A food quality supervision method, platform and device

Abstract

The present invention provides a food quality supervision method, platform, and device, relating to the technical field of food quality supervision, including: collecting food processing data based on a target food processing chain; determining a first critical control point and a first food quality supervision framework based on industry quality standards; determining a second critical control point and a second food quality supervision framework based on internal enterprise quality standards; determining a first safety assessment level and a first set of potential risk points; determining a second safety assessment level and a second set of potential risk points; and establishing a food quality management strategy to synchronously monitor and manage the quality of the target food processing chain. The present invention addresses the technical problem that existing technologies lack accurate and systematic risk assessment tools, resulting in potential risks being overlooked or the severity of risks being insufficiently assessed, leading to insufficient efficiency and accuracy in food safety supervision.

Description

Technical Field

[0001] The present invention relates to the technical field of food quality supervision, and in particular to a food quality supervision method, platform and device. Background Art

[0002] With the globalization and complexity of the food supply chain, ensuring the safety and quality of food throughout the entire production, processing, and distribution process has become particularly important. However, traditional methods often rely on limited data points and subjective judgment when assessing risks, and lack accurate and systematic risk assessment tools. This leads to some potential risks being overlooked or the severity of risks being insufficiently assessed, resulting in insufficient efficiency and accuracy in food safety supervision. In addition, existing quality control measures often intervene only after problems have occurred and lack preventive measures. This delayed response pattern increases the risk of food safety accidents and may also lead to large-scale product recalls and loss of corporate reputation. Summary of the Invention

[0003] This application provides a food quality supervision method, platform and device to solve the technical problem that the existing technology lacks accurate and systematic risk assessment tools, resulting in potential risks being ignored or insufficient assessment of the severity of risks, leading to insufficient efficiency and accuracy of food safety supervision.

[0004] The first aspect disclosed in the present application provides a food quality supervision method, which includes: collecting food processing data based on a target food processing chain, wherein the food processing data is associated with multiple food processing links; determining a first critical control point and a first food quality supervision framework based on the food processing link through industry quality standards; determining a second critical control point and a second food quality supervision framework based on the food processing link through the enterprise's internal quality standards; determining a first safety assessment level and a first potential risk point set based on the food processing data through the first critical control point and the first food quality supervision framework; determining a second safety assessment level and a second potential risk point set based on the food processing data through the second critical control point and the second food quality supervision framework; setting a food quality management strategy through the first safety assessment level and the first potential risk point set, the second safety assessment level and the second potential risk point set, in combination with the first food quality supervision framework and the second food quality supervision framework, and synchronously performing quality monitoring and management on the target food processing chain.

[0005] The second aspect disclosed in the present application provides a food quality supervision platform, which is used for the above-mentioned food quality supervision method, and the platform includes: a processing data collection module, which is used to collect food processing data based on the target food processing chain, and the food processing data is associated with multiple food processing links; a first supervision framework determination module, which is used to determine the first critical control point and the first food quality supervision framework according to the food processing link through the industry quality standard; a second supervision framework determination module, which is used to determine the second critical control point and the second food quality supervision framework according to the food processing link through the enterprise internal quality standard; a first evaluation level determination module, which is used to determine the first critical control point and the second food quality supervision framework according to the food processing link through the enterprise internal quality standard; The assessment level determination module is used to determine the first safety assessment level and the first potential risk point set based on the food processing data through the first critical control points and the first food quality supervision framework; the second assessment level determination module is used to determine the second safety assessment level and the second potential risk point set based on the food processing data through the second critical control points and the second food quality supervision framework; the quality monitoring management module is used to set the food quality management strategy through the first safety assessment level and the first potential risk point set, the second safety assessment level and the second potential risk point set, in combination with the first food quality supervision framework and the second food quality supervision framework, and synchronously perform quality monitoring and management on the target food processing chain.

[0006] The third aspect disclosed in the present application provides an electronic device, including a memory and a processor, wherein the memory stores executable instructions, and when the processor executes the executable instructions stored in the memory, any step of the first aspect disclosed in the present application is implemented.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] By collecting data across the entire targeted food processing chain, including but not limited to temperature, humidity, hygiene data, and operational records, complete monitoring and recording of every link in the food processing process is ensured. Based on the food processing link, the first critical control point and the first food quality regulatory framework are determined using industry quality standards, and the second critical control point and the second food quality regulatory framework are determined using internal enterprise quality standards. By integrating industry and internal enterprise standards, not only is compliance with regulatory requirements ensured for food processing activities, but also internal enterprise standards for food safety and quality control are enhanced, enabling the implementation of strict control measures for the targeted food processing chain. By analyzing the collected data and conducting safety assessments at both the industry and internal enterprise standards levels, the food processing process can be monitored in real time, effectively improving the overall quality and safety of products. Furthermore, current risks can be identified as well as potential risks predicted, allowing enterprises to intervene in advance to mitigate or eliminate them. Based on the actual situation and historical data of food processing, combined with the first and second food quality regulatory frameworks, targeted management strategies are formulated and implemented, making quality control both forward-looking and adaptive. By implementing this comprehensive food quality regulatory approach, enterprises can ensure food safety while improving production efficiency and product quality, and reducing costs caused by quality issues.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A flowchart of a food quality supervision method provided in an embodiment of the present application.

