Microbial culture experiment data cloud processing system

Abstract

The invention discloses a microculture experimental data cloud processing system, and relates to the technical field of microculture data processing, and the system comprises an experimental data collection module which generates a standardized microculture data set; the growth rule mining module is used for performing time sequence trend analysis and core feature extraction, dividing microorganism growth stages, extracting key parameters of each stage and generating a microorganism growth rule feature set; the influence factor analysis module is used for analyzing influence factors of the microbial growth state to obtain an influence factor analysis report; the anomaly detection module is used for outputting anomaly early warning and cause analysis results; and the experiment scheme recommendation module is used for generating an optimal culture scheme suggestion adaptive to the target microorganisms. According to the method, the technical problems of dispersed data processing and inaccurate growth rule mining of traditional microorganism culture are solved through the core technologies of accurately mining the microorganism growth rule, analyzing the synergistic effect through multi-factor correlation modeling and intelligently generating the culture scheme.

Description

Technical Field

[0001] This invention relates to the field of microbial culture data processing technology, and more specifically to a cloud processing system for microbial culture experimental data. Background Technology

[0002] Microbial culture is a core component in fields such as bioengineering, pharmaceutical research and development, and food fermentation. Its culture results directly determine the success or failure of experiments and the efficiency of industrialization. Precise processing of experimental data, in-depth exploration of growth patterns, and scientific optimization of culture programs are key to improving culture quality.

[0003] Current data processing in microbial culture experiments suffers from the following problems: data processing is fragmented, relying heavily on manual organization of multi-source data from sensors, instruments, and manual recording, lacking a standardized integration mechanism, resulting in chaotic data timelines, poor correlation, and difficulty in supporting systematic analysis; growth pattern mining is not precise enough, traditional methods rely heavily on experience to divide growth stages, failing to extract key parameters of each stage through quantitative models, and thus failing to adapt to real-time changes in microbial growth status; synergistic and antagonistic effects among multiple factors are ignored, making it difficult to determine the scientifically optimal culture condition range; anomaly detection is delayed, with growth anomalies mostly discovered after the fact, lacking forward-looking prediction of abnormal trends and failing to accurately pinpoint the inducing factors.

[0004] Solving this technical problem is a technical challenge that needs to be overcome by those skilled in the art. Summary of the Invention

[0005] To address the aforementioned technical problems, a cloud processing system for microbial culture experimental data is provided, and this technical solution resolves the problems described above.

[0006] To achieve the above objectives, the technical solution adopted by the present invention is as follows: A cloud processing system for microbial culture experimental data includes: an experimental data acquisition module, a growth pattern mining module, an influencing factor analysis module, an anomaly detection module, and an experimental protocol recommendation module; The experimental data acquisition module is used to acquire multi-source experimental data and auxiliary data of the culture environment during the microbial culture process, and generate a standardized microbial culture dataset. The growth pattern mining module is electrically connected to the experimental data acquisition module and is used to perform time-series trend analysis and core feature extraction based on the standardized microbial culture dataset, divide the microbial growth stages and extract key parameters of each stage, and generate a microbial growth pattern feature set. The influencing factor analysis module is electrically connected to the growth pattern mining module and is used to analyze the influencing factors of microbial growth status based on the microbial growth pattern feature set and obtain an influencing factor analysis report. The anomaly detection module is electrically connected to the experimental data acquisition module and the growth pattern mining module. It is used to establish a normal growth benchmark model based on the standardized microbial culture dataset and the microbial growth pattern feature set, locate the abnormal causes through the influencing factor analysis report, and output anomaly warning and cause analysis results. The experimental protocol recommendation module is electrically connected to the influencing factor analysis module and the anomaly detection module, and is used to generate optimal culture protocol suggestions suitable for the target microorganism based on the influencing factor analysis report and the inducing factor analysis results.

