A quality management method, system and equipment for highland barley red yeast rice extract

Abstract

The present application discloses a quality management method, system and equipment for highland barley red yeast rice extract, including: sampling and testing the target extract according to a preset sampling rule to obtain the test process data and test results; judging whether the test result is credible according to the test process data and the test result; when the test result is credible, storing the test process data and the test result in a database that cannot be tampered with; obtaining the target product serial number of the target product corresponding to the target extract, generating a target URL according to the target product serial number, and the page pointed to by the target URL is configured to display the test process data and test results in the database; generating a target QR code label according to the target URL, and matching the target QR code label with the target product. The present application solves the problem that the prior art lacks an effective quality management method, and there is fraud in actual testing, which easily leads to accidents.

Description

Technical Field

[0001] The present application relates to the field of production quality management, and in particular to a method, system and equipment for quality management of highland barley red yeast rice extract. Background Art

[0002] Highland barley has the characteristics of high protein, high fiber, high vitamins, low fat and low sugar. It also contains oleic acid, linoleic acid, linolenic acid, etc. which have the effect of lowering cholesterol, 18 kinds of amino acids and various trace elements. It itself has rich nutrition and various pharmacological effects.

[0003] Highland barley red yeast rice is made from highland barley as the main raw material and fermented by Monascus purpureus. Monascus has a long history of medicinal and edible use in my country, and has the effects of lowering blood pressure and lipids, promoting blood circulation and removing blood stasis, and promoting digestion and strengthening the spleen. Highland barley red yeast rice, which is made from highland barley as the raw material and fermented by Monascus purpureus with high lovastatin production, can not only effectively lower cholesterol, but also the natural lovastatin produced after fermentation can play the role of lowering blood pressure and lipids, promoting blood circulation and removing blood stasis, while not causing damage to the liver and kidneys of the human body.

[0004] Since highland barley red yeast rice extract is often taken directly, the quality and safety of related products are of high quality. However, there is currently a lack of effective quality management methods, and fake highland barley may exist in actual testing, which can easily lead to accidents. Summary of the invention

[0005] The invention provides a method, system and equipment for quality management of highland barley red yeast rice extract, which at least solves the problem that the prior art lacks an effective quality management method and that fake highland barley exists in actual detection, thus easily leading to accidents.

[0006] The present invention provides a method for quality management of highland barley red yeast rice extract, comprising the following steps:

[0007] Sampling and testing the target extract according to the preset sampling rules to obtain the testing process data and test results;

[0008] Judging whether the detection result is credible according to the detection process data and the detection result;

[0009] When the detection result is credible, the detection process data and the detection result are stored in a tamper-proof database;

[0010] Obtaining a target product serial number of a target product corresponding to the target extract, generating a target URL according to the target product serial number, wherein the page pointed to by the target URL is configured to display the detection process data and the detection result in the database;

[0011] A target two-dimensional code tag is generated according to the target URL, and the target two-dimensional code tag is matched with the target product.

[0012] Optionally, the step of performing sampling detection on the target extract according to a preset sampling rule to obtain detection process data and detection results includes:

[0013] Selecting an extract to be tested from the target extracts according to a preset sampling rule, and acquiring an image of the extract to be tested as a first image;

[0014] Obtaining the content of effective components and harmful components of the extract to be tested as the test result by liquid chromatography, obtaining an image of a solution of the extract to be tested as a second image, and obtaining a liquid chromatogram of the extract to be tested as a third image;

[0015] The first image, the second image and the third image belong to the detection process data.

[0016] Optionally, the step of judging whether the detection result is credible based on the detection process data and the detection result includes:

[0017] According to the first image, the second image and the third image, determining whether the first image, the second image and the third image match by using a matching analysis model;

[0018] When the first image, the second image and the third image match, determining whether the third image matches the detection result;

[0019] When the third image matches the detection result, the detection result is credible.

