Food-borne strain propagation risk early warning system and method based on clustering analysis

Abstract

The invention relates to the technical field of bacterial strain propagation risks, in particular to a food-borne bacterial strain propagation risk early warning system and method based on clustering analysis, and the method comprises the steps: comprehensively calculating the bacterial adhesion capability, the environmental inhibition capability and the chemical protection capability from the physical, chemical and biological characteristics of food and the environment of the food; food surface contamination characteristic evaluation is formed; meanwhile, by analyzing the cross contamination risk of background bacterial colonies and fresh products, a food contamination risk sequence is generated, then by means of a K-Means risk clustering model, in combination with historical data and eating habits, feature groups with different risk levels are automatically found and defined, the risk category can be rapidly judged through risk assessment grouping, and the risk assessment efficiency is improved. Therefore, the accuracy, the foresight and the response efficiency of risk identification are remarkably improved.

Description

Technical Field

[0001] This application relates to the field of strain transmission risk technology, and in particular to a foodborne strain transmission risk early warning system and method based on cluster analysis. Background Technology

[0002] Currently, risk warnings for foodborne pathogens mainly rely on microbial limit standards based on terminal sampling and preventive systems based on HACCP. While the former has legal force, it suffers from significant delays, high costs, and limited coverage, failing to provide advance warnings. The latter focuses on controlling key points in the process but is insufficient in risk quantification, struggling to dynamically adapt to complex and changing environments and product combinations, and lacking the ability to integrate multi-source information for comprehensive assessment. Furthermore, while emerging predictive microbiology models can simulate microbial behavior, their parameters heavily depend on specific experiments, lacking versatility, and are mostly limited to a few factors such as temperature and pH, making it difficult to systematically quantify key influences such as the physicochemical properties of food surfaces on bacterial adhesion and residue. Overall, existing technologies struggle to achieve real-time, multi-dimensional, and precise quantification of forward-looking risk warnings. Summary of the Invention

[0003] To overcome the shortcomings of existing technologies, this application provides a risk early warning system and method for foodborne bacterial strain transmission based on cluster analysis. This solution quantifies and intelligently groups complex food safety risks in a multi-dimensional and hierarchical manner. First, through risk data collection and evaluation, it comprehensively calculates bacterial adhesion ability, environmental inhibition ability, and chemical protection ability from two levels: the physical, chemical, and biological characteristics of the food itself and its environment, forming an assessment of food surface contamination characteristics. Simultaneously, by analyzing the risk of cross-contamination between background colonies and fresh products, a food contamination risk sequence is generated. Subsequently, using the K-Means risk clustering model, combined with historical data and eating habits, it automatically discovers and defines characteristic groups with different risk levels. It can quickly determine the risk category through risk assessment grouping and implement precise intervention, thereby significantly improving the accuracy, foresight, and response efficiency of risk identification.

[0004] To achieve the above objectives, this application adopts the following technical solution: In the first aspect, this application provides a foodborne bacterial strain transmission risk early warning system based on cluster analysis, including the following modules: The system comprises a risk data acquisition module, a data evaluation module, a clustering risk grouping module, a risk assessment module, and a risk early warning module. The risk data acquisition module acquires the inherent characteristics of the food surface and the characteristics of the environment in which the food is located. The data evaluation module assesses the surface contamination characteristics of the food based on its inherent characteristics and assesses the risk of food contamination based on the environmental characteristics of the food's location. The clustering risk grouping module performs risk clustering based on historical data and historical consumption habits. The risk assessment module performs risk assessment grouping based on the results of the surface contamination characteristic assessment and the risk assessment. The risk early warning module provides early warning of the risk of transmission based on the risk assessment grouping results.

[0005] In one implementation of this application, the inherent characteristics of the food surface specifically include: physical characteristics including surface roughness, porosity, and surface area / volume ratio; chemical characteristics including pH value, water activity (Aw), and inherent nutrients (such as protein and fat content); and biological characteristics including the content of antibacterial substances. Specifically, pH value (acidity / alkalinity) measures the acidity or alkalinity of the environment; most bacteria grow best in a neutral environment, and excessive acidity or alkalinity inhibits their growth; water activity refers to the content of free water available to microorganisms in the food, ranging from 0 (anhydrous) to 1.0 (pure water); inherent nutrients include proteins, carbohydrates, fats, vitamins, and minerals provided by the food itself, which serve as fuel for bacterial growth; and temperature includes average temperature and its fluctuation range. Temperature directly affects enzyme activity and determines growth rate; the temperature danger zone typically refers to 4°C to 60°C. Relative humidity primarily affects the growth of microorganisms on the food surface and in the surrounding environment, and is crucial for preventing cross-contamination during storage. All these characteristics are averaged values. The environmental characteristics of the food's location include: physical environment (average temperature, temperature fluctuation range, and relative humidity); biological environment (known total bacterial count (APC) or background concentration of specific pathogens); and cross-contamination environment (physical distance or frequency of contact with fresh products, especially poultry and seafood).

