System and method for identifying and tracing producing areas of agricultural products based on characteristic fingerprints

Abstract

The invention relates to the technical field of agricultural product producing area identification and traceability, in particular to an agricultural product producing area identification and traceability system and method based on feature fingerprints, and the method comprises the steps: collecting agricultural product samples to obtain a target sample set; performing dominant feature fingerprint marking on the target sample set according to dominant features of the agricultural products, and performing one-class division on the target sample set according to a dominant marking result to obtain a plurality of one-class sample clusters; performing recessive feature fingerprint marking on the target sample set according to recessive features of the agricultural products, and performing second-class division on the target sample set according to a recessive marking result to obtain a plurality of second-class sample clusters; comparing the first-class division result with the second-class division result to determine to open a successive verification mode or an independent verification mode; and based on the successive verification mode, obtaining each verification result, and determining whether to output an actual origin tracing result according to each verification result.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural product origin identification and tracing technology, and in particular to an agricultural product origin identification and tracing system and method based on feature fingerprints. Background Art

[0002] At present, when tracing the origin of agricultural products based on their characteristics, the classification of their origin is inaccurate due to the one-sided description of their characteristics, which affects the accuracy of their origin traceability. In addition, when tracing the origin of agricultural products, the traceability process without classification and accuracy judgment may lead to erroneous traceability results. Agricultural products may have similar characteristics, and agricultural products from different origins may be difficult to distinguish. Direct traceability without classification may lead to agricultural products from different origins being misjudged as having the same source.

[0003] Chinese patent application publication number CN113406245A discloses a soybean origin traceability identification method based on the combination of MALDI□TOF / TOF and I RMS technology. Through the new soft ionization biomass spectrometry technology MALDI□TOF / TOF, combined with stable isotope ratio analysis technology, a soybean origin traceability identification method based on the fusion of MALDI□TOF / TOF and stable isotope content analysis is established. By referring to the high-resolution mass spectrometry data of triglyceride compounds in the soybean oil sample to be tested and the stable isotope ratio of water-soluble protein in the soybean powder sample, the two data are fused and introduced into the soybean origin traceability identification model to predict the origin of the soybean to be tested.

[0004] This shows that the current agricultural product origin traceability technology cannot guarantee the accuracy of traceability. Summary of the invention

[0005] To this end, the purpose of the present invention is to provide a system and method for identifying and tracing the origin of agricultural products based on feature fingerprints, so as to overcome the problem that the current agricultural product origin tracing technology cannot guarantee the accuracy of tracing.

[0006] To achieve the above object, the present invention provides, on one hand, a method for identifying and tracing the origin of agricultural products based on feature fingerprints, comprising:

[0007] Collecting target agricultural product samples with a preset initial sample capacity to obtain a target sample set;

[0008] According to the dominant characteristics of the target agricultural product, the target sample set is marked with a dominant characteristic fingerprint to obtain a dominant marking result, and the target sample set is divided into one category according to the dominant marking result to obtain a plurality of one-category sample clusters;

[0009] According to the latent characteristics of the target agricultural product, the target sample set is marked with latent characteristic fingerprints to obtain latent marking results, and the target sample set is divided into two categories according to the latent marking results to obtain a number of two-category sample clusters;

[0010] Compare the first-category classification result and the second-category classification result to determine whether to start the successive verification mode or the individual verification mode;

[0011] Based on the successive verification mode, obtaining each verification result, and determining whether to output the actual origin tracing result according to each verification result;

[0012] Based on the separate verification mode, the first category division results and the second category division results are respectively verified separately to obtain the first category verification results and the second category verification results, and it is determined whether to output the actual origin traceability results based on the first category verification results and the second category verification results.

[0013] Furthermore, the process of performing explicit feature fingerprint marking on the target sample set according to the explicit features of the target agricultural product to obtain an explicit marking result, and classifying the target sample set into one category according to the explicit marking result to obtain a plurality of one-category sample clusters includes:

[0014] Determine each explicit feature vector according to the explicit features of the target agricultural product, and perform explicit feature fingerprint marking on each target sample point according to each explicit feature vector to determine the explicit identifier of each target sample point;

[0015] Based on the explicit identifier, each target sample point is classified into one category according to the initial explicit classification standard to obtain each sample cluster corresponding to different origin types;

[0016] The target sample set includes a number of target sample points; and the sample cluster includes a number of target sample points with explicit identifiers.

