Automatic quality monitoring method and system for pineapple wine fermentation

Abstract

The invention relates to an automatic quality monitoring method and system for pineapple wine fermentation, and the method comprises the steps: obtaining microbial community information of a first fermentation liquid of pineapple wine to be monitored through a high-throughput sequencing technology, inputting the microbial community information into a pineapple wine fermentation quality prediction model, and obtaining a prediction result, and finally, monitoring the quality of the to-be-monitored pineapple wine according to the prediction result. Wherein the pineapple wine fermentation quality prediction model is formed by training a machine learning model according to pineapple wine fermentation quality parameters and pineapple wine fermentation microbial community data. The composition and change of the microbial community in the pineapple wine fermentation process are monitored in real time through the high-throughput sequencing technology, the correlation model between the microbial community structure and the fermentation quality is established in combination with the machine learning algorithm, the fermentation conditions can be dynamically adjusted, and therefore the precision of automatic quality monitoring for pineapple wine fermentation is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an automated quality monitoring method and system for pineapple wine fermentation. Background Art

[0002] During the pineapple wine fermentation process, the microbial community structure is complex and undergoes significant dynamic changes. The microbial community includes not only bacteria but also various microorganisms such as yeasts and molds. These microorganisms interact with each other during the fermentation process and jointly affect the fermentation quality:

[0003] The microbial community structure changes significantly during the fermentation process. For example, at the initial stage of fermentation, yeasts and molds may dominate, while at the later stage of fermentation, other acid-tolerant or alcohol-tolerant microorganisms may gradually gain the upper hand. Traditional monitoring methods are difficult to capture these dynamic changes in real time.

[0004] The microbial community is not only complex and diverse in terms of species, but its functions are also extremely rich. For example, lactic acid bacteria are involved in glycolysis and acid metabolism, while yeasts are mainly responsible for ethanol synthesis. Traditional monitoring methods are difficult to deeply analyze the functional diversity of the microbial community and its association with fermentation quality. The structure and function of the microbial community during the fermentation process are closely related to the fermentation quality. For example, certain bacterial genera may have a significant positive correlation with reducing sugar and starch contents, while other bacterial genera may have a significant negative correlation with acidity and moisture contents. Traditional monitoring methods cannot monitor these correlation changes in real time, making it difficult to achieve precise control of the fermentation process.

[0005] From the above, it can be seen that the existing automated quality monitoring methods for pineapple wine fermentation have the problem of low monitoring accuracy. Summary of the Invention

[0006] In order to improve the accuracy of automated quality monitoring for pineapple wine fermentation, the present application provides an automated quality monitoring method and system for pineapple wine fermentation.

[0007] To solve the above technical problems, an embodiment of the present invention provides an automated quality monitoring method for pineapple wine fermentation. The method includes the following steps:

[0008] Obtain the first fermentation broth of the pineapple wine to be monitored;

[0009] Obtain the microbial community information of the first fermentation broth according to high-throughput sequencing technology;

[0010] Input the microbial community information into the pineapple wine fermentation quality prediction model to obtain a prediction result;

[0011] Perform quality monitoring on the pineapple wine to be monitored according to the prediction result;

[0012] Among them, the training process of the pineapple wine fermentation quality prediction model is as follows:

[0013] Obtain the pineapple wine fermentation quality parameters and the pineapple wine fermentation microbial community data;

[0014] Train a machine learning model based on the pineapple wine fermentation quality parameters and the pineapple wine fermentation microbial community data to generate a pineapple wine fermentation quality prediction model.

[0015] As an optimal solution, in the step of training a machine learning model based on the pineapple wine fermentation quality parameters and the pineapple wine fermentation microbial community data to generate a pineapple wine fermentation quality prediction model, the following steps are included:

[0016] Based on the pineapple wine fermentation quality parameters and the pineapple wine fermentation microbial community data, form a training data set and a validation data set;

[0017] Input the training data set into the machine learning model and calculate the first predicted value as the output;

[0018] Calculate the first error between the first predicted value and the true value through a loss function;

[0019] Perform backpropagation based on the first error to update the parameters of the machine learning model;

[0020] Validate the machine learning model according to the validation data set to generate a pineapple wine fermentation quality prediction model.

[0021] As an optimal solution, in the step of obtaining the pineapple wine fermentation quality parameters and the pineapple wine fermentation microbial community data, the following steps are included:

[0022] Obtain the pineapple wine alcohol content data, the pineapple wine sugar content data, and the pineapple wine acidity data;

[0023] Perform data cleaning operations on the pineapple wine alcohol content data, the pineapple wine sugar content data, and the pineapple wine acidity data to obtain the pineapple wine fermentation quality parameters;

[0024] Obtain the sequencing data of the microbial community in the pineapple wine according to the high-throughput sequencing technology; among them, the sequencing data is the operational taxonomic unit abundance data or the amplicon sequence variant abundance data;

[0025] Perform quality control operations, low-quality sequence removal operations, splicing operations, and chimera removal operations on the sequencing data to obtain the pineapple wine fermentation microbial community data.

[0026] As an optimal solution, in the step of performing quality monitoring on the pineapple wine to be monitored according to the prediction results, the following steps are included:

[0027] Obtain the first correlation between the pineapple wine fermentation quality parameters and the pineapple wine fermentation microbial community data according to the prediction result;

[0028] Set the regulation target according to the first correlation and in combination with the pineapple wine fermentation microbial community data;

[0029] Regulate the pineapple wine fermentation quality parameters according to the regulation target.

[0030] As a preferred solution, it further includes:

[0031] Obtain the relative abundance of harmful microorganisms according to the microbial community information;

[0032] When the relative abundance of harmful microorganisms is greater than the preset threshold, adjust the temperature or pH value of the first fermentation broth.