[0011] Figure 2 A schematic diagram of the structure of a food quality supervision platform provided in an embodiment of the present application.

[0012] Figure 3 This is a diagram of the internal structure of the electronic device provided in an embodiment of the present application.

[0013] Explanation of the accompanying drawings: processing data collection module 10, first regulatory framework determination module 20, second regulatory framework determination module 30, first evaluation level determination module 40, second evaluation level determination module 50, quality monitoring management module 60, bus 300, receiver 301 processor 302, transmitter 303, memory 304, bus interface 305. DETAILED DESCRIPTION

[0014] The embodiments of the present application provide a food quality supervision method to solve the technical problem that the existing technology lacks accurate and systematic risk assessment tools, resulting in potential risks being ignored or insufficient assessment of the severity of risks, leading to insufficient efficiency and accuracy of food safety supervision.

[0015] After introducing the basic principles of this application, various non-limiting embodiments of this application will be specifically described below in conjunction with the accompanying drawings. It should be understood that the specific embodiments described here are only used to explain this application and are not used to limit this application.

[0016] Example 1, as Figure 1 As shown, the embodiment of the present application provides a food quality supervision method, the method comprising:

[0017] Based on a target food processing chain, food processing data is collected, where the food processing data is associated with a plurality of food processing links.

[0018] First, it is necessary to clearly define the specific food processing chain to be monitored. It can be the processing process of any type of food such as meat, dairy products, fruits and vegetables. The processing chain usually includes all links from raw material procurement to raw material inspection, processing, cooking, cooling, packaging, storage and final distribution. Identify the key links in the target food processing chain and obtain multiple food processing links, each of which may have an impact on food quality.

[0019] Food processing data is collected for multiple food processing links. The types of data collected include: physical and chemical data, including temperature, humidity, pH value, additive content, microbial activity, etc.; operation records, including operating conditions of each link, such as cooking temperature and time, cooling speed, etc.; hygiene control data, including the cleanliness of facilities, staff hygiene habits, disinfection frequency, etc.; supply chain information, including raw material sources, batch numbers, supplier information, etc.

[0020] By collecting food processing data, necessary information and data support are provided for subsequent risk assessment, quality control and risk management.

[0021] Based on the food processing links, the first critical control point and the first food quality supervision framework are determined through industry quality standards.

[0022] Authoritative industry quality standards are applied to each food processing link to ensure that every step in the food processing process meets regulatory requirements and safety production standards.

[0023] Based on industry quality standards, identify the links that may lead to food safety risks if they are out of control. These links are defined as the first critical control points. For example, in meat processing, the sterilization or cooking process can be a critical control point because improper handling can lead to the survival or proliferation of harmful bacteria.

[0024] Create the first food quality supervision framework around the identified first critical control point. This framework includes: monitoring procedures: establish monitoring procedures for the first critical control point to ensure that all operations meet the company's high standards; corrective and preventive measures, define corrective and preventive measures when monitoring indicators do not meet the standards, and adjust the process when necessary.

[0025] Through this step, we can ensure that risks in the food production process are effectively controlled, and also provide a systematic management and operation guide for food safety.

[0026] Based on the food processing links, the second critical control point and the second food quality supervision framework are determined through the company's internal quality standards.

[0027] For each food processing link, the company's internal quality standards should be clearly defined. These standards may be stricter than industry standards, or include additional quality goals, such as reducing nutritional loss during processing, maintaining the freshness and taste of food, etc. The setting of internal quality standards of the company usually takes into account the brand image, market positioning and customer expectations.

[0028] Similar to industry standards, second critical control points are identified based on the company's internal quality standards. However, the analysis here focuses on meeting the company's specific quality control needs. For example, if the company prioritizes product appearance, the packaging process could be a second critical control point. A second food quality regulatory framework is created around the identified second critical control points, which also includes monitoring procedures and corrective and preventive measures.

[0029] Through this approach, companies can not only meet industry standards, but also produce high-quality food according to their own standards. This dual regulatory framework ensures food safety and quality while meeting internal company requirements.