[0020] Optionally, the step of determining whether the first image, the second image and the third image match by using a matching analysis model according to the first image, the second image and the third image includes:

[0021] Establishing an initial matching analysis model, wherein the matching analysis model is configured to take at least an image of the extract to be tested and an image of the extract solution to be tested as input parameters, or at least an image of the extract solution to be tested and a liquid chromatogram of the extract to be tested as input parameters, or at least an image of the extract to be tested and a liquid chromatogram of the extract to be tested as input parameters, and whether there is a match as an output parameter;

[0022] Acquire a group of images marked as matching to train and verify the initial matching analysis model;

[0023] Using the verified initial matching analysis model as the matching analysis model;

[0024] Inputting the first image and the second image as a group of images, the second image and the third image as a group of images, and the first image and the third image as a group of images into the matching analysis model;

[0025] According to the result output by the matching analysis model, it is determined whether the first image, the second image and the third image match.

[0026] Optionally, the step of determining whether the third image matches the detection result includes:

[0027] According to the third image and the image detection model, obtaining the effective component content and the harmful component content corresponding to the third image;

[0028] According to the effective component content and the harmful component content corresponding to the third image and the detection result, determining whether the third image matches the detection result;

[0029] When the error between the effective component content and the harmful component content corresponding to the third image and the detection result is not greater than a preset first threshold, the third image matches the detection result.

[0030] Optionally, after the step of obtaining the target product serial number of the target product corresponding to the target extract and generating the target URL according to the target product serial number, the step further includes:

[0031] Acquire a target factory image of the target product when it leaves the factory, and store the target factory image in a database;

[0032] The page pointed to by the target URL is also configured to display the target factory image in the database.

[0033] Optionally, also include:

[0034] Recording access records of the page pointed to by the target URL, wherein the access records include the account type and the number of accesses;

[0035] When the number of visits to a preset account type exceeds a preset number, a preset prompt message is displayed on the page pointed to by the target URL.

[0036] In another aspect, a quality management system for highland barley red yeast rice extract includes a quality management platform and a detection platform;

[0037] The detection platform is configured as follows:

[0038] Sampling and testing the target extract according to the preset sampling rules to obtain the testing process data and test results;

[0039] Judging whether the detection result is credible according to the detection process data and the detection result;

[0040] When the test result is credible, the test process data and the test result are sent to the quality management platform;

[0041] The quality management platform is configured to:

[0042] Receiving the detection process data and the detection result sent by the detection platform, and storing the detection process data and the detection result in a tamper-proof database;

[0043] Obtaining a target product serial number of a target product corresponding to the target extract, generating a target URL according to the target product serial number, wherein the page pointed to by the target URL is configured to display the detection process data and the detection result in the database;

[0044] A target two-dimensional code tag is generated according to the target URL, and the target two-dimensional code tag is matched with the target product.

[0045] Optionally, the detection platform includes an experimental detection module, an image acquisition module, a simulation detection module and a judgment module;

[0046] The experimental detection module is configured as follows:

[0047] Obtaining the content of effective components and harmful components of the extract to be tested as the test result by liquid chromatography;

[0048] The image acquisition module is configured as follows:

[0049] Acquiring an image of the extract to be tested as a first image;

[0050] Acquire an image of a solution of the extract to be tested as a second image;

[0051] Acquiring a liquid chromatogram of the extract to be tested as a third image;

[0052] The analog detection module is configured as follows:

[0053] According to the third image, obtaining the effective component content and the harmful component content corresponding to the third image;

[0054] The determination module is configured as follows:

[0055] determining whether the first image, the second image, and the third image match;

[0056] Determining whether the third image matches the detection result;

[0057] Whether the detection result is credible is determined based on whether the first image, the second image and the third image match and whether the third image matches the detection result.

[0058] On the other hand, a device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement any of the above methods.

[0059] On the other hand, a computer-readable storage medium is provided. The device includes a memory and a processor. The memory stores a computer program. The processor executes the computer program to implement any of the above methods.

