A microbial early warning and forecasting system and method

Abstract

The application discloses a microbial early warning and prediction system and method, the system comprises a data integration module, an operation modeling module, a model verification module and a total evaluation module, the data integration module associates public microbial information with customer information, and transmits the associated data to the operation modeling module; the operation modeling module operates and models the associated data, and transmits the result to the model verification module, the model verification module is used for verifying the accuracy and rationality of the individualized customized model, and transmitting the processed information to the total evaluation module, finally, the total evaluation module outputs a risk index, a risk description and a recommended improvement scheme according to the information of the operation modeling module. Due to the adoption of the above technology, the application comprehensively, systematically and multi-dimensionally analyzes various aspects of products and factories, achieves the purposes that prediction and recommended results are more accurate, application fields are more extensive, interpretation modes are more detailed and convenient, and the like.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of microorganism prediction information, and in particular to a microorganism early warning and prediction system. BACKGROUND

[0002] Microorganisms are a major cause of product spoilage and impact on product quality, and product spoilage often brings direct economic losses to customers. Predictive microbiology is an interdisciplinary subject combining microbiology, chemistry, mathematics, statistics and applied computer technology, which uses mathematical methods to describe the response relationship between bacterial number changes and external environmental factors under different environmental conditions, and makes predictions on the growth kinetics of microorganisms, thereby contributing to the correct handling of products by customers. Therefore, in order to prevent problems from occurring, the prediction of microorganisms has become an extremely important link in product production and sales.

[0003] At present, more than ten kinds of microorganism prediction software have been developed in the world, among which the most famous are FoodMicromodel developed by the UK Ministry of Agriculture, Fisheries and Food (UKMAFF) based on a database and mathematical model in 1992, Pathogen Modeling Program developed by the US Department of Agriculture, and ComBase (Combined Database) integrated from the former two. These software usually assesses the risk according to the storage environment conditions and food materials and the current quality state of the food, and predicts the shelf life of the food.

[0004] However, the above-mentioned system has great limitations in terms of factors and prediction methods, and the current predictive microbiology and some existing prediction systems (such as the above-mentioned software) are mainly suitable for the food field, and ignore the needs of the industrial coatings, cosmetics, daily necessities and other fields. SUMMARY

[0005] In order to solve at least one of the above problems, the present application provides a new microorganism early warning and prediction system and method, which can comprehensively and systematically evaluate and analyze from the raw materials of the product to the production factory, the production process and the sales and use of the product, and is suitable for various fields (such as chemical coatings, cosmetics, daily necessities, etc.), so as to have a more extensive application field and market.

[0006] The microorganism early warning and prediction system comprises a data integration module, an operation modeling module, a model verification module and a general evaluation module.

[0007] The data integration module associates self-built microorganism information, publicly disclosed microorganism information and customer information obtained by the system, and transmits the associated data to the operation modeling module.

[0008] The operation modeling module operates the associated data according to a preset algorithm, constructs a personalized customization model, and obtains operation and analysis results, and transmits the model operation results to the model verification module;

[0009] The model verification module compares the model operation results with actual situations, verifies the accuracy and rationality of the personalized customization model, and transmits the processed information to the overall evaluation module;

[0010] The overall evaluation module outputs a microbial contamination risk index, a risk explanation, and a recommended improvement plan according to the information of the model verification module;

[0011] characterized in that the operation modeling module further comprises:

[0012] A factory evaluation module analyzes and evaluates the internal and external environment of the factory, as well as the factory system and management level;

[0013] A product evaluation module analyzes and evaluates the microorganisms, preservative properties, and contamination causes of products according to product raw materials, storage and preservation methods, and product usage;

[0014] A process evaluation module evaluates all links in the sample production process; and

[0015] The model verification module further comprises:

[0016] A data verification module compares the model operation results with actual situations and obtains verification results;

[0017] A data correction module adjusts the model operation results when the verification results have large errors.

[0018] In the above system, the data integration module further comprises:

[0019] A microbial database construction module stores self-built microbial information data and obtains publicly available microbial information data;

[0020] An information input module is used to input and / or automatically obtain water system, product production process, factory environment, factory management, product, and product usage information.

