated and the non-appearance quality evaluation indicators; Step S103: Obtain the appearance image of the product to be evaluated on the blockchain, and perform a comparative analysis based on the appearance image of the product to be evaluated and the appearance image of the standard sample product to obtain an image comparison result; Step S104: generating a quality assessment result of the product to be assessed based on the non-appearance quality index and the image comparison result.

[0023] In summary, the present invention obtains the basic information of the product to be evaluated based on the full-process traceability information platform of the industrial chain information, determines the category of the product to be evaluated based on the basic information of the product to be evaluated; obtains the non-appearance quality evaluation index corresponding to the category of the product to be evaluated based on the category of the product to be evaluated, and obtains the non-appearance quality index of the product to be evaluated based on the basic information of the product to be evaluated and the non-appearance quality evaluation index, and accurately evaluates the non-appearance quality of the product based on the non-appearance quality index, thereby ensuring the reliability of the traceability mechanism and further improving the accuracy of product quality evaluation.

[0024] Furthermore, the appearance image of the product to be evaluated on the blockchain is obtained, and a comparative analysis is performed based on the appearance image of the product to be evaluated and the appearance image of the standard sample product to obtain a picture comparison result. The quality of the product's appearance can be evaluated based on the picture comparison result, thereby improving the efficiency of product quality management.

[0025] In some embodiments, determining the category to which the product to be evaluated belongs based on the basic information of the product to be evaluated specifically includes the following process: The basic information of the product to be evaluated is used as sample points, and the sample points are combined into a data set ,in, represents a d-dimensional vector, ; n represents the number of sample points; Computational Dataset Any two sample points , The Euclidean distance ,in, ; Get the distance matrix and set the initial density radius threshold ; According to the distance matrix and Get the density of each sample point : ; According to the density of each sample Calculate the distance between the sample and the sample with greater density than itself ; The distance obtained and density Multiply to get a new variable , Follows a normal distribution and will fall within the interval Points outside of are called center points, where is the mean of the normal distribution, is the standard deviation of the normal distribution; perform k-means clustering on the center points: Step 1: Select the initial center point, each center point represents the mean of a category; Step 2: Calculate the distance between other samples and the center point, and assign samples according to the closest distance; Step 3: Recalculate the mean of each category; Step 4: Use the mean of step 3 as the center point and repeat step 1 until the minimum sum of squared errors is obtained. The category corresponding to the minimum sum of squared errors is recorded as the category to which the product to be evaluated belongs.

[0026] In some embodiments, Figure 2 This is another workflow diagram of a product quality management method based on blockchain and full-process traceability of industrial chain information according to an embodiment of the present invention. Figure 2 As shown, obtaining the non-appearance quality index of the product to be evaluated based on the basic information of the product to be evaluated and the non-appearance quality evaluation index analysis specifically includes the following steps: Step S201: based on the basic information of the product to be evaluated, the number of raw material types and the corresponding content of each raw material type in the product to be evaluated are obtained; based on the non-appearance quality evaluation index, the number of raw material types that should be in the product to be evaluated and the minimum content of each raw material type are obtained; the difference A between the number of raw material types in the product to be evaluated and the number of raw material types that should be in the product to be evaluated are calculated; and the number B of raw material types whose content corresponding to each raw material type in the product to be evaluated does not exceed the minimum content of each raw material type is calculated; Step S202: obtaining the number of processing steps of the product to be evaluated based on the basic information of the product to be evaluated, obtaining the number of processing steps that the product to be evaluated should have based on the non-appearance quality evaluation index, and calculating the ratio C of the number of processing steps to the number of processing steps that should have; Step S203: based on the basic information of the product to be evaluated, the transportation time and storage time of the product to be evaluated are obtained; based on the non-appearance quality evaluation index, the maximum transportation time and the maximum storage time of the product to be evaluated are obtained; the sum of the transportation time and the storage time is calculated; the sum of the maximum transportation time and the maximum storage time is calculated; and the ratio D of the two sums is calculated; Step S204: Substitute the difference A, the number of types B, the proportion C and the ratio D into the calculation formula of the non-appearance quality index of the product to be evaluated to calculate the non-appearance quality index PGZ of the product to be evaluated. The calculation formula is as follows: ; in, , are weight coefficients, The value of is 2.72.

[0027] In some embodiments, Figure 3 This is another workflow diagram of a product quality management method based on blockchain and full-process traceability of industrial chain information according to an embodiment of the present invention. Figure 3 As shown, before obtaining the appearance image of the product to be evaluated on the blockchain, the method also includes the following process: Step 1: Obtain the original color image of the product to be evaluated on the blockchain, convert the original color image to Lab space, retain the color component a and b channel images, and perform grayscale enhancement on the L channel image representing the brightness of the image; Step 2: Decompose the L channel image using an edge-preserving guided filter to obtain a structure image T and a texture image t; Step 3: Use a Gaussian filter to estimate the uneven illumination background of the structural image T and decompose the structural image into a background image S and an edge image E; Step 4: synthesize the edge image E and the texture image t into a new L1 channel image; Step 5, performing contrast enhancement processing on the L channel image to obtain an L2 channel image; Step six, the L2 and new L1 channel images and the color component a and b channel images are synthesized into a final enhanced image, which is recorded as the appearance image of the product to be evaluated.