[0030] Based on the food processing data, a first safety assessment level and a first set of potential risk points are determined through the first critical control points and the first food quality supervision framework.

[0031] Based on the first food quality regulatory framework, food processing data is analyzed, such as through trend analysis and anomaly detection, to identify any anomalies or trends in the data. These anomalies or trends indicate potential risk points in food processing. For example, if the temperature of a critical control point frequently exceeds the safe range, it is marked as a potential risk point. Based on the results of the data analysis, a safety assessment is conducted on each first critical control point, such as classifying the risk level as low, medium, or high. The assessment of each critical control point takes into account its impact on the safety of the final product and the probability of risk occurrence. All potential risk points are identified and combined into a first potential risk point set. These risk points are determined by evaluating the deviations, anomalies, and inconsistencies of the data from industry standards to determine their potential impact on food safety.

[0032] Based on the food processing data, a second safety assessment level and a second set of potential risk points are determined through the second critical control points and the second food quality supervision framework.

[0033] Similarly, based on internal enterprise standards and applying the Second Food Quality Regulatory Framework, food processing data is analyzed, such as through trend analysis and anomaly detection, to identify any possible quality issues or deviations. Based on the data analysis results, a safety and quality assessment is conducted for each Second Critical Control Point (CCP), such as by classifying the risk level and analyzing the impact of each point on the final product quality. All potential risk points are identified from the analysis of the Second Critical Control Points, resulting in a Second Potential Risk Point Set. These risk points are determined in accordance with the requirements of the Second Regulatory Framework and cover a wide range of issues, from microscopic quality deviations to those that may affect consumer satisfaction.

[0034] By using the first safety assessment level and the first set of potential risk points, the second safety assessment level and the second set of potential risk points, combined with the first food quality supervision framework and the second food quality supervision framework, a food quality management strategy is set to synchronously monitor and manage the quality of the target food processing chain.

[0035] Merge and analyze the first safety assessment level with the first set of potential risk points and the second safety assessment level with the second set of potential risk points to identify all overlapping and unique risk points, so as to determine which risk points are the most urgent and important and require increased attention and immediate processing; combine the requirements of the first and second food quality regulatory frameworks to create a unified operating model to ensure that all control points and monitoring activities are effectively managed, including updating operating manuals, training plans and quality inspection processes.

[0036] Based on the combined risk assessment, a comprehensive food quality management strategy is developed, for example, priority setting to determine which risk points need to be addressed first to reduce their potential impact on food safety and quality; resource allocation to ensure that necessary resources are reasonably allocated to address key issues; and designing preventive measures and corrective actions for each potential risk point.

[0037] Based on the established food quality management strategy, information technology and automation tools are used to achieve synchronized quality monitoring and management across the entire food processing chain, including real-time data collection, analysis, and feedback systems to enable timely operational adjustments and address unexpected quality issues. Through this integrated approach, food manufacturers can ensure that their products maintain the highest safety and quality standards throughout the entire production and supply chain, while also being able to promptly respond to any potential risks and quality issues to protect consumer health.

[0038] Furthermore, the food processing data is associated with a plurality of food processing links, and the method includes:

[0039] Acquire food category indicators, which include meat, dairy products, and fruits and vegetables; add multiple specified feature sets under the food category indicators, and the multiple specified feature sets are mapped one-to-one with the food category indicators; based on the target food processing chain, collect the food processing data under the constraints of the food category indicators and the multiple specified feature sets.

[0040] Food is divided into basic categories such as meat, dairy products, fruits and vegetables. Each category has its own specific processing and quality control requirements. By classifying the different types of food involved in the food processing chain, targeted data collection and analysis can be achieved.

[0041] For each food category indicator, a specific set of designated features is defined. These feature sets encompass key attributes that impact food quality and safety. For example, for meat, the feature set includes protein content, moisture ratio, and pathogen detection; for dairy products, it includes fat content, total bacterial count, and shelf life; and for fruits and vegetables, it includes pesticide residue detection, maturity, and color. Determining the association mapping between each feature set and the corresponding food category facilitates systematic quality monitoring of specific categories.

[0042] Within the constraints of established food category indicators and a specified feature set, comprehensive food processing data is collected for detailed quality analysis. Specifically, key data collection points are identified based on the specific links in the food processing chain (such as procurement, processing, packaging, storage, etc.) and the specified feature set. Sensors and automatic recording devices are then used to collect data. For example, temperature sensors are used to monitor the storage temperature of meat, and laboratory tests are used to determine the fat content of dairy products. This collected data is then aggregated to form food processing data. By monitoring the specific characteristics of different food categories, comprehensive and accurate quality control is ensured throughout the food processing chain.