[0017] Furthermore, the process of performing implicit feature fingerprint marking on the target sample set according to the implicit features of the target agricultural product to obtain an implicit marking result, and dividing the target sample set into two categories according to the implicit marking result to obtain a plurality of two-category sample clusters includes:

[0018] Determine a latent feature vector according to the latent feature of the target agricultural product, and perform invisible feature fingerprint marking on each target sample point according to the latent feature vector to determine the latent identifier of each target sample point;

[0019] Based on the implicit identifier, each target sample point is divided into two categories according to the initial implicit classification standard to obtain two-category sample clusters corresponding to different origin types;

[0020] The second type of sample clusters include a number of target sample points with implicit identifiers.

[0021] Furthermore, the process of comparing the first-category classification result and the second-category classification result to determine whether to start the successive verification mode or the individual verification mode includes:

[0022] Identify a class of partitions to determine the number of class of partitions and the capacity of each class of sample clusters;

[0023] Identify the two-class partitions to determine the number of two-class partitions and the capacity of each two-class sample cluster;

[0024] Perform a comparison based on the number of the first-category division and the number of the second-category division to determine whether to start a supplementary comparison mode;

[0025] Based on starting the supplementary comparison mode, performing a secondary comparison according to the capacity of each type one sample cluster and the capacity of each type two sample cluster, and determining to start the successive verification mode or the separate verification mode according to the secondary comparison result;

[0026] The one-category division result includes: the number of the one-category divisions and the capacity of each one-category sample cluster; the two-category division result includes: the number of the two-category divisions and the capacity of each two-category sample cluster.

[0027] Furthermore, the process of performing secondary comparison according to the capacity of each first-category sample cluster and the capacity of each second-category sample cluster includes:

[0028] Obtain the maximum sample capacity and the minimum sample capacity of each class of sample clusters;

[0029] Obtain the maximum two-category sample capacity and the minimum two-category sample capacity in each two-category sample cluster capacity;

[0030] Comparing the maximum sample size of the first category with the maximum sample size of the second category to obtain a maximum comparison result;

[0031] Comparing the minimum sample size of the first category with the minimum sample size of the second category to obtain a minimum comparison result;

[0032] The number of items in the maximum comparison result and the minimum comparison result that meet a single determination condition is determined.

[0033] Furthermore, the process of determining whether to output the actual origin tracing result according to each verification result includes:

[0034] Based on the successive verification mode, adjusting the initial sample capacity according to a one-time verification standard to obtain a verification sample capacity;

[0035] Performing a one-time verification division based on the verification sample capacity and the dominant characteristics and the invisible characteristics of the target agricultural product to obtain a number of one-time verification type one sample clusters and a number of one-time verification type two sample clusters;

[0036] Determine the number of explicit divisions for one-time verification and the number of implicit divisions for one-time verification according to each one-time verification type one sample cluster and each one-time verification type two sample cluster;

[0037] A verification result is determined according to the number of explicit divisions of the verification and the number of implicit divisions of the verification.

[0038] Furthermore, the process of determining whether to output the actual origin tracing result according to each verification result also includes:

[0039] Based on the successive verification mode, adjusting the target classification standard according to the secondary verification standard to obtain the actual classification standard;

[0040] Performing secondary verification division on the initial sample capacity to obtain a number of secondary verification type 1 sample clusters and a number of secondary verification type 2 sample clusters;

[0041] Determine the number of explicit divisions of secondary verification and the number of implicit divisions of secondary verification according to each secondary verification type 1 sample cluster and each secondary verification type 2 sample cluster;

[0042] Determine a secondary verification result according to the number of secondary verification explicit divisions and the number of secondary verification implicit divisions;

[0043] Determine whether the first verification result is consistent with the second verification result, and output the actual origin tracing result based on the consistency of the verification results.

[0044] Furthermore, the process of determining a verification result according to the number of explicit divisions of the verification and the number of implicit divisions of the verification includes:

[0045] Determining whether the primary verification result is consistent with the initial result or inconsistent with the initial result according to the second difference absolute value combined with a preset difference evaluation value;

[0046] Based on the absolute value of the second difference being greater than or equal to the difference evaluation value, determining that the first verification result is consistent with the initial result;

[0047] Based on the absolute value of the second difference being smaller than the difference evaluation value, determining that the first verification result is inconsistent with the initial result;

[0048] The second absolute value of the difference is the absolute value of the difference between the number of explicit divisions in the one-time verification and the number of implicit divisions in the one-time verification.

