Traceability management method and system based on food quality testing

Abstract

The present invention discloses a traceability management method and system based on food quality inspection, which relates to the technical field of food quality inspection. A unique production serial number is assigned to each piece of food, and dimensional information such as production time, batch, and process node are integrated to synchronously associate equipment operating parameters and video feature parameters. Based on batch and time clustering data, standardized operating intervals of production parameters are dynamically counted to generate adaptive thresholds of equipment parameters and dynamic fitting intervals of video features, thereby eliminating manual setting deviations. After unqualified products are found in random inspections, spatiotemporal neighboring batches are retrieved according to their serial numbers, and the deviations of monitoring parameters of each batch from the standard interval are compared to calculate a weighted production status assessment value. When the value is lower than the set threshold, high-risk serial numbers are automatically marked and a targeted recall is triggered. The above-mentioned technical solution of the present invention realizes the integration of multi-source data for comprehensive analysis, thereby achieving faster and more accurate positioning of other foods with abnormal quality.

Description

Technical Field

[0001] The present invention relates to the technical field of food quality detection, and in particular to a traceability management method and system based on food quality detection. Background Art

[0002] Currently, food production quality control relies mainly on manual sampling and single-dimensional data traceability, making it difficult to accurately locate and quickly respond to quality risks under complex processes. In traditional methods, equipment operating parameters and video surveillance information exist in isolation, resulting in inefficient tracing of abnormal events and an inability to effectively link production data anomalies with specific quality defects. For example, when food is contaminated with foreign matter, a large amount of time is required to check equipment logs and video records one by one, and manually set static parameter thresholds cannot dynamically adapt to equipment aging or environmental changes, which can easily lead to misjudgments or missed detections. In addition, existing appearance defect detection technologies are limited by factors such as uneven lighting and food deformation, resulting in a high false alarm rate. When unqualified food is found after sampling, the batch-level extensive recall mechanism can easily lead to increased economic losses. To address the above problems, there is an urgent need to develop a traceability management system that integrates multi-source data dynamic modeling, intelligent parameter interval calibration, and proactive risk prediction to achieve refined quality control and precise risk interception throughout the entire production chain. Summary of the Invention

[0003] The purpose of the present invention is to provide a traceability management method and system that can trace and determine the source of food with abnormal quality by combining multi-source data analysis.

[0004] The present invention discloses a traceability management method based on food quality detection, comprising:

[0005] A food production serial number is constructed for each food product, and the production serial number includes the production time, production batch, production sequence within the production batch, and the production steps to which it belongs. A production monitoring parameter group is constructed for each production serial number, and the production monitoring parameter group includes several production equipment operating parameters and monitoring video feature parameters;

[0006] Based on the production batch and production time in the production serial number, the production monitoring parameter group is classified, and the classified production monitoring parameter group is analyzed within a range to determine the first standard production operation parameter range of the production equipment operation parameter and the second standard production operation parameter range of the monitoring video feature parameter;

[0007] Finished food products are randomly inspected to identify food products with unqualified quality. Based on the production serial numbers of the unqualified food products, other production serial numbers with similar production times and production batches are determined. The production monitoring parameter groups corresponding to other production serial numbers are compared with the first standard production operation parameter interval and the second standard production operation parameter interval respectively, and the production status assessment value is calculated. If the production status assessment value is less than or equal to the preset value, the corresponding production serial number is marked as abnormal, and the corresponding food is retrieved for quality inspection.

[0008] In some embodiments disclosed herein, the production equipment operating parameters include:

[0009] Cleaning machine operating parameters, including water pressure, water temperature, and spray time;

[0010] Sorting machine operating parameters, including vibration frequency, color sorting accuracy, and rejection rate;

[0011] Dryer operating parameters, including hot air temperature, humidity, and material residence time;

[0012] Mixer operating parameters, including speed, torque, current load, and material temperature;

[0013] Homogenizer operating parameters, including pressure, cycle times, and particle size;

[0014] Fermentation tank operating parameters, including temperature, pH, dissolved oxygen concentration, and agitation rate;

[0015] Pasteurizer operating parameters, including temperature profile, hold time, and flow rate;

[0016] UHT sterilizer operating parameters, instantaneous temperature, cooling rate, steam pressure;

[0017] Microwave sterilizer operating parameters, power density, frequency, and material penetration depth;

[0018] Filling machine operating parameters, filling volume error, liquid level, sealing pressure;

[0019] Vacuum sealing machine operating parameters, vacuum degree, sealing temperature, and residual oxygen;

[0020] Labeling machine operating parameters, positioning accuracy, glue coating thickness, label adhesion rate.