[0033] As a preferred solution, in the step of obtaining the microbial community information of the first fermentation broth according to the high-throughput sequencing technology, it includes the following steps:

[0034] Obtain the DNA sample of the first fermentation broth;

[0035] Perform PCR amplification on the 16S rRNA gene of the DNA sample according to specific primers to obtain an amplification product;

[0036] Perform high-throughput sequencing on the amplification product to generate sequence data;

[0037] Perform clustering analysis on the sequence data to generate the microbial community information of the first fermentation broth.

[0038] As a preferred solution, it further includes:

[0039] Screen the beneficial microorganisms in the first fermentation broth according to the gene editing technology in combination with the microbial community information;

[0040] Modify the metabolic pathways of the beneficial microorganisms through the CRISPR-Cas system.

[0041] Correspondingly, the present invention also provides an automated quality monitoring system for pineapple wine fermentation, including: an acquisition module, a sequencing module, a prediction module, and a monitoring module;

[0042] Among them, the acquisition module is used to acquire the first fermentation broth of the pineapple wine to be monitored;

[0043] The sequencing module is used to obtain the microbial community information of the first fermentation broth according to the high-throughput sequencing technology;

[0044] The prediction module is used to input the microbial community information into the pineapple wine fermentation quality prediction model to obtain a prediction result;

[0045] For quality monitoring of pineapple wine to be monitored according to the prediction results;

[0046] Among them, the training process of the pineapple wine fermentation quality prediction model is as follows:

[0047] Obtain the pineapple wine fermentation quality parameters and the pineapple wine fermentation microbial community data;

[0048] Train a machine learning model based on the pineapple wine fermentation quality parameters and the pineapple wine fermentation microbial community data to generate a pineapple wine fermentation quality prediction model.

[0049] Correspondingly, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that when the processor executes the computer program, the steps of an automated quality monitoring method for pineapple wine fermentation as described in any one of the above are implemented.

[0050] Correspondingly, the present invention also provides a storage medium storing a computer program, characterized in that when the computer program is executed by a processor, the steps of an automated quality monitoring method for pineapple wine fermentation as described in any one of the above are implemented.

[0051] After obtaining the microbial community information of the first fermentation broth of the pineapple wine to be monitored through high-throughput sequencing technology, the technical solution of the present invention inputs the microbial community information into the pineapple wine fermentation quality prediction model to obtain a prediction result, and finally monitors the quality of the pineapple wine to be monitored according to the prediction result. Among them, the pineapple wine fermentation quality prediction model is trained by a machine learning model based on pineapple wine fermentation quality parameters and pineapple wine fermentation microbial community data. By combining the machine learning model with microbial community monitoring data, an association model between the microbial community structure and fermentation quality is established, which can capture the non-linear and complex relationships in the microbial community, and identify the optimal range of key microhabitat characteristics through individual conditional expectation analysis. It can not only accurately predict the fermentation quality, but also provide a scientific basis for parameter regulation in the fermentation process. Further, the technical solution of the present invention performs quality monitoring through the prediction result generated by the pineapple wine fermentation quality prediction model, thereby improving the accuracy of automatic quality monitoring for pineapple wine fermentation, dynamically adjusting the parameters in the fermentation process according to the changes in the microbial community structure, ensuring the optimization of the fermentation process, being able to provide real-time feedback on the changes in the microbial community, and achieving precise regulation through an automatic control unit, improving fermentation efficiency and product quality. Moreover, the technical solution of the present invention uses 16S rRNA gene amplicon high-throughput sequencing technology to amplify and sequence the 16S rRNA gene in the microbial community through specific primers, and can quickly and accurately obtain the composition information of the microbial community. This method does not depend on the culturing ability of bacteria in the sample and can comprehensively cover all microorganisms in the sample, including difficult-to-culture microorganisms. At the same time, high-throughput sequencing technology can process a large number of samples in a short time, providing an efficient technical means for monitoring the microbial community in the fermentation process. Description of the Drawings

[0052] Figure 1 is a flowchart of the steps of an automatic quality monitoring method for pineapple wine fermentation in an embodiment of the present application;

[0053] Figure 2 is a structural diagram of an automatic quality monitoring system for pineapple wine fermentation in an embodiment of the present application;

[0054] Figure 3 is a schematic diagram of the hardware structure of an electronic device in an embodiment of the present application.

[0055] Reference Numerals in the Drawings:

[0056] Acquisition module 201, sequencing module 202, prediction module 203, and monitoring module 204. Detailed Embodiments

[0057] To make the objectives, technical solutions and advantages of the present application more clearly understood, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the embodiments of the present application. They are only examples of devices and methods that are consistent with some aspects of the embodiments of the present application.

[0058] It can be understood that the terms "first", "second", etc. used in the present application may be used in this document to describe various concepts, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of the present application, the first information may also be referred to as the second information. Similarly, the second information may also be referred to as the first information. Depending on the context, the words "if", "when" as used herein may be interpreted as "when...", "while...", or "in response to determining".

[0059] The terms "at least one", "a plurality of", "each", "any one", etc. used in the present application, at least one includes one, two or more than two, a plurality of includes two or more than two, each refers to each one of the corresponding plurality, and any one refers to any one of the plurality.

[0060] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application and are not intended to limit the present application.

[0061] Traditional monitoring methods are difficult to deeply analyze the functional diversity of microbial communities and their association with fermentation quality. The structure and function of microbial communities during the fermentation process are closely related to fermentation quality. For example, certain bacterial genera may have a significant positive correlation with the content of reducing sugars and starch, while some other bacterial genera may have a significant negative correlation with acidity and moisture content. Traditional monitoring methods cannot monitor these correlation changes in real time, making it difficult to achieve precise control of the fermentation process. From the above, it can be seen that the existing automated quality monitoring methods for pineapple wine fermentation have the problem of low monitoring accuracy.