[0049] Furthermore, the process of determining the secondary verification result according to the number of secondary verification explicit divisions and the number of secondary verification implicit divisions includes:

[0050] Determining whether the secondary verification result is consistent with the initial result or inconsistent with the initial result according to the third difference absolute value combined with the difference evaluation value;

[0051] Based on the third difference absolute value being greater than or equal to the difference evaluation value, determining that the secondary verification result is consistent with the initial result;

[0052] Based on the absolute value of the third difference being smaller than the difference evaluation value, determining that the secondary verification result is inconsistent with the initial result;

[0053] The third difference absolute value is the absolute value of the difference between the number of explicit divisions of the secondary verification and the number of implicit divisions of the secondary verification.

[0054] Another aspect of the present invention provides an agricultural product origin identification and tracing system based on feature fingerprints, comprising:

[0055] A sample collection module, which is used to collect target agricultural product samples according to a preset initial sample capacity to obtain a target sample set;

[0056] An explicit feature analysis module, which is used to perform explicit feature analysis on the target sample set to obtain an explicit feature fingerprint;

[0057] A latent feature analysis module, which is used to perform latent feature analysis on the target sample set to obtain a latent feature fingerprint;

[0058] A partitioning and clustering module, which is used to perform one-category partitioning and two-category partitioning on samples according to each characteristic fingerprint, so as to obtain a number of one-category sample clusters and a number of two-category sample clusters;

[0059] A verification mode selection module, which is used to compare the first-class division result and the second-class division result to determine whether to adopt a successive verification mode or a separate verification mode;

[0060] A successive verification module, which is used to perform multiple divisions through multiple verifications to obtain each verification result, and decide whether to output the actual origin traceability result according to each verification result;

[0061] A separate verification module is used to independently verify the first-category classification results and the second-category classification results respectively, and combine the two types of verification results to determine whether to output the actual origin traceability results.

[0062] Compared with the prior art, the beneficial effect of the present invention lies in that, by combining explicit physical characteristics and implicit chemical characteristics, the characteristics of soybeans can be described more comprehensively, thereby improving the accuracy of origin identification, using explicit characteristics and implicit characteristics to perform one-category and two-category classification respectively, and verifying the results through successive verification or separate verification mode, thereby enhancing the reliability of the classification results, and through a multi-level verification process, reducing misjudgment due to a single feature or a single analysis method, thereby improving the accuracy of the overall traceability, and by quantifying the physical and chemical characteristics of soybeans, making origin identification more objective, reducing the uncertainty caused by subjective judgment, and accurate origin traceability results can help agricultural product quality control, ensure product quality and safety, and improve the accuracy and efficiency of soybean origin identification.

[0063] By comprehensively describing soybean samples, the accuracy of classification is improved. The explicit identifier, as a characteristic fingerprint, can uniquely identify the explicit characteristics of each target sample point, which is convenient for subsequent classification and traceability. The initial explicit classification standard based on the explicit identifier can quickly classify soybean samples with similar characteristics into one category to improve classification efficiency. The explicit characteristics are closely related to the growth environment of soybeans. Classification can reflect the adaptability of soybeans to the environment and help understand the characteristics of different origins. Through the explicit identifier, the source of soybean samples can be tracked, the traceability of the product can be enhanced, and the explicit characteristics of soybeans can be effectively used for classification and traceability, which improves the accuracy and efficiency of classification and traceability.

[0064] By analyzing the latent characteristics of soybean mineral content, we can have a deeper understanding of the intrinsic quality of soybean and the influence of the growth environment, thereby improving the depth and accuracy of classification. Combining explicit and implicit characteristics, soybean samples can be classified from multiple dimensions to enhance the comprehensiveness and reliability of classification. As a concentrated representation of mineral content, the implicit identifier can uniquely identify the mineral composition of each target sample point, facilitating accurate classification and traceability. Mineral content is closely related to the growth environment of soybean. Through implicit characteristic classification, we can analyze the adaptability of soybean to specific soil and climatic conditions, and provide guidance for agricultural production. Implicit characteristic fingerprint markers can help to more accurately track the origin of soybeans, especially when the explicit characteristics are similar, the implicit characteristics can provide additional distinguishing information.

[0065] By comparing the results of the first and second category classifications, it is possible to effectively decide whether to adopt a successive verification mode or a separate verification mode, thereby improving the efficiency of the entire verification process. By comparing according to the number and capacity of sample clusters, verification resources can be better allocated. By supplementing the comparison mode, the inconsistency between the classification results of explicit and implicit characteristics can be identified, so that measures can be taken to improve the consistency and reliability of classification. Through detailed comparative analysis, misjudgment due to single feature classification can be reduced, ensuring that the final traceability results are more accurate. According to the setting of the difference evaluation value and the standard capacity difference, the system can flexibly adapt to different classification requirements and sample characteristics, improve the overall adaptability, and through precise comparison and verification mode selection, the accuracy of soybean origin traceability can be further improved.