[0006] In one implementation of this application, the evaluation of food surface contamination characteristics includes the following specific aspects: Step 1: Obtain the surface roughness, porosity, and surface area / volume ratio of the food surface. Then, perform a weighted summation of the standardized results of these parameters to obtain the bacterial adhesion anomaly. The standardization process involves dividing the obtained parameter by its corresponding safe value. Initial bacterial adhesion to an object's surface is the first step in contamination. This process is heavily influenced by the physical properties of the surface. Higher surface roughness, greater porosity, and a larger surface area / volume ratio provide more hiding places and adhesion areas for bacteria, making them more difficult to clean and significantly increasing the risk and intensity of adhesion. By quantifying these key physical parameters, this step allows for an objective comparison of the contamination susceptibility of different food or packaging material surfaces. Step 2: Obtain the pH value, water activity, inherent nutrient composition, average ambient temperature, temperature fluctuation range, and relative humidity of the food. Simultaneously, obtain the safe range corresponding to the suitable environmental conditions for bacterial growth. The suitable environmental conditions for bacterial growth are determined through bacterial tolerance experiments, using the parameter range corresponding to the minimum reproductive activity of bacteria. Compare the obtained pH value, water activity, inherent nutrient composition, average ambient temperature, temperature fluctuation range, and relative humidity of the food with the corresponding parameter ranges of the suitable environmental conditions for bacterial growth to obtain the bacterial growth inhibition results for each parameter. Weighted summation of all bacterial growth inhibition results yields the environmental bacterial growth inhibition result. The parameter comparison process is as follows: the absolute value of the corresponding parameter value minus the median value of the corresponding parameter's safe range is divided by the range value of the corresponding parameter's safe range. The range value is the maximum value minus the minimum value of the corresponding parameter's safe range. Step 3: Obtain the content of antimicrobial agent per unit mass of food surface. Divide the content of antimicrobial agent per unit mass of food surface by the safe content to obtain the safe value of the antimicrobial agent. In the food industry, legally added antimicrobial agents or disinfectant residues used in the processing are direct chemical means of actively inhibiting or killing surface microorganisms. Their effectiveness is directly related to the effective concentration at the point of action. This step introduces a quantitative assessment of active intervention factors. By comparing the measured antimicrobial agent content with the known safe and effective concentration, it is possible to clearly determine whether the protective ability of the chemical barrier is sufficient. Obtain the results of abnormal bacterial attachment, inhibition of environmental bacterial growth, and the safe value of the antimicrobial agent as an assessment sequence of food surface contamination characteristics.

[0007] In one implementation of this application, the food contamination risk assessment specifically includes the following: Step 1: Obtain the known total number of background bacterial colonies and their physical distance from the fresh product. Also, obtain the shelf life and duration of the fresh product. The shelf life of the fresh product is obtained by averaging historical shelf life data. For example, the average shelf life of fresh beef under the corresponding refrigeration scenario is two days, and the number of bacteria on the surface of fresh meat should be less than 10,000 per gram. Step 2: Obtain the background colony hazard value by dividing the known total background colony count by the corresponding safe value of the total background colony count; Step 3: Analyze the contamination status of fresh products on food by considering the physical distance between fresh products and food at various times, as well as the weight, shelf life, and duration of the fresh products. Specifically, the steps are as follows: Divide the duration of fresh products at the corresponding time by the shelf life to obtain the fresh product presence anomaly at that time; divide the safe distance by the physical distance between the fresh product and food at the corresponding time to obtain the fresh product distance anomaly at that time; perform a weighted sum of the fresh product presence anomaly and the fresh product distance anomaly at the corresponding time to obtain the fresh product contamination anomaly; multiply the fresh product contamination anomaly by the standardized weight of the fresh product at the corresponding time to obtain the fresh product anomaly at that time. Standardization involves removing unit processes, i.e., dividing by the standard weight. Integrate the fresh product anomaly at the corresponding time over the time length and divide by the standard time to obtain the fresh product contamination anomaly on food. Use the background bacterial colony hazard value and the fresh product contamination anomaly on food as a food contamination risk sequence.