[0062] In view of this, an automated quality monitoring method and system for pineapple wine fermentation are provided in the embodiments of the present application. After obtaining the microbial community information of the first fermentation broth of the pineapple wine to be monitored through high-throughput sequencing technology, the microbial community information is input into the pineapple wine fermentation quality prediction model to obtain a prediction result. Finally, the quality of the pineapple wine to be monitored is monitored according to the prediction result. Among them, the pineapple wine fermentation quality prediction model is trained by using the pineapple wine fermentation quality parameters and the pineapple wine fermentation microbial community data. By combining the machine learning model with the microbial community monitoring data, an association model between the microbial community structure and the fermentation quality is established, which can capture the non-linear and complex relationships in the microbial community, and identify the optimal range of key microhabitat characteristics through individual conditional expectation analysis. It can not only accurately predict the fermentation quality, but also provide a scientific basis for parameter regulation in the fermentation process. Further, the technical solution of the present invention monitors the quality through the prediction result generated by the pineapple wine fermentation quality prediction model, thereby improving the accuracy of the automated quality monitoring for pineapple wine fermentation, dynamically adjusting the parameters in the fermentation process according to the changes in the microbial community structure, ensuring the optimization of the fermentation process, being able to timely feedback the changes in the microbial community, and achieving precise regulation through the automated control unit, improving the fermentation efficiency and product quality. Moreover, the technical solution of the present invention uses the 16S rRNA gene amplicon high-throughput sequencing technology to amplify and sequence the 16S rRNA gene in the microbial community through specific primers, and can quickly and accurately obtain the composition information of the microbial community. This method does not depend on the culturing ability of bacteria in the sample and can comprehensively cover all microorganisms in the sample, including those that are difficult to culture. At the same time, the high-throughput sequencing technology can process a large number of samples in a short time, providing an efficient technical means for monitoring the microbial community in the fermentation process.

[0063] The automated quality monitoring method and system for pineapple wine fermentation provided in the embodiments of the present application relate to the technical field of data processing. The automated quality monitoring method and system for pineapple wine fermentation provided in the embodiments of the present application can be applied to a terminal, can also be applied to a server, or can be software running on a terminal or a server. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, a vehicle-mounted terminal, etc., but is not limited thereto; the server side can be configured as an independent physical server, can also be configured as a server cluster or a distributed system composed of multiple physical servers, or can be configured as a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network; the software can be an application for implementing the vehicle sideslip angle calculation method, etc., but is not limited to the above forms.

[0064] This application can be used in numerous general-purpose or special-purpose computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and so on. This application can be described in a first context of computer-executable instructions executed by a computer, such as program modules. First, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This application can also be practiced in a distributed computing environment where tasks are executed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0065] The following further elaborates on this application in conjunction with the accompanying drawings.

[0066] In one embodiment, as Figure 1 shown, this application discloses an automated quality monitoring method for pineapple wine fermentation, specifically including the following steps:

[0067] S101: Obtain the first fermentation broth of the pineapple wine to be monitored.

[0068] S102: Obtain the microbial community information of the first fermentation broth according to high-throughput sequencing technology.

[0069] In this embodiment, in the step of obtaining the microbial community information of the first fermentation broth according to high-throughput sequencing technology, the following steps are included:

[0070] Obtain the DNA sample of the first fermentation broth;

[0071] Perform PCR amplification on the 16S rRNA gene of the DNA sample according to specific primers to obtain an amplification product;

[0072] Perform high-throughput sequencing on the amplification product to generate sequence data;

[0073] Perform clustering analysis on the sequence data to generate the microbial community information of the first fermentation broth.

[0074] Furthermore, perform high-throughput sequencing on the amplification product to obtain a large amount of sequence data. Through bioinformatics analysis, cluster the sequence data into OTUs (operational taxonomic units) or ASVs (amplicon sequence variants), and perform species annotation.

[0075] The compositional changes of the microbial community can be quantified by calculating relative abundances and diversity indices:

[0076] Relative abundance = (number of sequences of OTU or ASV / total number of sequences in the sample) × 100%;

[0077] By calculating the relative abundances of each OTU or ASV, the proportions of different microorganisms in the community can be understood.

[0078] In recent years, high-throughput sequencing technology has been widely used in the monitoring of microbial communities. This technology can comprehensively cover all microorganisms in a sample, including those that are difficult to culture. Through high-throughput sequencing technology, a large number of samples can be processed in a short time, providing an efficient technical means for the monitoring of microbial communities during the fermentation process. In addition, by combining high-throughput sequencing technology with machine learning algorithms, an association model between the microbial community structure and fermentation quality can be established, thus providing a scientific basis for parameter regulation during the fermentation process.

[0079] In summary, the traditional methods for monitoring microbial communities in liquor have significant deficiencies in terms of real-time performance, accuracy, monitoring of dynamic changes, analysis of functional diversity, correlation analysis, real-time feedback and regulation capabilities, as well as data processing and application, and it is difficult to meet the requirements for monitoring the dynamic changes of microbial communities during the fermentation process of modern pineapple wine. The application of high-throughput sequencing technology combined with machine learning algorithms provides new ideas and methods for solving these problems.

[0080] Furthermore, it also includes:

[0081] Screening beneficial microorganisms in the first fermentation broth according to gene editing technology combined with microbial community information;

[0082] Modifying the metabolic pathways of beneficial microorganisms through the CRISPR-Cas system.

[0083] Among them, the beneficial microorganisms include: Saccharomyces cerevisiae, lactic acid bacteria.

[0084] The CRISPR-Cas gene editing technology includes editing the promoter region of microorganisms to enhance the expression level of specific genes, thereby improving the fermentation performance of microorganisms. By modifying the metabolic pathways of microorganisms through the CRISPR-Cas system, the synthesis ability of key metabolites during the fermentation process of pineapple wine is enhanced.