[0043] Furthermore, based on the target food processing chain, the food processing data is collected under the constraints of the food category index and a plurality of specified feature sets, and the method further includes:

[0044] Based on the target food processing chain, processing and storage conditions are obtained; based on the processing and storage conditions, processing operation records and hygiene control data are collected in each food processing link; and an anomaly perception network is fitted based on the processing operation records and hygiene control data corresponding to the multiple food processing links. The anomaly perception network is used to capture abnormal deviation parameters corresponding to the target food processing chain.

[0045] Determine the processing and storage conditions for each link in the target food processing chain. These conditions directly affect the quality and safety of the food. Specifically, based on the food type and safety standards, determine the processing and storage conditions that must be followed at each link, such as temperature, humidity, pH value, etc.; in the actual processing environment, check and record the existing processing and storage conditions, including equipment type, temperature control system, cleaning and maintenance procedures, etc.; install monitoring equipment such as temperature and humidity sensors to monitor and record key parameters in real time.

[0046] Under established processing and storage conditions, systematically collect processing operation records and hygiene control data for each link to monitor the compliance and hygiene safety of the processing process. Specifically, establish a detailed recording system to record key operation data at each food processing link, such as processing time, batches of raw materials used, operators, etc.; conduct regular and irregular hygiene inspections and record hygiene control data, including equipment cleaning, personal hygiene of staff, disinfection frequency, etc.

[0047] The anomaly perception network is used to automatically identify and respond to abnormal deviations that may occur in food processing, thereby ensuring the stability of the processing process and product quality. The specific fitting process is as follows: select a model suitable for processing time series data, such as a recurrent neural network, a long short-term memory network, etc., and design a network structure, including an input layer, a hidden layer, and an output layer. The input layer receives the processed feature data, and the output layer generates corresponding anomaly detection results. Key features, such as temperature fluctuations, abnormal processing time, and hygiene compliance deviations, are extracted from processing operation records and hygiene control data. Data is labeled based on key features to obtain a training data set. The model is trained using the labeled training data set, including known abnormal events and normal operation data, to help the model learn to distinguish between normal and abnormal situations. Finally, an anomaly perception network with an accuracy that meets the requirements is obtained. Processing operation records and hygiene control data can be input in real time to monitor possible anomalies.

[0048] Furthermore, based on the food processing data, determining a first safety assessment level and a first set of potential risk points through the first critical control points and the first food quality supervision framework, the method includes:

[0049] Based on the abnormality perception network, the first food quality supervision framework is connected and the first deviation set is marked; based on the food processing data, the safety status of the points corresponding to the first critical control point is evaluated through the first deviation set, and the first safety assessment level is determined; at the same time, the change trend corresponding to the first deviation set is analyzed, the potential risk factors are analyzed, and the first potential risk point set is obtained; the first safety assessment level is synchronously updated with the first potential risk point set.

[0050] The anomaly perception network is connected to the first food quality supervision framework to process real-time processing operation and hygiene control data, and output any identified deviations. These deviations are matched with the critical control points in the first food quality supervision framework, marking the specific deviation points that affect food safety or quality. The deviations of all critical control points are sorted out to form a first deviation set, which includes various deviations ranging from improper temperature control to failure to meet hygiene standards.

[0051] Analyze the actual or potential impact of each deviation point in the first deviation set, such as the severity of the impact on food safety, the frequency and duration of the deviation, etc. Set a safety assessment level for each critical control point based on the severity and scope of the deviation, such as low, medium, and high risk levels, and determine the first safety assessment level accordingly.

[0052] Analyze the data change trends in the first deviation set and identify potential risk factors. Specifically, use statistical and data analysis tools, such as time series analysis and regression analysis, to identify trends and patterns in deviation data to determine whether the deviation is an isolated event or a persistent trend. Based on the trend and frequency of the deviation, as well as related environmental and operating conditions, identify possible risk factors. For example, if the temperature recorded at a certain temperature control point is too high for several consecutive cycles, it may indicate equipment failure or improper operation. Integrate all identified potential risk factors to form the first potential risk point set. Each risk point records relevant data and background information in detail.

[0053] Establish a regular assessment mechanism to periodically review the first deviation set and the first potential risk point set to ensure their accuracy and timeliness. When new data analysis indicates the need to adjust the existing assessment level or risk point, update it immediately, including adjusting the operational strategy or preventive measures based on the new risk assessment. In this way, it can ensure that the entire food processing chain can flexibly and quickly adjust safety measures and operational strategies when facing potential risks and changes, prevent food safety incidents, and protect consumer health.