[0008] In one implementation of this application, the risk clustering grouping includes the following specific content: This study obtains historical data on people's eating habits, historical food surface contamination characteristic assessment sequences, and historical food contamination risk sequences. The eating habits data includes the proportion and frequency of various ways of consuming corresponding foods in the relevant region, including food cooking time and temperature, obtained through historical custom statistics. Simultaneously, it obtains the judgment results regarding whether the bacterial infection rate of the corresponding purchaser exceeds the safety threshold. Based on the historical data on people's eating habits, historical food surface contamination characteristic assessment sequences, historical food contamination risk sequences, and the judgment results, a K-Means risk clustering model is constructed, taking the people's eating habits, food surface contamination characteristic assessment sequences, and food contamination risk sequences as inputs and outputting the judgment results regarding whether the bacterial infection rate of the corresponding purchaser exceeds the safety threshold.

[0009] In one implementation of this application, the risk assessment grouping includes the following specific contents: The system acquires real-time data on people's eating habits for the corresponding food, assesses the surface contamination characteristics of the food, and imports the food contamination risk sequence into the K-Means risk clustering model. The output is a judgment result indicating whether the infection rate of the corresponding purchaser exceeds the safety threshold.

[0010] In one implementation of this application, the propagation risk warning includes the following specific contents: If the assessment result of whether the infection rate of the corresponding purchaser exceeds the safety threshold is yes, then a transmission risk warning needs to be issued and the corresponding food should be removed from the shelves. If the assessment result is no, then no transmission risk warning needs to be issued and sales can continue.

[0011] Secondly, this application also provides a method for early warning of the risk of foodborne bacterial strain transmission based on cluster analysis, including the following specific steps: To obtain the inherent surface characteristics of food and the characteristics of the environment in which the food is located; The surface contamination characteristics of food are assessed based on the inherent characteristics of the food surface, and the risk of food contamination is assessed based on the environmental characteristics of the location of the food. Risk clustering was performed based on historical data and historical consumption habits; Risk assessment groups were formed based on the results of food surface contamination characteristics assessment and food contamination risk assessment. Risk warnings will be issued based on the risk assessment grouping results.

[0012] Thirdly, this application provides an electronic conduit, comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes a foodborne strain transmission risk warning method based on cluster analysis by calling the computer program stored in the memory.

[0013] Fourthly, this application provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform a cluster analysis-based method for early warning of the risk of foodborne bacterial strain transmission.

[0014] Compared with the prior art, this application has the following advantages and beneficial effects: This application employs a multi-dimensional and hierarchical quantitative assessment and intelligent grouping of complex food safety risks. Firstly, through risk data collection and evaluation, it comprehensively calculates bacterial adhesion ability, environmental inhibition ability, and chemical protection ability from both the food's own physicochemical and biological characteristics and its surrounding environment, forming an assessment of food surface contamination characteristics. Simultaneously, by analyzing background colonies and the risk of cross-contamination with fresh products, it generates a food contamination risk sequence. Subsequently, using the K-Means risk clustering model, combined with historical data and consumption habits, it automatically identifies and defines characteristic groups with different risk levels. This allows for rapid determination of their risk category through risk assessment grouping, enabling precise intervention and significantly improving the accuracy, foresight, and response efficiency of risk identification. Attached Figure Description

[0015] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 This is a schematic diagram of the overall process of an embodiment of the method of this application; Figure 2 This is a schematic diagram of the process for evaluating the surface contamination characteristics of food according to an embodiment of the method of this application; Figure 3 This is a flowchart illustrating the clustering algorithm in an embodiment of the method of this application; Figure 4 This is a schematic diagram of the module composition structure of an embodiment of the system in this application. Detailed Implementation

[0016] The technical solution of this application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments and specific features in the embodiments are detailed descriptions of the technical solution of this application, rather than limitations thereof. In the absence of conflict, the embodiments and technical features in the embodiments can be combined with each other.