[0021] In the above system, the factory evaluation module further comprises:

[0022] A factory environment evaluation module analyzes and evaluates the geographical location, external climate, seasonal factors, and internal sanitary environment factors of the factory site;

[0023] a factory management evaluation module for analyzing and evaluating personnel and document management and health management of the factory;

[0024] a water system evaluation module for analyzing and evaluating process water and cleaning water of the factory.

[0025] In the system, the product evaluation module further comprises a raw material analysis module; and the product evaluation module further comprises a pollution history tracking module for monitoring drug-resistant bacteria in samples.

[0026] In the system, the total evaluation module further comprises:

[0027] a risk indication module for indicating a microbial contamination risk index according to data evaluated by the information processing module;

[0028] an interpretation module for interpreting the microbial contamination risk index;

[0029] an optimization suggestion module for giving a corresponding improvement scheme according to the microbial contamination risk index of the risk indication module.

[0030] In the system, the interpretation module further comprises:

[0031] an automatic interpretation module for automatically outputting a preliminary interpretation result according to the microbial contamination risk index of microbial contamination;

[0032] a consultation interpretation module for having a dialogue with an expert to interpret the microbial contamination risk index in detail and in depth.

[0033] In the system, the information input module further comprises a position sensing module for automatically identifying position information of the factory and automatically reading average humidity, average temperature, climate and seasonal information of a location according to the position information.

[0034] Meanwhile, the application also introduces a microbial early warning and forecasting method, which comprises:

[0035] Step 1: establishing a microbial information database, collecting various microbial information data and corresponding drug sensitivity information.

[0036] Step 2: inputting or automatically acquiring water system, product production process, factory environment, factory management, product and product use information;

[0037] Step 3: formulating a contribution index score scheme of each variable to microbial contamination risk, associating the information in Step 2 with the data of the microbial information database in Step 1, and formulating a contribution index score scheme of each variable to microbial contamination risk.

[0038] Step 4: Operation (operation rule) and fitting, determining the operation and fitting method according to the microbial contamination risk index scoring scheme in step 3, and operating and fitting according to the method;

[0039] Step 5: Establishing a personalized customization model, constructing a personalized customization model according to the operation and fitting results of step 4, and obtaining model operation results;

[0040] Step 6: Testing and correcting the model operation results in step 5, comparing the model operation structure with the actual situation, and correcting the model operation results if the accuracy or fitting degree is low;

[0041] Step 7: Outputting the overall microbial contamination risk index score according to the model operation results tested or corrected in step 6;

[0042] Step 8: Interpreting the microbial contamination risk index score in step 7, analyzing the contamination causes, and giving operation suggestions and improvement schemes.

[0043] In the above method, the microbial information in step 1 includes self-built microbial information and publicly disclosed microbial information; the product use information in step 2 includes product raw material information, product preservation and storage information; step 2 further includes inputting or automatically obtaining microbial contamination history information.

[0044] In the above method, the interpretation in step 8 includes system automatic interpretation and expert interpretation; step 8 further includes predicting sample shelf life, recommending a preservation system, and optimizing additive dosage.

[0045] The advantages and beneficial effects of the present application are:

[0046] The present application provides a brand new microbial early warning and forecasting method and system, which adopts the combination of multiple modules and analysis and evaluation methods to comprehensively, systematically and multi-dimensionally analyze the internal and external environmental conditions of product production plants, plant management, product raw materials, product production processes and product use, and adds a model verification module and an expert interpretation module and an expert interpretation link, so as to achieve the purposes of more accurate prediction and suggestion results, more extensive application field, more detailed and convenient interpretation mode, etc. BRIEF DESCRIPTION OF DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiment or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0048] Figure 1 is a structural block diagram of a biological early warning and forecasting system in an embodiment of the present application;

[0049] Figure 2 is a flow chart of a biological early warning and forecasting method in an embodiment of the present application. DETAILED DESCRIPTION

[0050] The specific embodiments of the present application are described below in conjunction with the accompanying drawings and examples. The following examples are only used to more clearly illustrate the technical solutions of the present application, and cannot be used to limit the protection scope of the present application.