[0007] Preferably, the growth pattern mining module includes: The time-series feature deep extraction unit extracts time-series data of three core growth indicators—cell concentration, metabolite content, and cell activity—from a standardized microbial culture dataset; it uses the sliding window method to analyze the local change trends of the time-series and extracts three types of dynamic features: trend slope, fluctuation amplitude, and peak characteristics; and it uses statistical analysis algorithms to calculate four types of statistical features for each core indicator—mean, variance, growth rate, and cumulative amount—to construct a multi-dimensional time-series feature matrix. Intelligent Modeling Unit for Growth Stages: Based on a multi-dimensional temporal feature matrix, a clustering algorithm is used to identify the inflection points and stage boundaries of the growth curve, automatically dividing it into four growth stages: lag phase, log phase, stationary phase, and decline phase. For each growth stage, a stage-specific feature model is constructed, and the Logistic growth model is used to quantify the key parameters of each stage. The model formula is as follows:

[0008] In the formula for The bacterial concentration at any given time, This represents the maximum cell concentration during the stationary phase. The logarithmic growth rate constant is... To cultivate time, The time corresponding to the inflection point of the growth curve. It is a natural constant; By establishing a model of the connection relationship between each growth stage through a time-series correlation algorithm, the triggering conditions and characteristic change patterns of stage transitions are revealed, and a feature set of microbial growth patterns containing stage features, parameter thresholds, and correlation rules is formed.

[0009] Preferably, the growth pattern mining module further includes: The dynamic optimization unit for growth patterns introduces a time decay factor to weight continuously collected time-series data, strengthening the influence of recent data on the growth pattern model; it updates the growth pattern feature set based on a sliding time window to adapt to the dynamic changes in microbial growth status in real time; and it mines the commonalities and specificities of growth patterns of similar microorganisms by comparing the growth pattern feature sets of different batches of experiments.

[0010] Preferably, the influencing factor analysis module includes: Multi-factor correlation modeling unit: Five key culture condition parameters—temperature, pH, culture medium formulation, inoculum size, and dissolved oxygen concentration—are selected to establish a mapping relationship with the characteristic set of microbial growth patterns. Correlation analysis algorithms are used to quantify the correlation strength between each culture condition parameter and key growth parameters, including growth rate, peak concentration, and stage duration, to screen core influencing factors. A multi-factor interaction model is constructed to analyze the synergistic and antagonistic effects among core influencing factors, clarifying the comprehensive influence of different factor combinations on microbial growth status.

[0011] Preferably, the influencing factor analysis module further includes: Optimal Condition Interval Determination Unit: Based on a multi-factor correlation model, a gradient analysis algorithm is used to traverse the value ranges of the core influencing factors to determine the optimal value intervals when each factor acts alone; combined with the interaction law, the optimal parameter configuration of the multi-factor combination is optimized to form an optimal condition combination that takes into account both the optimality of a single factor and the synergy of multiple factors; the reliability of the optimal condition interval is verified through a significance test algorithm, the interval boundaries and adjustment rules are marked, and condition adaptation suggestions are supplemented for three types of culture objectives: bacterial cell proliferation, efficient extraction of metabolites, and directed domestication of bacterial strains, forming a complete influencing factor analysis report.

[0012] Preferably, the anomaly detection module includes: The benchmark model construction unit is based on the microbial growth pattern feature set and the normal culture data of similar microorganisms in history. It constructs a normal growth benchmark model that includes the normal fluctuation range of key parameters at each growth stage and the threshold of time-series change trends. Combined with the optimal condition interval in the influencing factor analysis report, it sets the anomaly judgment threshold for different culture stages, forming a stage-by-stage and index-by-index anomaly judgment system. It configures an update mechanism for the benchmark model to continuously optimize the model parameters through newly added normal experimental data.

[0013] Preferably, the anomaly detection module further includes: Anomaly Identification and Cause Localization Unit: This unit compares the current time-series data of microbial culture with the normal growth baseline model in real time, calculates the quantified value of the deviation, and triggers an anomaly warning when the deviation exceeds a preset threshold. Based on the influencing factor analysis report, it correlates the changes in culture condition parameters during the anomaly occurrence period to analyze whether the core influencing factors deviate from the optimal range. Combined with the growth stage transition relationship model, it determines whether the anomaly originates from a stage transition anomaly, identifies the anomaly cause type as environmental parameter fluctuations, operational procedure deviations, abnormal culture medium components, or inoculum deviations, and outputs anomaly warnings and cause analysis results including the anomaly level, occurrence point, cause details, and emergency treatment suggestions.