[0085] The CRISPR-Cas gene editing technology includes editing the promoter region of microorganisms specifically as follows: modifying the following genes of Saccharomyces cerevisiae: improving ethanol tolerance by expressing the Pdc6 gene; knocking out the HOG1 gene to reduce hydrogen sulfide production; introducing exogenous ester synthase genes to enhance the synthesis of pineapple flavor substances (such as ethyl acetate).

[0086] S103: Input the microbial community information into the pineapple wine fermentation quality prediction model to obtain a prediction result.

[0087] In this embodiment, the training process of the pineapple wine fermentation quality prediction model is as follows:

[0088] Obtain the pineapple wine fermentation quality parameters and the pineapple wine fermentation microbial community data;

[0089] Train a machine learning model based on the pineapple wine fermentation quality parameters and the pineapple wine fermentation microbial community data to generate a pineapple wine fermentation quality prediction model.

[0090] Among them, in the step of obtaining the pineapple wine fermentation quality parameters and the pineapple wine fermentation microbial community data, the following steps are included:

[0091] Obtain the pineapple wine alcohol content data, the pineapple wine sugar content data, and the pineapple wine acidity data;

[0092] Perform data cleaning operations on the pineapple wine alcohol content data, the pineapple wine sugar content data, and the pineapple wine acidity data to obtain the pineapple wine fermentation quality parameters; among them, the data cleaning operations include handling missing values, outliers, and duplicate data to ensure the quality and consistency of the data;

[0093] Obtain the sequencing data of the microbial community in the pineapple wine according to the high-throughput sequencing technology; among them, the sequencing data is the operational taxonomic unit (OTU) abundance data or the amplicon sequence variant (ASV) abundance data;

[0094] Perform quality control operations, low-quality sequence removal operations, splicing operations, and chimera removal operations on the sequencing data to obtain the pineapple wine fermentation microbial community data.

[0095] Specifically, the frequency of high-throughput sequencing analysis is once every 24 to 48 hours to grasp the dynamic changes of the microbial community in real time.

[0096] Furthermore, methods such as principal component analysis (PCA), principal coordinates analysis (PCoA), or non-metric multidimensional scaling (NMDS) can be used to reduce the dimension of the high-dimensional microbial community data.

[0097] In a specific embodiment, in the step of training a machine learning model based on the pineapple wine fermentation quality parameters and the pineapple wine fermentation microbial community data to generate a pineapple wine fermentation quality prediction model, the following steps are included:

[0098] Form a training data set and a validation data set according to the pineapple wine fermentation quality parameters and the pineapple wine fermentation microbial community data;

[0099] Input the training data set into the machine learning model and calculate the first predicted value as the output.

[0100] Calculate the first error between the first predicted value and the true value through the loss function.

[0101] Perform backpropagation based on the first error to update the parameters of the machine learning model.

[0102] Validate the machine learning model according to the validation data set to generate a pineapple wine fermentation quality prediction model.

[0103] Among them, during the process of validating the machine learning model according to the validation data set, the mean squared error (MSE) and the R-squared coefficient can be used to evaluate the model performance.

[0104] In a specific embodiment, a random forest model can be used to predict the relationship between the pineapple wine fermentation quality parameter Q and the pineapple wine fermentation microbial community data X. The random forest model can be expressed as:

[0105] Q = f(X) + ∈;

[0106] Where f(X) is the fermentation quality predicted by the random forest model (i.e., the prediction result), and ∈ is the error term.

[0107] S104: Conduct quality monitoring on the pineapple wine to be monitored according to the prediction result.

[0108] In this embodiment, in the step of conducting quality monitoring on the pineapple wine to be monitored according to the prediction result, the following steps are included:

[0109] Obtain the first correlation between the pineapple wine fermentation quality parameter and the pineapple wine fermentation microbial community data according to the prediction result.

[0110] Set the regulation target according to the first correlation in combination with the pineapple wine fermentation microbial community data.

[0111] Regulate the pineapple wine fermentation quality parameter according to the regulation target.

[0112] Among them, the real-time monitored microbial community data (such as the relative abundance of OTU) is input into the pre-trained machine learning model, and the model will output the prediction result, that is, the relationship between the fermentation quality index (such as alcohol content) and the microbial community characteristics. Analyze the prediction result to determine which pineapple wine fermentation microbial community data has a significant correlation with the pineapple wine fermentation quality parameter, and obtain the first correlation.

[0113] Exemplarily, part of the prediction results of the pineapple wine fermentation quality prediction model are shown in Table 1:

[0114]

[0115] Table 1: Partial prediction results of the pineapple wine fermentation quality prediction model

[0116] If the model prediction result shows that the abundance of the specific operational taxonomic unit OTU_A is positively correlated with the alcohol content, it indicates that OTU_A has a positive impact on the fermentation quality. In the prediction result, the abundance of OTU_A is positively correlated with the alcohol content, and the correlation coefficient is 0.85. The current abundance of OTU_A is lower than expected. It is recommended to increase the fermentation temperature to promote the growth of OTU_A and increase the alcohol content.

[0117] Use the trained random forest model f(X) (i.e., the pineapple wine fermentation quality prediction model) to predict the fermentation quality Q under the current microbial community structure, and calculate the deviation ΔQ between the predicted value f(X) and the target fermentation quality Q target (i.e., the regulation target):

[0118] ΔQ = Q target - f(X);

[0119] Regulate the pineapple wine fermentation quality parameters according to the deviation ΔQ.

[0120] Among them, according to the analysis of the prediction results, determine the microbial community characteristics and fermentation quality indicators that need to be regulated. For example, if the abundance of OTU_A in the prediction result f(X) is lower than expected Q target , and is positively correlated with the alcohol content in the pineapple wine fermentation quality parameters, then increase the abundance of OTU_A by ΔQ until the expected Q target is used as the regulation target, and regulate the alcohol in the pineapple wine fermentation quality parameters, that is, increase the alcohol content.

