Preserved meat production quality detection method and system based on characteristic analysis

Abstract

The invention relates to the technical field of food quality detection, in particular to a preserved meat production quality detection method and system based on feature analysis. The method comprises the following steps: acquiring multi-modal preserved meat detection data, endowing a detection object with an identifier, and associating key data; dividing the quality grade of the preserved meat, judging the current quality grade of the preserved meat according to the key data, and outputting; dividing preserved meat quality stability grades, predicting the current preserved meat quality stability grade according to the key data, and outputting the current preserved meat quality stability grade; respectively acquiring a preserved meat quality grade and a preserved meat quality stability grade, and integrating and outputting detection data; the system comprises a multi-modal data processing module, a quality grade division module, a quality stability grade division module and a detection data integration module. The identifier is given to the preserved meat, the key data is associated, the quality grade is judged according to the identifier and the key data of each piece of preserved meat, the quality stability grade is predicted, the characteristics of the preserved meat are prevented from being confused, and therefore the detection precision is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of food quality detection, and in particular to a method and system for detecting the quality of bacon production based on feature analysis. Background Art

[0002] During the production process of bacon, quality testing is required. Traditional quality testing requires sampling the bacon and then using chemical methods for testing, which takes a long time and damages the integrity of the product.

[0003] Currently, visible light detection, such as hyperspectral imaging and polarization imaging, can be used to collect the surface characteristics of bacon; however, in the above methods, a large amount of bacon is detected, and the current characteristics of bacon are easily confused, affecting the detection accuracy. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for detecting the quality of bacon production based on feature analysis, aiming to solve the technical problems in the existing technology of using visible light to detect bacon, the amount of bacon detected is large, the current features of bacon are easily confused, and the detection accuracy is affected.

[0005] To achieve the above object, the present invention adopts a method for detecting the quality of bacon production based on feature analysis, comprising the following steps:

[0006] Obtain multimodal bacon inspection data, assign identifiers to inspection objects, and associate key data;

[0007] Classify bacon quality grades, determine the current bacon quality grade based on key data, and output it;

[0008] Classify the quality stability level of bacon, predict the current quality stability level of bacon based on key data, and output it;

[0009] Obtain the bacon quality grade and bacon quality stability grade respectively, and integrate and output the test data.

[0010] Among them, in the steps of obtaining multimodal bacon detection data, assigning identifiers to detection objects, and associating key data:

[0011] Obtaining multimodal detection data of bacon, where the multimodal detection data includes hyperspectral imaging, polarization imaging, and three-dimensional topography measurement data;

[0012] Divide the current bacon into multiple surface areas;

[0013] Define abnormal data in hyperspectral imaging, polarization imaging, and 3D topography measurement data as key data, and associate the key data with surface areas.

[0014] Before obtaining the multimodal detection data of bacon:

[0015] The current location data of the bacon is obtained, and a unique detection identifier is assigned to the current bacon according to the current location data.

[0016] Among them, in the step of classifying the quality grade of bacon, judging the current quality grade of bacon based on key data, and outputting it:

[0017] Define characteristic quantities, and set a first threshold, a second threshold, a third threshold, and a characteristic value; wherein the characteristic quantities include nitrite content, oxide layer thickness, and surface crack ratio;

[0018] Obtain a first threshold value based on the nitrite content, obtain a second threshold value based on the oxide layer thickness, obtain a third threshold value based on the surface crack ratio, and calculate a characteristic value;

[0019] Divide the quality level of bacon and judge the current quality level of bacon based on the characteristic value.

[0020] Among them, in the step of classifying the quality grade of bacon and determining the current quality grade of bacon according to the characteristic value:

[0021] Divide the first-level judgment value and the second-level judgment value;

[0022] When the characteristic value is less than or equal to the first-level judgment value, the current bacon quality level is output as first-level;

[0023] When the characteristic value is greater than the first-level judgment value and less than the second-level judgment value, the current bacon quality grade is output as level two;

[0024] When the characteristic value is greater than or equal to the second-level judgment value, the current bacon quality level is output as level three.

[0025] Among them, in the step of classifying the bacon quality stability level, predicting the current bacon quality stability level based on key data, and outputting it:

[0026] Define short-term stability characteristics and obtain the current short-term stability level of bacon based on key data;

[0027] Define long-term stability characteristics and obtain the long-term stability level of the current bacon based on key data.

[0028] After defining the long-term stability characteristics and obtaining the long-term stability level of the current bacon based on the key data:

[0029] Get the short-term stability level and long-term stability level of the current bacon respectively, and output the bacon quality stability level.

[0030] Among them, in the steps of respectively obtaining the bacon quality grade and the bacon quality stability grade and integrating and outputting the test data:

[0031] Establish a bacon testing database and enter quality characteristics and recommended descriptions;

[0032] Obtain the bacon quality grade and bacon quality stability grade respectively, compare the quality characteristics, and output the comparison results.

