Microbial agent preparation control method based on bacterial strain reproduction characteristic analysis

Abstract

The invention discloses a microbial agent preparation control method based on bacterial strain reproduction characteristic analysis, and aims to improve the preparation quality of a microbial agent. The method comprises the following steps: acquiring reproduction data and metabolite data of a target strain, carrying out environmental sensitivity analysis to obtain a reproduction-environmental sensitivity index and a metabolism-environmental sensitivity index, further constructing a preparation quality prediction model, and carrying out real-time prediction on the quality of the target microbial agent. By comparing actual preparation quality data, whether metabolic imbalance exists or not is judged, and actual metabolite change data is obtained. And analyzing the data by adopting Fourier transform, identifying the change characteristics of metabolites, and finally determining a metabolic optimization strategy so as to optimize the preparation process. The quality of the microbial agent can be effectively controlled, the production efficiency is improved, and the stability of the product is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of microbial agent preparation, and in particular to a microbial agent preparation control method based on strain reproduction characteristic analysis. Background Art

[0002] With the continuous development of microbial technology, the application of microbial agents in agriculture, environmental protection, food industry and other fields has gradually attracted widespread attention. As an important biological agent, the preparation quality of microbial agents directly affects their application effect and economic benefits. Therefore, improving the production efficiency and quality of microbial agents has become an urgent problem to be solved in the current field of microbial preparation.

[0003] In the preparation process of microbial inoculants, the reproduction characteristics of the strains and the changes in metabolites are key factors affecting the quality of the inoculants. Traditional methods for preparing microbial inoculants often rely on experience and experimental data, making it difficult to accurately predict quality fluctuations during the preparation process and lacking systematic quality control methods. This method is not only inefficient and costly, but also difficult to cope with complex production environments and dynamic changes in strain metabolism.

[0004] At present, there are some quality control methods based on strain growth characteristics or metabolic processes, but these methods generally lack consideration of environmental factors and interactions between strains, and cannot achieve precise regulation of strain growth and metabolism under variable environmental conditions. Especially in large-scale industrial production, how to effectively control the quality of microbial agents and improve the controllability and stability of the preparation process is still a technical problem.

[0005] Therefore, the present invention provides a microbial agent preparation control method based on strain reproduction characteristic analysis, which aims to establish an efficient quality prediction and optimization mechanism by systematically analyzing the reproduction characteristics and metabolite changes of the target strain under different environmental conditions, thereby overcoming the defects in the prior art and improving the production quality and stability of the microbial agent. Summary of the invention

[0006] In order to solve at least one of the above technical problems, the present invention proposes a microbial agent preparation control method based on strain reproduction characteristic analysis.

[0007] The first aspect of the present invention provides a method for controlling the preparation of a microbial agent based on strain reproduction characteristics analysis, comprising: Obtain target strain type data required for preparation of target microbial inoculants, obtain reproduction data and metabolite data of each target strain under various environmental characteristics, perform environmental sensitivity analysis on the target strain based on the reproduction data and metabolite data, and determine the reproduction-environmental sensitivity index and metabolism-environmental sensitivity index of each target strain; Constructing a preparation quality prediction model of the target microbial agent according to the reproduction-environment sensitivity index and the metabolism-environment sensitivity index, and predicting the current preparation quality of the target microbial agent according to the preparation quality prediction model to obtain a preparation quality prediction result; Acquire actual preparation quality data of the target microbial inoculant, compare the actual preparation quality data with the preparation quality prediction result, and determine the metabolic imbalance state of the target strain; If the target strain is in a metabolic imbalance state, obtain actual metabolite change data of the target microbial inoculant, analyze the actual metabolite change data based on Fourier transform, and determine the change characteristics of the actual metabolites; The metabolic optimization strategy for each time node is determined according to the change characteristics of the actual metabolites.

[0008] In this scheme, the reproduction data and metabolite data of each target strain under various environmental characteristics are obtained, and the environmental sensitivity analysis of the target strain is performed based on the reproduction data and metabolite data to determine the reproduction-environmental sensitivity index and metabolism-environmental sensitivity index of each target strain, specifically: Obtain strain samples of each target strain type according to the target strain type data, place the strain samples under different environmental characteristics for reproduction and preparation of target microbial agents, and obtain reproduction data and metabolite data of the target strains under various environmental characteristics for reproduction and preparation of target microbial agents; The reproduction data and metabolite data were combined with each environmental characteristic to construct the reproduction-environment data matrix and the metabolism-environment data matrix; Calculating the covariance matrix of the reproduction-environment data matrix and the metabolism-environment data matrix, calculating the eigenvalues ​​and eigenvectors of the covariance matrix, and selecting the eigenvectors corresponding to the first k largest eigenvalues ​​to construct an eigenvector matrix; According to the multiplication of the reproduction-environment data matrix and the metabolism-environment data matrix with the corresponding eigenvector matrix, a reproduction-environment principal component score matrix and a metabolism-environment principal component score matrix are obtained; The degree of influence of each environmental characteristic on the reproduction and metabolism of the target strain is determined according to the reproduction-environment principal component score matrix and the metabolism-environment principal component score matrix to obtain the reproduction-environment sensitivity index and the metabolism-environment sensitivity index.

[0009] In this scheme, the preparation quality prediction model of the target microbial agent is constructed according to the reproduction-environmental sensitivity index and the metabolism-environmental sensitivity index, and the current preparation quality of the target microbial agent is predicted according to the preparation quality prediction model to obtain the preparation quality prediction result, which is specifically: Obtaining the reproduction data and metabolic data of the target strain during the preparation of the target microbial agent, performing a correlation analysis on the reproduction data and the metabolic data based on the Pearson correlation coefficient, determining the influence of the reproduction of the target strain on the metabolic condition, and obtaining the influence data; Constructing a preparation quality prediction model based on a fuzzy logic algorithm, and importing the influencing data into the preparation quality prediction model to construct the influence condition restriction of the target strain reproduction on metabolism; Using the preparation environment characteristics and the initial target strain quantity information for preparing the target microbial inoculant as input data for the preparation quality prediction model; The reproduction-environment sensitivity index and the metabolism-environment sensitivity index are introduced into the preparation quality prediction model to construct the reproduction quality membership function and the metabolism quality membership function of the target strain under different environmental characteristics; According to the influencing data, the reproduction quality membership function and the metabolic quality membership function, a preparation quality fuzzy rule base for preparing a target microbial agent by using a target strain under different strain numbers and different environmental characteristics is constructed, and the preparation quality fuzzy rule base is used as a prediction basis for a preparation quality prediction model; Obtaining initial target strain quantity information and current preparation environment characteristics for the preparation of the target microbial agent, importing the initial target strain quantity information and current preparation environment characteristics into the preparation quality prediction model, and determining the current reproduction quality and current metabolic quality of the target strain under the current preparation environment characteristics according to the reproduction quality membership function and the metabolic quality membership function and the influencing condition constraints; The current reproduction quality and the current metabolic quality are compared with the preparation quality fuzzy rule base, and the preparation quality of the target microbial agent prepared by the target strain under the current environmental characteristics is predicted to obtain a preparation quality prediction result.