[0066] By successively verifying and comparing the results of different verification steps, the accuracy of soybean origin traceability can be significantly improved, and the errors that may be introduced by a single division can be reduced. Multiple verifications ensure the consistency and stability of the classification standards, thereby enhancing the reliability of the overall classification system. By adjusting the classification standards, the classification can be made more detailed and the resolution of the classification can be improved. By comparing the results of the first verification and the second verification, the misjudgment in the classification process can be effectively identified and reduced. By comparing the results of different verification steps, the consistency of the data can be ensured, which is crucial for establishing a reliable traceability system. Comprehensive consideration of the two characteristics can more comprehensively evaluate the samples and improve the comprehensiveness of the classification.

[0067] By reanalyzing and verifying the explicit and implicit characteristics of the samples, the accuracy of the classification results can be ensured and classification errors can be reduced. By individually verifying the explicit and implicit characteristics of each sample cluster, the stability and reliability of the classification results can be verified and the accuracy of traceability can be improved. By checking the stability of the characteristics within the sample cluster, the stability of the classification results can be evaluated, providing a basis for the output of the final traceability results and ensuring the accuracy and reliability of the traceability results. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 This is a flow chart of a method for identifying and tracing the origin of agricultural products based on feature fingerprints according to an embodiment of the present invention;

[0069] Figure 2 This is a comparison flow chart of a method for identifying and tracing the origin of agricultural products based on feature fingerprints in an embodiment of the present invention;

[0070] Figure 3 This is a flow chart of successive verification in a method for identifying and tracing the origin of agricultural products based on characteristic fingerprints in an embodiment of the present invention;

[0071] Figure 4 The system block diagram of the agricultural product origin identification and traceability system based on feature fingerprints according to an embodiment of the present invention. DETAILED DESCRIPTION

[0072] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0073] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0074] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0075] See also Figure 1 As shown, the present invention provides a method for identifying and tracing the origin of agricultural products based on characteristic fingerprints;

[0076] In this embodiment, the target agricultural product is soybean, and other agricultural products may also be selected. When this embodiment identifies and traces the origin of agricultural products based on the characteristic fingerprints of agricultural products, the type of agricultural products is not specifically limited and will not be elaborated here.

[0077] The method includes:

[0078] Step S100, collecting soybean samples with a preset initial sample volume to obtain a target sample set;

[0079] Step S200, performing dominant feature fingerprint marking on the target sample set according to the dominant feature of soybean to obtain dominant marking results, and classifying the target sample set into one category according to the dominant marking results to obtain a plurality of one category sample clusters;

[0080] Step S300, performing implicit feature fingerprint marking on the target sample set according to the implicit feature of soybean to obtain an implicit marking result, and dividing the target sample set into two categories according to the implicit marking result to obtain a plurality of two-category sample clusters;

[0081] Step S400, comparing the first-category classification result and the second-category classification result to determine whether to start the successive verification mode or the individual verification mode;

[0082] Step S500, based on the successive verification mode, obtaining each verification result, and determining whether to output the actual origin tracing result according to each verification result;

[0083] Step S600, based on the separate verification mode, separately verify the first category classification result and the second category classification result to obtain a first category verification result and a second category verification result, and determine whether to output the actual origin traceability result based on the first category verification result and the second category verification result.

[0084] In this embodiment, the dominant feature is the physical feature of soybeans, and the physical features of soybeans, such as shape, size, color and texture, are extracted using image processing technology; the recessive feature is the chemical feature of soybeans, and the chemical features of soybeans, such as protein content, fat content, fatty acid composition, amino acid composition or mineral content, are extracted using chemical analysis technology. In the specific implementation process, the image processing technology can obtain the image data of soybeans through an industrial camera and perform corresponding processing on the image data. The specific processing process includes: segmenting the soybean image into different areas, such as bean grain area and background area, and extracting the physical features of soybeans from the segmented image, for example: using geometric features (such as area, perimeter, circularity, etc.) or shape descriptors (such as Hu moment, Zern moment, etc.) The shape of soybeans is described by using the number of pixels or area of ​​soybeans in the image, the size of soybeans is described by using methods such as color histogram, color moment or color space conversion to describe the color of soybeans, and the texture of soybeans is described by using methods such as gray level co-occurrence matrix, local binary pattern (LBP) or wavelet transform. Chemical analysis technology can analyze the chemical composition of soybeans by using spectral analysis, chromatographic analysis or mass spectrometry. In this embodiment, the image processing technology and the chemical analysis technology are not specifically limited and will not be repeated here.

