Food quality safety tracking management system based on big data

Abstract

The invention discloses a food quality safety tracking management system based on big data, and relates to the technical field of food, and the system comprises the steps: collecting the label identification data and storage stacking parameters of to-be-tracked food; extracting a label risk coefficient between a label inconsistency degree and a quality compliance risk based on the historical supervision data, and processing the label risk coefficient and the label identification data to obtain a label risk value; according to the storage stacking parameters of the to-be-tracked food, the stacking abnormal degree value of the to-be-tracked food in the storage process is judged; processing the stacking abnormal degree value and the label identification data to obtain a storage standard interference value; according to the storage specification interference value, the storage specification interference degree of the to-be-tracked food is judged, and first-grade storage specification interference and second-grade storage specification interference are obtained; the method has the effect of improving the efficiency and effect of food quality safety management.

Description

Technical Field

[0001] This invention relates to the field of food technology, and more specifically, to a food quality and safety tracking and management system based on big data. Background Technology

[0002] As the food industry develops rapidly, food quality and safety issues have received increasing attention. Traditional food quality and safety tracking and management methods struggle to comprehensively assess the correlation between labeling discrepancies and quality compliance risks, and cannot promptly and accurately identify the potential impact of stacking issues on food quality. Furthermore, traditional methods lack effective utilization of big data, failing to extract valuable information from historical regulatory data to provide a basis for food quality and safety tracking. They also struggle to analyze actual food quality data based on different storage standards and interference levels to generate effective early warning and tracking results. This makes it difficult to guarantee the accuracy and timeliness of food quality and safety management, thus failing to meet the management needs of food quality and safety. Summary of the Invention

[0003] In view of the shortcomings of existing technologies, the purpose of this invention is to provide a food quality and safety tracking and management system based on big data.

[0004] To achieve the above objectives, the present invention provides the following technical solution: A food quality and safety tracking and management system based on big data includes: Data Acquisition Module: Collects label identification data and storage stacking parameters of the food products to be tracked; Processing module: Extracts the label risk coefficient between the degree of label non-compliance and quality compliance risk based on historical regulatory data, and processes the label risk coefficient and label identification data to obtain the label risk value; Judgment module: Determines the degree of stacking abnormality of the food to be tracked during the storage process based on the storage stacking parameters of the food to be tracked; Processing and Judgment Module: Processes the stacking anomaly level value and label identification data to obtain the storage specification interference value; judges the storage specification interference level of the food to be tracked based on the storage specification interference value to obtain the first level storage specification interference and the second level storage specification interference; First analysis module: If the interference is at the first level of warehousing specifications, the warehousing stacking parameters and label risk values ​​are processed and analyzed to obtain the first actual quality data; The second analysis module: If it is a second-level warehousing specification interference, the stacking deviation value and label interference degree corresponding to the abnormal warehousing specification interference are processed to obtain the additional risk value. The additional risk value, warehousing risk coefficient and label risk value are processed and analyzed to obtain the second actual quality data. Generation module: Generates food quality and safety early warning and tracking results based on the first or second actual quality data.

[0005] Preferably, the label risk coefficient between the degree of label non-compliance and quality compliance risk is extracted based on historical regulatory data, specifically including the following steps: Extract historical data with inconsistent labels from historical regulatory data; The label deviation magnitude is obtained by calculating the difference between historical label discrepancies and compliance standard data. Extract the label deviation amplitude from historical regulatory data to identify the historical compliance risk values ​​of the food products being tracked. The label risk coefficient is obtained by calculating the ratio between the historical compliance risk value and the label deviation amplitude.

[0006] Preferably, the label risk coefficient and label identification data are processed to obtain the label risk value, specifically including the following steps: The label deviation value is obtained by calculating the difference between the label identification data and the standard label identification value; The label risk value is obtained by multiplying the label risk coefficient by the label deviation value.

[0007] Preferably, determining the degree of stacking anomaly of the food to be tracked during storage based on its storage stacking parameters specifically includes the following steps: A stacking benchmark set is constructed based on warehouse stacking parameters and category characteristic parameters of the food to be tracked; wherein, the stacking benchmark set includes standard stacking pressure thresholds for different time periods, standard misalignment angle thresholds of adjacent food items to be tracked, and stacking stability attenuation coefficients; Collect the actual pressure value of the food to be tracked, the actual misalignment angle of adjacent food items, and the real-time tilt angle of the food items during the stacking process; The pressure deviation index is obtained by comparing the actual pressure value with the standard stacking pressure threshold for the corresponding time period; the angle deviation index is obtained by comparing the actual misalignment angle with the standard misalignment angle threshold; and the tilt deviation index is obtained by multiplying the difference between the real-time tilt angle and the initial stacking tilt angle by the stacking stability attenuation coefficient. The damage correlation coefficient is determined based on the correlation between historical packaging damage data of the food to be tracked and storage stacking parameters. The basic stability coefficient is obtained by detecting the flatness of the ground in the storage area. The stacking anomaly degree value is determined based on the pressure deviation index, angle deviation index, tilt deviation index, damage correlation coefficient, and foundation stability coefficient.

[0008] Preferably, the stacking anomaly level value and label identification data are processed to obtain the warehouse standard interference value, specifically including the following steps: The label identification data includes warehouse restriction markings and traceability association information; Extract deviation features between actual stacking and labeling requirements from warehouse restriction labels; extract warehouse area mismatch features caused by labeling errors from traceability and correlation information; The deviation feature and the warehouse area mismatch feature are combined to form an interference feature set; Based on the food category storage specifications, the influence weight of each feature in the interference feature set is determined, and the label specification misleading degree is obtained by weighting the interference feature set and the influence weight. The stacking anomaly level and label specification misleadingness are input into the synergistic effect model to obtain the warehouse specification interference value.

[0009] Preferably, the degree of storage specification interference of the food to be tracked is determined based on the storage specification interference value to obtain the first level storage specification interference and the second level storage specification interference, specifically including the following steps: Compare the warehouse standard interference value with the preset warehouse standard interference threshold; If the storage specification interference value is less than the preset storage specification interference threshold, the storage specification interference level of the food to be tracked is determined to be the first level of storage specification interference. If the storage specification interference value is greater than or equal to the preset storage specification interference threshold, the storage specification interference level of the food to be tracked is determined to be Level 2.