[0121] Furthermore, specific regulation instructions can be generated according to the regulation target, combined with the relationship between known microbial growth conditions and fermentation parameters. If we want to promote the growth of OTU_A, according to previous research or experimental data, OTU_A grows better at higher temperatures, then the generated regulation instruction is to increase the fermentation temperature. It is carried out immediately after determining the regulation target. The generation of regulation instructions requires an in-depth understanding of microbial growth characteristics and the fermentation process in order to formulate reasonable regulation measures.

[0122] In a specific embodiment, set Q target to the relative abundance of OTU_A = 0.18. The abundance of OTU_A in the prediction result f(X) = 0.15, then ΔQ = 0.03. The generated regulation instruction is: increase the fermentation temperature from 30°C to 32°C. The monitored data after regulation is shown in Table 2:

[0123]

[0124] Table 2: Monitoring Data of Pineapple Wine Fermentation Quality after Regulation

[0125] From the above, it can be seen that the abundance of OTU_A increases, and the alcohol content also increases accordingly, indicating that the regulation measures are effective. Through the above steps, it is possible to dynamically adjust the parameters during the fermentation process according to the model prediction results, optimize the fermentation conditions, and thus improve the fermentation efficiency and product quality of pineapple wine.

[0126] Adjust the parameters during the fermentation process according to the generated regulation instructions through an automated control system or manual operation. For example, if the regulation instruction is to increase the fermentation temperature, then the operator or the automated system will increase the temperature set value of the fermentation tank. Execute as soon as possible after the regulation instruction is generated. The time to execute the regulation instruction depends on the specific situation of the fermentation process and the feasibility of the regulation measures. For example, if the temperature regulation system of the fermentation tank responds quickly, the temperature adjustment can be completed within a few minutes. After executing the regulation instruction, continue to monitor the changes in the microbial community and the fermentation quality indicators to evaluate the regulation effect. If the regulation measures are effective, the characteristics of the microbial community and the fermentation quality indicators will change in the expected direction; if the effect is not ideal, it may be necessary to readjust the regulation strategy.

[0127] It is carried out after executing the regulation instruction and usually takes a certain amount of time to observe the regulation effect. For example, the response of the microbial community may take several hours to a day to become apparent. The evaluation results will be fed back into the model for subsequent prediction and regulation. Update and optimize the machine learning model according to the results of the effect evaluation. If the regulation effect is good, new data can be fed back into the model to further improve the accuracy and adaptability of the model; if the effect is not good, it may be necessary to readjust the model or reselect the regulation parameters. This is a continuous process throughout the fermentation cycle. The model is usually updated and optimized after each effect evaluation to ensure that the model can better adapt to the dynamic changes during the fermentation process.

[0128] During the fermentation process, traditional regulation methods usually rely on experience or preset parameters and are difficult to dynamically adjust the fermentation conditions according to the actual changes in the microbial community, resulting in unstable fermentation efficiency and product quality. In the embodiments of the present invention, regulation instructions are generated through a machine learning model, and the parameters during the fermentation process (such as temperature, pH value, dissolved oxygen concentration, etc.) are dynamically adjusted according to the changes in the microbial community structure to ensure the optimization of the fermentation process. This method can provide real-time feedback on the changes in the microbial community and achieve precise regulation through an automated regulation unit, improving the fermentation efficiency and product quality.

[0129] Traditional statistical methods (such as regression analysis, analysis of variance, principal component analysis, etc.) have limitations in dealing with the complex non-linear relationship between microbial communities and fermentation quality, and cannot accurately capture the dynamic association between microbial community structure and fermentation quality. This technology combines machine learning algorithms with microbial community monitoring data to establish an association model between microbial community structure and fermentation quality. Machine learning algorithms can capture non-linear and complex relationships in microbial communities and identify the optimal range of key microhabitat characteristics through individual conditional expectation analysis. This method can not only accurately predict fermentation quality, but also provide a scientific basis for parameter regulation in the fermentation process.

[0130] In a specific embodiment, it further includes:

[0131] According to the microbial community information, obtain the relative abundance of harmful microorganisms;

[0132] When the relative abundance of harmful microorganisms is greater than the preset threshold, adjust the temperature or pH value of the first fermentation broth.

[0133] Exemplarily, the harmful microorganisms are acetic acid bacteria or molds.

[0134] The automated control system executes specific regulation measures according to the preset program. For example, raise the temperature of the fermentation tank to the sterilization temperature through a heating element and maintain it for a period of time; or adjust the pH value by adding acidic or alkaline solutions. It is executed immediately after the regulation instruction is generated, and the execution time depends on the complexity of the regulation measure. For example, temperature adjustment may take from a few minutes to more than ten minutes.

[0135] In a specific embodiment, if it is detected that the proportion of harmful microorganisms (such as molds) > 5%, then automatically inject probiotic preparations or adjust the pH to below 3.5, or automatically raise the temperature of the fermentation tank to the sterilization temperature (such as 121 °C) for short-term high-temperature sterilization.

[0136] In a specific embodiment, during the fermentation process of pineapple wine, through high-throughput sequencing technology, it is monitored that the relative abundance of a certain harmful microorganism (such as a certain mold) exceeds the preset 5% threshold in the monitoring on the 3rd day. Immediately start the sterilization program, raise the temperature of the fermentation tank from 30 °C to 121 °C, and maintain it for 15 minutes for high-temperature sterilization. At the same time, the system adjusts the pH value to 4.5 to inhibit the growth of harmful microorganisms. 24 hours after the regulation measures are executed, the changes in the microbial community are monitored again, and it is found that the relative abundance of harmful microorganisms drops to 2%, and the fermentation quality index returns to normal. According to the effect of this regulation, the system feeds the new data back into the model to further optimize the model.