[0085] Specifically, the embodiments of the present invention can more comprehensively describe the characteristics of soybeans by combining explicit physical characteristics and implicit chemical characteristics, thereby improving the accuracy of origin identification, using explicit characteristics and implicit characteristics to perform one-category and two-category classification respectively, and verifying the results through successive verification or separate verification modes, thereby enhancing the reliability of the classification results. Through a multi-level verification process, misjudgment due to a single feature or a single analysis method is reduced, and the accuracy of the overall traceability is improved. By quantifying the physical and chemical characteristics of soybeans, origin identification is made more objective, and the uncertainty caused by subjective judgment is reduced. Accurate origin traceability results can help agricultural product quality control, ensure product quality and safety, and improve the accuracy and efficiency of soybean origin identification.

[0086] Specifically, the process of performing dominant feature fingerprint marking on the target sample set according to the dominant feature of soybean to obtain dominant marking results, and classifying the target sample set into one category according to the dominant marking results to obtain a plurality of one-category sample clusters in this embodiment includes:

[0087] Step S210, determining each dominant feature vector according to the dominant feature of soybean, and performing a dominant feature fingerprint mark on each target sample point according to each dominant feature vector to determine a dominant identifier of each target sample point;

[0088] Step S220, based on the explicit identifier, classify each target sample point into one category according to the initial explicit classification standard to obtain each sample cluster corresponding to different origin types;

[0089] The target sample set includes a number of target sample points; and the sample cluster includes a number of target sample points with explicit identifiers.

[0090] In this embodiment, each dominant feature vector includes: a shape vector, a size vector, a color vector and a texture vector. For any target sample point, the dominant feature of the target sample point is first identified. The specific identification process includes: 1) For the shape vector: obtain the appearance of the soybean, such as round, elliptical, and kidney-shaped, which is determined by calculating the geometric parameters of the soybean contour during the specific implementation process; 2) For the size vector: obtain the size of the soybean, such as length, width, and thickness, which is quantified by measuring these physical dimensions during the specific implementation process to obtain soybeans of different sizes; 3) For the color vector: refers to the color attribute of the soybean, which can be represented by the coordinates of the color space (such as RGB, HSV values) during the specific implementation process; 4) For the texture vector: reflects the texture and pattern of the soybean surface, and can extract the texture features of the soybean through texture analysis technology (such as grayscale co-occurrence matrix) during the specific implementation process to determine soybeans of different textures;

[0091] The characteristic data of the target sample point is collected, and a comprehensive characteristic fingerprint, i.e., an explicit identifier, is generated by encoding the characteristic data. In this embodiment, the explicit identifier is a concentrated representation of the characteristic of the target sample point, and can uniquely identify the explicit characteristic of the target sample point; wherein, the explicit identifier for any target sample point includes the shape information, size information, color information, and texture information of the target sample point. For example, the explicit identifier corresponding to any target sample point is: [circular, size: 8.2 mm × 6.5 mm × 4.3 mm, HSV: (60°, 80%, 90%), smooth texture], where size: 8.2mm×6.5mm×4.3mm means that the length of the target sample point is 8.2mm, the width is 6.5mm, and the thickness is 4.3mm; HSV: (60°, 80%, 90%) means H (hue): indicates the type of soybean color, S (saturation): indicates the purity of soybean color, high saturation means brighter color, V (brightness): indicates the brightness of soybean color, that is, the corresponding soybean is mature yellow at this time;

[0092] In this embodiment, the initial dominant classification standard is set based on the dominant characteristics of soybeans, and is used to classify target sample points with similar characteristics into the same category. The specific setting process includes: a specific type of shape parameter, a specific range of size parameter, a similarity threshold of color feature, and a classification standard of texture feature. Sample points whose dominant identifiers meet the same classification standard are classified into one category to form a sample cluster. For example, for the shape vector type that is consistent, the size parameter corresponding to the size vector is within the set fluctuation range, the HSV value difference corresponding to the color vector is within the set similarity threshold, and the dominant identifiers with consistent texture features are classified into one category to form sample clusters of one category. Since the dominant characteristics of soybeans are closely related to their growth environment (i.e., origin), the environmental conditions of different origins (such as soil type, climate conditions, etc.) will affect the shape, size, color and texture of soybeans. Therefore, soybeans with similar dominant characteristics come from the same origin. Classification by dominant identifiers is actually to group soybeans with similar environmental adaptability together, thereby forming a sample cluster corresponding to different origin types.