[0010] Preferably, if the interference is a first-level warehousing standard, the warehousing stacking parameters and label risk values ​​are processed and analyzed to obtain the first actual quality data, specifically including the following steps; Determine the impact of warehouse stacking parameters on the storage risk value of the food to be tracked; The first storage risk assessment value is obtained by judging the risk of the storage process affecting the quality of the food to be tracked based on the storage risk value and storage stacking parameters. The initial quality supervision data is corrected based on the label risk value and the first warehousing risk assessment value to obtain the first actual quality data.

[0011] Preferably, the method further includes the following steps: Detect the stacking deviation value corresponding to the warehouse stacking parameters; detect the degree of label interference corresponding to the label identification data; The associated compliance risk value is obtained by analyzing the degree of label interference and the associated compliance risk caused by warehouse stacking deviations. Based on the associated compliance risk value, the stacking deviation value is adapted to the deviation breakdown in the warehousing process to obtain the warehouse stacking deviation value to be tracked.

[0012] Preferably, the additional risk value is obtained by processing the stacking deviation value and label interference degree corresponding to the abnormal interference conditions of the warehousing specifications, specifically including the following steps: The additional risk value is obtained by extracting the additional risk caused by historical stacking deviations from historical regulatory data. The historical additional risk amplitude is obtained by calculating the difference between the historical additional risk value and the historical normal warehousing risk value. The additional risk factor is obtained by comparing the historical additional risk amplitude and the historical stacking deviation value. The additional risk value of the food to be tracked during the storage process is obtained based on the additional risk factors and the stacking deviation value of the food to be tracked.

[0013] The additional risk value, warehousing risk coefficient, and label risk value are processed and analyzed to obtain the second actual quality data, specifically including the following steps: The second warehousing risk assessment value is determined based on the additional risk value and the warehousing risk coefficient to determine the impact of the warehousing process on the traceable food. The initial quality supervision data is corrected based on the second warehousing risk assessment value and the label risk value to obtain the second actual quality data.

[0014] Compared with the prior art, the present invention has the following beneficial effects: This invention, by collecting label data and storage stacking parameters of the food to be tracked, can comprehensively and accurately obtain relevant food information, laying a data foundation for subsequent quality and safety tracking. The processing module extracts label risk coefficients from historical regulatory data to obtain label risk values, enabling early assessment and prediction of quality compliance risks related to food labels, facilitating proactive measures to avoid quality and safety hazards caused by labeling issues. In terms of storage process monitoring, the judgment module determines the degree of stacking anomalies based on storage stacking parameters, enabling timely detection of potential anomalies in the storage stacking process, ensuring the safety of food storage, and reducing adverse effects on food quality caused by improper stacking. The processing judgment module combines the stacking anomaly value and label data to obtain a storage compliance interference value, distinguishing different levels of storage compliance interference. This allows for a more detailed analysis of the impact of storage compliance on food quality, making quality and safety control in the storage process more targeted. For different levels of warehousing standard interference, the first and second analysis modules employ corresponding processing and analysis methods to obtain the first and second actual quality data, respectively. These modules can calculate the actual quality data of the food based on different interference scenarios, improving the accuracy of quality assessment. Finally, the generation module generates food quality and safety early warning and tracking results based on the actual quality data, facilitating rapid implementation of quality and safety assurance measures and effectively improving the efficiency and effectiveness of food quality and safety management. Attached Figure Description

[0015] Figure 1 This invention presents a schematic diagram of a food quality and safety tracking and management system based on big data. Figure 2 This invention presents a schematic diagram illustrating the steps involved in obtaining a stacking anomaly value in a big data-based food quality and safety tracking and management system. Detailed Implementation

[0016] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0017] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0018] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single embodiment or an embodiment selectively excluded from other embodiments.

[0019] Reference Figures 1-2 As shown.

[0020] The embodiments further illustrate the food quality and safety tracking and management system based on big data proposed in this invention.

[0021] A food quality and safety tracking and management system based on big data includes: The data acquisition module uses the SC-500 intelligent data acquisition terminal, which integrates multiple sensors and is deployed in the food storage area and label processing station; the processing module is the SRV-8000 data processing server; the judgment module is the JD-700 intelligent analysis workstation; the processing and judgment module is the DM-900 decision management server, which undertakes decision analysis tasks; the first analysis module and the second analysis module belong to the Ana-600 dual-path analysis server cluster, which run different analysis algorithms respectively; the generation module is the Gen-1000 early warning generation server, which is responsible for generating early warning results.

[0022] The acquisition module connects to the processing module via an industrial Ethernet network to transmit data in real time. The processing module sends data to the judgment module and the processing judgment module via a message queue and a wired network, respectively. The judgment module transmits data to the processing judgment module via a high-speed bus. The processing judgment module communicates with the first analysis module and the second analysis module using a RESTful API. The first analysis module and the second analysis module transmit data to the generation module via the UDP protocol. The generation module then pushes the early warning results and writes them to the traceability database via the HTTP protocol.

[0023] Data Acquisition Module: Collects label identification data and storage stacking parameters of the food products to be tracked; Processing module: Extracts the label risk coefficient between the degree of label non-compliance and quality compliance risk based on historical regulatory data, and processes the label risk coefficient and label identification data to obtain the label risk value; Judgment module: Determines the degree of stacking abnormality of the food to be tracked during the storage process based on the storage stacking parameters of the food to be tracked; Processing and Judgment Module: Processes the stacking anomaly level value and label identification data to obtain the storage specification interference value; judges the storage specification interference level of the food to be tracked based on the storage specification interference value to obtain the first level storage specification interference and the second level storage specification interference; The specific types of initial quality control data include physicochemical indicators, microbiological testing data, sensory quality data, and packaging integrity data. Physicochemical indicators include protein and fat content; microbiological testing data includes total bacterial count; and sensory quality data includes color and odor. These data are obtained in the laboratory using liquid chromatography and microbial culture equipment, or can be collected in real-time by online monitoring equipment on the production line. The correction coefficient in the correction formula is based on statistics from a large amount of historical quality data. A regression model is used to determine the coefficient values ​​under different interference factors, ensuring that the first and second actual quality data accurately reflect the true quality status of the food.

[0024] First analysis module: If the interference is at the first level of warehousing specifications, the warehousing stacking parameters and label risk values ​​are processed and analyzed to obtain the first actual quality data; The second analysis module: If it is a second-level warehousing specification interference, the stacking deviation value and label interference degree corresponding to the abnormal warehousing specification interference are processed to obtain the additional risk value. The additional risk value, warehousing risk coefficient and label risk value are processed and analyzed to obtain the second actual quality data. Generation module: Generates food quality and safety early warning and tracking results based on the first or second actual quality data.