[0137] During the fermentation process of pineapple wine, the microbial community structure is complex and undergoes significant dynamic changes. The microbial community includes not only bacteria but also various microorganisms such as yeasts and molds. These microorganisms interact with each other during the fermentation process and jointly affect the fermentation quality: The microbial community structure changes significantly during the fermentation process. For example, at the initial stage of fermentation, yeasts and molds may dominate, while at the later stage of fermentation, other acid-tolerant or alcohol-tolerant microorganisms may gradually gain the upper hand. Traditional monitoring methods are difficult to capture these dynamic changes in real time. The microbial community is not only complex and diverse in terms of species, but its functions are also extremely rich. For example, lactic acid bacteria are involved in glycolysis and acid metabolism, while yeasts are mainly responsible for ethanol synthesis. Traditional monitoring methods are difficult to deeply analyze the functional diversity of the microbial community and its relationship with fermentation quality.

[0138] Traditional monitoring methods cannot monitor the changes in the microbial community in real time and can only be analyzed after the fermentation ends. This lag makes it difficult to detect and correct problems that occur during the fermentation process in a timely manner, resulting in unstable fermentation quality. In addition, due to the lack of real-time data support, traditional monitoring methods are difficult to achieve dynamic regulation of the fermentation process. In the embodiments of the present invention, high-throughput sequencing technology is used to monitor the composition and changes of the microbial community during the fermentation process of pineapple wine in real time, and a correlation model between the microbial community structure and fermentation quality is established in combination with machine learning algorithms, which can dynamically adjust the fermentation conditions to ensure the dominant position of beneficial microorganisms, thereby improving fermentation efficiency and product quality. This method can not only monitor the changes in the microbial community in real time, but also provide a scientific basis for the optimization of the fermentation process through data analysis and model prediction.

[0139] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution is prior or posterior. The execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0140] It can be understood that the content in the above method embodiments is applicable to the device embodiments of the present invention. The functions specifically implemented by the device embodiments are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those in the above method embodiments. Please refer to Figure 2 , Figure 2 which schematically shows an automated quality monitoring system for pineapple wine fermentation, characterized in that the system includes: an acquisition module 201, a sequencing module 202, a prediction module 203, and a monitoring module 204;

[0141] Among them, the acquisition module 201 is used to acquire the first fermentation broth of the pineapple wine to be monitored.

[0142] The sequencing module 202 is used to obtain the microbial community information of the first fermentation broth according to high-throughput sequencing technology.

[0143] In this embodiment, in the step of obtaining the microbial community information of the first fermentation broth according to the high-throughput sequencing technology, the following steps are included:

[0144] Obtain a DNA sample of the first fermentation broth;

[0145] Perform PCR amplification on the 16S rRNA gene of the DNA sample according to specific primers to obtain an amplification product;

[0146] Perform high-throughput sequencing based on the amplification product to generate sequence data;

[0147] Perform clustering analysis based on the sequence data to generate the microbial community information of the first fermentation broth.

[0148] Use high-throughput sequencing technology to monitor the composition and changes of the microbial community during the pineapple wine fermentation process to ensure the dominant position of beneficial microorganisms.

[0149] In this embodiment, it further includes: screening beneficial microorganisms in the first fermentation broth according to gene editing technology combined with microbial community information. Modify the metabolic pathways of beneficial microorganisms through the CRISPR-Cas system. Screen and optimize beneficial microorganisms during the fermentation process through CRISPR-Cas gene editing technology to improve their fermentation efficiency and product quality.

[0150] The prediction module 203 is used to input the microbial community information into the pineapple wine fermentation quality prediction model to obtain a prediction result.

[0151] Among them, the training process of the pineapple wine fermentation quality prediction model is as follows:

[0152] Obtain pineapple wine fermentation quality parameters and pineapple wine fermentation microbial community data;

[0153] Train a machine learning model according to the pineapple wine fermentation quality parameters and pineapple wine fermentation microbial community data to generate a pineapple wine fermentation quality prediction model.

[0154] In this embodiment, in the step of obtaining the pineapple wine fermentation quality parameters and pineapple wine fermentation microbial community data, the following steps are included:

[0155] Obtain pineapple wine alcohol content data, pineapple wine sugar content data, and pineapple wine acidity data;

[0156] Perform data cleaning operations on the pineapple wine alcohol content data, pineapple wine sugar content data, and pineapple wine acidity data to obtain pineapple wine fermentation quality parameters;

[0157] Obtain the sequencing data of the microbial community in pineapple wine according to high-throughput sequencing technology; wherein, the sequencing data is operational taxonomic unit abundance data or amplicon sequence variant abundance data;

[0158] Perform quality control operations, low-quality sequence removal operations, splicing operations, and chimera removal operations on the sequencing data to obtain the pineapple wine fermentation microbial community data.

[0159] Further, in the step of training a machine learning model based on the pineapple wine fermentation quality parameters and the pineapple wine fermentation microbial community data to generate a pineapple wine fermentation quality prediction model, the following steps are included:

[0160] Based on the pineapple wine fermentation quality parameters and the pineapple wine fermentation microbial community data, form a training data set and a validation data set;

[0161] Input the training data set into the machine learning model and calculate the output first prediction value;

[0162] Calculate the first error between the first prediction value and the true value through a loss function;

[0163] Perform backpropagation according to the first error and update the parameters of the machine learning model;

[0164] Validate the machine learning model according to the validation data set to generate a pineapple wine fermentation quality prediction model.

[0165] In this embodiment, use a machine learning algorithm combined with microbial community monitoring data to establish an association model between the microbial community structure and the fermentation quality, and generate a regulation instruction.

[0166] The monitoring module 204 is used to monitor the quality of the pineapple wine to be monitored according to the prediction result. Automatically adjust the parameters during the fermentation process according to the regulation instruction to optimize the fermentation conditions.