[0014] Preferably, the anomaly detection module further includes: Anomaly Trend Prediction Unit: Based on real-time time-series data from a standardized microbial culture dataset, this unit uses a trend prediction algorithm to analyze the changing trends of growth indicators; compares the trend prediction results with the expected trends of a normal growth benchmark model to identify potential risks that may lead to future anomalies; and, in conjunction with an influencing factor analysis report, determines whether the potential risks stem from the slow drift of culture condition parameters, providing early risk warnings and preventative measures suggestions to achieve proactive early warning of anomalies.

[0015] Preferably, the experimental scheme recommendation module includes: Intelligent Solution Generation Unit: Based on the optimal condition combination and condition adaptation suggestions under three types of culture objectives from the influencing factor analysis report, and through risk points and emergency treatment suggestions in the abnormal early warning and cause analysis results, it matches successful experimental cases consistent with the current microbial species and culture objectives from the historical experimental database stored in the cloud; it extracts the core configuration information of the case, such as the proportion of culture medium components, the staged control curve of environmental parameters, the inoculation operation specifications, and the process sampling nodes; it determines the culture medium control parameters and inoculation amount by combining the optimal condition combination; it supplements the indicator judgment thresholds, sampling time intervals, and data records of process monitoring, and integrates them to form a microbial culture solution that includes culture condition parameters, operation procedure specifications, monitoring plan, and emergency pretreatment measures.

[0016] Preferably, the experimental scheme recommendation module further includes: The scheme dynamic optimization unit receives the updated standardized microbial culture dataset and growth pattern feature set in real time during the microbial culture process, compares the actual execution effect of the current culture scheme with the expected growth target, and uses the gradient descent algorithm to adjust the key parameters in the scheme for the discrepancies, optimizes the switching nodes and specific values ​​of the control parameters at each growth stage, feeds the optimized scheme back to the historical experimental database, and updates the parameter weights of the scheme recommendation model.

[0017] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention solves the technical problems of traditional microbial culture, such as scattered data processing, inaccurate growth pattern mining, difficulty in determining the optimal scientific culture condition range, and lagging anomaly detection, by standardizing and integrating multi-source experimental data, accurately mining microbial growth patterns using Logistic growth model and clustering algorithm, analyzing synergistic effects through multi-factor correlation modeling, prospective anomaly detection and cause localization, and intelligent generation and optimization of culture programs. It achieves intelligent and precise control of microbial culture. Attached Figure Description

[0018] Figure 1 This is a system framework diagram of the present invention; Figure 2 This is a flowchart illustrating the steps of the present invention. Detailed Implementation

[0019] The following description is intended to disclose the invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art.

[0020] Reference Appendix Figure 1 - Appendix Figure 2 As shown: This application provides a cloud processing system for microbial culture experimental data. The core implementation process of this system includes the following steps: Step 101: Obtain multi-source experimental data and auxiliary data of the culture environment during the microbial culture process through the experimental data acquisition module, and generate a standardized microbial culture dataset; Step 102: Perform time-series trend analysis and core feature extraction on the standardized microbial culture dataset through the growth pattern mining module, divide the growth stages and quantify key parameters to generate a microbial growth pattern feature set; Step 103: By using the influencing factor analysis module to correlate growth pattern characteristics with culture condition parameters, quantify the influence weights and determine the optimal intervals, and output an influencing factor analysis report; Step 104: Construct a benchmark model based on a standardized dataset and a growth pattern feature set using the anomaly detection module, identify growth anomalies and locate the causes, and output anomaly warnings and cause analysis results; Step 105: Using the experimental protocol recommendation module, combined with the influencing factor analysis report, anomaly analysis results, and historical data, generate and optimize the optimal culture protocol.

[0021] The above scheme, based on standardized data collection, enables precise discovery of growth patterns and quantitative analysis of influencing factors. Combined with forward-looking anomaly detection and dynamic scheme optimization, it constructs a closed-loop process encompassing data collection, pattern discovery, factor analysis, anomaly prevention and control, and scheme optimization. This solves the problems of scattered data processing, coarse pattern discovery, and poor scheme adaptability in traditional microbial culture, significantly improving the intelligence level and success rate of culture experiments.