[0010] In this scheme, the actual preparation quality data of the target microbial inoculant is obtained, and the actual preparation quality data is compared with the preparation quality prediction result to determine the metabolic imbalance state of the target strain, specifically: The preparation quality prediction result is used as the benchmark quality data for the preparation of the target microbial agent under the current environmental characteristics; Acquire actual preparation quality data of the target microbial inoculant prepared under current environmental characteristics, compare the actual preparation quality data with the reference quality data, and calculate the Euclidean distance between the actual preparation quality data and the reference quality data; The metabolic imbalance state of the target strain is determined according to the Euclidean distance.

[0011] In this scheme, if the target strain is in a metabolic imbalance state, the actual metabolite change data of the target microbial inoculant is obtained, and the actual metabolite change data is analyzed based on Fourier transform to determine the change characteristics of the actual metabolites, specifically: If the target strain has a metabolic imbalance, the metabolite changes of the target strain during the preparation of the target microbial agent are monitored based on a mass spectrometer to obtain actual metabolite change data, which includes actual metabolite substance type change data and actual metabolite concentration change data; Based on the Hanning window, the actual metabolite change data is framed according to a preset window size to obtain actual metabolite change data segments; Performing a fast Fourier transform on each of the actual metabolite change data segments to calculate the spectrum energy distribution of each actual metabolite change data segment; The multi-scale feature extraction of the spectrum energy distribution is performed based on the wavelet packet decomposition algorithm. The multi-scale feature includes frequency component, amplitude, phase and frequency band energy proportion of the frequency component, so as to obtain the change characteristics of the actual metabolites.

[0012] In this solution, the metabolic optimization strategy for each time node is determined according to the change characteristics of the actual metabolites, specifically: Acquire historical metabolite characteristics of different metabolic imbalance patterns of the target strain, and construct a metabolic imbalance pattern library by combining the metabolic imbalance patterns and corresponding historical metabolite characteristics; Constructing a bidirectional LSTM classification model based on an attention mechanism, performing a data link operation between the metabolic imbalance pattern library and the classification model, and constructing a multi-scale feature vector based on the change characteristics of the actual metabolites; Importing the multi-scale feature vector into the classification model to perform dynamic weight matching with each historical metabolite feature in the metabolic imbalance pattern library, and outputting a confidence matrix of the metabolic imbalance type; Determine the imbalance type of the target strain at each time point in the process of preparing the target microbial inoculant according to the confidence matrix, wherein the imbalance type includes metabolite inhibition and insufficient nutrients; The optimization strategy for each time node is determined according to the imbalance type of the target strain at each time node.

[0013] In this solution, the optimization strategy for each time node is determined according to the imbalance type of the target strain at each time node, specifically: If the imbalance type is metabolite inhibition, the type of inhibitory metabolite causing metabolic inhibition on the target strain is determined according to the actual metabolite change data, the actual metabolite change data is analyzed based on a back propagation network to determine the production rate mutation point of the inhibitory metabolite, and the metabolic change path of the inhibitory metabolite is determined according to the production rate mutation point; Determine the inhibition time point of the inhibitory metabolite on the metabolism of the target strain according to the metabolic change path, obtain the molecular size data of the inhibitory metabolite type, perform pore size matching of the nanoporous material according to the molecular size data to obtain the pore size distribution of the nanoporous material, and perform an adsorption operation on the inhibitory metabolite at the inhibition time point according to the nanoporous material with the pore size distribution to obtain a first metabolic optimization strategy; If the imbalance type is insufficient nutrients, obtain the reproduction number change information of each target strain during the preparation of the target microbial inoculant. If the reproduction number of a certain target strain continues to increase while the reproduction of another target strain stagnates, the type of insufficient nutrients is marked as bacterial nutrient competition type. If all target strains stop reproducing, the type of insufficient nutrients is marked as substrate component deficiency type. When the type of nutrient deficiency is bacterial nutrient competition type, the Lotka-Volterra competition model is used to invert the replacement trajectory of the dominant bacterial community, and the competitive strain type and the competitive substrate type are identified according to the replacement trajectory. The addition type of the competitive inhibitor and the substrate supplement type are determined according to the competitive strain type and the competitive substrate type. The nutrient components prepared by the target microbial inoculant are adjusted according to the addition type of the competitive inhibitor and the substrate supplement type to obtain the second metabolic optimization strategy; When the type of nutrient deficiency is substrate deficiency, the concentration change data of the substrate is obtained, and the substrate deficiency type is determined according to the substrate concentration change data. The nutrient components of the target strain in the target microbial agent preparation process are supplemented according to the substrate deficiency type to obtain a third metabolic optimization strategy.

[0014] The second aspect of the present invention further provides a microbial inoculant preparation control system based on strain reproduction characteristic analysis, the system comprising: a memory, a processor, the memory comprising a microbial inoculant preparation control method program based on strain reproduction characteristic analysis, the microbial inoculant preparation control method program based on strain reproduction characteristic analysis when executed by the processor, implements the following steps: Obtain target strain type data required for preparation of target microbial inoculants, obtain reproduction data and metabolite data of each target strain under various environmental characteristics, perform environmental sensitivity analysis on the target strain based on the reproduction data and metabolite data, and determine the reproduction-environmental sensitivity index and metabolism-environmental sensitivity index of each target strain; Constructing a preparation quality prediction model of the target microbial agent according to the reproduction-environment sensitivity index and the metabolism-environment sensitivity index, and predicting the current preparation quality of the target microbial agent according to the preparation quality prediction model to obtain a preparation quality prediction result; Acquire actual preparation quality data of the target microbial inoculant, compare the actual preparation quality data with the preparation quality prediction result, and determine the metabolic imbalance state of the target strain; If the target strain is in a metabolic imbalance state, obtain actual metabolite change data of the target microbial inoculant, analyze the actual metabolite change data based on Fourier transform, and determine the change characteristics of the actual metabolites; The metabolic optimization strategy for each time node is determined according to the change characteristics of the actual metabolites.