[0051] System

[0052] As Figure 1As shown, the present application records a microbial early warning and prediction system, comprising a data integration module, an operation modeling module and a total evaluation module. The data integration module has Hanning self-built microbial information (including Hanning collected various standard strains and accumulated customer wild strains, etc.), and also records the information of the published microorganisms (such as the data archives of the common related microorganism growth and survival), and a database can be established inside the data integration module for storing the above self-built microbial information and obtaining the published microbial information; an information input module can also be independently set up for inputting and buffering the water system, product production process, factory environment, factory management, product and product use information. Then, the data integration module can convert the associated data into accurate mathematical language and transmit the associated data to the operation modeling module according to the characteristics of the actual object after associating the microbial information with the obtained customer information (the specific information types can be referred to in the examples below); the operation modeling module performs operation on the associated data according to the preset algorithm, constructs a personalized customized model and obtains operation and analysis results, and then transmits the model operation results to the model verification module; the model verification module compares the received model operation and analysis results with the actual situation (such as customer historical records, historical results) to verify the accuracy and rationality of the model. Further, the model verification module can have a data verification module and a data correction module, the data verification module compares the model operation results with the actual situation, if they are consistent, the results are given a judgment standard, and the microbial contamination risk index and the corresponding explanation are obtained, and the microbial contamination risk index and the personalized customized model information are transmitted to the total evaluation module; if the consistency is poor, the input information is modified through the data correction module, and modeling is performed again; the total evaluation module can output risk level, risk explanation and improvement scheme according to the information output by the operation modeling module. In order to more comprehensively analyze various microorganisms (including food field and chemical, daily necessities, cosmetics and other fields of microorganisms) and make the prediction results more accurate, the output more accurate, systematic and perfect measures, the operation modeling module of the microbial early warning and prediction system recorded in the present application analyzes and evaluates the internal and external environment of the factory, management and each link of the product from raw materials, production and processing to sales and use through the internal factory evaluation module, product evaluation module and process evaluation module. Specifically, the factory evaluation module is used to analyze and evaluate the internal and external environment of the factory and the management level of the factory system; the product evaluation module is used to analyze the microorganism, preservative property and pollution cause of the product according to the product raw materials, storage and preservative method, product use condition; the process evaluation module is used to evaluate all links in the sample production process. The parameters between the above modules will have interactive influence, and in the operation process, the collinearity is eliminated as much as possible by the regression model and other methods. Preferably, the factory evaluation module can be divided into a factory environment evaluation module and a water system evaluation module.The factory environment evaluation module is used for overall analysis and evaluation of the geographical location of the customer factory site, and the average temperature, humidity, climate, seasonal factors (such as the back-to-south season in South China, the plum rain season in East China, etc., to temperature and humidity and their changes, etc.) of the geographical location, and the internal sanitary environment of the customer factory. The factory management evaluation module can analyze and evaluate the internal personnel and document management of the factory. The water system module will evaluate the process water and cleaning water of the factory, and analyze the evaluation results. Finally, the analysis and evaluation results are summarized by using a specific algorithm, and a corresponding microbial prediction model (individualized customized model) is established.

[0053] In addition, the product evaluation module can further include a raw material analysis module for analyzing the content and types of microorganisms in raw materials. In order to more accurately predict microorganisms that may contaminate products, the product evaluation module can also include a contamination history tracking module for tracing the past microbial contamination complaint history or contamination history of products, and determining whether there are drug-resistant bacteria based on the contamination history or information provided by the customer.

[0054] The data integration module can further include an information input module. This module can obtain the data information to be analyzed by using a preset instruction or algorithm (see the embodiments below for details). For example, the customer can be asked to fill in the information required for system analysis, and a corresponding two-dimensional code is formed. At this time, the microbial early warning and prediction system can read the information by reading the two-dimensional code with a corresponding reading device (such as a code scanner). Of course, the information can also be directly input and cached in the module by manual input. The present application also provides a preferred scheme, in which the information input module includes a position sensing module. When it is installed at the customer end, the position sensing module can automatically identify the geographical information of the factory site, and read the corresponding external environmental information (such as average humidity, average temperature, and season, climate, etc.) of the factory site from the public internet according to the geographical information, thereby saving the customer from the tedious task of manually inputting the above information.