[0022] In some embodiments, step 101 generates a standardized microbial culture dataset through the experimental data acquisition module, including: Specifically, the core of the experimental data acquisition module is to achieve synchronous acquisition of multi-source data, unified format, and validity verification, providing high-quality basic data for subsequent analysis. The deployment of acquisition equipment needs to cover the entire microbial culture process, deploying sensor groups at key locations in the culture device, including temperature sensors, pH sensors, dissolved oxygen concentration sensors, and osmotic pressure sensors, and simultaneously configuring instruments such as colony counters, high-performance liquid chromatographs, and cell activity detectors to collect core growth index data; at the same time, environmental temperature, humidity, air pressure, and light intensity sensors are deployed in the laboratory environment to collect auxiliary data of the culture environment.

[0023] Multi-source data acquisition employs a synchronous triggering mechanism, using timestamps as a benchmark to achieve temporal alignment of real-time sensor data, instrument detection data, and manually recorded data. Sensor data is automatically acquired, instrument detection data is acquired synchronously at key stages of cultivation, and manually recorded data is uploaded in real-time through a structured input interface, including information such as inoculum size, culture medium formulation, and operation steps. The acquired multi-source data undergoes preprocessing: a median filtering algorithm is used to remove random noise from sensor data, and interpolation is used to complete missing data; heterogeneous data output from different instruments is format-converted to unify data units; and reasonable value ranges for each data point are established based on industry standards for microbial culture, eliminating invalid data outside these ranges. Finally, a standardized microbial culture dataset is generated, containing data source, acquisition timestamp, associated environmental parameters, and verification identifiers.

[0024] In some embodiments, step 102 generates a microbial growth pattern feature set through the growth pattern mining module, including: specifically, extracting complete time-series sequences of three core growth indicators—cell concentration, metabolite content, and cell activity—from a standardized microbial culture dataset, ensuring that the time-series data for each indicator is continuous and the timestamps are consistent. A sliding window method is used to segment the time-series sequence, and dynamic features are extracted by calculating the trend slope, fluctuation amplitude, and peak characteristics of the data within each window. Simultaneously, statistical analysis algorithms are used to calculate the mean, variance, growth rate, and cumulative amount of each core indicator across the entire time series, constructing a multi-dimensional time-series feature matrix containing both dynamic and statistical features. The matrix's row vectors represent feature combinations for each time node, and the column vectors represent single feature types, providing structured input for growth stage modeling.

[0025] Specifically, based on a multi-dimensional time-series feature matrix, a clustering algorithm is used to identify the inflection points and stage boundaries of the growth curve. The preset number of clusters corresponds to the lag phase, logarithmic phase, stationary phase, and decline phase. Cluster centers are determined by calculating the Euclidean distance between feature vectors, automatically dividing the time intervals of the four growth stages. For each growth stage, a stage-specific feature model is constructed, and the Logistic growth model is used to quantify key parameters. The model formula is as follows:

[0026] In the formula for The bacterial concentration at any given time, This represents the maximum cell concentration during the stationary phase. The logarithmic growth rate constant is... To cultivate time, The time corresponding to the inflection point of the growth curve. It is a natural constant; During the model fitting process, the time series data of bacterial cell concentration in the standardized dataset is used as the dependent variable and the culture time is used as the independent variable. The model parameters are solved by the least squares method: the maximum bacterial cell concentration in the stationary phase is determined by fitting the asymptotic value of the stationary phase data, the growth rate constant in the logarithmic phase is calculated by fitting the slope of the logarithmic phase data, and the time corresponding to the inflection point of the growth curve is determined by solving the time point corresponding to the maximum value of the model derivative.

[0027] A model of the connection relationship between each growth stage is established by using a time-series correlation algorithm. The correlation between key parameters of the previous stage and parameters of the next stage is analyzed to reveal the triggering conditions for stage transition. Finally, the stage division results, model parameters, and stage connection rules are integrated to form a feature set of microbial growth patterns that includes stage characteristics, parameter thresholds, and correlation rules.