[0017] Please see Figures 1 to 3 , Figure 1 This is a schematic diagram of the overall process of the foodborne bacterial strain transmission risk early warning method based on cluster analysis provided in the embodiments of this application, which specifically includes the following steps: To obtain the inherent surface characteristics of food and the characteristics of the environment in which the food is located; In this embodiment, it should be noted that the inherent characteristics of the food surface specifically include: physical characteristics, including surface roughness, porosity, and surface area / volume ratio; chemical characteristics, including pH value, water activity (Aw), and inherent nutrients (such as protein and fat content); and biological characteristics, including the content of antibacterial substances. Specifically, pH value (acidity / alkalinity) measures the acidity or alkalinity of the environment; most bacteria grow best in a neutral environment, and excessive acidity or alkalinity inhibits their growth; water activity refers to the content of free water available to microorganisms in the food, ranging from 0 (anhydrous) to 1.0 (pure water); inherent nutrients are the proteins, carbohydrates, fats, vitamins, and minerals provided by the food itself, which serve as fuel for bacterial growth; and temperature includes average temperature and its fluctuation range. Temperature directly affects enzyme activity and determines growth rate; the temperature danger zone typically refers to 4°C to 60°C. Relative humidity primarily affects the growth of microorganisms on the food surface and in the surrounding environment, and is crucial for preventing cross-contamination during storage. All these characteristics are averaged values. Environmental characteristics of the food's location include: physical environment (average temperature, temperature fluctuation range, and relative humidity); biological environment (known total bacterial count (APC) or background concentration of specific pathogens); and cross-contamination environment (physical distance or frequency of contact with fresh products, especially poultry and seafood). The surface contamination characteristics of food are assessed based on the inherent characteristics of the food surface, and the risk of food contamination is assessed based on the environmental characteristics of the location of the food. In this embodiment, the evaluation of food surface contamination characteristics includes the following specific aspects: Step 1: Obtain the surface roughness, porosity, and surface area / volume ratio of the food surface. Then, perform a weighted summation of the standardized results of these parameters to obtain the bacterial adhesion anomaly. The standardization process involves dividing the obtained parameter by its corresponding safe value. Initial bacterial adhesion to an object's surface is the first step in contamination. This process is heavily influenced by the physical properties of the surface. Higher surface roughness, greater porosity, and a larger surface area / volume ratio provide more hiding places and adhesion areas for bacteria, making them more difficult to clean and significantly increasing the risk and intensity of adhesion. By quantifying these key physical parameters, this step allows for an objective comparison of the contamination susceptibility of different food or packaging material surfaces. Step 2: Obtain the pH value, water activity, inherent nutrient composition, average ambient temperature, temperature fluctuation range, and relative humidity of the food. Simultaneously, obtain the suitable environmental conditions and corresponding safe ranges for bacterial growth. The suitable environmental conditions for bacterial growth are determined through bacterial tolerance experiments, using the parameter range corresponding to the minimum reproductive activity required for bacterial growth. Compare the obtained pH value, water activity, inherent nutrient composition, average ambient temperature, temperature fluctuation range, and relative humidity of the food with the corresponding parameter ranges for bacterial growth to obtain the bacterial growth inhibition results for each parameter. Finally, weightedly sum all the bacterial growth inhibition results to obtain the environmental bacterial growth inhibition result. The parameter comparison process involves subtracting the median value of the corresponding parameter's safe range from the corresponding parameter value. The result is calculated by dividing the absolute value by the range value of the corresponding parameter's safe range. The range value is the maximum value minus the minimum value of the corresponding parameter's safe range. Whether bacteria can reproduce and reach a pathogenic number after attachment depends entirely on the microenvironment conditions. pH, water activity, temperature, etc. are the core environmental factors that determine the rate of bacterial metabolism and division. Each pathogen has its specific tolerance range for growth and reproduction. The further the environmental parameters deviate from their optimal range, the stronger the inhibitory effect on their growth. This step realizes a comprehensive biological risk assessment of the chemical characteristics of the food itself and its storage environment. It can not only warn of the risk of rapid bacterial proliferation under certain conditions, but also identify those seemingly safe (such as acidic or dry foods) scenarios that may actually support the slow growth of specific resistant pathogens (such as acid-resistant Escherichia coli or dry-resistant Staphylococcus aureus), making the risk assessment more targeted and accurate. Step 3: Obtain the content of antimicrobial agent per unit mass of food surface. Divide the content of antimicrobial agent per unit mass of food surface by the safe content to obtain the safe value of antimicrobial agent. In the food industry, legally added antimicrobial agents (such as preservatives) or disinfectant residues used in the processing are direct chemical means of actively inhibiting or killing surface microorganisms. Their effectiveness is directly related to the effective concentration at the point of action. This step introduces a quantitative assessment of active intervention factors. By comparing the measured antimicrobial agent content with the known safe and effective concentration, it is possible to clearly determine whether the protective ability of the chemical barrier is sufficient. Obtain the results of abnormal bacterial attachment, inhibition of environmental bacterial growth, and the safe value of antimicrobial agent as an assessment sequence of food surface contamination characteristics. In this embodiment, the food contamination risk assessment specifically includes the following: Step 1: Obtain the known total number of background bacterial colonies and their physical distance from the fresh product. Also, obtain the shelf life and duration of the fresh product. The shelf life of the fresh product is obtained by averaging historical shelf life data. For example, the average shelf life of fresh beef under the corresponding refrigeration scenario is two days, and the number of bacteria on the surface of fresh meat should be less than 10,000 per gram. Step 2: Obtain the background colony hazard value by dividing the known total background colony count by the corresponding safe value of the total background colony count; Step 3: Analyze the contamination status of fresh produce on food by considering the physical distance between the fresh produce and the food at each time point, along with the corresponding weight, shelf life, and duration of exposure. Specifically: Divide the duration of fresh produce exposure at the corresponding time by the shelf life to obtain the fresh