[0055] On the other hand, the data integration module can further include a separate microbial database construction module for obtaining and storing (if necessary, manually supplementing and inputting) the growth and survival characteristics of various related microorganisms that have been publicly disclosed, and finally forming a wide range of application (especially in the industrial field) of the prediction microbiology information database.

[0056] The final result of the microbial early warning and prediction system described in the application is output by a total evaluation module, and the result includes a microbial contamination risk index, an interpretation of the risk index (i.e., an explanation of the risk level represented by the microbial contamination risk index), and corresponding operation recommendations and improvement schemes given according to the foregoing result (such as recommending a suitable preservative system, optimizing the additive amount, etc.). In order to process the above information more finely, the total evaluation module can be accurately divided into a risk indication module, an interpretation module, and an optimization recommendation module, which are respectively used to indicate the final index of the microbial contamination risk according to the data evaluated by the information processing module, interpret the microbial contamination risk index, and give corresponding improvement schemes according to the microbial contamination risk index of the risk indication module.

[0057] It should be noted that, as a preferred scheme, in addition to the preliminary interpretation according to the microbial contamination risk index, the microbial early warning and prediction system described in the application is also equipped with special technical experts to provide more detailed data interpretation and scheme support for customers who want to obtain more detailed and in-depth interpretation. Therefore, preferably, the interpretation module can be divided into an automatic interpretation module and an expert interpretation module (which can include an online real-time dialogue module), wherein the automatic interpretation module is used to automatically output a preliminary interpretation result according to the microbial contamination risk index, and the expert interpretation module is used to communicate with experts to interpret the microbial contamination risk index in detail and in depth. Preferably, the expert interpretation module has a real-time online dialogue system, and more preferably, the system can be applied to a mobile phone and synchronized with the mobile phone, so that customers can contact experts at any time and anywhere.

[0058] Method

[0059] The application also relates to a microbial early warning and prediction method, as shown in the description, in particular to the following steps: Figure 2

[0060] Step 1: Establishing a microbial information database, collecting various microbial information data and corresponding drug sensitivity information.

[0061] Step 2: Inputting or automatically obtaining water system, product production process, factory environment, factory management, product and product use information;

[0062] Step 3: Formulating a contribution index scoring scheme of each variable to microbial contamination risk, associating the information in the step 2 with the data of the microbial information database in the step 1, and formulating a contribution index scoring scheme of each variable to microbial contamination risk;

[0063] Step 4: Operation (operation rule) and fitting, determining an operation and fitting method according to the microbial contamination risk index scoring scheme in the step 3, and performing operation and fitting according to the method; ​

[0064] Step 5: Establish a personalized customization model, build a personalized customization model according to the operation and fitting results of step 4, and obtain model operation results;

[0065] Step 6: Verify and correct the model operation results in step 5, compare the model operation structure with the actual situation, and if the accuracy or fitting degree is low, correct the model operation results;

[0066] Step 7: Output the overall microbial contamination risk index score according to the model operation results verified or corrected in step 6;

[0067] Step 8: Interpret the microbial contamination risk index score in step 7, analyze the contamination causes, and give operation suggestions and improvement schemes.

[0068] It should be noted that the microbial information in step 1 includes self-built microbial information and publicly disclosed microbial information; the product use information in step 2 includes product raw material information, product preservation and storage information; the process of entering or automatically obtaining microbial contamination history information can also be added to step 2, so that the past microbial contamination complaint history or contamination history of the product can be traced, and whether it contains drug-resistant bacteria can be judged according to the contamination history or information provided by the customer; the interpretation in step 8 can include preliminary interpretation and deep interpretation, and deep interpretation can be carried out by a professional expert team (experts include corresponding technical experts) to provide more detailed data interpretation and scheme support for customers.

[0069] One of the embodiments of the specific operation of the microbial early warning and forecasting system and method involved in the present application will be provided below for reference by those skilled in the art.