[0015] The present invention discloses a microbial agent preparation control method based on strain reproduction characteristic analysis, aiming to improve the preparation quality of the agent. By obtaining the reproduction data and metabolite data of the target strain, an environmental sensitivity analysis is performed to obtain the reproduction-environmental sensitivity index and the metabolism-environmental sensitivity index, and then a preparation quality prediction model is constructed to predict the quality of the target microbial agent in real time. By comparing the actual preparation quality data, it is determined whether there is a metabolic imbalance, and the actual metabolite change data is obtained. Fourier transform is used to analyze these data, identify the characteristics of metabolite changes, and finally determine the metabolic optimization strategy to optimize the preparation process. The present invention can effectively control the quality of the microbial agent, improve production efficiency, and ensure the stability of the product. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flow chart showing a method for controlling the preparation of a microbial agent based on strain reproduction characteristics analysis of the present invention is shown; Figure 2 A flow chart of the present invention for determining the metabolic imbalance state of a target strain is shown; Figure 3 A flow chart showing the present invention for determining the changing characteristics of actual metabolites; Figure 4 A block diagram of a microbial inoculant preparation control system based on strain reproduction characteristic analysis of the present invention is shown. DETAILED DESCRIPTION

[0017] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0018] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0019] Figure 1 The flowchart of the present invention shows a method for controlling the preparation of a microbial agent based on the analysis of the reproduction characteristics of the strain.

[0020] like Figure 1 As shown, the first aspect of the present invention provides a method for controlling the preparation of a microbial agent based on strain reproduction characteristics analysis, comprising: S102, obtaining target strain type data required for preparing the target microbial agent, obtaining reproduction data and metabolite data of each target strain under various environmental characteristics, performing environmental sensitivity analysis on the target strain according to the reproduction data and metabolite data, and determining the reproduction-environmental sensitivity index and metabolism-environmental sensitivity index of each target strain; S104, constructing a preparation quality prediction model of the target microbial agent according to the reproduction-environment sensitivity index and the metabolism-environment sensitivity index, and predicting the current preparation quality of the target microbial agent according to the preparation quality prediction model to obtain a preparation quality prediction result; S106, obtaining actual preparation quality data of the target microbial inoculant, comparing the actual preparation quality data with the preparation quality prediction result, and determining the metabolic imbalance state of the target strain; S108, if the target strain is in a metabolic imbalance state, obtaining actual metabolite change data of the target microbial inoculant, analyzing the actual metabolite change data based on Fourier transform, and determining the change characteristics of the actual metabolites; S110, determining a metabolic optimization strategy for each time node according to the change characteristics of the actual metabolites.

[0021] It should be noted that by obtaining the reproduction data and metabolite data of the target strain and conducting environmental sensitivity analysis, we can deeply understand the specific effects of different environmental characteristics on the growth and metabolism of the strain, thereby obtaining the reproduction-environmental sensitivity index and the metabolism-environmental sensitivity index, which provide a scientific basis for the prediction of the preparation quality of the microbial agent. Secondly, the preparation quality prediction model established based on these indices can predict the preparation quality of the target microbial agent in real time, discover potential quality fluctuations and risks in advance, and thus optimize the production process. In addition, by comparing and analyzing the actual preparation quality data, it is possible to timely determine whether the strain is in a metabolic imbalance state and avoid the influence of unstable factors on the quality of the microbial agent. Once metabolic imbalance is found, the change characteristics of the metabolites are analyzed by Fourier transform, which provides precise guidance for adjusting the metabolic process of the strain and optimizing the production conditions, ensuring the stability and efficiency of the microbial agent. Finally, by dynamically adjusting the optimization strategy, the preparation conditions of the microbial agent can be adjusted in real time at different production stages, thereby improving production efficiency and reducing costs. The target strain types required for the preparation of the target microbial agent of the present invention include one or more types, and the preparation of the target microbial agent first requires the propagation of the target strain, and then the propagated target strain is subjected to metabolic fermentation, and the metabolites can be used to prepare the target microbial agent, and finally the prepared product is obtained.

[0022] According to an embodiment of the present invention, the reproduction data and metabolite data of each target strain under each environmental characteristic are obtained, and the environmental sensitivity analysis of the target strain is performed according to the reproduction data and metabolite data to determine the reproduction-environmental sensitivity index and metabolism-environmental sensitivity index of each target strain, specifically: Obtain strain samples of each target strain type according to the target strain type data, place the strain samples under different environmental characteristics for reproduction and preparation of target microbial agents, and obtain reproduction data and metabolite data of the target strains under various environmental characteristics for reproduction and preparation of target microbial agents; The reproduction data and metabolite data were combined with each environmental characteristic to construct the reproduction-environment data matrix and the metabolism-environment data matrix; Calculating the covariance matrix of the reproduction-environment data matrix and the metabolism-environment data matrix, calculating the eigenvalues ​​and eigenvectors of the covariance matrix, and selecting the eigenvectors corresponding to the first k largest eigenvalues ​​to construct an eigenvector matrix; According to the multiplication of the reproduction-environment data matrix and the metabolism-environment data matrix with the corresponding eigenvector matrix, a reproduction-environment principal component score matrix and a metabolism-environment principal component score matrix are obtained; The degree of influence of each environmental characteristic on the reproduction and metabolism of the target strain is determined according to the reproduction-environment principal component score matrix and the metabolism-environment principal component score matrix to obtain the reproduction-environment sensitivity index and the metabolism-environment sensitivity index.