[0093] Specifically, the embodiments of the present invention improve the accuracy of classification by comprehensively describing soybean samples. The explicit identifier, as a feature fingerprint, can uniquely identify the explicit features of each target sample point, which is convenient for subsequent classification and traceability. The initial explicit classification standard based on the explicit identifier can quickly classify soybean samples with similar features into one category, thereby improving classification efficiency. The explicit features are closely related to the growth environment of soybeans. Classification can reflect the adaptability of soybeans to the environment, which helps to understand the characteristics of different origins. The explicit identifier can be used to track the source of soybean samples, enhance product traceability, and effectively utilize the explicit features of soybeans for classification and traceability, thereby improving the accuracy and efficiency of classification and traceability.

[0094] Specifically, in this embodiment, the process of performing implicit feature fingerprint marking on the target sample set according to the implicit feature of soybean to obtain an implicit marking result, and dividing the target sample set into two categories according to the implicit marking result to obtain a plurality of two-category sample clusters includes:

[0095] Step S310, determining a latent feature vector according to the latent feature of soybeans, and marking each target sample point with an invisible feature fingerprint according to the latent feature vector to determine an implicit identifier of each target sample point;

[0096] Step S220, based on the implicit identifier, classify each target sample point into two categories according to the initial implicit classification standard to obtain two-category sample clusters corresponding to different origin types;

[0097] The second type of sample clusters include a number of target sample points with implicit identifiers.

[0098] In this embodiment, the hidden feature vector of soybean is selected as mineral content, and the hidden feature (mineral content) of soybean is identified. The mineral content in the soybean sample, including potassium, calcium, magnesium, iron, and zinc, is determined using an appropriate chemical analysis method (such as atomic absorption spectroscopy or inductively coupled plasma mass spectrometry). The mineral content data of each target sample point is recorded to generate a hidden identifier. For example, a hidden identifier may be expressed as [potassium: 100 mg / kg, calcium: 200 mg / kg, magnesium: 150 mg / kg, iron: 30 mg / kg, zinc: 20 mg / kg]. The hidden identifier is a concentrated representation of the mineral content of the target sample point and can uniquely identify the mineral composition of the target sample point. According to the distribution and correlation of the mineral content, an initial hidden classification standard is set. The specific setting process includes: a similarity threshold of the mineral content, comparing the hidden feature fingerprint with the initial hidden classification mark. For comparison, sample points that meet the same classification criteria are classified into the same category to form two-category sample clusters. For example, sample points with potassium content in the range of 90-110 mg / kg, calcium content in the range of 190-210 mg / kg, magnesium content in the range of 140-160 mg / kg, iron content in the range of 20-40 mg / kg, and zinc content in the range of 10-30 mg / kg are classified into the same two-category sample cluster. Soybean samples with similar mineral content characteristics are clustered together to form several two-category sample clusters. Since the mineral content is closely related to the growth environment (origin) of soybeans, the mineral content and fertility of the soil in different origins will affect the mineral absorption of soybeans. Therefore, classification through latent feature fingerprints is actually to cluster soybeans with similar mineral composition together. These soybeans may come from similar growth environments, thus forming two-category sample clusters corresponding to different origin types.

[0099] Specifically, the embodiments of the present invention analyze the latent characteristics of the mineral content of soybeans to gain a deeper understanding of the intrinsic quality of soybeans and the influence of the growth environment, thereby improving the depth and accuracy of classification. Combining explicit and implicit characteristics, soybean samples can be classified from multiple dimensions to enhance the comprehensiveness and reliability of classification. The implicit identifier, as a concentrated representation of the mineral content, can uniquely identify the mineral composition of each target sample point, facilitating accurate classification and traceability. The mineral content is closely related to the growth environment of soybeans. Through implicit feature classification, the adaptability of soybeans to specific soil and climatic conditions can be analyzed to provide guidance for agricultural production. Implicit feature fingerprint marking helps to more accurately track the origin of soybeans, especially when the explicit features are similar, the implicit features can provide additional distinguishing information.