[0028] Specifically, a time decay factor is introduced to weight the continuously collected time-series data, with the weight coefficient of recent data being higher than that of older data. This strengthens the influence of real-time data on the growth pattern model and avoids model bias caused by outdated historical data. The growth pattern feature set is dynamically updated based on a sliding time window. For each new data collection period, the feature matrix and model parameters are recalculated to adapt to changes in the microbial growth state in real time. The growth pattern feature sets of different batches of experiments are compared, and the similarity of feature vectors is calculated using a cosine similarity algorithm to discover the commonalities in the growth patterns of similar microorganisms under the same culture objectives. At the same time, the specific differences under different culture conditions are recorded. By iteratively optimizing the parameter threshold range of the feature model, the model's ability to generalize to the growth patterns of similar microorganisms in different batches and under different environments is improved.

[0029] In some embodiments, step 103 outputs an influencing factor analysis report through the influencing factor analysis module, including: specifically, selecting five key culture condition parameters—temperature, pH, culture medium formulation, inoculum size, and dissolved oxygen concentration—and establishing a mapping relationship with the characteristic set of microbial growth patterns. The mapping dimension includes the correspondence between each culture condition parameter and the key growth parameter. The Pearson correlation coefficient algorithm is used to quantify the correlation strength, calculate the correlation coefficient between each culture condition parameter and the key growth parameter, screen out the core factors that play a dominant role in microbial growth, construct a multi-factor interaction model, and use a multiple linear regression algorithm to analyze the synergistic and antagonistic effects among the core influencing factors. The model expression is:

[0030] In the formula, As a key growth parameter, As the core influencing factor, For constant terms, The influence coefficient of a single factor. The coefficients are used for interaction terms. The values ​​of each coefficient are determined by model fitting to clarify the comprehensive influence of multiple factors on the growth status of microorganisms.

[0031] Specifically, based on a multi-factor correlation model, a gradient analysis algorithm is used to traverse the value range of core influencing factors, calculate the values ​​of key growth parameters under each gradient, determine the optimal value range for each factor acting alone, and optimize the multi-factor combination by combining the interaction law. A response surface methodology is used to construct a relationship model between factor combinations and growth effects, finding the optimal condition combination that balances the optimality of a single factor and the synergistic effect of multiple factors. The reliability of the optimal condition range is verified through a significance test algorithm, the boundary values ​​of the range and adjustment rules are marked, and condition adaptation suggestions are supplemented for three types of culture objectives: bacterial cell proliferation, efficient extraction of metabolites, and targeted strain domestication. The priority of core influencing factors corresponding to different objectives is clarified, and finally, a complete influencing factor analysis report including influence weights, interaction mechanisms, optimal ranges, and adaptation rules is generated.

[0032] In some embodiments, step 104 outputs anomaly warnings and cause analysis results through the anomaly detection module, including: specifically, based on the microbial growth pattern feature set and historical normal culture data of similar microorganisms, a normal growth benchmark model is constructed. The model includes the normal fluctuation range and time-series change trend threshold of key parameters at each growth stage. Combined with the optimal condition interval in the influencing factor analysis report, sub-index anomaly judgment thresholds are set for each growth stage to form a stage-by-stage and sub-index anomaly judgment system. The benchmark model is configured with a dynamic update mechanism. Every time a certain amount of new normal culture data is added, the model parameters are updated using an online learning algorithm, and the normal fluctuation range and trend threshold of key parameters are recalculated to improve the model's adaptability to different culture environments and different batches of experiments, and avoid misjudgments of anomalies caused by model solidification.

[0033] Specifically, the system extracts real-time time-series data of the current microbial culture, compares it with the normal growth benchmark model index by index, calculates the quantified value of the deviation, and triggers an anomaly warning when the deviation exceeds a preset threshold, marking the anomaly level. Based on the influencing factor analysis report, it correlates the changes in culture condition parameters during the period of the anomaly, and analyzes whether the core influencing factors deviate from the optimal range by comparing the parameter values ​​before and after the anomaly. Combined with the growth stage transition relationship model, it determines whether the anomaly originates from a stage transition anomaly. The system uses an elimination method to locate the type of anomaly cause, specifically environmental parameter fluctuations, operational procedure deviations, abnormal culture medium components, and inoculum deviations. Finally, it outputs an anomaly warning and cause analysis results that include the anomaly level, occurrence point, cause details, and emergency treatment suggestions.