[0033] Among them, after the steps of respectively obtaining the bacon quality grade and the bacon quality stability grade, comparing the quality characteristics, and outputting the comparison results:

[0034] Based on the comparison results of the bacon quality grade and the bacon quality stability grade, the recommended description is integrated and the test data is output.

[0035] The present invention also provides a bacon production quality detection system based on feature analysis, comprising a multimodal data processing module, a quality grade classification module, a quality stability grade classification module, and a detection data integration module; wherein:

[0036] The multimodal data processing module is used to obtain multimodal bacon detection data, assign identifiers to detection objects, and associate key data;

[0037] The quality grade classification module is used to classify the quality grade of bacon, determine the current quality grade of bacon based on key data, and output it;

[0038] The quality stability grade classification module is used to classify the quality stability grade of bacon, predict the current quality stability grade of bacon based on key data, and output it;

[0039] The detection data integration module is used to respectively obtain the bacon quality grade and the bacon quality stability grade, and integrate and output the detection data.

[0040] The present invention provides a method and system for detecting the quality of bacon production based on feature analysis, which respectively adopt the multimodal data processing module, the quality grade classification module, the quality stability grade classification module, and the detection data integration module to perform the following steps: obtaining multimodal bacon detection data, assigning an identifier to the detection object, and associating key data; classifying the bacon quality grades, judging the current bacon quality grade based on the key data, and outputting it; classifying the bacon quality stability grades, predicting the current bacon quality stability grade based on the key data, and outputting it; respectively obtaining the bacon quality grade and the bacon quality stability grade, integrating and outputting the detection data; by assigning an identifier to the bacon and associating it with key data, judging the quality grade of each piece of bacon based on the identifier and key data, and predicting the quality stability grade, preventing the characteristics of the bacon from being confused, thereby improving the detection accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0042] Figure 1 The present invention is a flowchart of the steps of the method for detecting the quality of bacon production based on feature analysis.

[0043] Figure 2 It is a step flow chart of S100 of the present invention.

[0044] Figure 3 It is a step flow chart of S200 of the present invention.

[0045] Figure 4 It is a step flow chart of S300 of the present invention.

[0046] Figure 5 It is a step flow chart of S400 of the present invention.

[0047] Figure 6 It is a structural principle diagram of the bacon production quality detection system based on feature analysis of the present invention.

[0048] Figure 7 It is a structural principle diagram of the electronic device of the present invention.

[0049] 501-Multimodal data processing module, 502-Quality grade classification module, 503-Quality stability grade classification module, 504-Detection data integration module. DETAILED DESCRIPTION

[0050] Exemplary embodiments are described in detail herein, with examples illustrated in the accompanying drawings. When the following description refers to the drawings, identical numerals in different drawings represent identical or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with this application.

[0051] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. As used in this application and the appended claims, the singular forms "a," "an," "the," and "the" are intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0052] It should be understood that although the terms first, second, third, etc. may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0053] See also Figures 1 to 5 The present invention provides a method for detecting the quality of bacon production based on feature analysis, comprising the following steps:

[0054] S100: Acquire multimodal bacon detection data, assign identifiers to detection objects, and associate key data.

[0055] In this embodiment, multimodal bacon detection data is obtained, an identifier is assigned to the detection object, and key data is associated. The specific process is as follows:

[0056] S101: Acquire the current location data of the bacon, and assign a unique detection identifier to the current bacon according to the current location data;

[0057] S102: Acquire multimodal detection data of bacon, where the multimodal detection data includes hyperspectral imaging, polarization imaging, and three-dimensional topography measurement data;

[0058] S103: Dividing the current bacon into multiple surface areas based on the current position data of the detection object;

[0059] S104: Define abnormal data in hyperspectral imaging, polarization imaging, and three-dimensional topography measurement data as key data, and associate the key data with the surface area.

[0060] In the above process, when the bacon enters the detection area, a position sensor, such as a photoelectric sensor or radio frequency identification system, is used to obtain the bacon's current location data. For example, if a photoelectric sensor is used, when the bacon passes the sensor, the sensor records the moment of passage and its position relative to a reference point. Based on the bacon's initial identifier and the current location data, a unique detection identifier is generated.

[0061] For example:

[0062] The initial identifier is "LM20250101001";

[0063] The inspection station number is "A01";

[0064] The detection time is "2025-01-01 10:30:00";

[0065] The unique detection identifier can then generate "LM20250101001_A01_20250101103000".

[0066] The unique detection identifier is associated with all subsequent detection data of the bacon and stored in a database.

[0067] Obtain hyperspectral imaging, polarization imaging, and 3D topography measurement data of bacon:

[0068] Among them, in obtaining the hyperspectral imaging data of bacon:

[0069] The bacon was scanned using a hyperspectral imager to generate a hyperspectral data cube, which contains the spatial and spectral information of the bacon surface.

[0070] Among them, in obtaining the hyperspectral imaging data of bacon:

[0071] Polarization imaging equipment was used to photograph the bacon to obtain image data under different polarization states.