[0025] If this is the first actual quality data, it indicates that there may be potential problems with the labeling or storage of this batch of food, and therefore it is necessary to trace its subsequent flow.

[0026] If the data is the second actual quality data, an early warning tracking result will be generated, which will include clarifying the risk level of the food and recommending an immediate comprehensive investigation. At the same time, a detailed tracking of the food from production to sales will be initiated to ensure that any quality and safety issues can be detected and addressed in a timely manner.

[0027] The label risk coefficient, which is derived from historical regulatory data, relates the degree of label non-compliance to quality compliance risk. This process includes the following steps: Extract historical data with inconsistent labels from historical regulatory data; The label deviation magnitude is obtained by calculating the difference between historical label discrepancies and compliance standard data. Extract the label deviation amplitude from historical regulatory data to identify the historical compliance risk values ​​of the food products being tracked. The label risk coefficient is obtained by calculating the ratio between the historical compliance risk value and the label deviation amplitude.

[0028] First, extract historical labeling discrepancies from historical regulatory data. Suppose there was a batch of food products whose labels indicated a shelf life of 12 months, while the compliance standard requires a shelf life of 10 months; this constitutes a labeling discrepancy. Calculate the difference between the historical labeling discrepancies and the compliance standard data to obtain the label deviation magnitude; for example, in this case, the label deviation magnitude is 2 months.

[0029] To extract the historical compliance risk value of historically tracked food products corresponding to the label deviation amplitude from historical regulatory data, the specific numerical value D of the label deviation amplitude needs to be specified. The specific numerical value D of the label deviation amplitude is used as a search criterion to perform a matching search in the historical regulatory database. The historical regulatory database stores information on each batch of food from production to distribution, including label data and compliance risk assessment results, according to the structure of unique food identifiers and full-process data. The search function filters out all historically tracked food records that satisfy the condition that the label deviation amplitude equals D. Assume that each historically tracked food record in the database contains a food batch number, label deviation amplitude, and historical compliance risk value R. After filtering out records with a label deviation amplitude of D, the corresponding historical compliance risk value R is extracted from these records. For example, if the calculated label deviation amplitude D for a batch of biscuits is 2 months, the database is searched for batch records with a label deviation amplitude D equal to 2. Assuming there is a food product with batch number B20230501, whose record indicates a historical compliance risk value R = 0.6, then batch number B20230501 is included in the result set, and its R = 0.6 is the historical compliance risk value to be extracted.

[0030] The label risk coefficient is obtained by calculating the ratio between the historical compliance risk value and the label deviation amplitude. The label risk coefficient = historical compliance risk value ÷ label deviation amplitude. Therefore, the label risk coefficient is 0.6 ÷ 2 = 0.3.

[0031] Historical compliance risk value is a quantitative result of quality compliance risk based on past label deviations. Label deviation amplitude is a quantitative value of the actual deviation of the label from the standard. The label risk coefficient obtained by dividing the two represents the degree of quality compliance risk corresponding to a unit of label deviation. It is a quantitative extraction of the relationship between risk and deviation in historical data.

[0032] The label risk value is obtained by processing the label risk coefficient and label identification data, specifically including the following steps: The label deviation value is obtained by calculating the difference between the label identification data and the standard label identification value; The label risk value is obtained by multiplying the label risk coefficient by the label deviation value.

[0033] For example, if a batch of food labels indicates a shelf life of 12 months, while the standard labeling value specifies a shelf life of 10 months for this type of food, then subtracting the standard labeling value from the label data yields a label deviation value of 2 months. Multiplying the label risk coefficient by this label deviation value gives the label risk value. Assuming the label risk coefficient is 0.6, the label risk value = label risk coefficient × label deviation value, then the label risk value for this batch of food is 1.2. This calculation quantifies the degree of risk arising from label non-compliance with standards.

[0034] The determination of the degree of stacking abnormality of the food to be tracked during storage is based on the storage stacking parameters, specifically including the following steps: A stacking benchmark set is constructed based on warehouse stacking parameters and category characteristic parameters of the food to be tracked; the stacking benchmark set includes standard stacking pressure thresholds for different time periods, standard misalignment angle thresholds of adjacent food items to be tracked, and stacking stability attenuation coefficients. Collect the actual pressure value of the food to be tracked, the actual misalignment angle of adjacent food items, and the real-time tilt angle of the food items during the stacking process; The pressure deviation index is obtained by comparing the actual pressure value with the standard stacking pressure threshold for the corresponding time period; the angle deviation index is obtained by comparing the actual misalignment angle with the standard misalignment angle threshold; and the tilt deviation index is obtained by multiplying the difference between the real-time tilt angle and the initial stacking tilt angle by the stacking stability attenuation coefficient. The damage correlation coefficient is determined based on the correlation between historical packaging damage data of the food to be tracked and storage stacking parameters. First, historical packaging damage data was stratified by damage severity into minor, moderate, and severe damage levels. Corresponding storage stacking parameters, such as stacking height, stacking pressure, and stacking stability, were extracted. Then, multiple linear regression analysis was performed on each layer to determine the influence weight of each stacking parameter under different damage levels, thus obtaining preliminary correlation coefficients. Next, association rule mining algorithms, such as the Apriori algorithm, were used to mine frequent itemsets between specific stacking parameter combinations and packaging damage from historical data. This further validated and refined the correlation coefficients obtained from the regression, ultimately determining a damage correlation coefficient that reflects the strength of the association between the two. This provides a quantitative basis for predicting packaging damage risk and optimizing storage stacking standards.

[0035] The basic stability coefficient is obtained by detecting the flatness of the warehouse area floor. A laser flatness detector is used to detect the flatness of the warehouse area floor. During operation, the detector is placed at the starting position of the warehouse area. After the device is turned on, it is slowly moved along the preset detection path. The detection path is a grid-like path that covers the entire warehouse area. The device scans the ground in real time using a laser sensor and records the height difference data between the ground and the standard plane, thereby calculating the flatness deviation value of the ground. Based on the comparison result of the deviation value with the preset flatness standard, the basic stability coefficient is determined. The preset flatness standard is the industry floor flatness specification. For example, when the flatness deviation value is ≤2mm, the basic stability coefficient is 1; when the deviation value is between 2-5mm, the coefficient is 0.8. This quantifies the impact of floor flatness on the stability of warehouse stacking. The stacking anomaly degree value is determined based on the pressure deviation index, angle deviation index, tilt deviation index, damage correlation coefficient, and foundation stability coefficient.