[0021] In some embodiments disclosed herein, a method for determining characteristic parameters of a surveillance video includes:

[0022] The food assembly line area on the video image is delineated, and visual analysis technology is used to lock the individual food blocks in the food assembly line area. The movement rate of each individual food block and the degree of abnormality in the appearance of the individual food block are determined, and the movement rate of the individual food block and the degree of abnormality in the appearance of the individual food block are identified as monitoring video feature parameters.

[0023] In some embodiments disclosed herein, a method for determining the degree of abnormality in the appearance of a single food block using visual analysis technology includes:

[0024] Perform edge detection on the food production line area to determine several edge lines. Based on the distance between the ends of the edge lines, different edge lines are grouped together and their ends are linked to form the edge contour of the single food block.

[0025] A food block direction calibration template is set, the food block direction calibration template including a standard outline of the food block and a plurality of grayscale correction points within the standard outline. The food block direction calibration template and the edge outline are subjected to a plurality of dynamic transformation and comparison methods. The dynamic change comparison method includes rotating the angle of the food block direction calibration template and translating the position of the food block direction calibration template so that the standard outline of the food block direction calibration template and the edge outline of the food block direction calibration template coincide with each other, and comparing the grayscale values of the grayscale correction points to see if they are the same. If they are the same, the direction indicated by the food block direction calibration template at this time is used as the direction feature of the edge outline.

[0026] A food standard grayscale distribution template is set for the edge contour. Based on the determined directional characteristics of the edge contour, the food standard grayscale distribution template is adapted to the edge contour for comparison. The grayscale distribution characteristics within the edge contour and the grayscale distribution matching parameters of the food standard grayscale distribution template are determined. Based on the distribution matching parameter interval to which the grayscale distribution matching parameters belong, the degree of appearance abnormality of the monomer food block corresponding to the edge contour is determined.

[0027] In some embodiments disclosed herein, a method for determining a grayscale distribution characteristic within an edge contour and a grayscale distribution matching parameter of a food standard grayscale distribution template includes:

[0028] The food standard grayscale distribution template includes a number of contour blocks, and each contour block is set with a standard grayscale value. The food standard grayscale distribution template is compared with the corresponding contour block in the edge contour, and the grayscale value difference corresponding to each contour block is determined;

[0029] Based on the grayscale value differences corresponding to all the blocks within the contour, the grayscale distribution characteristics within the edge contour and the grayscale distribution matching parameters of the food standard grayscale distribution template are determined;

[0030] Among them, the expression for calculating the grayscale distribution matching parameter is:

[0031] ;

[0032] Among them, F is the grayscale distribution matching parameter, The number of blocks within the contour whose grayscale value difference is less than or equal to the preset value, is the total number of blocks within the contour, f is the contour block number proportional impact adjustment coefficient, c is the contour block number proportional impact adjustment constant, The preset maximum grayscale value difference, is the grayscale value difference of the x-th contour block.

[0033] In some embodiments disclosed herein, a method for performing interval analysis on the classified production monitoring parameter groups includes:

[0034] Constructing a horizontal axis corresponding to the parameters, determining the parameter mapping quantity corresponding to each parameter, constructing a mapping quantity vertical axis perpendicular to the parameter corresponding horizontal axis for the parameter mapping quantity, and constructing a parameter mapping quantity change curve based on the parameters in the plurality of production monitoring parameter groups, determining the curve midpoint of the parameter mapping quantity change curve, taking the curve midpoint as the starting point, gradually advancing the interval critical points toward both ends, and calculating the cumulative sum of the first curve values between the interval critical points and the cumulative sum of the second curve values outside the interval critical points;

[0035] Calculate the cumulative sum ratio of the cumulative sum of the first curve values and the cumulative sum of the second curve values. If the cumulative sum ratio is greater than or equal to the preset value, lock the interval critical point position and identify the interval between the interval critical points at this time as the first standard production operation parameter interval or the second standard production operation parameter interval.

[0036] In some embodiments disclosed herein, a method for comparing the production monitoring parameter groups corresponding to other production serial numbers with the first standard production operation parameter interval and the second standard production operation parameter interval includes:

[0037] Comparing the production equipment operating parameters of the production monitoring parameter group with the corresponding first standard production operating parameter interval, constructing a first adaptation operator based on the comparison result, and comparing the monitoring video feature parameters with the corresponding second standard production operating parameter interval, constructing a second adaptation operator based on the comparison result;

[0038] Determining a production status evaluation value based on the first adaptation operator and the second adaptation operator;

[0039] The expression for calculating the production status evaluation value is:

[0040] ;

[0041] Where, P is the production status assessment value, is the adaptation parameter of the i-th parameter, is the preset influence weight coefficient of the i-th parameter, and N is the total number of production equipment operating parameters and monitoring video feature parameters in the production monitoring parameter group;

[0042] Among them, determine the adaptation parameter of the i-th parameter The method includes determining whether the i-th parameter belongs to the standard production operation parameter range, and if so, Output 1, if not, then Output 0.