[0072] Among them, in obtaining the hyperspectral imaging data of bacon:

[0073] The bacon is scanned using a three-dimensional shape measuring instrument to obtain point cloud data or depth images of the bacon surface.

[0074] The surface area division strategy is determined based on the shape of the bacon, the inspection requirements, and the characteristics of each inspection modality. For example, for regularly shaped bacon, it can be divided according to equal area; for irregularly shaped bacon, it can be divided according to its main characteristic areas, such as lean meat area, fat area, and epidermal area.

[0075] Region division based on position data: Combine the current position data of the bacon and divide the surface of the bacon into multiple regions. For example, the bacon surface can be divided into six regions: top, bottom, left, right, front, and back. Each region can be defined by its range in the spatial coordinate system:

[0076] For example, in area 1: x∈[x1,x2], y∈[y1,y2], z∈[z1,z2].

[0077] The information of each divided surface area is associated with the unique detection identifier of the bacon and stored in the database to facilitate subsequent data processing and analysis.

[0078] Set the hyperspectral reflectance threshold range. If the reflectance of a certain band exceeds the range, it will be judged as abnormal data.

[0079] For example, for the reflectance R(λ0) of the cured meat at wavelength λ0, if R(λ0) < R_min(λ0) or R(λ0) > R_max(λ0), then R(λ0) is abnormal data. Here, R_min(λ0) and R_max(λ0) are the minimum and maximum values of the reflectance of this band statistically obtained from the hyperspectral data of normal cured meat.

[0080] Set the threshold ranges of the degree of polarization (DoP) and the angle of polarization (AoP). If the DoP or AoP of a certain pixel exceeds this range, it is determined as abnormal data.

[0081] For example, for the degree of polarization DoP, if DoP < DoP_min or DoP > DoP_max, then the degree of polarization of this pixel is abnormal data. DoP_min and DoP_max are the minimum and maximum values of the degree of polarization statistically obtained from the polarization imaging data of normal cured meat.

[0082] Set the surface roughness threshold Ra_max. If the surface roughness Ra of a certain area > Ra_max, it is determined that there is abnormal data in this area. The surface roughness Ra can be calculated by the following formula:

[0083]

[0084] where n is the number of measurement points in this area, z i is the z - coordinate value of the i - th measurement point, and E(z) is the average value of the z - coordinates of all measurement points in this area.

[0085] According to the above definition of abnormal data, extract key data from hyperspectral imaging, polarization imaging, and three - dimensional topography measurement data, and record the position information of the key data, such as the pixel coordinates (x, y, λ) in hyperspectral data, the pixel coordinates (x, y) in polarization imaging data, the area number in three - dimensional topography measurement data, etc.

[0086] According to the position information of the key data, associate it with the corresponding surface area. For example, if the pixel coordinates (x, y) corresponding to a certain hyperspectral abnormal data are within the range of area 1, then associate this abnormal data with area 1. Store the association information between the key data and the surface area in the database for subsequent analysis of the nitrite content distribution and quality status of different areas of the cured meat.

[0087] Through the above steps, multi - modal detection data of the cured meat can be obtained, the surface of the cured meat can be divided into areas, and key data can be extracted and associated with the areas, laying a foundation for subsequent in - depth analysis of quality indicators such as the nitrite content, the thickness of the oxide layer, and the proportion of surface cracks of the cured meat based on these data.

[0088] S200: Classify the quality grade of bacon, determine the current quality grade of bacon based on key data, and output it.

[0089] In this embodiment, the quality level of bacon is divided into different levels, and the current bacon quality level is determined based on key data and output. The specific process is as follows:

[0090] S201: defining characteristic quantities, and setting a first threshold, a second threshold, a third threshold, and a characteristic value; wherein the characteristic quantities include nitrite content, oxide layer thickness, and surface crack ratio;

[0091] S202: Obtaining a first threshold value based on the nitrite content, obtaining a second threshold value based on the oxide layer thickness, obtaining a third threshold value based on the surface crack ratio, and calculating a characteristic value;

[0092] S203: Classify the bacon quality grades and determine the current bacon quality grade according to the characteristic values.

[0093] Divide the first-level judgment value and the second-level judgment value;

[0094] When the characteristic value is less than or equal to the first-level judgment value, the current bacon quality level is output as first-level;

[0095] When the characteristic value is greater than the first-level judgment value and less than the second-level judgment value, the current bacon quality grade is output as level two;

[0096] When the characteristic value is greater than or equal to the second-level judgment value, the current bacon quality level is output as level three;.

[0097] In the above process, the characteristic quantities include nitrite content, oxide layer thickness, and surface crack ratio; among which:

[0098] Nitrite content This refers to the concentration of nitrite in bacon, usually measured in milligrams per kilogram (mg / kg). Nitrite content is an important indicator of bacon safety, as excessive nitrite levels may be harmful to human health.