[0054] Furthermore, based on the anomaly perception network, connecting the first food quality supervision framework, and marking the first deviation set, the method includes:

[0055] Connect to a food quality and safety event database, in which multiple food quality and safety events are recorded; based on the food quality and safety event database, match the first safety assessment level and the first potential risk point set to find a cluster of similar safety events; set an abnormal deviation threshold through the cluster of similar safety events, and the abnormal deviation threshold is used to determine whether to trigger a synchronous update instruction corresponding to the first safety assessment level and the first potential risk point set.

[0056] Create a database to store detailed information about food safety incidents as a food quality and safety incident database, including incident type, time of occurrence, food categories involved, cause analysis, processing results, etc. New food quality and safety incidents are regularly recorded in the database, and historical event information in the database is updated to support real-time data analysis and decision-making.

[0057] Utilizing the established food quality and safety event database, similar safety issues that may occur are identified by matching historical events with the current first safety assessment level and the first potential risk point set. Specifically, a data matching algorithm is used to compare the current first safety assessment level and the first potential risk point set with the historical events recorded in the event database. Based on the matching results, a cluster of similar safety events whose similarity meets the preset requirements is obtained.

[0058] Analyze the identified clusters of similar safety incidents and the data deviation patterns in the incidents, such as the specific numerical range of temperature control failure and the frequency of non-compliance with hygiene standards, so as to determine the characteristics and common triggering factors of these incidents. Based on the analysis results, define abnormal deviation thresholds. These thresholds are set based on dangers or failure points in past incidents and are used to monitor whether there are similar risk factors in the current production process. Threshold setting needs to comprehensively consider the severity and possibility of risk, as well as the company's specific requirements for safety tolerance.

[0059] The abnormal deviation threshold is integrated into the existing food quality monitoring system. When the data of any critical control point is detected to exceed the threshold, the first safety assessment level and the first potential risk point set are automatically triggered to be updated synchronously. This process ensures that food production companies can quickly identify and respond to potential food safety issues based on real-time data and historical event experience, greatly reducing the possibility of risks and improving the automation and intelligence level of food safety and quality management.

[0060] Furthermore, the abnormal deviation threshold is used to determine whether to trigger a synchronization update instruction corresponding to the first security assessment level and the first potential risk point set. The method includes:

[0061] When the abnormal deviation parameter corresponding to the target food processing chain captured by the abnormality perception network exceeds the abnormal deviation threshold, the local disturbance mechanism is activated; based on the local disturbance mechanism, the local disturbance impact factor is quantified:

[0062] ;

[0063] in, is the local disturbance influence factor, is the attenuation coefficient, is the abnormal deviation threshold, , The abnormal deviation threshold used to characterize the last synchronization update, The abnormal deviation parameters corresponding to the target food processing chain captured, It is used to characterize the basic abnormal deviation parameters corresponding to the cluster of similar security events. is the adjustment factor.

[0064] Specifically, when the abnormal deviation parameters captured by the abnormal perception network exceed the abnormal deviation threshold, the local disturbance mechanism is activated. Local disturbance refers to abnormal deviations that occur during food processing, such as temperature, humidity, pressure and other control parameters that exceed the normal operating range. Based on the local disturbance mechanism, the local disturbance impact factor is quantified to assess the impact of abnormal deviations on the entire processing process. The quantified local disturbance impact factors are as follows:

[0065] ;

[0066] Among them, the local disturbance influence factor It indicates the degree of influence of the local disturbance caused by the current abnormal deviation. It is reflected by quantifying the size of the abnormal deviation. The larger the deviation, the higher the value of the disturbance impact factor, which means the more serious the impact on the production process. is the abnormal deviation threshold, which is based on the basic abnormal deviation threshold and adjustment factors To adjust to reflect different operating conditions or environmental changes at different time points, the formula combines the current deviation and basic deviation The relative changes between .

[0067] This formula provides a quantitative indicator to assess the severity of production disturbances at any given moment by comparing the difference between the current abnormal deviation and the dynamic threshold and combining it with historical deviation data. This quantitative method helps to monitor the food processing environment in real time, ensure the stability of the production process, and adjust production parameters in a timely manner to prevent potential quality problems or safety risks.

[0068] Furthermore, based on the food quality and safety event database, searching for similar safety event clusters by matching the first safety assessment level and the first potential risk point set, the method includes:

[0069] The formula for finding similar security event clusters is as follows:

[0070] ;

[0071] in, Characterize the search results, is the safety assessment level of the kth food quality safety incident, is the security assessment level of the k-th security event cluster, is the standard deviation of the kth safety event cluster, p is the total number of safety events in the food quality and safety event database, is the weight factor of the kth food quality and safety incident, reflecting the importance of different food quality and safety incidents. , is the food quality and safety risk impact coefficient, is the impact coefficient of food quality and safety incidents, is the risk assessment value of the jth potential risk point set, is the evaluation value of the kth food quality and safety event, and m is the total number of historical potential risk point sets in the food quality and safety event database.