[0060] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0061] The invention discloses a method, system and equipment for quality management of highland barley red yeast rice extract, comprising: sampling and testing a target extract according to a preset sampling rule to obtain detection process data and detection results; judging whether the detection result is credible according to the detection process data and the detection result; when the detection result is credible, storing the detection process data and the detection result in a database that cannot be tampered with; obtaining a target product serial number of a target product corresponding to the target extract, generating a target URL according to the target product serial number, and the page pointed to by the target URL is configured to display the detection process data and the detection result in the database; generating a target QR code label according to the target URL, and matching the target QR code label with the target product. The invention solves the problem that the prior art lacks an effective quality management method, and there is fraud in actual detection, which easily leads to accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the specific implementation of the present application or the technical solution in the prior art, the following is a brief introduction to the drawings required for the specific implementation or the prior art description. In all drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, each element or part is not necessarily drawn according to the actual scale.

[0063] Figure 1 The figure is a flow chart of the quality management method of highland barley red yeast rice extract in this application;

[0064] Figure 2 This is a schematic diagram of the structure of a computer device in this application.

[0065] Markings in the figure: 101 - processor, 102 - communication bus, 103 - network interface, 104 - user interface, 105 - memory.

[0066] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0067] In order to enable those skilled in the art to better understand the scheme of the present disclosure, the technical scheme in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present disclosure.

[0068] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0069] Example 1

[0070] like Figure 1 As shown, a quality management method for highland barley red yeast rice extract comprises the following steps:

[0071] S1. Sampling and testing the target extract according to the preset sampling rules to obtain the testing process data and test results.

[0072] Optionally, the preset sampling rule may be a sampling method such as simple random sampling, systematic sampling or cluster sampling.

[0073] Optionally, when cluster sampling is used, clustering is done based on test weight.

[0074] Optionally, the test process data and test results are obtained according to the method described in QB / T 2847-2007.

[0075] S2. Determine whether the test results are credible based on the test process data and test results.

[0076] Optionally, the detection process data may be various parameters in the detection process, or may be images collected during the detection process.

[0077] By judging whether the test process data and test results match, we can avoid fraud by testers and improve the credibility of the data.

[0078] When the test results are credible;

[0079] S3. Store the detection process data and detection results in a tamper-proof database.

[0080] The test process data and test results are stored so that they can be viewed when needed.

[0081] S4, obtaining a target product serial number of a target product corresponding to the target extract, generating a target URL according to the target product serial number, and the page pointed to by the target URL is configured to display the detection process data and the detection results in the database;

[0082] S5. Generate a target QR code tag according to the target URL, and match the target QR code tag with the target product.

[0083] In order to facilitate users to query product quality inspection related data, a URL is generated for each product, and the URL is matched with the product through a QR code. Users can view the quality inspection related data of the products they purchased by scanning the corresponding QR code.

[0084] Example 2

[0085] This embodiment, based on the embodiment 1, provides a method for quality management of highland barley red yeast rice extract, comprising the following steps:

[0086] S1. Sampling and testing the target extract according to the preset sampling rules to obtain the testing process data and test results.

[0087] Optionally, the step of sampling and testing the target extract according to a preset sampling rule to obtain test process data and test results includes:

[0088] Selecting an extract to be tested from the target extracts according to a preset sampling rule, and acquiring an image of the extract to be tested as a first image;

[0089] Obtaining the content of effective components and harmful components of the extract to be tested as the test result by liquid chromatography, obtaining an image of the solution of the extract to be tested as the second image, and obtaining a liquid chromatogram of the extract to be tested as the third image;

[0090] The first image, the second image and the third image belong to the detection process data.

[0091] S2. Determine whether the test results are credible based on the test process data and test results.

[0092] Optionally, the step of judging whether the test result is credible based on the test process data and the test result includes:

[0093] According to the first image, the second image and the third image, determining whether the first image, the second image and the third image match by using a matching analysis model;

[0094] When the first image, the second image, and the third image match, determining whether the third image matches the detection result;

[0095] When the third image matches the detection result, the detection result is credible.