[0099] Oxide layer thickness (D ox ) refers to the average thickness of the oxide layer formed on the surface of bacon due to oxidation reactions, usually measured in microns (μm). The thickness of the oxide layer reflects the degree of oxidation in the bacon. An excessively thick oxide layer may result in a poor taste and color.

[0100] Surface crack ratio (P crack Surface crack coverage refers to the ratio of the surface crack area of bacon to the total surface area of the bacon, expressed as a percentage. This percentage reflects the degree of physical damage sustained by the bacon during processing, storage, or transportation. Excessive cracks may affect the appearance and shelf life of the bacon.

[0101] Set the first threshold T1 to determine whether the nitrite content exceeds the standard. According to the national food safety standards and relevant industry standards, set the upper limit value of the nitrite content as the first threshold. For example, the state stipulates that the nitrite residue in bacon shall not exceed 30 mg / kg, so T1 = 30 mg / kg.

[0102] The second threshold T2 is used to determine whether the thickness of the oxide layer is too large. According to the quality requirements of bacon and the acceptance level of consumers, set the upper limit value of the oxide layer thickness as the second threshold. For example, when the thickness of the oxide layer exceeds 50 μm, the taste and color of bacon will deteriorate significantly, so T2 = 50 μm.

[0103] The third threshold T3 is used to determine whether the proportion of surface cracks is too high. According to the appearance requirements of bacon and the purchase意愿 of consumers, set the upper limit value of the proportion of surface cracks as the third threshold. For example, when the proportion of surface cracks exceeds 10%, the acceptance of bacon by consumers will be significantly reduced, so T3 = 10%.

[0104] Definition of eigenvalue: Define a comprehensive eigenvalue (F) to comprehensively reflect the quality status of bacon. This eigenvalue can be calculated based on the nitrite content, oxide layer thickness, and proportion of surface cracks.

[0105] From the pre-set threshold library, obtain the corresponding first threshold T1, second threshold T2, and third threshold T3 according to the currently detected type of bacon.

[0106] Eigenvalue calculation: Use the method of weighted summation to calculate the comprehensive eigenvalue F. The formula is as follows:

[0107]

[0108] Where, w1, w2, and w3 are the weight coefficients of the nitrite content, oxide layer thickness, and proportion of surface cracks respectively, and w1 + w2 + w3 = 1.

[0109] According to the range of the comprehensive eigenvalue F, divide the quality grade of bacon into the following four grades:

[0110] First-class bacon: F ≤ 0.3. At this time, the nitrite content, oxide layer thickness, and proportion of surface cracks of the bacon are all at a low level, meeting the standards of high-quality bacon.

[0111] Second-class bacon: 0.3 < F ≤ 0.6. The bacon is slightly insufficient in some indicators, but still within the acceptable range, and the overall quality is good.

[0112] Third-class bacon: 0.6 < F ≤ 1.0. There are certain problems such as oxidation, cracks or the nitrite content approaching the upper limit in the bacon, but it does not affect the food safety, and the quality is average.

[0113] Unqualified bacon: F > 1.0. The nitrite content of the bacon exceeds the standard, the oxidation is serious, or there are too many surface cracks, and there are serious quality problems and it cannot enter the market for sale.

[0114] Quality grade judgment: Compare the calculated comprehensive characteristic value F with the above quality grade division rules to determine the quality grade to which the current bacon belongs.

[0115] Example: Suppose the nitrite content of a certain bacon Oxidation layer thickness D ox = 30μm, the proportion of surface cracks P crack = 5%, weight coefficients w1 = 0.5, w2 = 0.3, w3 = 0.2, the first threshold T1 = 30 mg / kg, the second threshold T2 = 50μm, the third threshold T3 = 10%.

[0116] Calculate the comprehensive characteristic value F:

[0117] F = 0.5×20 / 30 + 0.3×30 / 50 + 0.2×5 / 10 ≈ 0.33 + 0.18 + 0.1 = 0.61.

[0118] According to the third-level bacon: 0.6 < F ≤ 1.0. Then a certain bacon has problems such as a certain degree of oxidation, cracks, or the nitrite content approaching the upper limit, but it does not affect the food safety and the quality is average.

[0119] S300: Divide the quality stability grade of the bacon, predict the quality stability grade of the current bacon according to the key data, and output it.

[0120] In this embodiment, divide the quality stability grade of the bacon, predict the quality stability grade of the current bacon according to the key data, and output it. The specific process is as follows:

[0121] S301: Define the short-term stability characteristics and obtain the short-term stability grade of the current bacon according to the key data;

[0122] S302: Define the long-term stability characteristics and obtain the long-term stability grade of the current bacon according to the key data;

[0123] S303: Obtain the short-term stability grade and the long-term stability grade of the current bacon respectively, and output the quality stability grade of the bacon.