[0072] Specifically, the formula for finding clusters of similar security events is as follows:

[0073] f( );

[0074] This formula is used to find event clusters similar to specific food safety events in the food quality and safety event database. The formula is designed to find the event cluster with the maximum matching degree by comparing the safety assessment levels of different events and adjusting the weight factor and correlation coefficient. , which means the purpose of the formula is to find the cluster that maximizes the value of the following expression ,In other words, it looks for the event cluster that best represents or matches the given data characteristics; , which calculates the sum of squares of weighted differences of all events, aiming to find the cluster with the smallest difference in evaluation level; f( ), this function combines the risk assessment value and the event assessment value, adjusts the similarity score of the event cluster, and and Adjust the impact of risks and events.

[0075] Overall, this formula uses quantitative analysis to find the event cluster that is closest to the given safety event in terms of assessment level. This not only helps to identify other events with similar risk characteristics to the current event, but also allows for more targeted measures to be taken against these clusters in future safety management and preventive measures. Through this method, the efficiency and accuracy of the response to food safety incidents can be improved, and the food safety management system can be further strengthened.

[0076] In summary, the food quality supervision method provided by the embodiments of the present application has the following technical effects:

[0077] By collecting data across the entire targeted food processing chain, including but not limited to temperature, humidity, hygiene data, and operational records, complete monitoring and recording of every link in the food processing process is ensured. Based on the food processing link, the first critical control point and the first food quality regulatory framework are determined using industry quality standards, and the second critical control point and the second food quality regulatory framework are determined using internal enterprise quality standards. By integrating industry and internal enterprise standards, not only is compliance with regulatory requirements ensured for food processing activities, but also internal enterprise standards for food safety and quality control are enhanced, enabling the implementation of strict control measures for the targeted food processing chain. By analyzing the collected data and conducting safety assessments at both the industry and internal enterprise standards levels, the food processing process can be monitored in real time, effectively improving the overall quality and safety of products. Furthermore, current risks can be identified as well as potential risks predicted, allowing enterprises to intervene in advance to mitigate or eliminate them. Based on the actual situation and historical data of food processing, combined with the first and second food quality regulatory frameworks, targeted management strategies are formulated and implemented, making quality control both forward-looking and adaptive. By implementing this comprehensive food quality regulatory approach, enterprises can ensure food safety while improving production efficiency and product quality, and reducing costs caused by quality issues.

[0078] Example 2, based on the same inventive concept as a food quality supervision method in the above embodiment, Figure 2 As shown, the embodiment of the present application provides a food quality supervision platform, which includes:

[0079] A processing data collection module 10 is used to collect food processing data based on a target food processing chain, and the food processing data is associated with multiple food processing links; a first regulatory framework determination module 20 is used to determine a first critical control point and a first food quality regulatory framework based on the food processing link through industry quality standards; a second regulatory framework determination module 30 is used to determine a second critical control point and a second food quality regulatory framework based on the food processing link through the enterprise's internal quality standards; a first assessment level determination module 40 is used to determine a first critical control point and a second food quality regulatory framework based on the food processing data through industry quality standards; The first critical control point and the first food quality supervision framework determine the first safety assessment level and the first potential risk point set; the second assessment level determination module 50, the second assessment level determination module 50 is used to determine the second safety assessment level and the second potential risk point set based on the food processing data through the second critical control point and the second food quality supervision framework; the quality monitoring management module 60, the quality monitoring management module 60 is used to set a food quality management strategy through the first safety assessment level and the first potential risk point set, the second safety assessment level and the second potential risk point set, combined with the first food quality supervision framework and the second food quality supervision framework, and synchronously perform quality monitoring and management on the target food processing chain.

[0080] Furthermore, the platform also includes a food processing data acquisition module to perform the following steps:

[0081] Acquire food category indicators, which include meat, dairy products, and fruits and vegetables; add multiple specified feature sets under the food category indicators, and the multiple specified feature sets are mapped one-to-one with the food category indicators; based on the target food processing chain, collect the food processing data under the constraints of the food category indicators and the multiple specified feature sets.

[0082] Furthermore, the platform also includes an anomaly perception network fitting module to perform the following steps:

[0083] Based on the target food processing chain, processing and storage conditions are obtained; based on the processing and storage conditions, processing operation records and hygiene control data are collected in each food processing link; and an anomaly perception network is fitted based on the processing operation records and hygiene control data corresponding to the multiple food processing links. The anomaly perception network is used to capture abnormal deviation parameters corresponding to the target food processing chain.