[0036] First, a stacking benchmark set is constructed based on storage stacking parameters and food category characteristic parameters. The standard stacking pressure threshold, the standard misalignment angle threshold between adjacent food items, and the stacking stability attenuation coefficient are determined according to the stacking requirements during food storage and the characteristics of the food category. Category characteristic parameters include the food's packaging material, shape, density, and pressure resistance. For example, the standard stacking pressure threshold for liquid foods is set to 500 Pa, the standard misalignment angle threshold between adjacent foods is 5°, and the stacking stability attenuation coefficient is 0.9; for solid, shelf-stable foods, the standard stacking pressure threshold can be set to 1500 Pa, the standard misalignment angle threshold between adjacent foods is 10°, and the stacking stability attenuation coefficient is 0.7. By clearly defining these characteristic parameters for different food categories, a basis for constructing the stacking benchmark set can be provided, ensuring that the subsequent setting of stacking parameters conforms to the actual characteristics of the food category.

[0037] To determine the standard stacking pressure threshold, firstly, stacking tolerance tests are conducted on the food category under different pressures. For example, multiple groups of the same food category are selected and subjected to different levels of pressure. The damage to the food under each pressure is observed, and the maximum pressure value that will not cause damage is recorded. Combined with historical data of this food category during actual warehousing, the pressure range within which the food can be stably stored without quality problems during a normal storage period is calculated. The upper limit of this pressure range is taken as the standard stacking pressure threshold. The formula is: Standard stacking pressure threshold = Maximum no-damage test pressure value × Historical stability coefficient. The maximum no-damage test pressure value is the maximum pressure value that will not cause damage to the food packaging or quality, obtained by conducting pressure resistance tests on the food packaging and itself under stacking conditions. It is a basic reference value based on experiments. The historical stability coefficient is a correction coefficient that combines historical data of food storage and stacking to determine the impact of stacking environment and food characteristics on stacking pressure tolerance. It is used to reflect the impact of differences between actual storage scenarios and experimental scenarios on the pressure threshold. Multiplying the two results in the standard stacking pressure threshold, which is intended to make the standard stacking pressure threshold more closely match the actual storage environment and provide a reasonable benchmark for subsequent judgment of the degree of stacking anomalies. The historical stability coefficient is derived from the correlation statistics between pressure and quality stability in the historical storage of this type of food, and the range of the historical stability coefficient is 0.8-0.95.

[0038] The standard misalignment angle threshold for adjacent food items was determined through experiments. Food items of the same category were stacked at different adjacent misalignment angles and a simulated storage environment was created. The stability of the food items at each misalignment angle was observed, such as whether they were easy to tip over and whether the packaging was easily damaged. The maximum misalignment angle that ensures the stability of the food stack was found. Then, referring to historical storage data on problems caused by improper adjacent misalignment angles for this category of food items, the angle obtained from the experiment was corrected to obtain the standard misalignment angle threshold. That is, the standard misalignment angle threshold = the maximum stable misalignment angle in the experiment × the historical correction coefficient. The historical correction coefficient is determined based on the relationship between misalignment angle and problem occurrence rate in historical data, and the historical correction coefficient is 0.9-1.

[0039] The stacking stability decay coefficient is related to time and storage environment factors. By long-term monitoring of the decay of stacking stability of the same type of food during storage due to time and environmental changes, a stacking stability model is established to reflect the changes in stacking stability over time and with the environment, from which the decay coefficient is extracted. For example, monitoring the change in food stacking stability over time in a storage environment; if the stability changes with time t according to an exponential decay law, then the stacking stability is considered stable. ,in, For initial stability, k is the attenuation coefficient. The stacking stability attenuation coefficient k is determined by fitting multiple sets of monitoring data. Then, k is adjusted in combination with the influence of different storage environments to obtain the stacking stability attenuation coefficient applicable to this type of food.

[0040] For example, the standard stacking pressure threshold for food during the morning period is 5 Newtons; the standard misalignment angle threshold between adjacent food items is 3 degrees; and the stacking stability attenuation coefficient is 0.8. Next, actual data on the food to be tracked during the storage process is collected, assuming the actual pressure value is 6 Newtons; the actual misalignment angle between adjacent food items is 5 degrees; and the initial stacking tilt angle of the food to be tracked during the stacking process is 1 degree, and the real-time tilt angle of the food to be tracked during the stacking process is 3 degrees.

[0041] The pressure deviation index is obtained by comparing the actual pressure value with the standard stacking pressure threshold for the corresponding time period. The pressure deviation index is calculated as: Pressure Deviation Index = Actual Pressure Value ÷ Standard Stacking Pressure Threshold for the Corresponding Time Period. Here, the pressure deviation index is 6 ÷ 5 = 1.2. The actual pressure value is the pressure data collected in real time by pressure sensors during the food's stacking process in the warehouse, directly reflecting the current stacking pressure status. The standard stacking pressure threshold for the corresponding time period is the upper limit standard value for food quality and safety determined by combining food characteristics and storage environment factors at different time periods. Dividing the actual pressure value by the standard stacking pressure threshold for the corresponding time period yields the pressure deviation index. If the pressure deviation index is greater than 1, it indicates that the actual pressure exceeds the standard requirements for the corresponding time period, posing a risk of abnormal stacking pressure. If the pressure deviation index is less than or equal to 1, it indicates that the actual pressure is within the standard allowable range. This calculation provides a direct and quantitative assessment of whether the stacking pressure meets the specifications, offering a key quantitative indicator for subsequent evaluation of the degree of abnormality in warehouse stacking. The angle deviation index is obtained by comparing the actual misalignment angle with the standard misalignment angle threshold. Here, the angle deviation index is 5 - 3 = 2 degrees. The tilt deviation index is obtained by multiplying the difference between the real-time tilt angle and the initial stacking tilt angle by the stacking stability decay coefficient. Here, the tilt deviation index is (3-1)×0.8=1.6.