[0096] Optionally, the step of determining whether the first image, the second image, and the third image match by using a matching analysis model according to the first image, the second image, and the third image includes:

[0097] Establishing an initial matching analysis model, wherein the matching analysis model is configured to take at least an image of the extract to be tested and an image of the extract solution to be tested as input parameters, or at least an image of the extract solution to be tested and a liquid chromatogram of the extract to be tested as input parameters, or at least an image of the extract to be tested and a liquid chromatogram of the extract to be tested as input parameters, and whether there is a match as an output parameter;

[0098] Obtaining a group of images marked as matching to train and verify an initial matching analysis model;

[0099] The initial matching analysis model that has passed verification is used as the matching analysis model;

[0100] Inputting the first image and the second image as a group of images, the second image and the third image as a group of images, and the first image and the third image as a group of images into a matching analysis model;

[0101] According to the result output by the matching analysis model, it is determined whether the first image, the second image and the third image match.

[0102] Optionally, based on the results output by the matching analysis model, a method for determining whether the first image, the second image, and the third image match is that when the first image and the second image, the second image and the third image, and the first image and the third image all match, the first image, the second image, and the third image match.

[0103] Optionally, based on the results output by the matching analysis model, a method for determining whether the first image, the second image, and the third image match is that when there are at least two groups of matches among the first image and the second image, the second image and the third image, and the first image and the third image, the first image, the second image, and the third image match.

[0104] Optionally, based on the result output by the matching analysis model, a method for determining whether the first image, the second image, and the third image match is that when the first image and the second image, and the second image and the third image match, the first image, the second image, and the third image match.

[0105] Optionally, a method for judging whether the first image, the second image, and the third image match according to a result output by a matching analysis model is to match the result output by the matching analysis model to obtain a first matching degree between the first image and the second image, a second matching degree between the second image and the third image, and a third matching degree between the first image and the third image, and then judge whether the first image, the second image, and the third image match according to preset rules based on the first matching degree, the second matching degree, and the third matching degree.

[0106] Optionally, based on the first matching degree, the second matching degree and the third matching degree, a method for determining whether the first image, the second image and the third image match according to preset rules may be that if one, two or three items specified among the first matching degree, the second matching degree and the third matching degree exceed a preset threshold, or the sum of two or three of the items exceeds a preset threshold, then the first image, the second image and the third image match.

[0107] Optionally, based on the first matching degree, the second matching degree and the third matching degree, a method for determining whether the first image, the second image and the third image match according to preset rules may be to assign weight values ​​to the first matching degree, the second matching degree and the third matching degree respectively for weighted calculation, and if the value after weighted summation or weighted average exceeds a preset threshold, the first image, the second image and the third image match, wherein the weight value of the third matching degree is lower than the weight value of the first matching degree or the second matching degree.

[0108] Specifically, the weight ratio of the first matching degree to the second matching degree is 1 to 0.83 to 1 to 1.2, and the weight ratio of the first matching degree to the third matching degree is 1 to 0.15 to 1 to 0.25.

[0109] By analyzing whether the first image matches the second image, it can be ensured that the process of obtaining the solution of the extract to be tested based on the extract to be tested is credible. By analyzing whether the second image matches the third image, it can be ensured that the process of detecting the liquid chromatogram of the solution of the extract to be tested is credible. By analyzing whether the first image matches the third image, it can be further ensured that the process of obtaining the solution of the extract to be tested based on the extract to be tested and the process of detecting the liquid chromatogram of the solution of the extract to be tested are credible. At the same time, since the differences between the first image, the second image and the third image of different target extracts are small, the matching analysis model is prone to overfitting. If the first image, the second image and the third image are required to match each other at the same time, the misjudgment rate is high. This problem can be solved by reducing the weight of the matching of the first image and the third image or not considering whether the first image and the third image match.

[0110] Optionally, the matching analysis model can select a CNN model, such as VGG, ResNet, or an attention mechanism model for matching analysis.

[0111] Through the above steps, the consistency of the detection process data can be further ensured and the credibility of the detection results can be improved.

[0112] Optionally, the step of determining whether the third image matches the detection result includes:

[0113] According to the third image and the image detection model, obtaining the effective component content and the harmful component content corresponding to the third image;

[0114] According to the effective component content and harmful component content corresponding to the third image and the test result, determining whether the third image matches the test result;

[0115] When the error between the effective component content and the harmful component content corresponding to the third image and the detection result is not greater than a preset first threshold, the third image matches the detection result.