[0043] In some embodiments disclosed in the present invention, a traceability management system based on food quality testing is also disclosed, including:

[0044] The first module is used to construct a food production serial number for each food production, and the production serial number includes the production time, production batch, production sequence in the production batch, and the production step to which it belongs. A production monitoring parameter group is constructed for each production serial number, and the production monitoring parameter group includes several production equipment operating parameters and monitoring video feature parameters;

[0045] The second module is used to classify the production monitoring parameter groups based on the production batch and production time in the production serial number, and perform interval analysis on the classified production monitoring parameter groups to determine the first standard production operation parameter interval of the production equipment operation parameters and the second standard production operation parameter interval of the monitoring video feature parameters;

[0046] The third module is used to conduct random inspections on finished foods, identify foods that do not meet quality standards, and based on the production serial numbers of the foods that do not meet quality standards, determine other production serial numbers with similar production times and production batches, and compare the production monitoring parameter groups corresponding to other production serial numbers with the first standard production operation parameter interval and the second standard production operation parameter interval, respectively, to calculate a production status evaluation value. If the production status evaluation value is less than or equal to a preset value, the corresponding production serial number is marked as abnormal, and the corresponding food is retrieved for quality inspection.

[0047] The present invention discloses a traceability management method and system based on food quality inspection, which relates to the technical field of food quality inspection. A unique production serial number is assigned to each piece of food, and dimensional information such as production time, batch, and process node are integrated to synchronously associate equipment operating parameters and video feature parameters. Based on batch and time clustering data, standardized operating intervals of production parameters are dynamically counted to generate adaptive thresholds of equipment parameters and dynamic fitting intervals of video features, thereby eliminating manual setting deviations. After unqualified products are found in random inspections, spatiotemporal neighboring batches are retrieved according to their serial numbers, and the deviations of monitoring parameters of each batch from the standard interval are compared to calculate a weighted production status assessment value. When the value is lower than the set threshold, high-risk serial numbers are automatically marked and a targeted recall is triggered. The above-mentioned technical solution of the present invention realizes the integration of multi-source data for comprehensive analysis, thereby achieving faster and more accurate positioning of other foods with abnormal quality.

[0048] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 This is a method step diagram of the traceability management method based on food quality testing disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0050] The technical solution of the present invention is further described below with reference to the accompanying drawings and embodiments.

[0051] The following will be combined with the accompanying drawings and specific embodiments to clearly and completely describe the technical solutions of the present invention. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention and cannot be understood as limiting the scope of protection of the present invention. Those skilled in the art in this field can make some non-essential improvements and adjustments based on the content of the present invention described below. In the present invention, unless otherwise clearly specified and limited, the technical terms used in the present invention should have the common meanings understood by those skilled in the art of the present invention. Example

[0052] The purpose of the present invention is to provide a traceability management method and system that can trace and determine the source of food with abnormal quality by combining multi-source data analysis.

[0053] The present invention discloses a traceability management method based on food quality detection, see Figure 1 ,include:

[0054] In step S100, a food production serial number is constructed for the production of each food, and the production serial number includes the production time, production batch, production sequence in the production batch, and the corresponding production steps. A production monitoring parameter group is constructed for each production serial number, and the production monitoring parameter group includes several production equipment operating parameters and monitoring video feature parameters.

[0055] Step S100 achieves refined management and quality traceability throughout the entire production process by constructing a multi-source data association system with a composite coding structure. First, a unique production serial number is generated for each food item. The encoding incorporates four elements: production time (specific to microsecond accuracy), batch number (including production line number, date sequence, etc.), sequence code (sequential number within the batch), and identification of the corresponding production step (such as cleaning, sorting, and sterilization). This serial number uses hash encryption technology to form a uniquely indexed database primary key, ensuring that traceability can accurately locate the individual food item and its corresponding process node. Simultaneously, each serial number is mapped to a production monitoring parameter set consisting of two components: equipment operating parameters and video feature parameters.

[0056] Equipment operating parameters are directly collected from the sensors and control units of each production equipment, covering dozens of dynamic indicators such as the water flow pressure and spray time of the cleaning machine, the vibration frequency and color sorting accuracy of the sorting machine, the hot air temperature and humidity of the dryer, the pressure and particle size of the homogenizer, etc., forming multi-dimensional equipment status time series data.