[0042] First, a large amount of historical packaging damage data for the food products to be tracked, along with corresponding storage and stacking parameters such as stacking pressure, misalignment angle, and tilt angle, needs to be collected. Next, statistical analysis is performed on this data to identify the correlation patterns between historical packaging damage and storage and stacking parameters. For example, the probability of food packaging damage under different combinations of stacking pressure and misalignment angle parameters can be calculated. Then, a damage correlation model is constructed, using storage and stacking parameters as input and packaging damage as output. A linear regression method is used to build the model; assuming a logistic regression model is used, the formula is... Here, P is the probability of packaging damage, X is the combined value of storage and stacking parameters, and a and b are model coefficients determined by fitting historical data. The model calculates the predicted probability of food packaging damage under the current storage and stacking parameters, and then normalizes the predicted probability to obtain the damage correlation coefficient. For example, if the model calculates the probability of packaging damage to be 0.3 under a certain set of storage and stacking parameters, and the damage correlation coefficient is set to a range of 0 to 1, this probability value can be directly used as the damage correlation coefficient, ensuring that it accurately reflects the strong correlation between historical packaging damage data and storage and stacking parameters.

[0043] When inspecting the flatness of a warehouse area to obtain a basic stability coefficient, ground flatness testing equipment, such as a laser flatness meter, is typically used. During operation, the laser flatness meter is moved along a grid-like path within the warehouse area. The meter emits a laser beam to measure the height deviation of various points on the ground relative to a reference plane. The entire warehouse area is divided into multiple smaller zones, and ground height deviation data is collected for each zone. These height deviation data are then statistically calculated to determine an index reflecting ground flatness, such as the International Flatness Index. Assume the height deviation of various points on the ground within a small area is . , ,..., After obtaining the international flatness index of each small area, the international flatness index of all small areas within the entire storage area is used as the basis for calculation. A comprehensive assessment of the distribution is conducted. The smoother the ground, the higher the International Roughness Index. The smaller the value, the higher the basic stability coefficient. Establish a relationship between the basic stability coefficient and the international flatness index. The corresponding relationship, such as setting the basic stability coefficient. ,in It is the international flatness index when the ground is completely flat. The test results of ground flatness are converted into basic stability coefficients, thereby quantifying the impact of ground flatness on the stability of food storage stacking.

[0044] The degree of stacking anomaly is determined based on the pressure deviation index, angle deviation index, tilt deviation index, damage correlation coefficient, and basic stability coefficient. A weighted summation method is used to calculate the degree of stacking anomaly. Assuming the weights of each indicator are 0.3 for the pressure deviation index, 0.2 for the angle deviation index, 0.2 for the tilt deviation index, 0.15 for the damage correlation coefficient, and 0.15 for the basic stability coefficient, the degree of stacking anomaly is calculated as follows: 1.2 × 0.3 + 2 × 0.2 + 1.6 × 0.2 + 0.7 × 0.15 + 0.9 × 0.15 = 0.36 + 0.4 + 0.32 + 0.105 + 0.135 = 1.32. This calculation yields the degree of anomaly in the stacking of the food storage to be tracked, thus determining whether any abnormalities exist in the stacking.

[0045] The stacking anomaly level value and label identification data are processed to obtain the warehouse standard interference value, which specifically includes the following steps: Label identification data includes warehouse restriction markings and traceability information; Extract deviation features between actual stacking and labeling requirements from warehouse restriction labels; extract warehouse area mismatch features caused by labeling errors from traceability and correlation information; Among them, the combination of deviation features and warehouse area mismatch features constitutes the interference feature set; Based on the food category storage specifications, the influence weight of each feature in the interference feature set is determined, and the label specification misleading degree is obtained by weighting the interference feature set and the influence weight. The stacking anomaly level and label specification misleadingness are input into the synergistic effect model to obtain the warehouse specification interference value.

[0046] The synergistic effect model employs a deep neural network. Leveraging its multi-layered neuron structure, the deep neural network model can deeply explore the nonlinear synergistic relationship between stacking anomaly levels and label specification misleadingness, fitting the complex impact of both on storage specification interference values. The training data must cover at least 1000 historical samples, each containing stacking anomaly levels, label specification misleadingness, and corresponding storage specification interference values. The data must also cover different food categories and storage scenarios, such as ambient temperature storage and cold chain storage, to ensure the generalization ability of the deep neural network model. The core algorithm uses backpropagation, calculating the error between predicted and actual storage specification interference values ​​during training and propagating this error back from the output layer to the input layer, continuously adjusting the weights and biases of neurons in each layer. The deep neural network model parameters are set as follows: input layer with 2 neurons, 3 hidden layers with 16 neurons each, and output layer with 1 neuron; rectified linear units (RCUs) are used as the activation function to effectively alleviate the gradient vanishing problem; mean squared error is used as the loss function, ensuring the model can accurately output storage specification interference values ​​after training, providing reliable data support for subsequent interference level determination.

[0047] Labeling data includes storage restriction markings and traceability information. From the storage restriction markings, deviations between actual stacking and labeling requirements can be extracted. For example, if the label specifies no more than 5 layers per box, but the actual stacking is 8 layers, this is a deviation feature. From the traceability information, storage area mismatch features caused by labeling errors can be extracted. For example, food that should be stored in refrigerated area A might be stored in ambient temperature area B due to labeling errors; this is a storage area mismatch feature. Deviation features and storage area mismatch features together form the interference feature set.

[0048] To extract storage area mismatch features caused by identification errors from traceability information, it is first necessary to clarify the content of the traceability information, which typically records key information about the target storage area where food should be stored. The actual storage area of ​​the food is then compared with the target storage area in the traceability information. For example, if the traceability information specifies that a food should be stored in refrigerated area A, but it is actually stored in ambient temperature area B, a mismatch feature value can be calculated using the formula: Mismatch Feature Value = |Target Storage Area Code - Actual Storage Area Code| × Area Importance Coefficient. Here, the target storage area code and the actual storage area code represent different storage areas; for example, refrigerated area A is coded as 1, and ambient temperature area B is coded as 2. The area importance coefficient is determined based on the degree of influence of the storage area on food quality; for example, the importance coefficient for refrigerated food is 1.5, and for ambient temperature food it is 1. If the target storage area code is 1, the actual storage area code is 2, and the area importance coefficient is 1.5, then the mismatch characteristic value is |1-2|×1.5=1.5.