[0124] In the above process: Define the short-term stability characteristics, including:

[0125] The change rate of nitrite content The nitrite content of bacon is tested multiple times over a short period of time. The difference between the two consecutive test results and the ratio of the previous test result are calculated, and the average is taken as the rate of change of nitrite content. This characteristic reflects the fluctuation of nitrite content in bacon over a short period of time. The smaller the rate of change, the more stable the nitrite content in the bacon over a short period of time.

[0126] Oxide layer thickness growth rate (V ox ) : Regularly measure the thickness of the oxide layer on the surface of bacon over a short period of time. Calculate the ratio of the difference between two consecutive measurements to the time interval between measurements to determine the growth rate of the oxide layer thickness. The lower the growth rate, the less change in the degree of oxidation of the bacon over a short period of time, and the more stable the quality.

[0127] Surface crack growth rate (V crack ) Using image processing technology, we analyze images of the bacon surface taken over a short period of time and calculate the surface crack growth rate as the ratio of the increase in surface crack area between two consecutive tests to the time interval between tests. The slower the growth rate, the less physical damage the bacon has sustained over a short period of time, and the more stable its quality.

[0128] Set a corresponding threshold range for each short-term stability feature, and divide the short-term stability level of bacon into three levels: A, B, and C. For example:

[0129] A-level: V ox ≤2μm / day, V crack ≤0.5% / day.

[0130] B-level: 2μm / day <V ox ≤5μm / day, 0.5% / day <V crack ≤1% / day.

[0131] C-level: V ox >5μm / day, V crack >1% / day.

[0132] Obtaining the current short-term stability grade of bacon: Based on the calculation method and grade classification criteria for the above-mentioned short-term stability characteristics, the key data of the current bacon is processed and analyzed to determine the grade of the current bacon for each short-term stability characteristic. Then, taking into account the grade of each short-term stability characteristic, the short-term stability grade of the current bacon is determined according to certain rules (such as taking the average of the grades of each characteristic or using a weighted average method). For example, if the current bacon is graded A in terms of the rate of change of nitrite content, graded B in terms of the growth rate of oxide layer thickness, and graded A in terms of the surface crack propagation rate, the short-term stability grade is calculated using the average method as (A+B+A) / 3 = Grade B.

[0133] Define long-term stable characteristics, including:

[0134] Long-term fluctuation range of nitrite content The nitrite content in bacon was continuously monitored over a long period of time, and the difference between the maximum and minimum values was calculated as the long-term fluctuation range of nitrite content. The smaller the fluctuation range, the more stable the nitrite content in the bacon during long-term storage.

[0135] Maximum oxide layer thickness (D ox,max ) : Records the maximum thickness of the oxide layer during long-term storage. This value reflects the maximum possible degree of oxidation of the bacon over a long period of time. The smaller the maximum oxide layer thickness, the better the degree of oxidation is controlled over a long period of time, and the more stable the quality of the bacon.

[0136] The total surface crack area ratio (A crack During long-term storage, regularly acquire surface images of the bacon and calculate the ratio of the sum of all crack areas to the total surface area of the bacon. This ratio is used as the total surface crack area ratio. A smaller ratio indicates less physical damage to the bacon over time and more stable quality.

[0137] Long-term stability grading standards: Based on the market sales cycle, shelf life requirements, and consumers' expectations for long-term quality stability of bacon, corresponding threshold ranges are set for each long-term stability characteristic, and the long-term stability grades of bacon are divided into three grades: A, B, and C. For example:

[0138] Grade A: D ox,max ≤80μm, A crack ≤15%.

[0139] Class B: 80μm <D ox,max ≤120μm, 15% crack ≤25%.

[0140] Class C: D ox,max >120μm, A crack >25%.

[0141] Determining the Long-Term Stability Grade of the Current Bacon: Key data from the long-term storage process is processed and analyzed according to the calculation methods and grading standards for long-term stability characteristics. The grade of each long-term stability characteristic is determined. The long-term stability grade of the current bacon is determined using a similar approach to determining the short-term stability grade, such as an average or weighted average method, taking into account the grade of each long-term stability characteristic.

[0142] ​After obtaining the current short-term and long-term stability grades of the bacon, these two grades are integrated and comprehensively judged based on quality control requirements and the characteristics of the bacon product. For example, weights can be set for the short-term and long-term stability grades, and a comprehensive stability index can be obtained through weighted summation. The final quality stability grade is then divided according to the range of the comprehensive stability index. Assuming the short-term stability grade has a weight of 0.4 and the long-term stability grade has a weight of 0.6, if the short-term stability grade is B (quantifiable as 2 points) and the long-term stability grade is A (quantifiable as 1 point), the comprehensive stability index is 0.4×2+0.6×1=1.4.

[0143] Final quality stability grade classification: Based on the range of the comprehensive stability index, the quality stability grade of bacon is divided into four grades: excellent, good, medium and poor. For example:

[0144] Excellent: Comprehensive stability index ≤1.5.

[0145] Good: 1.5<comprehensive stability index≤2.5.

[0146] Medium: 2.5<comprehensive stability index≤3.5.