produce presence anomaly at that time; divide the safe distance by the physical distance between the fresh produce and the food at the corresponding time to obtain the fresh produce distance anomaly at that time; perform a weighted sum of the fresh produce presence anomaly and the fresh produce distance anomaly at the corresponding time to obtain the fresh produce contamination anomaly; and multiply the fresh produce contamination anomaly by the standardized weight of the fresh produce at the corresponding time to obtain the fresh produce anomaly at that time. Here, standardization refers to removing unit process... That is, dividing by the standard weight, integrating the fresh product anomaly over the time length and dividing by the standard time yields the fresh product contamination anomaly to food. The background colony hazard value and the fresh product contamination anomaly to food are used as the food contamination risk sequence. The fresh product existence time / shelf life quantifies the degree of spoilage and microbial growth potential of the fresh product itself, and the safe distance / physical distance quantifies the spatial transmission risk. The closer the distance, the higher the risk of cross-contamination through air suspension, contact, splashing and other means. In toxicology and microbial risk assessment, the probability of infection or disease is related to the exposure dose. Here, the fresh product anomaly can be regarded as a proxy indicator of the potential exposure dose of the target food. Risk clustering was performed based on historical data and historical consumption habits; In this embodiment, risk clustering includes the following specific aspects: The process involves acquiring historical data on people's eating habits, historical food surface contamination characteristic assessment sequences, and historical food contamination risk sequences. Eating habits include the proportion and frequency of various consumption methods for corresponding foods in the relevant region, including food cooking time and temperature, obtained through historical custom statistics. Simultaneously, the process yields results indicating whether the bacterial infection rate of the corresponding purchaser exceeds a safe threshold. Based on these data, a K-Means risk clustering model is constructed, taking the historical data on people's eating habits, food surface contamination characteristic assessment sequences, and food contamination risk sequences as inputs, and outputting the results indicating whether the bacterial infection rate of the corresponding purchaser exceeds a safe threshold. The specific steps are as follows: 1. Constructing feature vectors and data preprocessing 1.1 Constructing Feature Vectors: Calculate all feature values ​​for each object to be evaluated in the dataset (e.g., each food-consumer group combination) to form an original data record: (surface contamination risk, cross-contamination risk, environmental microbial risk, consumption habit risk, judgment result); 1.2 Data Preprocessing: Standardize all feature values ​​(e.g., use Z-score standardization) so that the mean of each feature is 0 and the standard deviation is 1. This step is to ensure that all features have the same importance when calculating distance and to avoid features with large dimensions dominating the clustering results. 2. Determine the optimal number of clusters 2.1. Select the optimal range of cluster size: Select a reasonable range of optimal cluster size for the search (e.g., from 2 to 10). 2.2. Calculate the sum of squared intra-cluster deviations for each optimal cluster size: For each candidate optimal cluster size, run the K-Means algorithm once and calculate the sum of squared intra-cluster deviations for that optimal cluster size (i.e., the sum of the squared distances from each sample to the center of its cluster). 2.3. Plot a line graph with the optimal number of clusters as the x-axis and the corresponding sum of squared deviations within clusters as the y-axis; 2.4. Observe the curve and find the inflection point. Before this inflection point, the rate of decline of the curve exceeds 10%, and after the inflection point, the rate of decline is halved. The optimal number of clusters corresponding to this inflection point is the recommended optimal number of clusters. Final confirmation based on business interpretation: Observe the clustering results generated by the suggested optimal number of clusters (e.g., K=4), and judge from a business perspective whether these categories have a clear and reasonable distinction of risk levels (e.g., whether the accuracy of the results exceeds the set value, preferably 85%); if the classification results are difficult to interpret, the optimal number of clusters can be fine-tuned (e.g., try K=3 or K=5) and re-evaluated; 3. Perform K-Means clustering Initialize the model: Initialize the K-Means model using the optimal number of clusters determined in step two; Set the random seed: To ensure reproducible results for each run, a fixed random seed needs to be set. Setting the random seed is achieved through a specific function or parameter. This operation initializes the internal state of the pseudo-random number generator, ensuring it starts from the same starting point. This guarantees that algorithms involving randomness (such as the initial centroid selection in K-Means) produce identical results each time. For example, when building a K-Means model using the Scikit-learn library in Python, the random seed can be set using the `random_state` parameter during model initialization, preferably 42; Train the model: Input the standardized feature matrix prepared in step one into the K-Means model for training. The algorithm automatically assigns all data records to the optimal number of clusters; In-depth analysis of the original data of samples within each cluster verifies the accuracy of the labels, obtaining the model with the highest accuracy as the K-Means risk clustering model, forming a specific profile of each risk group. The core advantage of the model lies in elevating the judgment result for a single record to a risk classification of the entire consumer group; avoiding subjective risk threshold rules. The model clusters data based entirely on the distribution patterns of the data itself. By analyzing the population profile of each cluster, it is possible to clearly identify which types of food, which consumption habits, and under what circumstances the risk is highest. This provides a direct basis for developing precise food safety intervention measures (such as targeted public education for specific groups and enhanced testing of specific foods). Risk assessment groups were formed based on the results of food surface contamination characteristics assessment and food contamination risk assessment. In this embodiment, the risk assessment grouping includes the following specific contents: The system acquires real-time information on people's eating habits for the corresponding food, assesses the characteristics of food surface contamination, and imports the food contamination risk sequence into the K-Means risk clustering model. The output is the judgment result of whether the infection rate of the corresponding purchaser exceeds the safety threshold. Risk warnings will be issued based on the risk assessment grouping results. In this embodiment, the risk warning is disseminated, including the following specific details: If the determination of whether the infection rate of the corresponding purchaser exceeds the safety threshold is yes, a transmission risk warning needs to be issued and the corresponding food should be removed from the shelves. If the determination is no, no transmission risk warning is issued and sales can continue. The determination result is sent to the client via wired or wireless means.