[0167] In this embodiment, in the step of monitoring the quality of the pineapple wine to be monitored according to the prediction result, the following steps are included:

[0168] Obtain the first correlation between the pineapple wine fermentation quality parameters and the pineapple wine fermentation microbial community data according to the prediction result;

[0169] Set a regulation target in combination with the pineapple wine fermentation microbial community data according to the first correlation;

[0170] Regulate the pineapple wine fermentation quality parameters according to the regulation target.

[0171] In a specific embodiment, it further includes:

[0172] Obtain the relative abundance of harmful microorganisms according to the microbial community information;

[0173] When the relative abundance of harmful microorganisms is greater than a preset threshold, adjust the temperature or pH value of the first fermentation broth.

[0174] An automated quality monitoring system for pineapple wine fermentation combines the real-time monitoring of microbial communities by high-throughput sequencing technology and the optimization of microorganisms by gene editing technology. At the same time, the fermentation parameters are dynamically adjusted through an automated system to ensure the optimization of the fermentation process. By using high-throughput sequencing technology to monitor the composition and changes of microbial communities in the pineapple wine fermentation process in real time, and establishing an association model between the microbial community structure and fermentation quality by combining machine learning algorithms, the fermentation conditions can be dynamically adjusted to ensure the dominant position of beneficial microorganisms, thereby improving fermentation efficiency and product quality. This method can not only monitor the changes of microbial communities in real time, but also provide a scientific basis for the optimization of the fermentation process through data analysis and model prediction.

[0175] For the specific limitations of an automated quality monitoring system for pineapple wine fermentation, reference can be made to the limitations of an automated quality monitoring method for pineapple wine fermentation in the above text, which will not be elaborated here. Each module in the above-mentioned automated quality monitoring system for pineapple wine fermentation can be implemented in whole or in part by software, hardware, and their combinations. The above-mentioned modules can be embedded in the processor of the electronic device in hardware form or be independent of it, or be stored in the memory of the electronic device in software form, so that the processor can call and execute the operations corresponding to each of the above modules.

[0176] It can be understood that the content in the above method embodiments is applicable to the device embodiments of the present application. The functions specifically implemented by the device embodiments of the present application are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those of the above method embodiments.

[0177] In one embodiment, an electronic device is provided. The electronic device can be a server, and its internal structure diagram can be as Figure 3 shown. The electronic device includes:

[0178] A processor 801, which can be implemented in ways such as a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided by the embodiments of the present application;

[0179] The memory 802 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM), etc. The memory 802 can store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 802 and are called by the processor 801 to execute the vehicle sideslip angle calculation method of the embodiments of this application;

[0180] The input / output interface 803 is used to implement information input and output;

[0181] The communication interface 804 is used to implement communication interaction between this device and other devices, and can communicate through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.);

[0182] The bus 805 transmits information between various components of the device (such as the processor 801, the memory 802, the input / output interface 803, and the communication interface 804);

[0183] Among them, the processor 801, the memory 802, the input / output interface 803, and the communication interface 804 are communicatively connected to each other inside the device through the bus 805.

[0184] Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the electronic device is used to store the database. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements an automated quality monitoring method for pineapple wine fermentation.

[0185] In one embodiment, an electronic device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented:

[0186] Obtain the first fermentation broth of the pineapple wine to be monitored;

[0187] Obtain the microbial community information of the first fermentation broth according to high-throughput sequencing technology;

[0188] Input the microbial community information into the pineapple wine fermentation quality prediction model to obtain a prediction result;

[0189] Perform quality monitoring on the pineapple wine to be monitored according to the prediction results;

[0190] Among them, the training process of the pineapple wine fermentation quality prediction model is as follows:

[0191] Obtain the pineapple wine fermentation quality parameters and the pineapple wine fermentation microbial community data;

[0192] Train a machine learning model based on the pineapple wine fermentation quality parameters and the pineapple wine fermentation microbial community data to generate a pineapple wine fermentation quality prediction model.

[0193] In one embodiment, a storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0194] Obtain the first fermentation broth of the pineapple wine to be monitored;

[0195] Obtain the microbial community information of the first fermentation broth according to the high-throughput sequencing technology;

[0196] Input the microbial community information into the pineapple wine fermentation quality prediction model to obtain the prediction results;

[0197] Perform quality monitoring on the pineapple wine to be monitored according to the prediction results;

[0198] Among them, the training process of the pineapple wine fermentation quality prediction model is as follows:

[0199] Obtain the pineapple wine fermentation quality parameters and the pineapple wine fermentation microbial community data;

[0200] Train a machine learning model based on the pineapple wine fermentation quality parameters and the pineapple wine fermentation microbial community data to generate a pineapple wine fermentation quality prediction model.

[0201] In the embodiments of the present application, the automated quality monitoring method and system for pineapple wine fermentation obtain the microbial community information of the first fermentation broth of the pineapple wine to be monitored through high-throughput sequencing technology, input the microbial community information into the pineapple wine fermentation quality prediction model to obtain a prediction result, and finally perform quality monitoring on the pineapple wine to be monitored according to the prediction result; among them, the pineapple wine fermentation quality prediction model is trained by a machine learning model based on pineapple wine fermentation quality parameters and pineapple wine fermentation microbial community data. By combining the machine learning model with microbial community monitoring data, an association model between the microbial community structure and fermentation quality is established, which can capture the non-linear and complex relationships in the microbial community and identify the optimal range of key microhabitat characteristics through individual conditional expectation analysis. It can not only accurately predict the fermentation quality, but also provide a scientific basis for parameter regulation in the fermentation process. Further, the technical solution of the present invention performs quality monitoring through the prediction result generated by the pineapple wine fermentation quality prediction model, thereby improving the accuracy of automated quality monitoring for pineapple wine fermentation, dynamically adjusting the parameters in the fermentation process according to the changes in the microbial community structure, ensuring the optimization of the fermentation process, being able to provide real-time feedback on the changes in the microbial community, and achieving precise regulation through the automated control unit, improving the fermentation efficiency and product quality. Moreover, the technical solution of the present invention uses 16S rRNA gene amplicon high-throughput sequencing technology to amplify and sequence the 16S rRNA gene in the microbial community through specific primers, and can quickly and accurately obtain the composition information of the microbial community. This method does not depend on the culturing ability of bacteria in the sample and can comprehensively cover all microorganisms in the sample, including those that are difficult to culture. At the same time, high-throughput sequencing technology can process a large number of samples in a short time, providing an efficient technical means for monitoring the microbial community in the fermentation process.