[0100] See also Figure 2 As shown, it is a comparison flow chart, wherein the process of comparing the first-category classification result and the second-category classification result to determine whether to start the successive verification mode or the separate verification mode includes:

[0101] Step S410, identifying a class of partitions to determine the number of the class of partitions and the capacity of each class of sample clusters;

[0102] Step S420, identifying the two-class partitions to determine the number of two-class partitions and the capacity of each two-class sample cluster;

[0103] Step S430, performing a comparison based on the number of the first-category division and the number of the second-category division to determine whether to start a supplementary comparison mode;

[0104] Step S440, based on starting the supplementary comparison mode, performing a secondary comparison according to the capacity of each first-category sample cluster and the capacity of each second-category sample cluster, and determining to start the successive verification mode or the separate verification mode according to the secondary comparison result;

[0105] The one-category division result includes: the number of the one-category divisions and the capacity of each one-category sample cluster; the two-category division result includes: the number of the two-category divisions and the capacity of each two-category sample cluster.

[0106] Specifically, in this embodiment, the process of comparing the number of the first-category division and the number of the second-category division to determine whether to start the supplementary comparison mode includes:

[0107] Step S421, determining whether to start the supplementary comparison mode according to the first difference absolute value combined with a preset difference evaluation value;

[0108] Step S422, based on the absolute value of the first difference being greater than or equal to the difference evaluation value, determining to start the successive verification mode;

[0109] Step S423, based on the first difference absolute value being smaller than the difference evaluation value, determining to start the supplementary comparison mode;

[0110] The first absolute value of the difference is the absolute value of the difference between the number of the first-class divisions and the number of the second-class divisions.

[0111] In the specific implementation process, the difference evaluation value is used to measure the degree of difference between the two classification results. Specifically, it is used to measure the inconsistency or difference between the one-category classification (based on explicit characteristics) and the two-category classification (based on implicit characteristics). If the number of the two classifications is very different, this indicates that there are significant differences between the origin classification results of the soybean samples based on different characteristics, and further verification and analysis are needed. The setting of the difference evaluation value is affected by the actual classification accuracy and the initial sample capacity. In this embodiment, the difference evaluation value is set to 10. For example, if there are 50 sample clusters in the one-category classification and 45 sample clusters in the two-category classification, the absolute value of the first difference is 5. If the preset difference evaluation value is 10, then because the absolute value of the difference is less than the difference evaluation value, it will be determined to start the supplementary comparison mode.

[0112] Specifically, in this embodiment, the process of performing secondary comparison according to the capacity of each type 1 sample cluster and the capacity of each type 2 sample cluster includes:

[0113] Step S4411, obtaining the maximum sample capacity and the minimum sample capacity of each sample cluster;

[0114] Step S4412, obtaining the maximum two-category sample capacity and the minimum two-category sample capacity in each two-category sample cluster capacity;

[0115] Step S4413, comparing the maximum sample size of the first category with the maximum sample size of the second category to obtain a maximum comparison result;

[0116] Step S4414, comparing the minimum sample size of the first category with the minimum sample size of the second category to obtain a minimum comparison result;

[0117] Step S4415, determining the number of items in the maximum comparison result and the minimum comparison result that meet a single determination condition.

[0118] Specifically, in this embodiment, the process of determining the number of items in the maximum comparison result and the minimum comparison result that meet a single determination condition includes:

[0119] Calculating the maximum capacity difference between the maximum sample capacity of the first category and the maximum sample capacity of the second category, and determining whether the single determination condition is met according to the maximum capacity difference;

[0120] Calculate the minimum capacity difference between the minimum sample capacity of the first category and the minimum sample capacity of the second category, and determine whether the single determination condition is met according to the minimum capacity difference;

[0121] Among them, based on the maximum capacity difference being less than or equal to the preset standard capacity difference, the maximum comparison result is determined to meet the single judgment condition; based on the maximum capacity difference being greater than the standard capacity difference, the maximum comparison result is determined to not meet the single judgment condition; based on the minimum capacity difference being less than or equal to the standard capacity difference, the minimum comparison result is determined to meet the single judgment condition; based on the minimum capacity difference being greater than the standard capacity difference, the minimum comparison result is determined to not meet the single judgment condition.

[0122] In the specific implementation process, the standard capacity difference is used to measure whether the difference between the maximum or minimum sample capacity in the first category sample cluster and the second category sample cluster is within an acceptable range. The specific setting is affected by the actual classification accuracy and the initial sample capacity. In this embodiment, the standard capacity difference is set to 5.

[0123] Specifically, in this embodiment, the process of determining to start the successive verification mode or the individual verification mode according to the secondary comparison result includes:

[0124] Step S4421, when the number of items is 2, it is determined to start the separate verification mode;

[0125] Step S4422, based on the fact that the number of items is less than 2, it is determined to start the successive verification mode.