[0034] Specifically, based on real-time time-series data from standardized microbial culture datasets, a short-term prediction model is constructed using a trend prediction algorithm. Recent time-series data is input to predict future growth indicator trends. The prediction results are compared with the expected trends of a normal growth benchmark model, and the trend deviation rate is calculated. When the trend deviation rate exceeds a set standard, it is identified as a potential abnormal risk. Combined with an influencing factor analysis report, it is determined whether the potential risk stems from a slow drift in culture condition parameters. Risk warnings and preventative measures are provided in advance, achieving proactive early warning of anomalies and allowing sufficient time for timely intervention.

[0035] In some embodiments, step 105 generates and dynamically optimizes the optimal culture protocol through the experimental protocol recommendation module, including: specifically, based on the optimal condition combination in the influencing factor analysis report, the adaptation suggestions under the three types of culture objectives, and the risk points and emergency treatment suggestions in the abnormal warning and cause analysis results, matching the most similar successful experimental cases from the historical experimental database stored in the cloud. Extracting the core configuration information from the cases, including the proportion of culture medium components, the staged control curve of environmental parameters, the inoculation operation specifications, and the process sampling nodes; adjusting the case configuration in conjunction with the optimal condition combination to determine the culture medium control parameters and the precise value of the inoculation amount; supplementing the indicator judgment thresholds, sampling time intervals, and data recording requirements for process monitoring, and integrating them to form a complete microbial culture protocol that includes culture condition parameters, operation procedure specifications, monitoring protocols, and emergency pretreatment measures.

[0036] Specifically, the system receives updated standardized microbial culture datasets and dynamic updates of growth pattern feature sets in real time during the microbial culture process. It periodically compares the actual performance of the current culture program with the expected growth target, and uses a gradient descent algorithm to adjust key parameters in the program for the discrepancies. It optimizes the switching nodes and specific values ​​of control parameters at each growth stage. The optimized program is fed back to the historical experimental database in a structured format, which is associated with the microbial species, culture target, and optimization basis of the current experiment. A weighted update algorithm is used to adjust the parameter weights of the program recommendation model, thereby improving the accuracy of subsequent program recommendations for similar microorganisms and similar culture scenarios.

[0037] In summary, the advantages of this invention are as follows: This invention achieves automatic and accurate division of growth stages and adaptation of growth patterns by deeply extracting temporal features, intelligently modeling growth stages, and using dynamic optimization units in the growth pattern mining module, combined with the Logistic growth model to quantify key parameters of each growth stage. This solves the problems of traditional stage division based on experience and poor data correlation, and significantly improves the accuracy and timeliness of growth pattern representation.

[0038] The influencing factor analysis module comprehensively considers the individual effects and interactive effects of five key cultivation condition parameters through multi-factor correlation modeling and optimal condition interval calibration. It clarifies the optimal combination of conditions under different cultivation objectives, makes up for the limitations of traditional single-factor analysis, and provides scientific parameter support for cultivation programs.

[0039] The anomaly detection module integrates benchmark model construction, anomaly identification and cause localization, and trend prediction units. It can not only identify current growth anomalies in real time and accurately locate the causes, but also provide early warning of potential risks. It completely solves the pain points of traditional anomaly detection being lagging and the causes being unclear, and provides a reliable basis for taking timely emergency measures.

[0040] The intelligent generation and dynamic optimization unit of the experimental protocol recommendation module generates targeted and complete culture protocols based on the analysis results of influencing factors, anomaly feedback, and historical experimental data. It can also dynamically adjust key parameters according to real-time data, realizing intelligent and adaptive optimization of the protocol, which greatly improves the adaptability and execution effect of the culture protocol.

[0041] The system as a whole constructs a closed-loop processing mechanism for the entire process of data acquisition, pattern mining, factor analysis, anomaly detection, and scheme recommendation. It realizes standardized integration of multi-source data, in-depth mining of growth patterns, scientific optimization of culture conditions, early prevention and control of abnormal risks, and dynamic iteration of schemes. It significantly improves the intelligence level and experimental success rate of microbial culture, effectively reduces resource waste, and provides strong technical support for research and industrial application in the field of microbial culture.