[0057] Video feature parameters are extracted through machine vision technology, including:

[0058] Movement rate of individual food blocks: Use a visual analysis algorithm based on optical flow to track the movement trajectory and speed of food on the production line and identify transmission anomalies (such as blockages or sudden speed changes).

[0059] Degree of Appearance Abnormality: Contour edge detection techniques (such as the Canny operator) are used to delineate the outline of individual food items. Dynamic alignment (rotation and translation) with an orientation calibration template is used to calibrate their posture. Surface defects (such as wrinkles in packaging and missing labels) are quantified based on a grayscale distribution matching parameter (F value; higher F values indicate lower abnormality). Grayscale matching is achieved by normalizing the difference in feature values between the standard template and the detection area. An abnormality is determined when the cumulative difference exceeds a threshold.

[0060] The core of this step lies in the structured integration of multidimensional spatiotemporal and process data: using serial numbers as a link, discrete equipment operation data, continuous visual feature data, and spatiotemporal information from production nodes are bound together to construct a data unit for the entire lifecycle of a single food item. This provides the fundamental data structure for subsequent anomaly detection and refined recall based on dynamic parameter intervals (steps S200-S300), thereby upgrading traditional batch-based, extensive quality control to precise traceability at the process level and even the equipment level.

[0061] In some embodiments disclosed in the present invention, the operating parameters of the production equipment include: cleaning machine operating parameters, including water flow pressure, water temperature, and spray time; sorting machine operating parameters, including vibration frequency, color sorting accuracy, and rejection rate; dryer operating parameters, including hot air temperature, humidity, and material residence time; mixer operating parameters, including speed, torque, current load, and material temperature; homogenizer operating parameters, including pressure value, number of cycles, and particle size; fermentation tank operating parameters, including temperature, pH value, dissolved oxygen concentration, and stirring rate; pasteurizer operating parameters, including temperature curve, holding time, and flow rate; UHT sterilizer operating parameters, including instantaneous temperature, cooling rate, and steam pressure; microwave sterilizer operating parameters, including power density, frequency, and material penetration depth; canning machine operating parameters, including canning quantity error, liquid level height, and sealing pressure; vacuum sealing machine operating parameters, including vacuum degree, sealing temperature, and residual oxygen; labeling machine operating parameters, including positioning accuracy, glue coating thickness, and label adhesion rate.

[0062] In some embodiments disclosed herein, a method for determining characteristic parameters of a surveillance video includes:

[0063] In step S101, the food assembly line area on the video image is delineated, and visual analysis technology is used to lock the individual food blocks in the food assembly line area. The movement rate of each individual food block and the degree of abnormality in the appearance of the individual food block are determined, and the movement rate and the degree of abnormality in the appearance of the individual food block are identified as monitoring video feature parameters.

[0064] In some embodiments disclosed herein, a method for determining the degree of abnormality in the appearance of a single food block using visual analysis technology includes:

[0065] In step S1011, contour edge detection is performed on the food production line area to determine a number of contour edge lines. Based on the distance between the ends of the contour edge lines, different contour edge lines are grouped together and the end-to-end correlation is performed to form the edge contour of a single food block.

[0066] Contour extraction and segmentation (step S1011): Using edge detection algorithms (such as the Canny operator), the initial contours of the food in the production line video are identified. Endpoint clustering and region growing algorithms are used to complete broken edges. Using the Euclidean distance between edge endpoints (with a set threshold, such as 5 pixels), non-closed contours are recursively joined to generate closed polygons enclosing the food (e.g., the outline of a milk carton). The minimum bounding rectangle (MBR) is used to optimize the contour topology and eliminate external noise interference (e.g., removing the conveyor belt background).

[0067] In step S1012, a food block direction calibration template is set, wherein the food block direction calibration template includes a standard outline of the food block and a plurality of grayscale correction points within the standard outline. The food block direction calibration template and the edge outline are dynamically transformed and compared several times. The dynamic change comparison method includes rotating the angle of the food block direction calibration template and translating the position of the food block direction calibration template so that the standard outline of the food block direction calibration template and the edge outline of the food block direction calibration template coincide with each other, and comparing the grayscale values of the grayscale correction points to see if they are the same. If they are the same, the direction indicated by the food block direction calibration template at this time is used as the direction feature of the edge outline.