[0116] The step of obtaining the effective component content and the harmful component content corresponding to the third image according to the third image and the image detection model comprises:

[0117] performing preprocessing according to the third image;

[0118] Convert the preprocessed third image into an embedded feature, and use the embedded feature to input a feature encoder for encoding processing;

[0119] Using the target encoder to perform hybrid parallel attention calculations on the embedded features, the results of which are used to fuse with the residual of the embedded features to obtain high-frequency features; and

[0120] The high-frequency features are input into a convolutional feedforward network, and the convolutional feedforward network is used to perform data dimension reduction to obtain the effective component content and the harmful component content corresponding to the third image;

[0121] Specifically, preprocessing is performed according to the third image; wherein the preprocessing method includes noise removal:

[0122] ;

[0123] in, represents the third image data after preprocessing, represents the coordinates of the spectrum in the third image, represents the two-dimensional inverse wavelet transform operation, represents a two-dimensional wavelet transform operation, represents the third image data, represents the symbolic function, Represents the noise threshold.

[0124] Specifically, in the step of converting the preprocessed third image data into an embedded feature, and the embedded feature is used to input a feature encoder for encoding processing, the embedding method includes:

[0125] ;

[0126] in, Represents the frequency domain corresponding to the spatial domain The complex value of the position in The coordinates in the spatial domain are The target sample intensity at M represents the length of the target sample in the first direction, N Indicates the length of the target sample in the second direction.

[0127] When the test results are credible;

[0128] S3. Store the detection process data and detection results in a tamper-proof database.

[0129] When the test result is unreliable, a prompt message is sent to the tester.

[0130] Optionally, situations where the detection result is unreliable include: the first image, the second image and the third image do not match, or the effective component content and the harmful component content corresponding to the third image do not match the detection result.

[0131] S4. Obtain a target product serial number of a target product corresponding to the target extract, generate a target URL according to the target product serial number, and the page pointed to by the target URL is configured to display the detection process data and detection results in the database.

[0132] Optionally, after the step of obtaining a target product serial number of a target product corresponding to the target extract and generating a target URL according to the target product serial number, the step further includes:

[0133] Obtaining a target factory image of the target product when it leaves the factory, and storing the target factory image in a database;

[0134] The page pointed to by the target URL is also configured to display the target factory image in the database.

[0135] By adding the target factory image to the page pointed to by the target URL, users can obtain the target factory image by scanning the QR code, making it easier for users to compare whether the product appearance is consistent with that when it left the factory.

[0136] S5. Generate a target QR code tag according to the target URL, and match the target QR code tag with the target product.

[0137] Optionally, also include:

[0138] Record the access records of the page pointed to by the target URL, including the account type and the number of visits;

[0139] When the number of visits to a preset account type exceeds the preset number, the preset prompt message is displayed on the page pointed to by the target URL.

[0140] Optional, account type includes dealer account or user account. The default value for an unlogged-in account is a user account.

[0141] When the number of times the user account visits the page pointed to by the target URL exceeds n times, the page pointed to by the target URL will display that the QR code has been scanned n times. Specifically, n can be a positive integer such as 1, 2, 5, etc.

[0142] When m different user accounts visit the page pointed to by the target URL, the page pointed to by the target URL displays that the QR code has been scanned by m users. Specifically, m can be a positive integer such as 1, 2, or 5.

[0143] Optionally, the QR code is also covered with a scratch-off coating.

[0144] Example 3

[0145] A highland barley red yeast rice extract quality management system, comprising a quality management platform and a detection platform;

[0146] The detection platform is configured as:

[0147] Sampling and testing the target extract according to the preset sampling rules to obtain the testing process data and test results;

[0148] Determine whether the test results are credible based on the test process data and test results;

[0149] When the test results are credible, the test process data and test results are sent to the quality management platform;

[0150] The quality management platform is configured to:

[0151] Receive the test process data and test results sent by the test platform, and store the test process data and test results in a tamper-proof database;

[0152] Obtaining a target product serial number of a target product corresponding to a target extract, generating a target URL according to the target product serial number, wherein a page pointed to by the target URL is configured to display the detection process data and the detection results in the database;

[0153] Generate a target QR code tag based on the target URL, and match the target QR code tag with the target product.