[0049] The influence weights of each feature in the interference feature set are determined based on the food category warehousing specifications. Assume the weight of the storage area mismatch feature is 0.6, and the weight of the deviation feature is 0.4. The label specification misleading degree is calculated by weighting the values ​​of each feature in the interference feature set (assuming the stacking deviation feature value is 3 and the storage area mismatch feature value is 4) with their corresponding influence weights. The formula is: Label Specification Misleading Degree = (Stacking Deviation Feature Value × Stacking Deviation Weight) + (Storage Area Mismatch Feature Value × Storage Area Mismatch Weight). Here, the label specification misleading degree is (3 × 0.4) + (4 × 0.6) = 1.2 + 2.4 = 3.6. The stacking deviation feature value refers to the quantified value of the deviation between the actual storage stacking situation and the stacking requirements stated on the label, such as the difference between the actual stacking height and the height stated on the label. The stacking deviation weight is a weight coefficient determined based on the degree of influence of this stacking deviation on the storage specifications; the greater the influence, the higher the weight. The warehouse area mismatch feature value is a quantified value of the degree to which the actual warehouse area does not match the warehouse area labeled on the label. For example, it quantifies the regional difference between actual storage in area A and label labeling in area B. The warehouse area mismatch weight is a weighting coefficient set according to the degree of influence of the mismatch on the warehouse specifications. The label specification misleading degree is obtained by multiplying the feature value by the corresponding weight and then adding them together. This can quantitatively reflect the degree to which the label labeling misleads the warehouse specifications in terms of stacking and warehouse area.

[0050] The synergistic effect model is trained using a large amount of historical data. By inputting the stacking anomaly degree value and the label specification misleading degree into the synergistic effect model, the storage specification interference value is obtained, thereby quantifying the degree of interference of storage specifications on food quality and safety.

[0051] The degree of storage specification interference of the food to be tracked is determined based on the storage specification interference value, resulting in first-level and second-level storage specification interference. The specific steps include: Compare the warehouse standard interference value with the preset warehouse standard interference threshold; If the storage specification interference value is less than the preset storage specification interference threshold, the storage specification interference level of the food to be tracked is determined to be the first level of storage specification interference. If the storage specification interference value is greater than or equal to the preset storage specification interference threshold, the storage specification interference level of the food to be tracked is determined to be Level 2.

[0052] For example, a preset storage specification interference threshold can be set to 0.6, a value obtained based on historical data statistics. When the storage specification interference value is less than 0.6, it is determined to be Level 1 storage specification interference; when the storage specification interference value is greater than or equal to 0.6, it is determined to be Level 2 storage specification interference. In actual operation, the storage specification interference level of the food to be tracked can be clearly determined, providing a clear basis for subsequent quality data analysis under different levels of interference.

[0053] Such numerical comparisons can quickly classify the degree of interference with storage standards for different foods, thus providing a basis for subsequent quality analysis and early warning measures for different levels of interference.

[0054] If the interference is due to the first-level warehousing standard, the warehousing stacking parameters and label risk values ​​are processed and analyzed to obtain the first actual quality data, which specifically includes the following steps; Determine the impact of warehouse stacking parameters on the storage risk value of the food to be tracked; The first storage risk assessment value is obtained by judging the risk of the storage process affecting the quality of the food to be tracked based on the storage risk value and storage stacking parameters. The initial quality supervision data is corrected based on the label risk value and the first warehousing risk assessment value to obtain the first actual quality data.

[0055] First, assess the impact of storage stacking parameters on the storage risk value of the tracked food. For example, for a batch of food requiring refrigeration, overly dense stacking can impede airflow, increasing the storage risk value. Based on the determined storage risk value and specific storage stacking parameters, assess the impact of the storage process on the quality risk of the meat product, thus obtaining the first storage risk assessment value.

[0056] First, it's necessary to clarify the specific content of the storage stacking parameters, such as stacking height, stacking density, and spacing between adjacent food items. Then, collect a large amount of historical data, covering the quality changes of food during storage and corresponding risk events under different storage stacking parameters. Analyze this historical data to establish a correlation model between storage stacking parameters and storage risk values. For example, a multiple linear regression model could be used, assuming the storage risk value is... Given a stacking height of h, a stacking density of d, and a spacing of s between adjacent food items, the construction formula is as follows: ,in , , The coefficients are obtained by fitting historical data, and 'e' is the error term. The corresponding storage risk value is calculated by substituting the storage stacking parameters of the food to be tracked into this formula. The model is then corrected by incorporating real-time monitored storage environment data to make the calculated storage risk value more accurate.

[0057] Initial quality control data is obtained after the food has undergone comprehensive testing by the quality control department or the company's own quality testing department before it enters the storage stage.

[0058] Assuming the warehouse risk value is used This indicates that if the risk coefficient related to the warehouse stacking parameters is k, then the first warehouse risk assessment value is... For example, warehouse risk value The risk assessment value for the first warehouse is 0.6, and the risk coefficient k is 1.2. It is 0.72. The initial quality supervision data is corrected by combining the label risk value to obtain the first actual quality data. For example, if the initial quality supervision data is 80, then the first actual quality data is... =80−(0.5+0.72)×10=80−12.2=67.8.

[0059] It also includes the following steps: Detect the stacking deviation value corresponding to the warehouse stacking parameters; detect the degree of label interference corresponding to the label identification data; The associated compliance risk value is obtained by analyzing the degree of label interference and the associated compliance risk caused by warehouse stacking deviations. A multiple linear regression model was used as the statistical model to calculate the joint compliance risk value formed by label interference and storage stacking deviation. First, label interference and storage stacking deviation were used as independent variables, and historical joint compliance risk values ​​were used as dependent variables. Weight coefficients for each variable were determined through training on a large amount of historical data. The current values ​​of label interference and storage stacking deviation were then substituted into the statistical model to obtain the associated compliance risk value. The calculation logic of the statistical model lies in quantifying the combined impact of label interference and storage stacking deviation on joint compliance risk. The weight coefficients reflect the proportion of different factors in the formation of joint risk, thus enabling the associated compliance risk value to accurately reflect the degree of food quality compliance risk under the combined effect of these two factors, providing data support for subsequent risk assessment and control.

[0060] Based on the associated compliance risk value, the stacking deviation value is adapted to the deviation breakdown in the warehousing process to obtain the warehouse stacking deviation value to be tracked.

[0061] First, the stacking deviation value corresponding to the storage stacking parameters is detected, and at the same time, the label interference level corresponding to the label identification data is detected. For example, for a batch of food to be tracked, the stacking situation during storage is detected, and it is found that the actual stacking height deviates from the standard stacking height, thus obtaining the stacking deviation value; the labels of the food to be tracked are detected, and if the storage conditions are incorrectly stated on the labels, the degree of label interference is determined.