[0084] Furthermore, the platform further includes a first potential risk point set acquisition module to perform the following operation steps:

[0085] Based on the abnormality perception network, the first food quality supervision framework is connected and the first deviation set is marked; based on the food processing data, the safety status of the points corresponding to the first critical control point is evaluated through the first deviation set, and the first safety assessment level is determined; at the same time, the change trend corresponding to the first deviation set is analyzed, the potential risk factors are analyzed, and the first potential risk point set is obtained; the first safety assessment level is synchronously updated with the first potential risk point set.

[0086] Furthermore, the platform also includes an abnormal deviation threshold setting module to perform the following operation steps:

[0087] Connect to a food quality and safety event database, in which multiple food quality and safety events are recorded; based on the food quality and safety event database, match the first safety assessment level and the first potential risk point set to find a cluster of similar safety events; set an abnormal deviation threshold through the cluster of similar safety events, and the abnormal deviation threshold is used to determine whether to trigger a synchronous update instruction corresponding to the first safety assessment level and the first potential risk point set.

[0088] Furthermore, the abnormal deviation threshold setting module further includes the following operation steps:

[0089] When the abnormal deviation parameter corresponding to the target food processing chain captured by the abnormality perception network exceeds the abnormal deviation threshold, the local disturbance mechanism is activated; based on the local disturbance mechanism, the local disturbance impact factor is quantified:

[0090] ;

[0091] in, is the local disturbance influence factor, is the attenuation coefficient, is the abnormal deviation threshold, , The abnormal deviation threshold used to characterize the last synchronization update, The abnormal deviation parameters corresponding to the target food processing chain captured, It is used to characterize the basic abnormal deviation parameters corresponding to the cluster of similar security events. is the adjustment factor.

[0092] Furthermore, the abnormal deviation threshold setting module further includes:

[0093] The formula for finding similar security event clusters is as follows:

[0094] ;

[0095] in, Characterize the search results, is the safety assessment level of the kth food quality safety incident, is the security assessment level of the k-th security event cluster, is the standard deviation of the kth safety event cluster, p is the total number of safety events in the food quality and safety event database, is the weight factor of the kth food quality and safety incident, reflecting the importance of different food quality and safety incidents. , is the food quality and safety risk impact coefficient, is the impact coefficient of food quality and safety incidents, is the risk assessment value of the jth potential risk point set, is the evaluation value of the kth food quality and safety event, and m is the total number of historical potential risk point sets in the food quality and safety event database.

[0096] Through the detailed description of a food quality supervision method mentioned above in this specification, those skilled in the art can clearly understand a food quality supervision platform in this embodiment. Since it corresponds to the method disclosed in the embodiment, the description is relatively simple. For relevant matters, please refer to the method part.

[0097] Example 3, as Figure 3 As shown, it is a schematic diagram of the structure of an exemplary electronic device of the present application. Figure 3 In the figure, the bus architecture is represented by bus 300, which can include any number of interconnected buses and bridges. Bus 300 connects various circuits including one or more processors represented by processor 302 and memory represented by memory 304. Bus 300 can also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are all well known in the art and therefore will not be described further herein. Bus interface 305 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 can be the same component, namely a transceiver, which provides a unit for communicating with various other devices over a transmission medium. Processor 302 is responsible for managing bus 300 and general processing, while memory 304 can be used to store data used by processor 302 when performing operations.