[0068] Direction Correction and Template Matching (Step S1012): A preset food standard orientation template (e.g., the outline of a complete yogurt cup) is loaded, and N key grayscale correction points are calibrated within it (typically located in the label printing area). The template's rotation angle (1° steps within ±30°) and translation offset (±20 pixels) are dynamically adjusted using an iterative closest point (ICP) algorithm to maximize the overlap between the template outline and the detected outline (using the principle of minimizing the difference area). The grayscale matching of the grayscale correction points is also verified (e.g., CMYK channel difference ≤ 10). If all key points pass verification (e.g., 8 / 10 points match), the rotation transformation matrix at this point is recorded, and the standardized orientation of the individual food item (horizontal rotation correction offset angle θ) is output.

[0069] In step S1013, a food standard grayscale distribution template is set for the edge contour. Based on the determined directional characteristics of the edge contour, the food standard grayscale distribution template is adapted to the edge contour for comparison, and the grayscale distribution characteristics within the edge contour and the grayscale distribution matching parameters of the food standard grayscale distribution template are determined. Based on the distribution matching parameter interval to which the grayscale distribution matching parameters belong, the degree of appearance abnormality of the monomer food block corresponding to the edge contour is determined.

[0070] Grayscale distribution defect detection (step S1013): For the single food item after orientation correction, a mask is superimposed to capture its effective area. A block-based grayscale comparison strategy is applied.

[0071] In some embodiments disclosed herein, a method for determining a grayscale distribution characteristic within an edge contour and a grayscale distribution matching parameter of a food standard grayscale distribution template includes:

[0072] Step S10131: The food standard grayscale distribution template includes a plurality of contour blocks, and each contour block is set with a standard grayscale value. The food standard grayscale distribution template is compared with the corresponding contour block in the edge contour, and the grayscale value difference corresponding to each contour block is determined;

[0073] Step S10132: determining the grayscale distribution characteristics within the edge contour and the grayscale distribution matching parameters of the food standard grayscale distribution template based on the grayscale value differences corresponding to all the blocks within the contour;

[0074] Among them, the expression for calculating the grayscale distribution matching parameter is:

[0075] ;

[0076] Among them, F is the grayscale distribution matching parameter, The number of blocks within the contour whose grayscale value difference is less than or equal to the preset value, is the total number of blocks within the contour, f is the contour block number proportional impact adjustment coefficient, c is the contour block number proportional impact adjustment constant, The preset maximum grayscale value difference, is the grayscale value difference of the x-th contour block.

[0077] In step S200, the production monitoring parameter group is classified based on the production batch and production time in the production serial number, and the classified production monitoring parameter group is analyzed in intervals to determine the first standard production operation parameter interval of the production equipment operation parameters and the second standard production operation parameter interval of the monitoring video feature parameters.

[0078] Step S200 uses dynamic data modeling and parameter benchmark self-calibration strategies to construct standardized parameter ranges that adapt to changes in the production environment. First, based on the batch and time tags in the production serial number, the device operating parameters and video feature parameter groups under similar production conditions are systematically aggregated to form a dataset cluster divided by time and space dimensions. The specific process includes the following two core operations:

[0079] Equipment parameter interval calibration: Using a hierarchical sliding window statistical method, equipment parameters within the same batch (such as sorter vibration frequency and pasteurization temperature) are grouped by time window (e.g., 30-minute slices). Kernel density estimation (KDE) is used to calculate the parameter distribution probability density function. Confidence intervals with a confidence level of α = 0.05 (e.g., the pasteurization temperature range [72.4°C, 75.8°C]) are used to cover the normal fluctuation range of production data, replacing manual threshold setting based on experience. A dynamic calibration mechanism is introduced to address equipment performance degradation. Using a Gaussian mixture model (GMM), new batch data is analyzed for short-term (e.g., the past week) and long-term (the past three months) distribution differences, autonomously adjusting the confidence interval boundaries.

[0080] Video feature interval modeling: Based on the dynamic baseline of visual features (such as the F-value of the appearance abnormality of individual food items) and the correlation between batches, a time-series recursive model is established. An LSTM network is used to learn the fluctuation patterns of features within a batch during continuous production (such as the temporal variation of the packaging integrity score), predict feature thresholds for the next time period, and assess deviation tolerances (such as a grayscale matching tolerance of ±10%). Feature data from adjacent batches (such as the batch from the first 30 minutes of a production line) is also integrated to ensure the adaptability and robustness of video features.

[0081] In some embodiments disclosed herein, a method for performing interval analysis on the classified production monitoring parameter groups includes:

[0082] Step S201: construct a horizontal axis corresponding to the parameters, determine the parameter mapping quantity corresponding to each parameter, construct a mapping quantity vertical axis perpendicular to the parameter corresponding horizontal axis for the parameter mapping quantity, and construct a parameter mapping quantity change curve based on the parameters in several production monitoring parameter groups, determine the midpoint of the parameter mapping quantity change curve, take the midpoint of the curve as the starting point, gradually advance the interval critical points to both ends, calculate the cumulative sum of the first curve values between the interval critical points and the cumulative sum of the second curve values outside the interval critical points.