[0070] A microbial database is established to collect publicly disclosed microbial physiological and ecological information and drug sensitivity information, as well as wild bacteria and drug-resistant bacteria information accumulated by our technical staff over the years. The factory data collected by the client in the information input module of the data integration module is entered, and after the information in the data integration module is associated, all data is transmitted to the operation modeling module for centralized evaluation and operation. In the operation, those skilled in the art will simplify the specific problems as necessary and make appropriate assumptions in precise language, and on the basis of the assumptions, appropriate mathematical tools are used to describe the mathematical relationship between variables and constants, and the corresponding mathematical structure is established. The factory evaluation module of the operation modeling module processes and evaluates the information related to the factory environment and management; the product evaluation module of the operation modeling module processes and evaluates the information related to the product itself and the use of the product; the process evaluation module of the operation modeling module processes and evaluates the information related to the production and processing of the product, which is as follows:

[0071] The factory environment evaluation module in the factory evaluation module evaluates and calculates the microbial contamination risk index corresponding to the information according to the following information;

[0072] 1. Factory external environment

[0073] Geographical location, average temperature, average humidity, climate, seasonal factors of the customer's location.

[0074] 2. Factory internal hygiene environment

[0075] 1) Is the factory area regularly cleaned?

[0076] 2) Does the factory building have an air purification system? If so, further evaluate and calculate the filtration method and replacement frequency;

[0077] 3) Is there regular inspection of the microbial conditions in the air inside the factory building? If so, further evaluate and calculate the detection frequency, method, and historical records.

[0078] The factory management evaluation module in the factory evaluation module evaluates and calculates the microbial contamination risk index corresponding to the information according to the following information;

[0079] 3. Personnel and document management

[0080] 1) Are there regular microbial concept trainings for relevant staff?

[0081] 2) Are there standard operating procedures (SOPs) for each operation?

[0082] 3) Are there process record sheets for each work section?

[0083] The water system evaluation module in the factory evaluation module evaluates and calculates the microbial contamination risk index corresponding to the information according to the following information;

[0084] 4. Factory water system

[0085] 1) Process water

[0086] a. Type (municipal tap water / reverse osmosis water / ion exchange softened water / others);

[0087] b. Storage (tank / barrel);

[0088] c. Turnover speed;

[0089] d. Sterilization treatment method (chemical agent / UV / reverse osmosis / others);

[0090] 2) Cleaning water

[0091] a. Type (municipal tap water / reverse osmosis water / ion exchange softened water / others);

[0092] b. Storage (tanks / barrels);

[0093] c. Turnover speed;

[0094] d. Sterilization treatment method (chemical agents / UV / reverse osmosis / other).

[0095] The raw material analysis module and contamination history tracking module in the product evaluation module evaluate and calculate the microbial contamination risk index corresponding to the following information;

[0096] 5. Raw material situation*

[0097] 1) Is there an established raw material warehousing system? If so, further evaluate and calculate the raw material warehousing system;

[0098] 2) Are there any raw materials that are susceptible to contamination? If so, further evaluate and calculate their names and contents;

[0099] 3) Are sampling tools and other tools that come into contact with raw materials regularly cleaned and disinfected? If so, further evaluate and calculate the frequency and method of cleaning and disinfection.

[0100] 4) Is the material added manually during production?

[0101] 5) Are there any components that affect the activity of the preservative? If so, further evaluate and calculate their names and contents.

[0102] 6) Moisture content in the formula;

[0103] 7) Customer complaints and history of microbial contamination (whether there are drug-resistant bacteria).

[0104] At the same time, the product evaluation module will also evaluate and calculate the microbial contamination risk index corresponding to the information based on the following information;

[0105] 6. Product Information*

[0106] 1) Product type, pH;

[0107] 2) Type and dosage of preservatives;

[0108] 3) Method of adding preservatives (addition time / temperature / addition point);

[0109] 4) Product packaging (small drums / ton drums; for daily chemical products, there are also pump-head packaging, wide-mouth cans, etc.);

[0110] 5) Product storage conditions (temperature / time).

[0111] 7. Product Usage

[0112] 1) Product usage conditions (region / climate);

[0113] 2) Product usage method (single use / multiple uses);

[0114] 3) Current shelf life of the product.