[0023] It should be noted that after the principal component analysis algorithm (PCA) is introduced to construct the reproduction data and metabolite data with each environmental feature into a reproduction-environment data matrix and a metabolism-environment data matrix, the calculated covariance matrix can reflect the degree of linear correlation between the variables in the data set (environmental features and reproduction and metabolism data). The eigenvalue in the covariance matrix represents the data variance in the direction of the corresponding eigenvector. The larger the variance, the more information the data in that direction contains. The principal component score matrix is ​​obtained by multiplying the original data matrix (reproduction-environment data matrix and metabolism-environment data matrix) with the eigenvector matrix. The principal component score matrix maps the original reproduction-environment data matrix and metabolism-environment data matrix to a new space composed of principal components (directions determined by the eigenvectors corresponding to the first k largest eigenvalues). In this new space, each principal component represents a comprehensive mode of influence of environmental factors on reproduction or metabolism. The size of the principal component score reflects the degree of performance of each sample (i.e., strain experimental samples under different environmental characteristics) under these comprehensive influence modes. The principal component with a large score change has a more significant effect on reproduction or metabolism corresponding to the combination of environmental factors. By analyzing the relationship between the principal component score and the original environmental characteristics, the degree of influence of each environmental characteristic on reproduction and metabolism can be determined, and then the reproduction-environment sensitivity index and metabolism-environment sensitivity index can be obtained; the reproduction-environment sensitivity index reflects the growth rate, reproduction cycle and other characteristics of microorganisms in different environments; the metabolism-environment sensitivity index evaluates the degree of change of metabolites (such as organic acids, amino acids, enzymes, etc.) of microbial strains in different environments; the reproduction data includes the change of reproduction rate and the reproduction number of the target strain, the reproduction cycle data, and the metabolite data includes the type of metabolites and the change of metabolite content; the environmental characteristics include temperature, pH value, oxygen concentration, and nutrient content. The reproduction-environment sensitivity index reflects the significance of the change of strain reproduction (such as growth rate, cell density, etc.) when the environmental factors (such as temperature, nutrients, etc.) change. The higher the index, the more sensitive the environmental characteristics are to the reproduction of the strain, that is, a small change in the environmental factors will cause a large change in the reproduction of the strain; the metabolism-environment sensitivity index reflects the significance of the change of strain metabolites (type, concentration, yield, etc.) when the environmental factors change. The higher the index, the more sensitive the environmental factors are to the metabolism of the strain, and environmental changes will significantly affect the production of metabolites.

[0024] According to an embodiment of the present invention, the preparation quality prediction model of the target microbial agent is constructed according to the reproduction-environmental sensitivity index and the metabolism-environmental sensitivity index, and the current preparation quality of the target microbial agent is predicted according to the preparation quality prediction model to obtain a preparation quality prediction result, which is specifically: Obtaining the reproduction data and metabolic data of the target strain during the preparation of the target microbial agent, performing a correlation analysis on the reproduction data and the metabolic data based on the Pearson correlation coefficient, determining the influence of the reproduction of the target strain on the metabolic condition, and obtaining the influence data; Constructing a preparation quality prediction model based on a fuzzy logic algorithm, and importing the influencing data into the preparation quality prediction model to construct the influence condition restriction of the target strain reproduction on metabolism; Using the preparation environment characteristics and the initial target strain quantity information for preparing the target microbial inoculant as input data for the preparation quality prediction model; The reproduction-environment sensitivity index and the metabolism-environment sensitivity index are introduced into the preparation quality prediction model to construct the reproduction quality membership function and the metabolism quality membership function of the target strain under different environmental characteristics; According to the influencing data, the reproduction quality membership function and the metabolic quality membership function, a preparation quality fuzzy rule base for preparing a target microbial agent by using a target strain under different strain numbers and different environmental characteristics is constructed, and the preparation quality fuzzy rule base is used as a prediction basis for a preparation quality prediction model; Obtaining initial target strain quantity information and current preparation environment characteristics for the preparation of the target microbial agent, importing the initial target strain quantity information and current preparation environment characteristics into the preparation quality prediction model, and determining the current reproduction quality and current metabolic quality of the target strain under the current preparation environment characteristics according to the reproduction quality membership function and the metabolic quality membership function and the influencing condition constraints; The current reproduction quality and the current metabolic quality are compared with the preparation quality fuzzy rule base, and the preparation quality of the target microbial agent prepared by the target strain under the current environmental characteristics is predicted to obtain a preparation quality prediction result.

[0025] It should be noted that since the reproduction of the target strain will affect the metabolism of the target strain in the subsequent preparation of the target microbial inoculant, for example, if the reproduction number is too small, it will affect the subsequent production of metabolites. Therefore, the reproduction and metabolism are analyzed for correlation to determine the influence of the reproduction of the target strain on the metabolism; a preparation quality prediction model is constructed based on the fuzzy logic algorithm, and the above-mentioned influencing data are imported into the model to construct the conditional restrictions on the influence of the reproduction of the target strain on the metabolism. The growth and metabolism of microorganisms are greatly affected by environmental factors. Different environmental characteristics such as temperature, pH value, oxygen concentration, nutrient content, and the initial number of strains will affect the quality of inoculant preparation. The fuzzy logic algorithm can handle these multi-dimensional input information well, and consider their impact on the preparation quality. The reproduction-environmental sensitivity index and the metabolism-environmental sensitivity index are imported into the preparation quality prediction model to construct the reproduction quality membership function and metabolic quality membership function of the target strain under different environmental characteristics. The membership function can fuzzify the reproduction and metabolic quality of strains under different environments and describe the relationship between them and environmental characteristics, which is in line with the actual situation that the quality state in the process of microbial growth and metabolism is not absolutely clear. According to the influence data, the reproduction quality membership function and the metabolic quality membership function, a fuzzy rule base for the preparation quality of the target strain under different strain numbers and different environmental characteristics is constructed, and it is used as the prediction basis of the preparation quality prediction model. The fuzzy rule base integrates the relationship and influence of various factors, and contains fuzzy rules for preparation quality under different conditions, such as simulation rules such as high reproduction quality and high metabolic quality, high preparation quality. The reproduction data includes the reproduction number and the reproduction cycle; the metabolic data includes the type of metabolites, the content of metabolites, and the metabolic rate; the influence data is the influence of the different reproduction numbers and reproduction cycles of the target strain on the changes in the type and content of metabolites and the changes in the metabolic rate; the influence condition is limited to the metabolic information of the target strain in the preparation process of the target microbial agent under different reproduction conditions, that is, the metabolic information of the target strain under different reproduction conditions; the higher the reproduction-environment sensitivity index in the reproduction membership function, the lower the reproduction quality under the corresponding environmental characteristics.

[0026] Figure 2 A flow chart of the present invention for determining the metabolic imbalance state of a target strain is shown.

[0027] According to an embodiment of the present invention, the actual preparation quality data of the target microbial inoculant is obtained, the actual preparation quality data is compared with the preparation quality prediction result, and the metabolic imbalance state of the target strain is determined, specifically: S202, using the preparation quality prediction result as the benchmark quality data for preparing the target microbial agent under the current environmental characteristics; S204, obtaining actual preparation quality data of the target microbial inoculant prepared under the current environmental characteristics, comparing the actual preparation quality data with the reference quality data, and calculating the Euclidean distance between the actual preparation quality data and the reference quality data; S206, determining the metabolic imbalance state of the target strain according to the Euclidean distance.