[0083] Step S202, calculate the cumulative sum ratio of the cumulative sum of the first curve values and the cumulative sum of the second curve values. If the cumulative sum ratio is greater than or equal to a preset value, lock the interval critical point position, and identify the interval between the interval critical points at this time as the first standard production operation parameter interval or the second standard production operation parameter interval.

[0084] Step S300: random inspection is conducted on the finished food products, and the food with unqualified quality is determined. Based on the production serial number of the unqualified food, other production serial numbers with similar production time and production batch are determined, and the production monitoring parameter groups corresponding to the other production serial numbers are compared with the first standard production operation parameter interval and the second standard production operation parameter interval respectively, and the production status evaluation value is calculated. If the production status evaluation value is less than or equal to the preset value, the corresponding production serial number is marked as abnormal, and the corresponding food is retrieved for quality inspection.

[0085] Step S300 achieves efficient tracing and accurate recall of quality issues based on spatiotemporal diffusion risk modeling and multimodal evidence fusion mechanism.

[0086] Proximal batch selection: parse the production serial number of the unqualified product, extract its production timestamp, batch number and process node identifier, and build spatiotemporal proximity screening rules:

[0087] Temporal proximity: batches produced on the same production line with a time interval ≤ H hours (e.g., 2 hours); logical proximity: following the process sequence across processes (e.g., when a defective product is in the sterilization process, it is automatically associated with the batch of its predecessor cleaning process).

[0088] In some embodiments disclosed herein, a method for comparing the production monitoring parameter groups corresponding to other production serial numbers with the first standard production operation parameter interval and the second standard production operation parameter interval includes:

[0089] Step S301: compare the production equipment operating parameters of the production monitoring parameter group with the corresponding first standard production operating parameter interval, and construct a first adaptation operator based on the comparison result; compare the monitoring video feature parameters with the corresponding second standard production operating parameter interval, and construct a second adaptation operator based on the comparison result.

[0090] Step S302: Determine a production status evaluation value based on the first adaptation operator and the second adaptation operator.

[0091] The expression for calculating the production status evaluation value is:

[0092] ;

[0093] Where, P is the production status assessment value, is the adaptation parameter of the i-th parameter, is the preset influence weight coefficient of the i-th parameter, and N is the total number of production equipment operating parameters and monitoring video feature parameters in the production monitoring parameter group.

[0094] Among them, determine the adaptation parameter of the i-th parameter The method includes determining whether the i-th parameter belongs to the standard production operation parameter range, and if so, Output 1, if not, then Output 0.

[0095] In some embodiments disclosed in the present invention, a traceability management system based on food quality testing is also disclosed, including:

[0096] The first module is used to construct a food production serial number for each food production, and the production serial number includes the production time, production batch, production sequence in the production batch, and the production step to which it belongs. A production monitoring parameter group is constructed for each production serial number, and the production monitoring parameter group includes several production equipment operating parameters and monitoring video feature parameters;

[0097] The second module is used to classify the production monitoring parameter groups based on the production batch and production time in the production serial number, and perform interval analysis on the classified production monitoring parameter groups to determine the first standard production operation parameter interval of the production equipment operation parameters and the second standard production operation parameter interval of the monitoring video feature parameters;

[0098] The third module is used to conduct random inspections on finished foods, identify foods that do not meet quality standards, and based on the production serial numbers of the foods that do not meet quality standards, determine other production serial numbers with similar production times and production batches, and compare the production monitoring parameter groups corresponding to other production serial numbers with the first standard production operation parameter interval and the second standard production operation parameter interval, respectively, to calculate a production status evaluation value. If the production status evaluation value is less than or equal to a preset value, the corresponding production serial number is marked as abnormal, and the corresponding food is retrieved for quality inspection.

[0099] The present invention discloses a traceability management method and system based on food quality inspection, which relates to the technical field of food quality inspection. A unique production serial number is assigned to each piece of food, and dimensional information such as production time, batch, and process node are integrated to synchronously associate equipment operating parameters and video feature parameters. Based on batch and time clustering data, standardized operating intervals of production parameters are dynamically counted to generate adaptive thresholds of equipment parameters and dynamic fitting intervals of video features, thereby eliminating manual setting deviations. After unqualified products are found in random inspections, spatiotemporal neighboring batches are retrieved according to their serial numbers, and the deviations of monitoring parameters of each batch from the standard interval are compared to calculate a weighted production status assessment value. When the value is lower than the set threshold, high-risk serial numbers are automatically marked and a targeted recall is triggered. The above-mentioned technical solution of the present invention realizes the integration of multi-source data for comprehensive analysis, thereby achieving faster and more accurate positioning of other foods with abnormal quality.