[0115] The process assessment module calculates the corresponding microbial contamination risk index based on the following information;

[0116] 8. Production process information*

[0117] 1) Are there regular factory hygiene inspections? If so, further evaluate and calculate the time of the last factory hygiene inspection and the results of each inspection.

[0118] 2) Are there currently designated microbial sampling procedures? If so, what are they?

[0119] a. Sampling frequency;

[0120] b. Sampling point;

[0121] c. Detection methods;

[0122] d. Warning concentration (if the warning concentration is exceeded, corresponding cleaning and disinfection measures must be taken);

[0123] Perform evaluation calculations.

[0124] 3) Is there an established regular cleaning and disinfection process?

[0125] a. Frequency of cleaning and disinfection;

[0126] b. Objects to be cleaned and disinfected (storage tanks / pipelines / hose / pumps / filters / water / valves);

[0127] c. Cleaning methods (manual / soaking / pipe cleaning, planing / high-pressure water gun / chemical methods);

[0128] d. Disinfection methods

[0129] i. Chemical methods (reagents / concentration / temperature / contact time);

[0130] ii. Steam (temperature / contact time);

[0131] iii. Hot water (temperature / contact time);

[0132] e. Is there any verification of disinfection effectiveness? If so, further evaluate and calculate the disinfection effectiveness verification method.

[0133] The steps marked with * are key steps with a significant impact and require priority in parameter collection and computation.

[0134] The computational modeling module takes the evaluation results of all the sub-modules described above and applies them through the scientific core computation (preset algorithm) and fitting described earlier to establish a personalized microbial prediction model (personalized model). During modeling, factor correlation is considered, determined by correlation coefficients. If correlation is found, principal component analysis is used for filtering. Weights are determined using mathematical methods such as variance (one weight determination scheme involves using correlation coefficients to determine factor correlation; if correlation is found, principal component analysis is used to filter out correlated components, and component combinations and redefinition are performed; finally, combined with past experience, weights are determined using mathematical methods such as variance and n-variable equations). The data is then transmitted to the model verification module for validation and correction. The correction process can be divided into automatic system correction and manual correction (which can be achieved through the manual correction module). If the model closely matches reality, the calculation results are given their practical meaning and explained. If the model's calculation results do not closely match reality, the assumptions described above should be modified, and the modeling process should be repeated. The verified and corrected data will be input into the overall assessment module, which will then output the overall microbial contamination risk index. The interpretation module within the overall assessment module will then interpret each risk based on the microbial contamination risk index score, providing early warnings, forecasts, and suggested improvement plans. See the table below for details:

[0135]

[0136] Table 1: Reference Table for Output Results of Microbial Early Warning and Forecasting System

[0137] In addition, users or operators in this field can also contact or consult relevant specialized technical experts through the expert interpretation module in the interpretation module to obtain more detailed data interpretation and solution support.

[0138] The above description of the disclosed embodiments is intended to enable those skilled in the art to implement or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this invention should be included within the protection scope of this invention.

Claims

1. A microbial early warning and forecasting system, comprising a data integration module, a computational modeling module, a model verification module, and an overall evaluation module; The data integration module associates self-built microbial information, publicly available microbial information, and customer information acquired by the system, and transmits the associated data to the computational modeling module; The computational modeling module evaluates the associated data through its internal sub-modules and performs calculations on the evaluation results according to a preset algorithm. It uses the correlation coefficient to determine the correlation of factors. Once a correlation is found, it filters out the associated components using principal component analysis, groups and redefines the components, and finally determines the weights using mathematical means. It then constructs a personalized model and obtains the computational and analytical results, and transmits the model computation results to the model verification module. The model verification module compares the model calculation results with the actual situation to verify the accuracy and rationality of the personalized customized model, and transmits the processed information to the overall evaluation module. The overall evaluation module outputs a microbial contamination risk index, risk description, and suggested improvement plans based on the information from the model verification module. The sub-module of the computational modeling module is characterized in that it further comprises: The factory assessment module analyzes and evaluates the factory's internal and external environment, as well as its systems and management level, in the associated data. The product evaluation module analyzes and evaluates the product's microbiology, preservative properties, and causes of contamination based on the product's raw materials, storage and preservation methods, and product usage in the associated data. The process evaluation module evaluates all aspects of the sample production process in the associated data; The factory assessment module further includes: The factory environmental assessment module analyzes and evaluates the factory's geographical location, external climate, seasonal factors, and internal hygiene and environmental factors. The factory management assessment module analyzes and evaluates the factory's personnel and document management, as well as hygiene management. The water system assessment module analyzes and evaluates the process water and cleaning water used in the factory. Furthermore, the model verification module further includes: The data verification module is used to compare the model calculation results with the actual situation and obtain the verification results; The data correction module is used to adjust the model calculation results when the verification result error is large.