[0042] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claimed invention. The scope of protection claimed by the appended claims and their equivalents is defined.

Claims

1. A cloud processing system for microbial culture experimental data, characterized in that, include: The module includes: experimental data acquisition module, growth pattern mining module, influencing factor analysis module, anomaly detection module, and experimental scheme recommendation module. The experimental data acquisition module is used to acquire multi-source experimental data and auxiliary data of the culture environment during the microbial culture process, and generate a standardized microbial culture dataset. The growth pattern mining module is used to perform time-series trend analysis and core feature extraction based on the standardized microbial culture dataset, divide the microbial growth stages and extract key parameters for each stage, and generate a microbial growth pattern feature set. The influencing factor analysis module is used to analyze the influencing factors of microbial growth status based on the characteristic set of microbial growth patterns and obtain an influencing factor analysis report. The anomaly detection module is used to establish a normal growth benchmark model based on the standardized microbial culture dataset and the microbial growth law feature set, locate the abnormal causes through the influencing factor analysis report, and output anomaly warning and cause analysis results. The experimental protocol recommendation module is used to generate optimal culture protocol suggestions suitable for the target microorganism based on the influencing factor analysis report and the inducing factor analysis results.

2. The cloud processing system for microbial culture experimental data according to claim 1, characterized in that, The growth pattern mining module includes: The time-series feature deep extraction unit extracts time-series data of three core growth indicators—cell concentration, metabolite content, and cell activity—from a standardized microbial culture dataset; it uses the sliding window method to analyze the local change trends of the time-series and extracts three types of dynamic features: trend slope, fluctuation amplitude, and peak characteristics; and it uses statistical analysis algorithms to calculate four types of statistical features for each core indicator—mean, variance, growth rate, and cumulative amount—to construct a multi-dimensional time-series feature matrix. Intelligent Modeling Unit for Growth Stages: Based on a multi-dimensional temporal feature matrix, a clustering algorithm is used to identify the inflection points and stage boundaries of the growth curve, automatically dividing it into four growth stages: lag phase, log phase, stationary phase, and decline phase. For each growth stage, a stage-specific feature model is constructed, and the Logistic growth model is used to quantify the key parameters of each stage. The model formula is as follows: ， In the formula for The bacterial concentration at any given time, This represents the maximum cell concentration during the stationary phase. The logarithmic growth rate constant is... To cultivate time, The time corresponding to the inflection point of the growth curve. It is a natural constant; By establishing a model of the connection relationship between each growth stage through a time-series correlation algorithm, the triggering conditions and characteristic change patterns of stage transitions are revealed, and a feature set of microbial growth patterns containing stage features, parameter thresholds, and correlation rules is formed.

3. The microbial culture experimental data cloud processing system according to claim 2, characterized in that, The growth pattern mining module also includes: The dynamic optimization unit for growth patterns introduces a time decay factor to weight continuously collected time-series data, strengthening the influence of recent data on the growth pattern model; it updates the growth pattern feature set based on a sliding time window to adapt to the dynamic changes in microbial growth status in real time; and it mines the commonalities and specificities of growth patterns of similar microorganisms by comparing the growth pattern feature sets of different batches of experiments.

4. The microbial culture experimental data cloud processing system according to claim 3, characterized in that, The influencing factor analysis module includes: Multi-factor correlation modeling unit: Five key culture condition parameters—temperature, pH, culture medium formulation, inoculum size, and dissolved oxygen concentration—are selected to establish a mapping relationship with the characteristic set of microbial growth patterns. Correlation analysis algorithms are used to quantify the correlation strength between each culture condition parameter and key growth parameters, including growth rate, peak concentration, and stage duration, to screen core influencing factors. A multi-factor interaction model is constructed to analyze the synergistic and antagonistic effects among core influencing factors, clarifying the comprehensive influence of different factor combinations on microbial growth status.