[0028] It should be noted that if the Euclidean distance is greater than the preset value, it is considered that the target strain has a metabolic imbalance. Since the reproduction and metabolism of the target strain are different under different environmental characteristics, the preparation quality of the target microbial agent under different environmental characteristics will be different. Therefore, the preparation quality prediction result is used as the benchmark quality data for the preparation of the target microbial agent under the current environmental characteristics. By comparing the benchmark quality data with the actual preparation quality data, it can be found that when the Euclidean distance between the quality of the target microbial agent prepared under the current environmental characteristics and the actual preparation quality is greater than the preset value, it means that the difference between the actual preparation quality and the preparation-based quality is too large. It can be considered that the metabolic imbalance of the target strain has led to a decrease in the preparation quality of the target microbial agent.

[0029] Figure 3 A flow chart of the present invention for determining the changing characteristics of actual metabolites is shown.

[0030] According to an embodiment of the present invention, if the target strain is in a metabolic imbalance state, the actual metabolite change data of the target microbial inoculant is obtained, and the actual metabolite change data is analyzed based on Fourier transform to determine the change characteristics of the actual metabolites, specifically: S302, if the target strain has a metabolic imbalance, monitor the metabolite changes of the target strain during the preparation of the target microbial inoculant based on a mass spectrometer to obtain actual metabolite change data, wherein the actual metabolite change data includes actual metabolite substance type change data and actual metabolite concentration change data; S304, performing a frame operation on the actual metabolite change data according to a preset window size based on a Hanning window to obtain actual metabolite change data segments; S306, performing a fast Fourier transform on each of the actual metabolite change data segments, and calculating the spectrum energy distribution of each actual metabolite change data segment; S308, extracting multi-scale features of the spectrum energy distribution based on a wavelet packet decomposition algorithm, wherein the multi-scale features include frequency components, amplitudes of frequency components, phases, and frequency band energy proportions, to obtain change characteristics of actual metabolites.

[0031] It should be noted that the fast Fourier transform algorithm can convert the actual metabolite change data in the time domain into the frequency domain, so that the periodicity, frequency characteristics and other information that are difficult to find in the time domain can be clearly presented. For example, the periodic frequency of the metabolite concentration change can be accurately known through frequency domain analysis, which helps to understand the rhythm of strain metabolism. On this basis, the wavelet packet decomposition algorithm further extracts multi-scale features of the spectrum energy distribution, and can obtain richer and more detailed metabolite change characteristics, such as frequency components, frequency component amplitudes, phases, and frequency band energy proportions. These features can reflect the essence of metabolite changes from different angles. For example, the frequency band energy proportion can reflect the contribution of different frequency ranges to the overall metabolic changes. Through real-time monitoring and analysis of actual metabolite change data, the fast Fourier transform algorithm and wavelet packet decomposition algorithm can keenly capture the slight abnormalities in metabolite changes. Before the target strain shows obvious metabolic imbalance, it may have been reflected in the change characteristics of the metabolites, such as abnormal fluctuations in the amplitude of certain frequency components, or changes in the frequency band energy proportion that deviate from the normal range. These early abnormal signals can serve as early warning indicators to help technicians detect potential metabolic imbalances in a timely manner.

[0032] According to an embodiment of the present invention, the metabolic optimization strategy for each time node is determined according to the change characteristics of the actual metabolites, specifically: Acquire historical metabolite characteristics of different metabolic imbalance patterns of the target strain, and construct a metabolic imbalance pattern library by combining the metabolic imbalance patterns and corresponding historical metabolite characteristics; Constructing a bidirectional LSTM classification model based on an attention mechanism, performing a data link operation between the metabolic imbalance pattern library and the classification model, and constructing a multi-scale feature vector based on the change characteristics of the actual metabolites; Importing the multi-scale feature vector into the classification model to perform dynamic weight matching with each historical metabolite feature in the metabolic imbalance pattern library, and outputting a confidence matrix of the metabolic imbalance type; Determine the imbalance type of the target strain at each time point in the process of preparing the target microbial inoculant according to the confidence matrix, wherein the imbalance type includes metabolite inhibition and insufficient nutrients; The optimization strategy for each time node is determined according to the imbalance type of the target strain at each time node.

[0033] It should be noted that by obtaining the historical metabolite characteristics of different metabolic imbalance patterns of the target strain and constructing a metabolic imbalance pattern library, and then combining the bidirectional LSTM (long short-term memory network) classification model based on the attention mechanism, the change characteristics of the actual metabolites can be compared and analyzed with the historical data. This method utilizes the empirical information in the historical data, making the analysis of the current actual metabolite change characteristics more comprehensive and accurate, so that the imbalance type of the target strain at each time point in the preparation process of the target microbial inoculant can be accurately determined, such as metabolite inhibition or insufficient nutrients.

[0034] According to an embodiment of the present invention, the optimization strategy for each time node is determined according to the imbalance type of the target strain at each time node, specifically: If the imbalance type is metabolite inhibition, the type of inhibitory metabolite causing metabolic inhibition on the target strain is determined according to the actual metabolite change data, the actual metabolite change data is analyzed based on a back propagation network to determine the production rate mutation point of the inhibitory metabolite, and the metabolic change path of the inhibitory metabolite is determined according to the production rate mutation point; Determine the inhibition time point of the inhibitory metabolite on the metabolism of the target strain according to the metabolic change path, obtain the molecular size data of the inhibitory metabolite type, perform pore size matching of the nanoporous material according to the molecular size data to obtain the pore size distribution of the nanoporous material, and perform an adsorption operation on the inhibitory metabolite at the inhibition time point according to the nanoporous material with the pore size distribution to obtain a first metabolic optimization strategy; It should be noted that in the process of preparing microbial agents, the target strains often face various imbalance problems, which affect the quality and preparation effect of the agents. Among them, metabolite inhibition and insufficient nutrients are two common problems. Metabolite inhibition may have a negative impact on strain metabolism due to the accumulation of certain metabolites, while insufficient nutrients may hinder strain reproduction due to nutritional competition among bacterial communities or insufficient components of the substrate itself; the metabolic change pathway can reflect the entire dynamic process from the production to the accumulation of inhibitory metabolites. By analyzing each link and key node in the pathway, the changes in inhibitory metabolites at different stages can be clearly seen. The production rate mutation point is an important sign, which indicates that the production rate of inhibitory metabolites has changed significantly after this point, which may mean that the inhibitory effect on the metabolism of the target strain is about to or has begun to increase. By analyzing along the metabolic change path from the point of rate mutation, we can accurately find the time point when the inhibitory metabolites have a substantial inhibition on the metabolism of the target strain; accurately determine the inhibition time point so that when the nanoporous material is adsorbed, it can intervene at the most appropriate time to minimize the impact of the inhibitory metabolites on the metabolism of the target strain, improve the metabolic efficiency and activity of the target strain, and ensure the normal progress of the microbial agent preparation process. By accurately removing the inhibitory metabolites, it helps to maintain the normal growth and reproduction of the target strain, reduce the strain variation and death caused by metabolic inhibition, and thus improve the quality and stability of the microbial agent.