[0098] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0099] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A food quality supervision method, characterized in that: The method comprises: Based on a target food processing chain, food processing data is collected, where the food processing data is associated with a plurality of food processing links; According to the food processing links, determine the first critical control point and the first food quality supervision framework through industry quality standards; Based on the food processing links, determine the second critical control point and the second food quality supervision framework through the company's internal quality standards; Based on the food processing data, determining a first safety assessment level and a first set of potential risk points through the first critical control points and the first food quality supervision framework; Based on the food processing data, determining a second safety assessment level and a second set of potential risk points through the second critical control points and the second food quality supervision framework; By combining the first safety assessment level and the first set of potential risk points, the second safety assessment level and the second set of potential risk points, and the first and second food quality regulatory frameworks, a food quality management strategy is set to synchronously monitor and manage the quality of the target food processing chain; Based on the food processing data, determining a first safety assessment level and a first set of potential risk points through the first critical control points and a first food quality regulatory framework, the method comprising: Based on the anomaly perception network, connecting to the first food quality supervision framework, marking a first deviation set; Based on the food processing data, evaluating the safety status of points corresponding to the first critical control point using the first deviation set, and determining a first safety assessment level; At the same time, analyzing the change trend corresponding to the first deviation set and analyzing the potential risk factors to obtain the first potential risk point set; The first safety assessment level is updated synchronously with the first set of potential risk points; Based on the anomaly perception network, connecting the first food quality supervision framework, and marking a first deviation set, the method includes: Connecting to a food quality and safety event database, wherein a plurality of food quality and safety events are recorded in the food quality and safety event database; Based on the food quality and safety event database, searching for clusters of similar safety events by matching the first safety assessment level and the first potential risk point set; Setting an abnormal deviation threshold based on the cluster of similar security events, wherein the abnormal deviation threshold is used to determine whether to trigger a synchronous update instruction corresponding to the first security assessment level and the first potential risk point set; Based on the food quality and safety event database, searching for similar safety event clusters by matching the first safety assessment level and the first potential risk point set, the method includes: The formula for finding similar security event clusters is as follows: f( )]； in, Characterize the search results, is the safety assessment level of the kth food quality safety incident, is the security assessment level of the k-th security event cluster, is the standard deviation of the kth safety event cluster, p is the total number of safety events in the food quality and safety event database, is the weight factor of the kth food quality and safety incident, reflecting the importance of different food quality and safety incidents. , is the food quality and safety risk impact coefficient, is the impact coefficient of food quality and safety incidents, is the risk assessment value of the jth potential risk point set, is the evaluation value of the kth food quality and safety event, and m is the total number of historical potential risk point sets in the food quality and safety event database.

2. A food quality supervision method according to claim 1, characterized in that: The food processing data is associated with a plurality of food processing links, and the method includes: Obtain food category indicators, including meat, dairy products, and fruits and vegetables; Adding multiple specified feature sets under the food category index, wherein the multiple specified feature sets are associated with the food category index in a one-to-one mapping manner; Based on a target food processing chain, the food processing data is collected under the constraints of the food category indicators and a plurality of specified feature sets.

3. A food quality supervision method according to claim 2, characterized in that: Based on the target food processing chain, the food processing data is collected under the constraints of the food category index and a plurality of specified feature sets, and the method further includes: Based on the target food processing chain, obtain processing and storage conditions; Through the processing and storage conditions, collect processing operation records and hygiene control data in each food processing link; An abnormality perception network is fitted through the processing operation records and hygiene control data corresponding to the multiple food processing links, and the abnormality perception network is used to capture abnormal deviation parameters corresponding to the target food processing chain.

4. A food quality supervision method according to claim 1, characterized in that: The abnormal deviation threshold is used to determine whether to trigger a synchronization update instruction corresponding to the first security assessment level and the first potential risk point set, and the method includes: When the abnormal deviation parameter corresponding to the target food processing chain captured by the abnormality perception network exceeds the abnormal deviation threshold, activating the local perturbation mechanism; Based on the local disturbance mechanism, the local disturbance impact factor is quantified: ; in, is the local disturbance influence factor, is the attenuation coefficient, is the abnormal deviation threshold, , The abnormal deviation threshold used to characterize the last synchronization update, The abnormal deviation parameters corresponding to the target food processing chain captured, It is used to characterize the basic abnormal deviation parameters corresponding to the cluster of similar security events. is the adjustment factor.

5. A food quality supervision platform, characterized in that: For implementing a food quality supervision method according to any one of claims 1 to 4, the platform comprises: a processing data collection module, the processing data collection module being used to collect food processing data based on a target food processing chain, the food processing data being associated with a plurality of food processing links; a first regulatory framework determination module, configured to determine a first critical control point and a first food quality regulatory framework based on the food processing link and industry quality standards; a second regulatory framework determination module, the second regulatory framework determination module being configured to determine a second critical control point and a second food quality regulatory framework based on the food processing link and the enterprise's internal quality standards; a first assessment level determination module, configured to determine a first safety assessment level and a first set of potential risk points based on the food processing data, through the first critical control points and a first food quality regulatory framework; a second assessment level determination module, configured to determine a second safety assessment level and a second set of potential risk points based on the food processing data, through the second critical control points and the second food quality supervision framework; A quality monitoring and management module is used to set a food quality management strategy through the first safety assessment level and the first potential risk point set, the second safety assessment level and the second potential risk point set, combined with the first food quality supervision framework and the second food quality supervision framework, to synchronously perform quality monitoring and management on the target food processing chain.

6. An electronic device, characterized in that: The electronic device comprises: a memory for storing executable instructions; The processor is configured to implement a food quality supervision method according to any one of claims 1 to 4 when executing executable instructions stored in the memory.

Images