5. The microbial culture experimental data cloud processing system according to claim 4, characterized in that, The influencing factor analysis module also includes: Optimal Condition Interval Determination Unit: Based on a multi-factor correlation model, a gradient analysis algorithm is used to traverse the value ranges of the core influencing factors to determine the optimal value intervals when each factor acts alone; combined with the interaction law, the optimal parameter configuration of the multi-factor combination is optimized to form an optimal condition combination that takes into account both the optimality of a single factor and the synergy of multiple factors; the reliability of the optimal condition interval is verified through a significance test algorithm, the interval boundaries and adjustment rules are marked, and condition adaptation suggestions are supplemented for three types of culture objectives: bacterial cell proliferation, efficient extraction of metabolites, and directed domestication of bacterial strains, forming a complete influencing factor analysis report.

6. The microbial culture experimental data cloud processing system according to claim 5, characterized in that, The anomaly detection module includes: The benchmark model construction unit is based on the microbial growth pattern feature set and the normal culture data of similar microorganisms in history. It constructs a normal growth benchmark model that includes the normal fluctuation range of key parameters at each growth stage and the threshold of time-series change trends. Combined with the optimal condition interval in the influencing factor analysis report, it sets the anomaly judgment threshold for different culture stages, forming a stage-by-stage and index-by-index anomaly judgment system. It configures an update mechanism for the benchmark model to continuously optimize the model parameters through newly added normal experimental data.

7. The microbial culture experimental data cloud processing system according to claim 6, characterized in that, The anomaly detection module also includes: Anomaly Identification and Cause Localization Unit: This unit compares the current time-series data of microbial culture with the normal growth baseline model in real time, calculates the quantified value of the deviation, and triggers an anomaly warning when the deviation exceeds a preset threshold. Based on the influencing factor analysis report, it correlates the changes in culture condition parameters during the anomaly occurrence period to analyze whether the core influencing factors deviate from the optimal range. Combined with the growth stage transition relationship model, it determines whether the anomaly originates from a stage transition anomaly, identifies the anomaly cause type as environmental parameter fluctuations, operational procedure deviations, abnormal culture medium components, or inoculum deviations, and outputs anomaly warnings and cause analysis results including the anomaly level, occurrence point, cause details, and emergency treatment suggestions.

8. The microbial culture experimental data cloud processing system according to claim 7, characterized in that, The anomaly detection module also includes: Anomaly Trend Prediction Unit: Based on real-time time-series data from a standardized microbial culture dataset, this unit uses a trend prediction algorithm to analyze the changing trends of growth indicators; compares the trend prediction results with the expected trends of a normal growth benchmark model to identify potential risks that may lead to future anomalies; and, in conjunction with an influencing factor analysis report, determines whether the potential risks stem from the slow drift of culture condition parameters, providing early risk warnings and preventative measures suggestions to achieve proactive early warning of anomalies.

9. The microbial culture experimental data cloud processing system according to claim 8, characterized in that, The experimental scheme recommendation module includes: Intelligent Solution Generation Unit: Based on the optimal condition combination and condition adaptation suggestions under three types of culture objectives from the influencing factor analysis report, and through risk points and emergency treatment suggestions in the abnormal early warning and cause analysis results, it matches successful experimental cases consistent with the current microbial species and culture objectives from the historical experimental database stored in the cloud; it extracts the core configuration information of the case, such as the proportion of culture medium components, the staged control curve of environmental parameters, the inoculation operation specifications, and the process sampling nodes; it determines the culture medium control parameters and inoculation amount by combining the optimal condition combination; it supplements the indicator judgment thresholds, sampling time intervals, and data records of process monitoring, and integrates them to form a microbial culture solution that includes culture condition parameters, operation procedure specifications, monitoring plan, and emergency pretreatment measures.

10. The microbial culture experimental data cloud processing system according to claim 9, characterized in that, The experimental scheme recommendation module also includes: The scheme dynamic optimization unit receives the updated standardized microbial culture dataset and growth pattern feature set in real time during the microbial culture process, compares the actual execution effect of the current culture scheme with the expected growth target, and uses the gradient descent algorithm to adjust the key parameters in the scheme for the discrepancies, optimizes the switching nodes and specific values ​​of the control parameters at each growth stage, feeds the optimized scheme back to the historical experimental database, and updates the parameter weights of the scheme recommendation model.

Images