[0147] Poor: Comprehensive stability index>3.5.

[0148] The finalized bacon quality stability grade is displayed prominently, such as prominently marking the stability grade on the front page of the test report. A stability grade label is added to each piece of bacon in the company's quality traceability system, allowing production, sales, and regulatory personnel to quickly understand the quality stability of the bacon. Furthermore, the stability grade information is stored in association with other bacon quality data, providing data support for the company's quality improvement and market decision-making.

[0149] S400: Obtain the bacon quality grade and the bacon quality stability grade respectively, and integrate and output the test data.

[0150] In this embodiment, the quality grade and stability grade of bacon are obtained respectively, and the test data are integrated and output. The specific process is as follows:

[0151] S401: Establish a bacon testing database and input quality characteristics and recommended descriptions;

[0152] S402: Obtain the bacon quality grade and the bacon quality stability grade respectively, compare the quality characteristics, and output the comparison result;

[0153] S403: According to the comparison results of the bacon quality grade and the bacon quality stability grade, the recommended description is integrated and the test data is output.

[0154] In the above process, several data tables are designed to store information related to bacon testing. For example, a "Bacon Basic Information Table" is created, containing fields such as bacon batch number, production date, and origin to uniquely identify each batch or piece of bacon. A "Quality Characteristics Table" is created to store various characteristic data related to bacon quality, such as nitrite content, oxide layer thickness, and surface crack percentage. A "Quality Grade Table" and a "Quality Stability Grade Table" are created to record the quality grade and quality stability grade of bacon, respectively. A "Recommended Description Table" is created to store recommended descriptions for different quality grades and quality stability grades.

[0155] Define appropriate data types for each field to ensure accurate data storage and efficient querying. For example, the batch number can be defined as a string, the nitrite content as a floating-point number, and the production date as a date and time. Also, set constraints such as field length and precision to prevent invalid data from being entered.

[0156] Based on the size of your business, the amount of data you need, and your data processing requirements, choose a suitable database management system, such as MySQL, Oracle, or SQL Server. These database management systems offer powerful data storage, management, and query capabilities, and can meet the storage and management requirements for bacon testing data.

[0157] From the acquired data on bacon quality grades and bacon quality stability grades, we extracted information related to quality characteristics and organized and pre-processed it. For example, we converted data on nitrite content, oxide layer thickness, and surface crack percentage, and processed outliers to ensure data accuracy and consistency.

[0158] According to the quality grade and quality stability grade of bacon, formulate corresponding recommended descriptions. Recommended descriptions should be targeted and practical, and be able to provide valuable reference information for consumers, producers and sellers. For example, for bacon with a first-level quality grade and an excellent quality stability grade, the recommended description can be "This bacon is of superior quality, all indicators meet high standards, and the quality is stable during storage and transportation. It is suitable as a high-end gift or a long-term household food reserve"; for bacon with a third-level quality grade and a medium quality stability grade, the recommended description can be "Some indicators of this bacon are slightly inferior to high-quality products, but are still within an acceptable range. It is recommended to be consumed in the short term, and attention should be paid to storage conditions."

[0159] Enter the organized quality characteristic data and the developed recommended descriptive data into the bacon testing database. This can be done manually through the database management system's graphical interface, or a data import tool can be developed to batch import pre-organized Excel or CSV format data files into the database to improve data entry efficiency.

[0160] Based on the bacon's batch number or other unique identifier, query the current bacon's quality grade and quality stability grade from the "Quality Grade Table" and "Quality Stability Grade Table" in the bacon testing database. Verify the retrieved quality grade and quality stability grade data to ensure accuracy and completeness. Check for null values and compliance with pre-set grading standards. If any data anomalies are found, promptly investigate and address them, such as re-querying the data or correcting erroneous data in the database.

[0161] Extract quality characteristic data related to the current bacon quality grade and quality stability grade from the "Quality Characteristics Table", such as nitrite content, oxide layer thickness, surface crack ratio, etc.

[0162] Based on the definitions of bacon quality grades and quality stability grades, corresponding quality characteristic comparison rules are developed. For example, for quality grades, corresponding quality characteristic threshold ranges can be set; for quality stability grades, corresponding quality characteristic variation ranges can be set. The current bacon quality characteristic data is compared with these threshold ranges and variation ranges.

[0163] Based on the comparison rules, quality characteristic comparison results are generated. These comparison results can be presented in tables, charts, or textual descriptions. For example, a table can be used to compare the quality characteristic data of the current bacon with the threshold ranges for each grade, with characteristic items exceeding the threshold range marked with different colors or symbols. A chart can also be used to intuitively display the changing trends of the quality characteristic data and compare them with the typical changing trends corresponding to different quality stability grades.

[0164] The generated quality feature comparison results are displayed on the inspection system's user interface. This can be done through paging or pop-up prompts to facilitate detailed information viewing. When displaying the results, you can also add necessary explanations and annotations to help users understand the meaning of the comparison results.