[0062] The deviation between actual stacking and labeling requirements is extracted from warehouse storage specifications. Interference-related features, such as storage area mismatch caused by labeling errors, are extracted from traceability information. For example, if a food label specifies a maximum stacking of 5 layers, but 8 layers are actually stacked, this is a deviation feature. If traceability information shows the food should be stored in the refrigerated area but was stored in the ambient temperature area due to labeling errors, this is a storage area mismatch feature. Next, the influence weights of these interference features are determined according to food category storage specifications. Assuming the deviation feature weight is w1 and the mismatch feature weight is w2, and combining this with the specific numerical values ​​of each feature, such as the deviation degree value f1 and the mismatch degree value f2, the influence weights are determined using formulas. Calculate the degree of label interference By comprehensively considering the various interference features and their influence weights in the label identification data in this way, the degree of label interference can be obtained, thereby quantifying the interference of label identification on warehousing and other processes.

[0063] Next, the associated compliance risk status formed by the degree of label interference and warehouse stacking deviation is statistically analyzed to obtain the associated compliance risk value. Assume the stacking deviation value is... The degree of label interference is indicated by... It is stated that through the constructed related compliance risk model Calculate the associated compliance risk value ,in and The weighting coefficients are determined based on historical data, and the stacking deviation values ​​are adapted to the deviation breakdown in the warehousing process based on the associated compliance risk values ​​to obtain the warehousing stacking deviation values ​​to be tracked.

[0064] Original stacking deviation value The factors in the warehousing process are broken down according to their weights. For example, the weight of stacking height in the warehousing process is assumed to be... The spacing factor has a weight of 1. The weight of the load-bearing factor is ,and .

[0065] Through formula The calculated warehouse stacking deviation value is obtained. Where n is the number of factors affecting the warehousing process. It is the weight of the i-th factor. It is the i-th factor and the associated compliance risk value The correlation coefficient.

[0066] The criteria for determining normal warehousing are established by analyzing the associated compliance risk values ​​of a large number of historical normal warehousing samples to determine the threshold range. For example, an associated compliance risk value ≤ 0.4 is set as the criterion for normal warehousing. This value needs to be based on historical data statistics. If 95% of the associated compliance risk values ​​in normal warehousing scenarios fall within this range, the degree of label interference and storage stacking deviation data in historical normal warehousing scenarios are collected, and the corresponding associated compliance risk values ​​are obtained by substituting them into a statistical model. After statistical analysis of these values, their distribution range is determined, which serves as the basis for calculating the risk value of historical normal warehousing. This clarifies the criteria for determining normal warehousing and provides a clear reference for risk assessment in the warehousing process.

[0067] For example, if the associated compliance risk value is high, it indicates that the warehousing process is greatly affected by the combined effects of label interference and stacking deviation. When breaking it down, more emphasis will be placed on analyzing the specific composition of stacking deviation from a warehousing perspective, so as to obtain the warehousing stacking deviation value to be tracked, in order to more accurately assess the impact of the warehousing process on food quality and safety.

[0068] The additional risk value is obtained by processing the stacking deviation value and label interference degree corresponding to abnormal interference conditions in warehousing specifications. The specific steps include: The additional risk value is obtained by extracting the additional risk caused by historical stacking deviations from historical regulatory data. The historical additional risk amplitude is obtained by calculating the difference between the historical additional risk value and the historical normal warehousing risk value. The additional risk factor is obtained by comparing the historical additional risk amplitude and the historical stacking deviation value. The additional risk value of the food to be tracked during the storage process is obtained based on the additional risk factors and the stacking deviation value of the food to be tracked.

[0069] The historical additional risk value is obtained by extracting the additional risks arising from historical stacking deviations from historical regulatory data. For example, if some biscuits are damaged by pressure due to stacking deviations, the resulting additional quality risk is the historical additional risk value. The difference between the historical additional risk value and the historical normal storage risk value is used to obtain the historical additional risk amplitude. Assuming the historical normal storage risk value refers to the quality risk value of biscuits under standard stacking, and assuming the historical normal storage risk value is 0.3, while the historical additional risk value is 0.5, then the historical additional risk amplitude is 0.5 - 0.3 = 0.2. The ratio between the historical additional risk amplitude and the historical stacking deviation value is used to obtain the additional risk factor. If the historical stacking deviation value is 2, then the additional risk factor is 0.2 ÷ 2 = 0.1. Based on the additional risk factor and the stacking deviation value to be tracked, the additional risk value of the food to be tracked during the storage process is obtained. For example, if the stacking deviation value of the food to be tracked is 3, then the additional risk value is 0.1 × 3 = 0.3, which is used to assess the additional quality risk of this batch of biscuits caused by stacking deviations.

[0070] The additional risk value, warehousing risk coefficient, and label risk value are processed and analyzed to obtain the second actual quality data, specifically including the following steps: The second warehousing risk assessment value is determined based on the additional risk value and the warehousing risk coefficient to determine the impact of the warehousing process on the traceable food. The initial quality supervision data is corrected based on the second warehousing risk assessment value and the label risk value to obtain the second actual quality data.

[0071] First, the secondary storage risk assessment value for traceable food is determined based on the additional risk value and the storage risk coefficient. For example, if a batch of traceable food has an additional risk value of 0.4 and a storage risk coefficient of 1.2, the secondary storage risk assessment value is calculated using the formula: Secondary Storage Risk Assessment Value = Additional Risk Value × Storage Risk Coefficient. The additional risk value represents the quantified risk generated by the higher level of interference; the storage risk coefficient reflects the weight of the risk level of the storage process itself on the final risk. The secondary storage risk assessment value obtained by multiplying the two values ​​comprehensively reflects the degree of storage risk after the combined effect of the additional risk and the storage risk coefficient under the second level of interference. Therefore, the secondary storage risk assessment value is 0.4 × 1.2 = 0.48. This value is then used to correct the initial quality supervision data based on the label risk value to obtain the secondary actual quality data. Assuming the initial quality supervision data is 90, the formula for calculating the second actual quality data is: Second actual quality data = Initial quality supervision data - (Second warehousing risk judgment value + Label risk value) × Correction coefficient. Here, the correction coefficient is set to 10, that is, 90 - (0.48 + 0.3) × 10 = 90 - 7.8 = 82.2.