[0100] Through the above description of the embodiments, those skilled in the art will clearly understand that the present invention can be implemented via hardware or by utilizing software combined with a necessary general-purpose hardware platform. Based on this understanding, the technical solution of the present invention can be embodied in the form of a software product. This software product can be stored on a non-volatile storage medium (such as a CD-ROM, USB flash drive, or external hard drive) and includes instructions for enabling a computer device (such as a personal computer, server, or network device) to execute the methods described in various implementation scenarios of the present invention.

[0101] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit the same. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solutions of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A traceability management method based on food quality testing, characterized in that: include: A food production serial number is constructed for each food product, and the production serial number includes the production time, production batch, production sequence within the production batch, and the production steps to which it belongs. A production monitoring parameter group is constructed for each production serial number, and the production monitoring parameter group includes several production equipment operating parameters and monitoring video feature parameters; Based on the production batch and production time in the production serial number, the production monitoring parameter group is classified, and the classified production monitoring parameter group is analyzed within a range to determine the first standard production operation parameter range of the production equipment operation parameter and the second standard production operation parameter range of the monitoring video feature parameter; Finished food products are randomly inspected to identify food products with unqualified quality. Based on the production serial numbers of the unqualified food products, other production serial numbers with similar production times and production batches are determined. The production monitoring parameter groups corresponding to other production serial numbers are compared with the first standard production operation parameter interval and the second standard production operation parameter interval respectively, and the production status assessment value is calculated. If the production status assessment value is less than or equal to the preset value, the corresponding production serial number is marked as abnormal, and the corresponding food is retrieved for quality inspection.

2. The traceability management method based on food quality detection according to claim 1 is characterized in that: Production equipment operating parameters include: Cleaning machine operating parameters, including water pressure, water temperature, and spray time; Sorting machine operating parameters, including vibration frequency, color sorting accuracy, and rejection rate; Dryer operating parameters, including hot air temperature, humidity, and material residence time; Mixer operating parameters, including speed, torque, current load, and material temperature; Homogenizer operating parameters, including pressure, cycle times, and particle size; Fermentation tank operating parameters, including temperature, pH, dissolved oxygen concentration, and agitation rate; Pasteurizer operating parameters, including temperature profile, hold time, and flow rate; UHT sterilizer operating parameters, instantaneous temperature, cooling rate, steam pressure; Microwave sterilizer operating parameters, power density, frequency, and material penetration depth; Filling machine operating parameters, filling volume error, liquid level, sealing pressure; Vacuum sealing machine operating parameters, vacuum degree, sealing temperature, and residual oxygen; Labeling machine operating parameters, positioning accuracy, glue coating thickness, label adhesion rate.

3. The traceability management method based on food quality detection according to claim 1 is characterized in that: Methods for determining characteristic parameters of surveillance video include: The food assembly line area on the video image is delineated, and visual analysis technology is used to lock the individual food blocks in the food assembly line area. The movement rate of each individual food block and the degree of abnormality in the appearance of the individual food block are determined, and the movement rate of the individual food block and the degree of abnormality in the appearance of the individual food block are identified as monitoring video feature parameters.

4. The traceability management method based on food quality detection according to claim 3 is characterized in that: Methods for determining the degree of abnormality in the appearance of individual food blocks using visual analysis technology include: Perform edge detection on the food production line area to determine several edge lines. Based on the distance between the ends of the edge lines, different edge lines are grouped together and their ends are linked to form the edge contour of the single food block. A food block direction calibration template is set, the food block direction calibration template including a standard outline of the food block and a plurality of grayscale correction points within the standard outline. The food block direction calibration template and the edge outline are subjected to a plurality of dynamic transformation and comparison methods. The dynamic change comparison method includes rotating the angle of the food block direction calibration template and translating the position of the food block direction calibration template so that the standard outline of the food block direction calibration template and the edge outline of the food block direction calibration template coincide with each other, and comparing the grayscale values of the grayscale correction points to see if they are the same. If they are the same, the direction indicated by the food block direction calibration template at this time is used as the direction feature of the edge outline. A food standard grayscale distribution template is set for the edge contour. Based on the determined directional characteristics of the edge contour, the food standard grayscale distribution template is adapted to the edge contour for comparison. The grayscale distribution characteristics within the edge contour and the grayscale distribution matching parameters of the food standard grayscale distribution template are determined. Based on the distribution matching parameter interval to which the grayscale distribution matching parameters belong, the degree of appearance abnormality of the monomer food block corresponding to the edge contour is determined.