[0165] Based on the comparison results of the bacon quality grade and quality stability grade, the system applies preset logical rules to determine the current quality status of the bacon. For example, if the quality grade is level 1 and the quality stability grade is excellent, the bacon quality is very good. If the quality grade is level 3 but the quality stability grade is poor, the bacon, while some indicators are currently acceptable, faces a high risk of quality changes in the future.

[0166] According to the result of logical judgment, the corresponding recommendation description is matched from the "recommendation description table".

[0167] All test data related to the current bacon are collected from the bacon test database, including basic bacon information, quality characteristic data, quality grade, quality stability grade, quality characteristic comparison results and integrated recommended descriptions.

[0168] Format the collected test data to ensure a uniform format and structure. For example, convert different types of data into standard JSON or XML formats to facilitate data transmission and storage. Also, perform necessary encoding and encryption on the data to ensure security and confidentiality.

[0169] Based on user needs and usage scenarios, select the appropriate output channel to output the integrated test data. For example, test data can be displayed as a report on the test system's user interface. Users can click the "Generate Report" button to obtain a report in PDF or HTML format containing all test information. Test data can also be uploaded to the company's quality traceability system for sharing and querying across internal departments. Key test information can also be sent to relevant personnel such as production managers, quality inspectors, or customers via SMS or email.

[0170] In the present invention, multimodal bacon detection data is first obtained, an identifier is assigned to the detection object, and key data is associated; then the bacon quality grades are divided, and the current bacon quality grade is judged according to the key data and output; then the bacon quality stability grades are divided, and the current bacon quality stability grade is predicted according to the key data and output; finally, the bacon quality grade and the bacon quality stability grade are obtained respectively, and the detection data are integrated and output; by assigning an identifier to the bacon and associating key data, the quality grade of each piece of bacon is judged based on the identifier and key data, and the quality stability grade is predicted, so as to prevent the characteristics of the bacon from being confused, thereby improving the detection accuracy.

[0171] Corresponding to the aforementioned embodiment of the method for detecting the quality of bacon production based on feature analysis, the present application also provides an embodiment of a system for detecting the quality of bacon production based on feature analysis.

[0172] Figure 6 This is a block diagram of a bacon production quality detection system based on feature analysis according to an exemplary embodiment. Figure 6 The system may include: a multimodal data processing module 501, a quality level classification module 502, a quality stability level classification module 503, and a detection data integration module 504; wherein:

[0173] The multimodal data processing module 501 is used to obtain multimodal bacon detection data, assign identifiers to detection objects, and associate key data;

[0174] The quality grade classification module 502 is used to classify the quality grade of bacon, determine the current quality grade of bacon based on key data, and output it;

[0175] The quality stability level classification module 503 is used to classify the quality stability level of bacon, predict the current quality stability level of bacon based on key data, and output the result.

[0176] The detection data integration module 504 is used to respectively obtain the bacon quality grade and the bacon quality stability grade, and integrate and output the detection data.

[0177] In this embodiment, the multimodal data processing module 501 obtains multimodal bacon detection data, assigns an identifier to the detection object, and associates key data; the quality grade division module 502 divides the bacon quality grade, judges the current bacon quality grade according to the key data, and outputs it; the quality stability grade division module 503 divides the bacon quality stability grade, predicts the current bacon quality stability grade according to the key data, and outputs it; the detection data integration module 504 respectively obtains the bacon quality grade and the bacon quality stability grade, integrates and outputs the detection data; by assigning an identifier to the bacon and associating key data, the quality grade is judged for the identifier and key data of each piece of bacon, and the quality stability grade is predicted, so as to prevent the characteristics of the bacon from being confused, thereby improving the detection accuracy.

[0178] Regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0179] For the system embodiment, since it basically corresponds to the method embodiment, the relevant parts can be referred to the partial description of the method embodiment. The device embodiment described above is only schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this application. A person of ordinary skill in the art can understand and implement it without paying any creative work.

[0180] Accordingly, the present application also provides an electronic device, comprising: one or more processors; a memory for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the above-mentioned method for detecting the quality of bacon production based on feature analysis. Figure 7As shown in FIG, a hardware structure diagram of a bacon production quality detection system based on feature analysis provided by an embodiment of the present invention is provided, in which any device with data processing capability is provided. Figure 7 In addition to the processor, memory, and network interface shown, any device with data processing capabilities in which the apparatus in the embodiment is located may also include other hardware, generally based on the actual functions of the device with data processing capabilities, which will not be described in detail.

[0181] Accordingly, the present application also provides a computer-readable storage medium having computer instructions stored thereon, which, when executed by a processor, implement the above-mentioned method for detecting the quality of bacon production based on feature analysis. The computer-readable storage medium may be an internal storage unit of any device with data processing capabilities described in any of the aforementioned embodiments, such as a hard disk or memory. The computer-readable storage medium may also be an external storage device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), an SD card, a flash card (Flash Card), etc. equipped on the device. Furthermore, the computer-readable storage medium may also include both an internal storage unit and an external storage device of any device with data processing capabilities. The computer-readable storage medium is used to store the computer program and other programs and data required by any device with data processing capabilities, and may also be used to temporarily store data that has been output or is to be output.