[0154] Optionally, the detection platform includes an experimental detection module, an image acquisition module, a simulation detection module and a judgment module;

[0155] The experimental detection module is configured as follows:

[0156] The content of effective components and harmful components of the extract to be tested are obtained as test results by liquid chromatography;

[0157] The image acquisition module is configured as follows:

[0158] Acquiring an image of the extract to be tested as a first image;

[0159] Acquire an image of a solution of the extract to be tested as a second image;

[0160] acquiring a liquid chromatogram of the extract to be tested as a third image;

[0161] The analog detection module is configured as:

[0162] According to the third image, the effective component content and the harmful component content corresponding to the third image are obtained;

[0163] The judgment module is configured as follows:

[0164] determining whether the first image, the second image, and the third image match;

[0165] determining whether the third image matches the detection result;

[0166] Whether the detection result is credible is determined based on whether the first image, the second image and the third image match and whether the third image matches the detection result.

[0167] Example 4

[0168] This embodiment provides a device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement any of the above methods.

[0169] Specifically, Figure 2 As shown, Figure 2 This is a schematic diagram of the structure of an electronic device of the hardware operating environment involved in the embodiment of the present application. The electronic device may include: a processor 101, such as a central processing unit (CPU), a communication bus 102, a user interface 104, a network interface 103, and a memory 105. Among them, the communication bus 102 is used to realize the connection and communication between these components. The user interface 104 may include a display (Display), an input unit such as a keyboard (Keyboard), and the user interface 104 may also include a standard wired interface and a wireless interface. The network interface 103 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface). The memory 105 may optionally be a storage device independent of the aforementioned processor 101. The memory 105 may be a high-speed random access memory (RAM) memory, or it may be a stable non-volatile memory (NVM), such as at least one disk storage. The processor 101 may be a general-purpose processor, including a central processing unit, a network processor, etc., or it may be a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component.

[0170] Those skilled in the art will appreciate that Figure 2 The structure shown in the figure does not constitute a limitation on the electronic device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0171] like Figure 2 As shown, the memory 105 as a storage medium may include an operating system, a network communication module, a user interface module, and an application program for implementing a quality management method for highland barley red yeast rice extract.

[0172] exist Figure 2In the electronic device shown, the network interface 103 is mainly used for data communication with the network server; the user interface 104 is mainly used for data interaction with the user; the processor 101 and the memory 105 in the present application can be set in the electronic device, and the electronic device calls the application program stored in the memory 105 for implementing a quality management method of highland barley red yeast rice extract through the processor 101 to implement the above method.

[0173] Example 5

[0174] This embodiment provides a computer-readable storage medium, on which a computer program is stored, and a processor executes the computer program to implement any of the above methods.

[0175] In some embodiments, the computer readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or various devices including one or any combination of the above memories. The computer may be various computing devices including intelligent terminals and servers.

[0176] In the above embodiments of the present disclosure, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0177] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of units can be a logical function division. There may be other division methods in 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. 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 units or modules, which can be electrical or other forms.

[0178] 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 over multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0179] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0180] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable non-volatile storage medium. Based on this understanding, the technical solution of the present disclosure is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a non-volatile storage medium, including a number of instructions to enable a device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the various embodiments of the present disclosure. The aforementioned non-volatile storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0181] The above are only preferred embodiments of the present disclosure. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present disclosure. These improvements and modifications should also be regarded as the protection scope of the present disclosure.