[0028] Furthermore, the L channel image is subjected to contrast enhancement processing to obtain the L2 channel image using a linear enhancement method, a nonlinear enhancement method and a histogram enhancement method.

[0029] In some embodiments, performing comparative analysis based on the appearance image of the product to be evaluated and the appearance image of the standard sample product to obtain the image comparison result specifically includes the following process: The appearance image of the product to be evaluated and the appearance image of the standard sample product are respectively input into the graph neural network encoder to obtain the node vector representation of the appearance image of the product to be evaluated. Vector representation of the graph , node vector representation of the appearance image of the standard sample product Vector representation of the graph ; Calculate the node mutual information value L between the appearance image of the product to be evaluated and the appearance image of the standard sample product: ; in, The number of nodes representing the appearance image of the product to be evaluated, The number of nodes representing the appearance images of standard sample products, Represents the node vector representation Vector representation of the graph The number of elements in the adjacency matrix of Represents the node vector representation Vector representation of the graph The number of elements in the adjacency matrix of ; The node mutual information value L is recorded as the graph comparison result.

[0030] In some embodiments, generating a quality assessment result of the product to be assessed based on the non-appearance quality index and the image comparison result specifically includes the following process: Loading the non-appearance quality index threshold, determining whether the non-appearance quality index of the product to be evaluated exceeds the non-appearance quality index threshold, if so, the non-appearance quality of the product to be evaluated is unqualified, if not, the non-appearance quality of the product to be evaluated is qualified; The node mutual information value threshold is loaded to determine whether the node mutual information value exceeds the node mutual information value threshold. If so, the appearance quality of the product to be evaluated is qualified; if not, the appearance quality of the product to be evaluated is unqualified.

[0031] It is worth noting that, before performing comparative analysis based on the appearance image of the product to be evaluated and the appearance image of the standard sample product, the method also includes preprocessing the appearance image of the product to be evaluated. The preprocessing includes image registration, the purpose of which is to calibrate the images at different times to the same coordinate system, thereby facilitating the computer to compare and analyze the images at different times.

[0032] Methods used: including transformation method, projection method, rotation method, affine transformation method and perspective transformation method, etc. Image registration is widely used in medical image processing, remote sensing image processing and other fields.

[0033] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0034] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0035] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0036] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only some logical function divisions. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0037] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0038] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A product quality management method based on blockchain and full-process traceability of industrial chain information, characterized in that: Applied to the full-process traceability information platform of the industrial chain, the methods include: Obtain basic information of the product to be evaluated based on the full-process traceability information platform of the industrial chain, and determine the category to which the product to be evaluated belongs based on the basic information of the product to be evaluated; Based on the category of the product to be evaluated, obtain the non-appearance quality evaluation index corresponding to the category of the product to be evaluated, and obtain the non-appearance quality index of the product to be evaluated based on the basic information of the product to be evaluated and the non-appearance quality evaluation index analysis; Obtain the appearance image of the product to be evaluated on the blockchain, perform comparative analysis based on the appearance image of the product to be evaluated and the appearance image of the standard sample product, and obtain image comparison results; The quality assessment results of the product to be assessed are generated based on the non-appearance quality index and the image comparison results.

2. The product quality management method based on blockchain and full-process traceability of industrial chain information according to claim 1 is characterized in that: Determine the specific category of the product to be evaluated based on the basic information of the product to be evaluated The process includes: The basic information of the product to be evaluated is used as sample points, and the sample points are combined into a data set ,in, represents a d-dimensional vector, ; n represents the number of sample points; Computational Dataset Any two sample points , The Euclidean distance ,in, ; Get the distance matrix and set the initial density radius threshold ; According to the distance matrix and Get the density of each sample point : ； According to the density of each sample Calculate the distance between the sample and the sample with greater density than itself ; The distance obtained and density Multiply to get a new variable , Follows a normal distribution and will fall within the interval Points outside of are called center points, where is the mean of the normal distribution, is the standard deviation of the normal distribution; perform k-means clustering on the center points: Step 1: Select the initial center point, each center point represents the mean of a category; Step 2: Calculate the distance between other samples and the center point, and assign samples according to the closest distance; Step 3: Recalculate the mean of each category; Step 4: Use the mean of step 3 as the center point and repeat step 1 until the minimum sum of squared errors is obtained. The category corresponding to the minimum sum of squared errors is recorded as the category to which the product to be evaluated belongs.