[0018] The benefits of this embodiment are as follows: This application performs multi-dimensional and hierarchical quantitative assessment and intelligent grouping of complex food safety risks; firstly, through risk data collection and assessment, it comprehensively calculates bacterial adhesion ability, environmental inhibition ability, and chemical protection ability from two levels: the physical, chemical, and biological characteristics of the food itself and its environment, forming an assessment of food surface contamination characteristics; simultaneously, by analyzing the risk of cross-contamination between background colonies and fresh products, it generates a food contamination risk sequence; subsequently, using the K-Means risk clustering model, combined with historical data and eating habits, it automatically discovers and defines characteristic groups with different risk levels, and can quickly determine their risk category through risk assessment grouping, and execute precise intervention, thereby significantly improving the accuracy, foresight, and response efficiency of risk identification.

[0019] Please see Figure 4 , Figure 4 This is a schematic diagram of the structure of a foodborne bacterial strain transmission risk early warning system based on cluster analysis provided in this application embodiment, including: The system comprises a risk data acquisition module, a data evaluation module, a clustering risk grouping module, a risk assessment module, and a risk early warning module. The risk data acquisition module acquires the inherent characteristics of the food surface and the characteristics of the environment in which the food is located. The data evaluation module assesses the surface contamination characteristics of the food based on its inherent characteristics and assesses the risk of food contamination based on the environmental characteristics of the food's location. The clustering risk grouping module performs risk clustering based on historical data and historical consumption habits. The risk assessment module performs risk assessment grouping based on the results of the surface contamination characteristic assessment and the risk assessment. The risk early warning module provides early warning of the risk of transmission based on the risk assessment grouping results. The connection structure of the corresponding system modules is as follows: Figure 4 As shown.