Claims

1. A quality management method for highland barley red yeast rice extract, characterized in that: The following steps are involved: Sampling and testing the target extract according to the preset sampling rules to obtain the testing process data and test results; Judging whether the detection result is credible according to the detection process data and the detection result; When the detection result is credible, the detection process data and the detection result are stored in a tamper-proof database; Obtaining a target product serial number of a target product corresponding to the target extract, generating a target URL according to the target product serial number, wherein the page pointed to by the target URL is configured to display the detection process data and the detection result in the database; Generate a target QR code tag according to the target URL, and match the target QR code tag with the target product; The step of sampling and testing the target extract according to a preset sampling rule to obtain test process data and test results includes: Selecting an extract to be tested from the target extracts according to a preset sampling rule, and acquiring an image of the extract to be tested as a first image; Obtaining the content of effective ingredients and harmful ingredients in the extract to be tested as the test result by liquid chromatography, obtaining an image of a solution of the extract to be tested as a second image, and obtaining a liquid chromatogram of the extract to be tested as a third image; The first image, the second image and the third image belong to the detection process data; the step of judging whether the detection result is credible according to the detection process data and the detection result comprises: According to the first image, the second image and the third image, determining whether the first image, the second image and the third image match by using a matching analysis model; When the first image, the second image and the third image match, determining whether the third image matches the detection result; When the third image matches the detection result, the detection result is credible; The step of determining whether the third image matches the detection result comprises: According to the third image and the image detection model, obtaining the effective component content and the harmful component content corresponding to the third image; According to the effective component content and the harmful component content corresponding to the third image and the detection result, determining whether the third image matches the detection result; When the error between the effective component content and the harmful component content corresponding to the third image and the detection result is not greater than a preset first threshold, the third image matches the detection result; The step of obtaining the effective component content and the harmful component content corresponding to the third image according to the third image and the image detection model comprises: performing preprocessing according to the third image; Convert the preprocessed third image into an embedded feature, and use the embedded feature to input a feature encoder for encoding processing; Using the target encoder to perform hybrid parallel attention calculations on the embedded features, the results of which are used to fuse with the residual of the embedded features to obtain high-frequency features; and The high-frequency features are input into a convolutional feedforward network, and the convolutional feedforward network is used to perform data dimension reduction to obtain the effective component content and the harmful component content corresponding to the third image; The preprocessing is performed according to the third image, and the preprocessing method includes noise removal: ； in, represents the third image data after preprocessing, represents the coordinates of the spectrum in the third image, represents the two-dimensional inverse wavelet transform operation, represents a two-dimensional wavelet transform operation, represents the third image data, represents the symbolic function, represents the noise threshold; In the step of converting the preprocessed third image data into embedded features, wherein the embedded features are input into a feature encoder for encoding processing, the embedding method includes: ； in, Represents the frequency domain corresponding to the spatial domain The complex value of the position in , The coordinates in the spatial domain are The target sample intensity at M represents the length of the target sample in the first direction, N Indicates the length of the target sample in the second direction.

2. A method for quality management of highland barley red yeast rice extract as claimed in claim 1, characterized in that: The step of determining whether the first image, the second image and the third image match by using a matching analysis model according to the first image, the second image and the third image comprises: Establishing an initial matching analysis model, wherein the matching analysis model is configured to take at least an image of the extract to be tested and an image of the extract solution to be tested as input parameters, or at least an image of the extract solution to be tested and a liquid chromatogram of the extract to be tested as input parameters, or at least an image of the extract to be tested and a liquid chromatogram of the extract to be tested as input parameters, and whether there is a match as an output parameter; Acquire a group of images marked as matching to train and verify the initial matching analysis model; Using the verified initial matching analysis model as the matching analysis model; Inputting the first image and the second image as a group of images, the second image and the third image as a group of images, and the first image and the third image as a group of images into the matching analysis model; According to the result output by the matching analysis model, it is determined whether the first image, the second image and the third image match.

3. A method for quality management of highland barley red yeast rice extract as claimed in claim 1, characterized in that: After the step of obtaining the target product serial number of the target product corresponding to the target extract and generating the target URL according to the target product serial number, the method further includes: Acquire a target factory image of the target product when it leaves the factory, and store the target factory image in a database; The page pointed to by the target URL is also configured to display the target factory image in the database.

4. A method for quality management of highland barley red yeast rice extract as claimed in claim 3, characterized in that: Also includes: Recording access records of the page pointed to by the target URL, wherein the access records include the account type and the number of accesses; When the number of visits to a preset account type exceeds a preset number, a preset prompt message is displayed on the page pointed to by the target URL.