[0035] If the imbalance type is insufficient nutrients, obtain the reproduction number change information of each target strain during the preparation of the target microbial inoculant. If the reproduction number of a certain target strain continues to increase while the reproduction of another target strain stagnates, the type of insufficient nutrients is marked as bacterial nutrient competition type. If all target strains stop reproducing, the type of insufficient nutrients is marked as substrate component deficiency type. When the type of nutrient deficiency is bacterial nutrient competition type, the Lotka-Volterra competition model is used to invert the replacement trajectory of the dominant bacterial community, and the competitive strain type and the competitive substrate type are identified according to the replacement trajectory. The addition type of the competitive inhibitor and the substrate supplement type are determined according to the competitive strain type and the competitive substrate type. The nutrient components prepared by the target microbial inoculant are adjusted according to the addition type of the competitive inhibitor and the substrate supplement type to obtain the second metabolic optimization strategy; It should be noted that by analyzing the change information of the reproduction number of each target strain during the preparation of the target microbial agent, it is possible to accurately distinguish whether the lack of nutrients is caused by the competition of bacterial communities or the lack of substrate components; the Lotka-Volterra competition model is a classic ecological model used to describe the competitive relationship between two or more species in a limited resource environment. In the microbial agent preparation environment, different target strains can be regarded as different competing species, which compete for limited nutritional resources and other living conditions. This model is based on the logistic equation of population growth, taking into account factors such as the growth rate of each population, the carrying capacity of the environment, and the competition coefficient between different populations, and can mathematically and quantitatively describe the relationship between the number of different populations over time. The replacement trajectory of the dominant bacterial community refers to the process and path in which the dominant position of different target strains in the bacterial community changes over time due to factors such as nutritional competition during the preparation of microbial agents. Based on the accurate identification of the types of competing strains and competitive substrates, the addition type of competitive inhibitors and the type of substrate supplementation are determined, and then the nutritional components of the target microbial agent preparation are reasonably adjusted. This can effectively regulate the competitive relationship between bacterial communities, inhibit excessive competition, promote the balanced growth of various strains, improve the quality and stability of microbial agents, ensure that various strains in the microbial agents can play their due role, and enhance the overall performance of the agents.

[0036] When the type of nutrient deficiency is substrate deficiency, the concentration change data of the substrate is obtained, and the substrate deficiency type is determined according to the substrate concentration change data. The nutrient components of the target strain in the target microbial agent preparation process are supplemented according to the substrate deficiency type to obtain a third metabolic optimization strategy.

[0037] It should be noted that by obtaining the concentration change data of the substrate to determine the type of substrate deficiency, it is possible to accurately find out which type or types of substrates are insufficient during the preparation of the target microbial agent. This avoids the blind supplementation of nutrients that may be caused by the inability to accurately determine the type of substrate deficiency; supplementing the nutrients of the target strain based on the determined type of substrate deficiency can achieve targeted and accurate supplementation. Matching the supplementation of nutrients with the actual needs of the strain will neither fail to solve the problem due to insufficient supplementation nor cause waste of resources due to excessive supplementation. It helps to improve the utilization efficiency of nutrients, ensure that the target strain can obtain the appropriate nutritional environment required for its growth and reproduction, promote the normal growth and metabolism of the strain, and ultimately improve the preparation quality of the target microbial agent.

[0038] According to an embodiment of the present invention, it also includes: Acquire the microbial attachment quantity change data of the target microbial inoculant preparation equipment within a preset time period, and construct the microbial attachment time change sequence data of the preparation equipment according to the microbial attachment quantity change data; Constructing a microbial attachment change prediction model based on a long short-term memory network, dividing the microbial attachment time change series data into prediction set data and training set data according to a preset ratio, and importing the training set data into the microbial attachment change prediction model for training operation; Importing the prediction set data into the trained microbial attachment change prediction model to predict the microbial attachment change in a future preset time period, and obtaining the prediction result of the microbial attachment quantity change; Determine the degree of contamination of the preparation equipment on the preparation of the target microbial inoculant within a preset time period in the future according to the prediction result of the change in the number of microorganisms attached; The preparation purity requirement of the target microbial inoculant is obtained, and the cleaning cycle of the preparation equipment is determined according to the preparation purity requirement and the contamination degree.

[0039] It should be noted that in the continuous production process of microbial agents, the production equipment has been running for a long time and aging, and the phenomenon of microbial attachment in the pipeline has become increasingly serious. Traditional cleaning methods are often based on fixed time intervals or empirical judgments, and lack scientific basis. At the same time, due to the complex and changeable microbial attachment situation, it is difficult to accurately estimate when it will have a serious impact on the preparation of the target microbial agent, resulting in the equipment cleaning time either too early to cause waste of resources, or too late to cause the quality of the microbial agent to be affected by contamination, thereby affecting product quality and production efficiency; by obtaining the data on the change in the number of microbial attachments and constructing time-varying series data, and using the long and short-term memory network to construct a prediction model, it is possible to effectively predict future changes in microbial attachment. Based on the prediction results of the change in the number of microbial attachments, it is possible to accurately determine the degree of contamination of the preparation equipment on the preparation of the target microbial agent within the preset time period in the future, so that the production personnel can clearly understand the contamination status of the equipment and make preparations in advance. Combined with the preparation purity requirements of the target microbial agent and the degree of equipment contamination, the cleaning cycle of the preparation equipment can be scientifically and reasonably determined. It not only avoids the waste of resources and equipment loss caused by excessive cleaning, but also prevents the quality of the agent from declining due to untimely cleaning, thereby reducing production costs and improving production efficiency while ensuring product quality.

[0040] Figure 4 A block diagram of a microbial inoculant preparation control system based on strain reproduction characteristic analysis of the present invention is shown.