[0202] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0203] Those skilled in the art can clearly understand that for the convenience and brevity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0204] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. An automated quality monitoring method for pineapple wine fermentation, characterized in that the method Including: Obtain the first fermentation broth of the pineapple wine to be monitored; Obtain the microbial community information of the first fermentation broth according to the high-throughput sequencing technology; Input the microbial community information into the pineapple wine fermentation quality prediction model to obtain a prediction result; Perform quality monitoring on the pineapple wine to be monitored according to the prediction result; Among them, the training process of the pineapple wine fermentation quality prediction model is as follows: Obtain the pineapple wine fermentation quality parameters and the pineapple wine fermentation microbial community data; Train a machine learning model according to the pineapple wine fermentation quality parameters and the pineapple wine fermentation microbial community data to generate the pineapple wine fermentation quality prediction model.

2. An automated quality monitoring method for pineapple wine fermentation according to claim 1, characterized in that, In the step of training a machine learning model according to the pineapple wine fermentation quality parameters and the pineapple wine fermentation microbial community data to generate the pineapple wine fermentation quality prediction model, the following steps are included: According to the pineapple wine fermentation quality parameters and the pineapple wine fermentation microbial community data, form a training data set and a validation data set; Input the training data set into the machine learning model and calculate the output of the first predicted value; Calculate the first error between the first predicted value and the true value through a loss function; Perform backpropagation according to the first error to update the parameters of the machine learning model; Verify the machine learning model according to the validation data set to generate the pineapple wine fermentation quality prediction model.

3. An automated quality monitoring method for pineapple wine fermentation according to claim 2, characterized in that, In the step of obtaining the pineapple wine fermentation quality parameters and the pineapple wine fermentation microbial community data, the following steps are included: Obtain the pineapple wine alcohol content data, the pineapple wine sugar content data, and the pineapple wine acidity data; Perform data cleaning operations on the pineapple wine alcohol content data, the pineapple wine sugar content data, and the pineapple wine acidity data to obtain the pineapple wine fermentation quality parameters; Obtain the sequencing data of the microbial community in the pineapple wine according to the high-throughput sequencing technology; among them, the sequencing data is operational taxonomic unit abundance data or amplicon sequence variant abundance data; Perform quality control operations, low-quality sequence removal operations, splicing operations, and chimera removal operations on the sequencing data to obtain the pineapple wine fermentation microbial community data.

4. An automated quality monitoring method for pineapple wine fermentation according to claim 3, characterized in that, In the step of performing quality monitoring on the pineapple wine to be monitored according to the prediction result, the following steps are included: Obtain the first correlation between the pineapple wine fermentation quality parameters and the pineapple wine fermentation microbial community data according to the prediction result; Set a regulation target according to the first correlation and in combination with the pineapple wine fermentation microbial community data; Regulate the pineapple wine fermentation quality parameters according to the regulation target.

5. An automated quality monitoring method for pineapple wine fermentation according to claim 4, characterized in that, It also includes: Obtain the relative abundance of harmful microorganisms according to the microbial community information; When the relative abundance of harmful microorganisms is greater than a preset threshold, adjust the temperature or pH value of the first fermentation broth.

6. An automated quality monitoring method for pineapple wine fermentation according to claim 5, characterized in that, In the step of obtaining the microbial community information of the first fermentation broth according to the high-throughput sequencing technology, the following steps are included: Obtain the DNA sample of the first fermentation broth; Perform PCR amplification on the 16S rRNA gene of the DNA sample according to specific primers to obtain an amplification product; Based on the amplified product, high-throughput sequencing is performed to generate sequence data; Based on the sequence data, cluster analysis is performed to generate the microbial community information of the first fermentation broth.

7. An automated quality monitoring method for pineapple wine fermentation according to claim 6, characterized in that, It further includes: According to gene editing technology and in combination with the microbial community information, beneficial microorganisms in the first fermentation broth are screened; The metabolic pathways of the beneficial microorganisms are modified through the CRISPR-Cas system.

8. An automated quality monitoring system for pineapple wine fermentation, characterized in that, The system includes: an acquisition module, a sequencing module, a prediction module, and a monitoring module; Among them, the acquisition module is used to acquire the first fermentation broth of the pineapple wine to be monitored; The sequencing module is used to obtain the microbial community information of the first fermentation broth according to high-throughput sequencing technology; The prediction module is used to input the microbial community information into the pineapple wine fermentation quality prediction model to obtain a prediction result; The monitoring module is used to perform quality monitoring on the pineapple wine to be monitored according to the prediction result; Among them, the training process of the pineapple wine fermentation quality prediction model is: Obtain the pineapple wine fermentation quality parameters and the pineapple wine fermentation microbial community data; According to the pineapple wine fermentation quality parameters and the pineapple wine fermentation microbial community data, a machine learning model is trained to generate the pineapple wine fermentation quality prediction model.

9. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, the steps of an automated quality monitoring method for pineapple wine fermentation according to any one of claims 1 to 7 are implemented.

10. A storage medium stores a computer program, characterized in that, When the computer program is executed by the processor, the steps of an automated quality monitoring method for pineapple wine fermentation according to any one of claims 1 to 7 are implemented.

Images