5. A quality management system for highland barley red yeast rice extract, characterized in that: Executing and implementing the method as described in any one of claims 1 to 4, including a quality management platform and a detection platform; The detection platform is configured as follows: Sampling and testing the target extract according to the preset sampling rules to obtain the testing process data and test results; Judging whether the detection result is credible according to the detection process data and the detection result; When the test result is credible, the test process data and the test result are sent to the quality management platform; The step of sampling and testing the target extract according to a preset sampling rule to obtain test process data and test results includes: Selecting an extract to be tested from the target extracts according to a preset sampling rule, and acquiring an image of the extract to be tested as a first image; Obtaining the content of effective ingredients and harmful ingredients in the extract to be tested as the test result by liquid chromatography, obtaining an image of a solution of the extract to be tested as a second image, and obtaining a liquid chromatogram of the extract to be tested as a third image; The first image, the second image and the third image belong to the detection process data; the step of judging whether the detection result is credible according to the detection process data and the detection result comprises: According to the first image, the second image and the third image, determining whether the first image, the second image and the third image match by using a matching analysis model; When the first image, the second image and the third image match, determining whether the third image matches the detection result; When the third image matches the detection result, the detection result is credible; The step of determining whether the third image matches the detection result comprises: According to the third image and the image detection model, obtaining the effective component content and the harmful component content corresponding to the third image; According to the effective component content and the harmful component content corresponding to the third image and the detection result, determining whether the third image matches the detection result; When the error between the effective component content and the harmful component content corresponding to the third image and the detection result is not greater than a preset first threshold, the third image matches the detection result; The step of obtaining the effective component content and the harmful component content corresponding to the third image according to the third image and the image detection model comprises: performing preprocessing according to the third image; Convert the preprocessed third image into an embedded feature, and use the embedded feature to input a feature encoder for encoding processing; Using the target encoder to perform hybrid parallel attention calculations on the embedded features, the results of which are used to fuse with the residual of the embedded features to obtain high-frequency features; and The high-frequency features are input into a convolutional feedforward network, and the convolutional feedforward network is used to perform data dimension reduction to obtain the effective component content and the harmful component content corresponding to the third image; The preprocessing is performed according to the third image, and the preprocessing method includes noise removal: ； in, represents the third image data after preprocessing, represents the coordinates of the spectrum in the third image, represents the two-dimensional inverse wavelet transform operation, represents a two-dimensional wavelet transform operation, represents the third image data, represents the symbolic function, represents the noise threshold; In the step of converting the preprocessed third image data into embedded features, wherein the embedded features are input into a feature encoder for encoding processing, the embedding method includes: ； in, Represents the frequency domain corresponding to the spatial domain The complex value of the position in , The coordinates in the spatial domain are The target sample intensity at M represents the length of the target sample in the first direction, N Indicates the length of the target sample in the second direction; The quality management platform is configured to: Receiving the detection process data and the detection result sent by the detection platform, and storing the detection process data and the detection result in a tamper-proof database; Obtaining a target product serial number of a target product corresponding to the target extract, generating a target URL according to the target product serial number, wherein the page pointed to by the target URL is configured to display the detection process data and the detection result in the database; A target two-dimensional code tag is generated according to the target URL, and the target two-dimensional code tag is matched with the target product.

6. A quality management system for highland barley red yeast rice extract as claimed in claim 5, characterized in that: The detection platform includes an experimental detection module, an image acquisition module, a simulation detection module and a judgment module; The experimental detection module is configured as follows: Obtaining the content of effective components and harmful components of the extract to be tested as the test result by liquid chromatography; The image acquisition module is configured as follows: Acquiring an image of the extract to be tested as a first image; Acquire an image of a solution of the extract to be tested as a second image; Acquiring a liquid chromatogram of the extract to be tested as a third image; The analog detection module is configured as follows: According to the third image, obtaining the effective component content and the harmful component content corresponding to the third image; The determination module is configured as follows: determining whether the first image, the second image, and the third image match; Determining whether the third image matches the detection result; Whether the detection result is credible is determined based on whether the first image, the second image and the third image match and whether the third image matches the detection result.

7. A device, characterized in that: The device comprises a memory and a processor, wherein a computer program is stored in the memory, and the processor executes the computer program to implement the method according to any one of claims 1 to 4.

Images