2. The microbial early warning and forecasting system as described in claim 1, characterized in that, The data integration module further includes: The microbial database construction module is used to store self-built microbial information and to obtain publicly available microbial information. The information input module is used to input and buffer information on water systems, product manufacturing processes, factory environment, factory management, products, and product usage.

3. The microbial early warning and forecasting system as described in claim 1, characterized in that, The product evaluation module further includes a raw material analysis module; the product evaluation module further includes a contamination history tracking module for monitoring drug-resistant bacteria in samples.

4. A microbial early warning and forecasting system as described in claim 1, characterized in that, The overall evaluation module further includes: The risk indicator module is used to indicate the risk index of microbial contamination; The interpretation module is used to interpret the microbial contamination risk index; The optimization suggestion module provides corresponding improvement plans based on the microbial contamination risk index of the risk indication module.

5. A microbial early warning and forecasting system as described in claim 4, characterized in that, The interpretation module further includes: The automatic interpretation module automatically outputs preliminary interpretation results based on the microbial contamination risk index; The expert interpretation module allows users to engage in dialogue with experts for a detailed and in-depth interpretation of the microbial contamination risk index.

6. A microbial early warning and forecasting system as described in claim 2, characterized in that, The information input module further includes a location sensing module, which is used to automatically identify the factory location information and automatically read the average humidity, average temperature, climate and seasonal information of the location based on the location information.

7. An application of the microbial early warning and forecasting system as described in any one of claims 1-6, characterized in that, The microbial early warning and forecasting system is applied in the fields of daily necessities and chemicals.

8. A method for conducting microbial early warning and forecasting using the microbial early warning and forecasting system as described in any one of claims 1-6, characterized in that, include: Step 1: Establish a microbial information database, summarizing various microbial information and corresponding drug sensitivity information; Step 2: Enter or automatically retrieve information on the water system, product manufacturing process, factory environment, factory management, products, and product usage; Step 3: Specify the contribution index scoring scheme of each variable to the risk of microbial contamination. In the data integration module, associate the information in Step 2 with the data in the microbial information database in Step 1, and formulate the contribution index scoring scheme of each variable to the risk of microbial contamination. Step 4: Perform calculations and fitting in the computational modeling module. Determine the calculation and fitting method based on the microbial contamination risk index scoring scheme in Step 3, and perform calculations and fitting according to this method. Step 5: Build a personalized customization model. Based on the calculation and fitting results of Step 4, construct a personalized customization model and obtain the model calculation results. Step 6: In the model verification module, verify and correct the model calculation results in Step 5, compare the model calculation structure with the actual situation, and correct the model calculation results if the accuracy or fit is low. Step 7: Based on the model calculation results that have been verified or corrected in Step 6, output the overall microbial contamination risk index score; Step 8: In the overall evaluation module, interpret the microbial contamination risk index score from Step 7, analyze the causes of contamination, and provide operational suggestions and improvement plans.

9. A microbial early warning and forecasting method as described in claim 8, characterized in that, The microbial information data in step 1 includes self-built microbial information data and publicly available microbial information data; the product usage information in step 2 includes product raw material information, product preservation and storage information; step 2 further includes recording or automatically acquiring microbial contamination history information.

10. A microbial early warning and forecasting method as described in claim 8, characterized in that, The interpretation in step 8 includes both automatic interpretation by the system and interpretation by experts; step 8 also further includes predicting the shelf life of the sample, recommending the preservation system, and optimizing the dosage.

Images