[0020] The parameters and steps for implementing the corresponding functions of each unit module in the foodborne strain transmission risk early warning system based on cluster analysis of this application can be referred to the parameters and steps in the embodiments of the foodborne strain transmission risk early warning method based on cluster analysis, and will not be repeated here.

[0021] Embodiments of this application also provide an electronic conduit, including a memory, a processor, and a communication bus; the memory and the processor are connected via the communication bus. The memory stores a foodborne strain transmission risk warning method based on cluster analysis, which can be loaded and executed by the processor as provided in the above embodiments.

[0022] The memory can be used to store instructions, programs, code, code sets, or instruction sets. The memory may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for at least one function, and instructions for implementing the cluster analysis-based foodborne strain transmission risk warning method provided in the above embodiments, etc. The data storage area may store data involved in the cluster analysis-based foodborne strain transmission risk warning method provided in the above embodiments, etc.

[0023] A processor may include one or more processing cores. The processor executes instructions, programs, code sets, or instruction sets stored in memory, and calls data stored in memory to perform various functions and process data as described in this application. The processor may be at least one of a specific application-specific integrated circuit, a digital signal processor, a digital signal processing device, a programmable logic device, a field-programmable gate array, a central processing unit, a controller, a microcontroller, and a microprocessor. It is understood that, for different pipelines, the electronic devices used to implement the above-described processor functions may also be other types, and the embodiments of this application do not specifically limit them.

[0024] A communication bus may include a pathway for transmitting information between the aforementioned components. The communication bus can be a PCI bus or an EISA bus, etc. Communication buses can be categorized into address buses, data buses, control buses, etc.

[0025] This application provides a computer-readable storage medium storing a computer program that can be loaded by a processor and executed as described in the above embodiments for a method for early warning of the risk of transmission of foodborne strains based on cluster analysis.

[0026] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the foregoing application concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions claimed in this application.

Claims

1. A foodborne bacterial strain transmission risk early warning system based on cluster analysis, characterized in that, The system includes the following modules: a risk data acquisition module, a data evaluation module, a clustering risk grouping module, a risk assessment module, and a risk warning module. The risk data acquisition module is used to acquire the inherent characteristics of the food surface and the characteristics of the environment in which the food is located. The data evaluation module is used to assess the surface contamination characteristics of the food based on its inherent characteristics, and simultaneously assess the risk of food contamination based on the environmental characteristics of the food's location. The clustering risk grouping module performs risk clustering based on historical data and historical consumption habits. The risk assessment module performs risk assessment grouping based on the results of the food surface contamination characteristic assessment and the food contamination risk assessment. The risk warning module provides a risk warning for the spread of the food based on the risk assessment grouping results.

2. The foodborne bacterial strain transmission risk early warning system based on cluster analysis according to claim 1, characterized in that, The inherent characteristics of the food surface specifically include: physical characteristics such as surface roughness, porosity, and surface area / volume ratio; chemical characteristics such as pH value, water activity, and inherent nutrient composition; and biological characteristics such as the content of antibacterial substances. The environmental characteristics of the food's location include: physical environment such as average ambient temperature, temperature fluctuation range, and relative humidity; biological environment such as the known total bacterial count or background concentration of specific pathogens; and cross-contamination environment such as physical distance from or frequency of contact with fresh products.

3. The foodborne bacterial strain transmission risk early warning system based on cluster analysis according to claim 1, characterized in that, The evaluation of food surface contamination characteristics includes the following specific aspects: Step 1: Obtain the surface roughness, porosity, and surface area / volume ratio of the food surface. Based on the standardized results of surface roughness, porosity, and surface area / volume ratio, perform a weighted summation to obtain the bacterial adhesion anomaly. The standardization process involves dividing the corresponding obtained parameter by the corresponding safe value. Step 2: Obtain the pH value, water activity, inherent nutrient composition, average ambient temperature, temperature fluctuation range, and relative humidity of the food. At the same time, obtain the safe range of the suitable environment for bacterial growth. Compare the obtained pH value, water activity, inherent nutrient composition, average ambient temperature, temperature fluctuation range, and relative humidity of the food with the corresponding parameter ranges of the suitable environment for bacterial growth to obtain the bacterial growth inhibition results for the corresponding parameters. Sum the bacterial growth inhibition results of all corresponding parameters to obtain the environmental bacterial growth inhibition result. Step 3: Obtain the content of antimicrobial agent per unit mass of food surface. Divide the content of antimicrobial agent per unit mass of food surface by the safe content to obtain the safe value of antimicrobial agent. Obtain the results of abnormal bacterial attachment, inhibition of environmental bacterial growth, and the safe value of antimicrobial agent as an evaluation sequence for food surface contamination characteristics.