5. The traceability management method based on food quality detection according to claim 4 is characterized in that: The method for determining the grayscale distribution characteristics within the edge contour and the grayscale distribution matching parameters of the food standard grayscale distribution template includes: The food standard grayscale distribution template includes a number of contour blocks, and each contour block is set with a standard grayscale value. The food standard grayscale distribution template is compared with the corresponding contour block in the edge contour, and the grayscale value difference corresponding to each contour block is determined; Based on the grayscale value differences corresponding to all the blocks within the contour, the grayscale distribution characteristics within the edge contour and the grayscale distribution matching parameters of the food standard grayscale distribution template are determined; Among them, the expression for calculating the grayscale distribution matching parameter is: ； Among them, F is the grayscale distribution matching parameter, The number of blocks within the contour whose grayscale value difference is less than or equal to the preset value, is the total number of blocks within the contour, f is the contour block number proportional impact adjustment coefficient, c is the contour block number proportional impact adjustment constant, The preset maximum grayscale value difference, is the grayscale value difference of the x-th contour block.

6. The traceability management method based on food quality detection according to claim 1 is characterized in that: The methods for performing interval analysis on the classified production monitoring parameter groups include: Constructing a horizontal axis corresponding to the parameters, determining the parameter mapping quantity corresponding to each parameter, constructing a mapping quantity vertical axis perpendicular to the parameter corresponding horizontal axis for the parameter mapping quantity, and constructing a parameter mapping quantity change curve based on the parameters in the plurality of production monitoring parameter groups, determining the curve midpoint of the parameter mapping quantity change curve, taking the curve midpoint as the starting point, gradually advancing the interval critical points toward both ends, and calculating the cumulative sum of the first curve values between the interval critical points and the cumulative sum of the second curve values outside the interval critical points; Calculate the cumulative sum ratio of the cumulative sum of the first curve values and the cumulative sum of the second curve values. If the cumulative sum ratio is greater than or equal to the preset value, lock the interval critical point position and identify the interval between the interval critical points at this time as the first standard production operation parameter interval or the second standard production operation parameter interval.

7. The traceability management method based on food quality testing according to claim 1 is characterized in that: The method of comparing the production monitoring parameter groups corresponding to other production serial numbers with the first standard production operation parameter interval and the second standard production operation parameter interval respectively includes: Comparing the production equipment operating parameters of the production monitoring parameter group with the corresponding first standard production operating parameter interval, constructing a first adaptation operator based on the comparison result, and comparing the monitoring video feature parameters with the corresponding second standard production operating parameter interval, constructing a second adaptation operator based on the comparison result; Determining a production status evaluation value based on the first adaptation operator and the second adaptation operator; The expression for calculating the production status evaluation value is: ； Where, P is the production status assessment value, is the adaptation parameter of the i-th parameter, is the preset influence weight coefficient of the i-th parameter, and N is the total number of production equipment operating parameters and monitoring video feature parameters in the production monitoring parameter group; Among them, determine the adaptation parameter of the i-th parameter The method includes determining whether the i-th parameter belongs to the standard production operation parameter range, and if so, Output 1, if not, then Output 0.

8. The traceability management system based on food quality testing is characterized by: The method for implementing the traceability management method according to any one of claims 1 to 7 comprises: The first module is used to construct a food production serial number for each food production, and the production serial number includes the production time, production batch, production sequence in the production batch, and the production step to which it belongs. A production monitoring parameter group is constructed for each production serial number, and the production monitoring parameter group includes several production equipment operating parameters and monitoring video feature parameters; The second module is used to classify the production monitoring parameter groups based on the production batch and production time in the production serial number, and perform interval analysis on the classified production monitoring parameter groups to determine the first standard production operation parameter interval of the production equipment operation parameters and the second standard production operation parameter interval of the monitoring video feature parameters; The third module is used to conduct random inspections on finished foods, identify foods that do not meet quality standards, and based on the production serial numbers of the foods that do not meet quality standards, determine other production serial numbers with similar production times and production batches, and compare the production monitoring parameter groups corresponding to other production serial numbers with the first standard production operation parameter interval and the second standard production operation parameter interval, respectively, to calculate a production status evaluation value. If the production status evaluation value is less than or equal to a preset value, the corresponding production serial number is marked as abnormal, and the corresponding food is retrieved for quality inspection.

Images