[0041] The second aspect of the present invention further provides a microbial inoculant preparation control system 4 based on strain reproduction characteristic analysis, the system comprising: a memory 41, a processor 42, the memory comprising a microbial inoculant preparation control method program based on strain reproduction characteristic analysis, the microbial inoculant preparation control method program based on strain reproduction characteristic analysis when executed by the processor, implements the following steps: Obtain target strain type data required for preparation of target microbial inoculants, obtain reproduction data and metabolite data of each target strain under various environmental characteristics, perform environmental sensitivity analysis on the target strain based on the reproduction data and metabolite data, and determine the reproduction-environmental sensitivity index and metabolism-environmental sensitivity index of each target strain; Constructing a preparation quality prediction model of the target microbial agent according to the reproduction-environment sensitivity index and the metabolism-environment sensitivity index, and predicting the current preparation quality of the target microbial agent according to the preparation quality prediction model to obtain a preparation quality prediction result; Acquire actual preparation quality data of the target microbial inoculant, compare the actual preparation quality data with the preparation quality prediction result, and determine the metabolic imbalance state of the target strain; If the target strain is in a metabolic imbalance state, obtain actual metabolite change data of the target microbial inoculant, analyze the actual metabolite change data based on Fourier transform, and determine the change characteristics of the actual metabolites; The metabolic optimization strategy for each time node is determined according to the change characteristics of the actual metabolites.

[0042] The present invention discloses a microbial agent preparation control method based on strain reproduction characteristic analysis, aiming to improve the preparation quality of the agent. By obtaining the reproduction data and metabolite data of the target strain, an environmental sensitivity analysis is performed to obtain the reproduction-environmental sensitivity index and the metabolism-environmental sensitivity index, and then a preparation quality prediction model is constructed to predict the quality of the target microbial agent in real time. By comparing the actual preparation quality data, it is determined whether there is a metabolic imbalance, and the actual metabolite change data is obtained. Fourier transform is used to analyze these data, identify the characteristics of metabolite changes, and finally determine the metabolic optimization strategy to optimize the preparation process. The present invention can effectively control the quality of the microbial agent, improve production efficiency, and ensure the stability of the product.

[0043] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0044] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0045] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0046] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0047] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0048] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for controlling the preparation of microbial agents based on strain reproduction characteristics analysis, characterized in that: The following steps are involved: Obtain target strain type data required for preparation of target microbial inoculants, obtain reproduction data and metabolite data of each target strain under various environmental characteristics, perform environmental sensitivity analysis on the target strain based on the reproduction data and metabolite data, and determine the reproduction-environmental sensitivity index and metabolism-environmental sensitivity index of each target strain; Constructing a preparation quality prediction model of the target microbial agent according to the reproduction-environment sensitivity index and the metabolism-environment sensitivity index, and predicting the current preparation quality of the target microbial agent according to the preparation quality prediction model to obtain a preparation quality prediction result; Acquire actual preparation quality data of the target microbial inoculant, compare the actual preparation quality data with the preparation quality prediction result, and determine the metabolic imbalance state of the target strain; If the target strain is in a metabolic imbalance state, obtain actual metabolite change data of the target microbial inoculant, analyze the actual metabolite change data based on Fourier transform, and determine the change characteristics of the actual metabolites; The metabolic optimization strategy for each time node is determined according to the change characteristics of the actual metabolites.

2. The method for controlling the preparation of microbial agents based on strain reproduction characteristics analysis according to claim 1, characterized in that: The reproduction data and metabolite data of each target strain under each environmental characteristic are obtained, and the environmental sensitivity analysis of the target strain is performed according to the reproduction data and metabolite data to determine the reproduction-environmental sensitivity index and metabolism-environmental sensitivity index of each target strain, specifically: Obtain strain samples of each target strain type according to the target strain type data, place the strain samples under different environmental characteristics for reproduction and preparation of target microbial agents, and obtain reproduction data and metabolite data of the target strains under various environmental characteristics for reproduction and preparation of target microbial agents; The reproduction data and metabolite data were combined with each environmental characteristic to construct the reproduction-environment data matrix and the metabolism-environment data matrix; Calculating the covariance matrix of the reproduction-environment data matrix and the metabolism-environment data matrix, calculating the eigenvalues ​​and eigenvectors of the covariance matrix, and selecting the eigenvectors corresponding to the first k largest eigenvalues ​​to construct an eigenvector matrix; According to the multiplication of the reproduction-environment data matrix and the metabolism-environment data matrix with the corresponding eigenvector matrix, a reproduction-environment principal component score matrix and a metabolism-environment principal component score matrix are obtained; The degree of influence of each environmental characteristic on the reproduction and metabolism of the target strain is determined according to the reproduction-environment principal component score matrix and the metabolism-environment principal component score matrix to obtain the reproduction-environment sensitivity index and the metabolism-environment sensitivity index.

3. The method for controlling the preparation of microbial inoculants based on strain reproduction characteristics analysis according to claim 1, characterized in that: The preparation quality prediction model of the target microbial agent is constructed according to the reproduction-environmental sensitivity index and the metabolism-environmental sensitivity index, and the current preparation quality of the target microbial agent is predicted according to the preparation quality prediction model to obtain the preparation quality prediction result, which is specifically: Obtaining the reproduction data and metabolic data of the target strain during the preparation of the target microbial agent, performing a correlation analysis on the reproduction data and the metabolic data based on the Pearson correlation coefficient, determining the influence of the reproduction of the target strain on the metabolic condition, and obtaining the influence data; Constructing a preparation quality prediction model based on a fuzzy logic algorithm, and importing the influencing data into the preparation quality prediction model to construct the influence condition restriction of the target strain reproduction on metabolism; Using the preparation environment characteristics and the initial target strain quantity information for preparing the target microbial inoculant as input data for the preparation quality prediction model; The reproduction-environment sensitivity index and the metabolism-environment sensitivity index are introduced into the preparation quality prediction model to construct the reproduction quality membership function and the metabolism quality membership function of the target strain under different environmental characteristics; According to the influencing data, the reproduction quality membership function and the metabolic quality membership function, a preparation quality fuzzy rule base for preparing a target microbial agent by a target strain under different strain numbers and different environmental characteristics is constructed, and the preparation quality fuzzy rule base is used as a prediction basis for a preparation quality prediction model; Obtaining initial target strain quantity information and current preparation environment characteristics for the preparation of the target microbial agent, importing the initial target strain quantity information and current preparation environment characteristics into the preparation quality prediction model, and determining the current reproduction quality and current metabolic quality of the target strain under the current preparation environment characteristics according to the reproduction quality membership function and the metabolic quality membership function and the influencing condition constraints; The current reproduction quality and the current metabolic quality are compared with the preparation quality fuzzy rule base, and the preparation quality of the target microbial agent prepared by the target strain under the current environmental characteristics is predicted to obtain a preparation quality prediction result.