[0182] Those skilled in the art will readily conceive of other embodiments of the present application after considering the specification and practicing the contents disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of this application and include common knowledge or customary techniques in the art that are not disclosed in this application.

[0183] It will be understood that the present application is not limited to the exact construction that has been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof.

Claims

1. A method for detecting the quality of bacon production based on feature analysis, characterized in that: The steps include: Obtain multimodal bacon inspection data, assign identifiers to inspection objects, and associate key data; Classify bacon quality grades, determine the current bacon quality grade based on key data, and output it; Classify the quality stability level of bacon, predict the current quality stability level of bacon based on key data, and output it; Obtain the bacon quality grade and bacon quality stability grade respectively, and integrate and output the test data.

2. The method for detecting the quality of bacon production based on characteristic analysis according to claim 1, wherein: In the steps of obtaining multimodal bacon inspection data, assigning identifiers to inspection objects, and associating key data: Obtaining multimodal detection data of bacon, wherein the multimodal detection data includes hyperspectral imaging, polarization imaging, and three-dimensional topography measurement data; Divide the current bacon into multiple surface areas; Define abnormal data in hyperspectral imaging, polarization imaging, and 3D topography measurement data as key data, and associate the key data with surface areas.

3. The method for detecting the quality of bacon production based on characteristic analysis according to claim 2, wherein: Before the step of obtaining multimodal detection data of bacon: The current location data of the bacon is obtained, and a unique detection identifier is assigned to the current bacon according to the current location data.

4. The method for detecting the quality of bacon production based on characteristic analysis according to claim 1, wherein: In the step of classifying bacon quality grades, judging the current bacon quality grade based on key data, and outputting it: Defining a feature quantity, and setting a first threshold, a second threshold, a third threshold, and a feature value; The characteristic quantities include nitrite content, oxide layer thickness, and surface crack ratio; Obtain a first threshold value based on the nitrite content, obtain a second threshold value based on the oxide layer thickness, obtain a third threshold value based on the surface crack ratio, and calculate a characteristic value; Divide the quality level of bacon and judge the current quality level of bacon based on the characteristic value.

5. The method for detecting the quality of bacon production based on characteristic analysis according to claim 4, wherein: In the step of classifying the quality grade of bacon and determining the current quality grade of bacon based on the characteristic value: Divide the first-level judgment value and the second-level judgment value; When the characteristic value is less than or equal to the first-level judgment value, the current bacon quality level is output as first-level; When the characteristic value is greater than the first-level judgment value and less than the second-level judgment value, the current bacon quality grade is output as level two; When the characteristic value is greater than or equal to the second-level judgment value, the current bacon quality level is output as level three.

6. The method for detecting the quality of bacon production based on characteristic analysis according to claim 1, wherein: In the steps of classifying the bacon quality stability level, predicting the current bacon quality stability level based on key data, and outputting the result: Define short-term stability characteristics and obtain the current short-term stability level of bacon based on key data; Define long-term stability characteristics and obtain the long-term stability level of the current bacon based on key data.

7. The method for detecting the quality of bacon production based on characteristic analysis according to claim 6, wherein: After defining the long-term stability characteristics and obtaining the long-term stability level of the current bacon based on key data: Get the short-term stability level and long-term stability level of the current bacon respectively, and output the bacon quality stability level.

8. The method for detecting the quality of bacon production based on characteristic analysis according to claim 1, wherein: In the steps of respectively obtaining the bacon quality grade and the bacon quality stability grade and integrating and outputting the test data: Establish a bacon testing database and enter quality characteristics and recommended descriptions; Obtain the bacon quality grade and bacon quality stability grade respectively, compare the quality characteristics, and output the comparison results.

9. The method for detecting the quality of bacon production based on characteristic analysis according to claim 8, wherein: After obtaining the bacon quality grade and bacon quality stability grade, comparing the quality characteristics, and outputting the comparison results: Based on the comparison results of the bacon quality grade and the bacon quality stability grade, the recommended description is integrated and the test data is output.

10. A bacon production quality detection system based on feature analysis, applied to the bacon production quality detection method based on feature analysis as claimed in claim 1, characterized in that: It includes multimodal data processing module, quality grade classification module, quality stability grade classification module, and detection data integration module; among which: The multimodal data processing module is used to obtain multimodal bacon detection data, assign identifiers to detection objects, and associate key data; The quality grade classification module is used to classify the quality grade of bacon, determine the current quality grade of bacon based on key data, and output it; The quality stability grade classification module is used to classify the quality stability grade of bacon, predict the current quality stability grade of bacon based on key data, and output it; The detection data integration module is used to respectively obtain the bacon quality grade and the bacon quality stability grade, and integrate and output the detection data.

Images