4. The foodborne bacterial strain transmission risk early warning system based on cluster analysis according to claim 1, characterized in that, The food contamination risk assessment specifically includes the following: Step 1: Obtain the known total number of background bacterial colonies and their physical distance from the fresh product. Also, obtain the shelf life and duration of the fresh product. The shelf life of the fresh product is obtained by averaging historical shelf life data. Step 2: Obtain the background colony hazard value by dividing the known total background colony count by the corresponding safe value of the total background colony count; Step 3: Analyze the contamination status of fresh products on food by considering the physical distance between fresh products and food at various times, as well as the weight, shelf life, and duration of the fresh products. Specifically, the steps are as follows: Divide the duration of fresh products at the corresponding time by the shelf life to obtain the fresh product presence anomaly at that time; divide the safe distance by the physical distance between the fresh product and food at the corresponding time to obtain the fresh product distance anomaly at that time; perform a weighted sum of the fresh product presence anomaly and the fresh product distance anomaly at the corresponding time to obtain the fresh product contamination anomaly; multiply the fresh product contamination anomaly by the standardized weight of the fresh product at the corresponding time to obtain the fresh product anomaly at that time; integrate the fresh product anomaly over the time length and divide by the standard time to obtain the fresh product contamination anomaly on food; and use the background bacterial colony hazard value and the fresh product contamination anomaly on food as a food contamination risk sequence.

5. The foodborne bacterial strain transmission risk early warning system based on cluster analysis according to claim 1, characterized in that, The risk clustering grouping includes the following specific contents: This study obtains historical data on people's eating habits, historical food surface contamination characteristic assessment sequences, and historical food contamination risk sequences. The eating habits data includes the proportion and frequency of various ways of consuming corresponding foods in the relevant region, including food cooking time and temperature, obtained through historical custom statistics. Simultaneously, it obtains the judgment results regarding whether the bacterial infection rate of the corresponding purchaser exceeds the safety threshold. Based on the historical data on people's eating habits, historical food surface contamination characteristic assessment sequences, historical food contamination risk sequences, and the judgment results, a K-Means risk clustering model is constructed, taking the people's eating habits, food surface contamination characteristic assessment sequences, and food contamination risk sequences as inputs and outputting the judgment results regarding whether the bacterial infection rate of the corresponding purchaser exceeds the safety threshold.

6. The foodborne bacterial strain transmission risk early warning system based on cluster analysis according to claim 1, characterized in that, The risk assessment grouping includes the following specific contents: The system acquires real-time data on people's eating habits for the corresponding food, assesses the surface contamination characteristics of the food, and imports the food contamination risk sequence into the K-Means risk clustering model. The output is a judgment result indicating whether the infection rate of the corresponding purchaser exceeds the safety threshold.

7. The foodborne bacterial strain transmission risk early warning system based on cluster analysis according to claim 1, characterized in that, The aforementioned risk warning for transmission includes the following specific contents: If the assessment result of whether the infection rate of the corresponding purchaser exceeds the safety threshold is yes, then a transmission risk warning needs to be issued and the corresponding food should be removed from the shelves. If the assessment result is no, then no transmission risk warning needs to be issued and sales can continue.

8. A method for early warning of foodborne bacterial strain transmission risk based on cluster analysis, implemented based on the foodborne bacterial strain transmission risk early warning system based on cluster analysis according to any one of claims 1-7, characterized in that, Specifically, it includes: To obtain the inherent surface characteristics of food and the characteristics of the environment in which the food is located; The surface contamination characteristics of food are assessed based on the inherent characteristics of the food surface, and the risk of food contamination is assessed based on the environmental characteristics of the location of the food. Risk clustering was performed based on historical data and historical consumption habits; Risk assessment groups were formed based on the results of food surface contamination characteristics assessment and food contamination risk assessment. Risk warnings will be issued based on the risk assessment grouping results.

9. An electronic conduit, comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; characterized in that the processor executes the foodborne strain transmission risk warning method based on cluster analysis as described in claim 8 by calling the computer program stored in the memory.

Images