[0072] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0073] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0074] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A big data-based food quality and safety traceability management system, characterized by, Comprise: The acquisition module: collect the label identification data and warehouse stacking parameters of the food to be tracked; The processing module: based on the historical supervision data, the label risk coefficient between the label inconsistency degree and the quality compliance risk is extracted, and the label risk value is obtained by processing the label risk coefficient and the label identification data; The judgment module: according to the warehouse stacking parameters of the food to be tracked, the stacking abnormality degree value of the food to be tracked in the warehouse process is judged; The processing judgment module: the stacking abnormality degree value and the label identification data are processed to obtain the warehouse specification interference value; according to the warehouse specification interference value, the warehouse specification interference degree of the food to be tracked is obtained to obtain the first grade warehouse specification interference and the second grade warehouse specification interference; The first analysis module: if it is the first grade warehouse specification interference, the warehouse stacking parameters and the label risk value are processed and analyzed to obtain the first actual quality data; The second analysis module: if it is the second grade warehouse specification interference, the stacking deviation value corresponding to the warehouse specification abnormal interference condition and the label interference degree are processed to obtain the additional risk value, and the additional risk value, the warehouse risk coefficient and the label risk value are processed and analyzed to obtain the second actual quality data; The generation module: according to the first actual quality data or the second actual quality data, the food quality safety early warning tracking result is generated. 2.The big data-based food quality and safety tracking management system according to claim 1, characterized in that, Based on the historical supervision data, the label risk coefficient between the label inconsistency degree and the quality compliance risk is extracted, which comprises the following steps: The historical label inconsistency data is extracted from the historical supervision data; The difference between the historical label inconsistency data and the compliance standard data is calculated to obtain the label deviation amplitude; The historical compliance risk value of the historical tracking food corresponding to the label deviation amplitude is extracted from the historical supervision data; The ratio between the historical compliance risk value and the label deviation amplitude is calculated to obtain the label risk coefficient. 3.The big data-based food quality and safety tracking management system according to claim 2, characterized in that, The label risk value is obtained by processing the label risk coefficient and the label identification data, which comprises the following steps: The difference between the label identification data and the standard label identification value is calculated to obtain the label deviation value; The label risk coefficient and the label deviation value are multiplied to obtain the label risk value. 4.The big data-based food quality and safety tracking management system according to claim 1, wherein, According to the warehouse stacking parameters of the food to be tracked, the stacking abnormality degree value of the food to be tracked in the warehouse process is judged, which comprises the following steps: Based on the warehouse stacking parameters and the category characteristic parameters of the food to be tracked, a stacking reference set is constructed; wherein, the stacking reference set contains standard stacking pressure threshold value in different time periods, standard misplacement angle threshold value of adjacent food to be tracked and stacking stability attenuation coefficient; The actual pressure value of the food to be tracked, the actual misplacement angle of adjacent food to be tracked and the real-time inclination angle of the food to be tracked in the stacking process are collected; The actual pressure value and the standard stacking pressure threshold value of the corresponding time period are processed by ratio to obtain the pressure deviation index; the actual misplacement angle and the standard misplacement angle threshold value are processed by difference to obtain the angle deviation index; the real-time inclination angle and the initial stacking inclination angle are processed by difference and then multiplied by the stacking stability attenuation coefficient to obtain the inclination deviation index; The damage correlation coefficient is determined according to the correlation between the historical packaging damage data of the food to be tracked and the warehouse stacking parameters; The ground flatness of the warehouse area is detected to obtain the basic stability coefficient; The stacking abnormality degree value is determined according to the pressure deviation index, the angle deviation index, the inclination deviation index, the damage correlation coefficient and the basic stability coefficient. 5.The big data-based food quality and safety tracking management system according to claim 1, wherein, The stacking abnormality degree value and the label identification data are processed to obtain a storage specification interference value, specifically including the following steps: The label identification data includes storage limitation annotations and traceability correlation information; The deviation features of the actual stacking from the annotation requirements are extracted from the storage limitation annotations, and the storage area mismatch features caused by the identification errors are extracted from the traceability correlation information; The deviation features and the storage area mismatch features are combined as an interference feature set; The influence weights of each feature in the interference feature set are determined according to the food category storage specification, and the interference feature set and the influence weights are weighted to obtain a label specification misleading degree; The stacking abnormality degree value and the label specification misleading degree are input into a synergistic model to obtain the storage specification interference value. 6.The big data-based food quality and safety tracking management system according to claim 1, wherein, The storage specification interference degree of the food to be tracked is determined according to the storage specification interference value to obtain a first grade storage specification interference and a second grade storage specification interference, specifically including the following steps: The storage specification interference value is compared with a preset storage specification interference threshold value; If the storage specification interference value is less than the preset storage specification interference threshold value, it is determined that the storage specification interference degree of the food to be tracked is a first grade storage specification interference; If the storage specification interference value is greater than or equal to the preset storage specification interference threshold value, it is determined that the storage specification interference degree of the food to be tracked is a second grade storage specification interference. 7.The big data-based food quality and safety tracking management system according to claim 1, wherein, If it is the first grade storage specification interference, the storage stacking parameters and the label risk value are processed and analyzed to obtain first actual quality data, specifically including the following steps: The influence of the storage stacking parameters on the storage risk value of the food to be tracked is determined; The quality risk of the food to be tracked is determined according to the storage risk value and the influence of the storage stacking parameters on the storage link to obtain a first storage risk judgment value; The initial quality supervision data is corrected according to the label risk value and the first storage risk judgment value to obtain the first actual quality data. 8.The big data-based food quality and safety tracking management system according to claim 7, wherein, Further including the following steps: The stacking deviation value corresponding to the storage stacking parameters is detected, and the label interference degree corresponding to the label identification data is detected; The correlation risk value is obtained by counting the correlation risk situation formed by the label interference degree and the storage stacking deviation; The stacking deviation value corresponding to the storage specification abnormal interference situation and the label interference degree are processed to obtain an additional risk value, specifically including the following steps: 9.The big data-based food quality and safety tracking management system according to claim 8, wherein, The additional risk value caused by the historical stacking deviation is extracted from the historical supervision data to obtain a historical additional risk value; The historical additional risk value and the historical normal storage risk value are processed by difference value to obtain a historical additional risk amplitude value; The historical additional risk amplitude value and the historical stacking deviation value are processed by ratio value to obtain an additional risk factor; The additional risk value of the food to be tracked in the storage process is obtained according to the additional risk factor and the storage stacking deviation value to be tracked. The additional risk value, the storage risk coefficient and the label risk value are processed and analyzed to obtain second actual quality data, specifically including the following steps: 10.The big data-based food quality and safety tracking management system according to claim 9, wherein, ​ The second storage risk judgment value of the food to be tracked is judged according to the additional risk value and the storage risk coefficient; The initial quality supervision data is corrected to obtain the second actual quality data according to the second storage risk judgment value and the label risk value.

Images