3. The product quality management method based on blockchain and full-process traceability of industrial chain information according to claim 1 is characterized in that: The non-appearance quality index of the product to be evaluated is obtained based on the basic information and non-appearance quality evaluation index of the product to be evaluated, which specifically includes the following process: Based on the basic information of the product to be evaluated, the number of raw material types and the corresponding content of each raw material type in the product to be evaluated are obtained; based on the non-appearance quality evaluation index, the number of raw material types that should be in the product to be evaluated and the minimum content of each raw material type are obtained; the difference A between the number of raw material types in the product to be evaluated and the number of raw material types that should be in the product to be evaluated is calculated; and the number B of raw material types whose content corresponding to each raw material type in the product to be evaluated does not exceed the minimum content of each raw material type is calculated; Based on the basic information of the product to be evaluated, the number of processing steps of the product to be evaluated is obtained; based on the non-appearance quality evaluation index, the number of processing steps that the product to be evaluated should have is obtained; and the ratio C of the number of processing steps to the number of processing steps that should have is calculated; Based on the basic information of the product to be evaluated, the transportation time and storage time of the product to be evaluated are obtained; based on the non-appearance quality evaluation index, the maximum transportation time and maximum storage time of the product to be evaluated are obtained; the sum of the transportation time and the storage time is calculated; the sum of the maximum transportation time and the maximum storage time is calculated; and the ratio D of the two sums is calculated; Substitute the difference A, the number of types B, the proportion C and the ratio D into the calculation formula of the non-appearance quality index of the product to be evaluated to calculate the non-appearance quality index PGZ of the product to be evaluated. The calculation formula is as follows: ； in, , are weight coefficients, The value of is 2.

72.

4. The product quality management method based on blockchain and full-process traceability of industrial chain information according to claim 1 is characterized in that: Before obtaining the appearance image of the product to be evaluated on the blockchain, the method further includes the following process: Step 1: Obtain the original color image of the product to be evaluated on the blockchain, convert the original color image to Lab space, retain the color component a and b channel images, and perform grayscale enhancement on the L channel image representing the brightness of the image; Step 2: Decompose the L channel image using an edge-preserving guided filter to obtain a structure image T and a texture image t; Step 3: Use a Gaussian filter to estimate the uneven illumination background of the structural image T and decompose the structural image into a background image S and an edge image E; Step 4: synthesize the edge image E and the texture image t into a new L1 channel image; Step 5, performing contrast enhancement processing on the L channel image to obtain an L2 channel image; Step six, the L2 and new L1 channel images and the color component a and b channel images are synthesized into a final enhanced image, which is recorded as the appearance image of the product to be evaluated.

5. The product quality management method based on blockchain and full-process traceability of industrial chain information according to claim 4 is characterized in that: The L channel image is contrast enhanced and the L2 channel image is obtained by linear enhancement, nonlinear enhancement and histogram enhancement.

6. The product quality management method based on blockchain and full-process traceability of industrial chain information according to claim 1 is characterized in that: Based on the comparative analysis of the appearance image of the product to be evaluated and the appearance image of the standard sample product, the specific comparison results are obtained. The process includes: The appearance image of the product to be evaluated and the appearance image of the standard sample product are respectively input into the graph neural network encoder to obtain the node vector representation of the appearance image of the product to be evaluated. Vector representation of the graph , node vector representation of the appearance image of the standard sample product Vector representation of the graph ; Calculate the node mutual information value L between the appearance image of the product to be evaluated and the appearance image of the standard sample product: ； in, The number of nodes representing the appearance image of the product to be evaluated, The number of nodes representing the appearance images of standard sample products, Represents the node vector representation Vector representation of the graph The number of elements in the adjacency matrix of Represents the node vector representation Vector representation of the graph The number of elements in the adjacency matrix of ; The node mutual information value L is recorded as the graph comparison result.

7. The product quality management method based on blockchain and full-process traceability of industrial chain information according to claim 1 is characterized in that: Generating the quality assessment results of the product to be assessed based on the non-appearance quality index and the image comparison results specifically includes the following processes: Loading the non-appearance quality index threshold, determining whether the non-appearance quality index of the product to be evaluated exceeds the non-appearance quality index threshold, if so, the non-appearance quality of the product to be evaluated is unqualified, if not, the non-appearance quality of the product to be evaluated is qualified; The node mutual information value threshold is loaded to determine whether the node mutual information value exceeds the node mutual information value threshold. If so, the appearance quality of the product to be evaluated is qualified; if not, the appearance quality of the product to be evaluated is unqualified.

8. The product quality management method based on blockchain and full-process traceability of industrial chain information according to claim 1 is characterized in that: Before performing comparative analysis based on the appearance image of the product to be evaluated and the appearance image of the standard sample product, the method further includes preprocessing the appearance image of the product to be evaluated.

Images