4. The method for controlling the preparation of microbial inoculants based on strain reproduction characteristics analysis according to claim 1, characterized in that: The actual preparation quality data of the target microbial inoculant is obtained, and the actual preparation quality data is compared with the preparation quality prediction result to determine the metabolic imbalance state of the target strain, specifically: The preparation quality prediction result is used as the benchmark quality data for the preparation of the target microbial agent under the current environmental characteristics; Acquire actual preparation quality data of the target microbial inoculant prepared under current environmental characteristics, compare the actual preparation quality data with the reference quality data, and calculate the Euclidean distance between the actual preparation quality data and the reference quality data; The metabolic imbalance state of the target strain is determined according to the Euclidean distance.

5. The method for controlling the preparation of microbial agents based on strain reproduction characteristics analysis according to claim 1, characterized in that: If the target strain is in a metabolic imbalance state, the actual metabolite change data of the target microbial inoculant is obtained, and the actual metabolite change data is analyzed based on Fourier transform to determine the change characteristics of the actual metabolites, specifically: If the target strain has a metabolic imbalance, the metabolite changes of the target strain during the preparation of the target microbial agent are monitored based on a mass spectrometer to obtain actual metabolite change data, which includes actual metabolite substance type change data and actual metabolite concentration change data; Based on the Hanning window, the actual metabolite change data is framed according to a preset window size to obtain actual metabolite change data segments; Performing a fast Fourier transform on each of the actual metabolite change data segments to calculate the spectrum energy distribution of each actual metabolite change data segment; The multi-scale feature extraction of the spectrum energy distribution is performed based on the wavelet packet decomposition algorithm. The multi-scale feature includes frequency component, amplitude, phase and frequency band energy proportion of the frequency component, so as to obtain the change characteristics of the actual metabolites.

6. The method for controlling the preparation of microbial inoculants based on strain reproduction characteristics analysis according to claim 1, characterized in that: The metabolic optimization strategy for each time node is determined according to the change characteristics of the actual metabolites, specifically: Acquire historical metabolite characteristics of different metabolic imbalance patterns of the target strain, and construct a metabolic imbalance pattern library by combining the metabolic imbalance patterns and corresponding historical metabolite characteristics; Constructing a bidirectional LSTM classification model based on an attention mechanism, performing a data link operation between the metabolic imbalance pattern library and the classification model, and constructing a multi-scale feature vector based on the change characteristics of the actual metabolites; Importing the multi-scale feature vector into the classification model to perform dynamic weight matching with each historical metabolite feature in the metabolic imbalance pattern library, and outputting a confidence matrix of the metabolic imbalance type; Determine the imbalance type of the target strain at each time point in the process of preparing the target microbial inoculant according to the confidence matrix, wherein the imbalance type includes metabolite inhibition and insufficient nutrients; The optimization strategy for each time node is determined according to the imbalance type of the target strain at each time node.

7. The method for controlling the preparation of microbial inoculants based on strain reproduction characteristics analysis according to claim 6, characterized in that: The optimization strategy for each time node is determined according to the imbalance type of the target strain at each time node, specifically: If the imbalance type is metabolite inhibition, the type of inhibitory metabolite causing metabolic inhibition on the target strain is determined according to the actual metabolite change data, the actual metabolite change data is analyzed based on a back propagation network to determine the production rate mutation point of the inhibitory metabolite, and the metabolic change path of the inhibitory metabolite is determined according to the production rate mutation point; Determine the inhibition time point of the inhibitory metabolite on the metabolism of the target strain according to the metabolic change path, obtain the molecular size data of the inhibitory metabolite type, perform pore size matching of the nanoporous material according to the molecular size data to obtain the pore size distribution of the nanoporous material, and perform an adsorption operation on the inhibitory metabolite at the inhibition time point according to the nanoporous material with the pore size distribution to obtain a first metabolic optimization strategy; If the imbalance type is insufficient nutrients, obtain the reproduction number change information of each target strain during the preparation of the target microbial inoculant. If the reproduction number of a certain target strain continues to increase while the reproduction of another target strain stagnates, the type of insufficient nutrients is marked as bacterial nutrient competition type. If all target strains stop reproducing, the type of insufficient nutrients is marked as substrate component deficiency type. When the type of nutrient deficiency is bacterial nutrient competition type, the Lotka-Volterra competition model is used to invert the replacement trajectory of the dominant bacterial community, and the competitive strain type and the competitive substrate type are identified according to the replacement trajectory. The addition type of the competitive inhibitor and the substrate supplement type are determined according to the competitive strain type and the competitive substrate type. The nutrient components prepared by the target microbial inoculant are adjusted according to the addition type of the competitive inhibitor and the substrate supplement type to obtain the second metabolic optimization strategy; When the type of nutrient deficiency is substrate deficiency, the concentration change data of the substrate is obtained, and the substrate deficiency type is determined according to the substrate concentration change data. The nutrient components of the target strain in the target microbial agent preparation process are supplemented according to the substrate deficiency type to obtain a third metabolic optimization strategy.

8. A microbial agent preparation control system based on strain reproduction characteristics analysis, characterized in that: The microbial inoculant preparation control system based on strain reproduction characteristic analysis includes a storage device and a processor, wherein the storage device includes a microbial inoculant preparation control method program based on strain reproduction characteristic analysis, and when the microbial inoculant preparation control method program based on strain reproduction characteristic analysis is executed by the processor, the following steps are implemented: Obtain target strain type data required for preparation of target microbial inoculants, obtain reproduction data and metabolite data of each target strain under various environmental characteristics, perform environmental sensitivity analysis on the target strain based on the reproduction data and metabolite data, and determine the reproduction-environmental sensitivity index and metabolism-environmental sensitivity index of each target strain; Constructing a preparation quality prediction model of the target microbial agent according to the reproduction-environment sensitivity index and the metabolism-environment sensitivity index, and predicting the current preparation quality of the target microbial agent according to the preparation quality prediction model to obtain a preparation quality prediction result; Acquire actual preparation quality data of the target microbial inoculant, compare the actual preparation quality data with the preparation quality prediction result, and determine the metabolic imbalance state of the target strain; If the target strain is in a metabolic imbalance state, obtain actual metabolite change data of the target microbial inoculant, analyze the actual metabolite change data based on Fourier transform, and determine the change characteristics of the actual metabolites; The metabolic optimization strategy for each time node is determined according to the change characteristics of the actual metabolites.

Images