[0126] Specifically, the embodiment of the present invention can effectively decide whether to adopt a successive verification mode or a separate verification mode by comparing the results of the first and second category classifications, thereby improving the efficiency of the entire verification process. By comparing according to the number and capacity of sample clusters, verification resources can be better allocated. By supplementing the comparison mode, the inconsistency between the classification results of explicit features and implicit features can be identified, so that measures can be taken to improve the consistency and reliability of classification. Through detailed comparative analysis, misjudgment caused by single feature classification can be reduced, ensuring that the final traceability result is more accurate. According to the setting of the difference evaluation value and the standard capacity difference, the system can flexibly adapt to different classification requirements and sample characteristics, improve the overall adaptability, and further improve the accuracy of soybean origin traceability through precise comparison and verification mode selection.

[0127] See also Figure 3 As shown, it is a flowchart of successive verification, wherein the process of determining whether to output the actual origin traceability result according to each verification result includes:

[0128] Step S510, based on the successive verification mode, adjusting the initial sample size according to a one-time verification standard to obtain a verification sample size;

[0129] Step S520, performing a primary verification division according to the dominant characteristics and the recessive characteristics of soybeans with the verification sample capacity, so as to obtain a plurality of primary verification class one sample clusters and a plurality of primary verification class two sample clusters;

[0130] Step S530, determining the number of explicit divisions for one verification and the number of implicit divisions for one verification according to each of the first-verification type one sample clusters and each of the first-verification type two sample clusters;

[0131] Step S540, determining a verification result according to the number of explicit divisions of the verification and the number of implicit divisions of the verification;

[0132] Step S550, based on the successive verification mode, adjusting the target classification standard according to the secondary verification standard to obtain the actual classification standard;

[0133] Step S560, performing secondary verification division on the initial sample capacity to obtain a number of secondary verification type 1 sample clusters and a number of secondary verification type 2 sample clusters;

[0134] Step S570, determining the number of secondary verification explicit divisions and the number of secondary verification implicit divisions according to each secondary verification type 1 sample cluster and each secondary verification type 2 sample cluster;

[0135] Step S580, determining a secondary verification result according to the number of secondary verification explicit divisions and the number of secondary verification implicit divisions;

[0136] Step S590, determining whether the first verification result is consistent with the second verification result, and outputting the actual origin tracing result when the verification results are consistent.

[0137] In this implementation, the primary verification standard is to increase the initial sample capacity to 1.5-2 times;

[0138] The process of determining a verification result according to the number of explicit divisions of the verification and the number of implicit divisions of the verification comprises:

[0139] Step S541, determining whether the primary verification result is consistent with the initial result or inconsistent with the initial result according to the second difference absolute value combined with the difference evaluation value;

[0140] Step S542, based on the absolute value of the second difference being greater than or equal to the difference evaluation value, determining that the first verification result is consistent with the initial result;

[0141] Step S423, based on the absolute value of the second difference being smaller than the difference evaluation value, determining that the first verification result is inconsistent with the initial result;

[0142] The second absolute value of the difference is the absolute value of the difference between the number of explicit divisions in the one-time verification and the number of implicit divisions in the one-time verification.

[0143] Specifically, in this embodiment, the process of adjusting the target classification standard according to the secondary verification standard based on the successive verification mode to obtain the actual classification standard includes:

[0144] When the absolute value of the first difference is greater than or equal to the difference evaluation value, the classification standard corresponding to the larger value of the number of the first-class division and the number of the second-class division is selected as the target classification standard. For example, if the number of the first-class division is greater than the number of the second-class division, the initial implicit classification standard is selected as the target classification standard; if the number of the first-class division is less than the number of the second-class division, the initial explicit classification standard is selected as the target classification standard;

[0145] In this embodiment, based on the selection of the initial implicit classification standard as the target classification standard, the secondary verification standard is to reduce the similarity threshold of the mineral content, so that the implicit classification standard is more refined; based on the selection of the initial explicit classification standard as the target classification standard, the secondary verification standard is to reduce the set fluctuation range and the set similarity threshold, so that the explicit classification standard is more refined;

[0146] The process of determining the secondary verification result according to the number of secondary verification explicit divisions and the number of secondary verification implicit divisions includes:

[0147] Step S581, determining whether the secondary verification result is consistent with the initial one or inconsistent with the initial one according to the third difference absolute value combined with the difference evaluation value;

[0148] Step S582, based on the third difference absolute value being greater than or equal to the difference evaluation value, determining that the secondary verification result is consistent with the initial result;

[0149] Step S583, based on the absolute value of the third difference being smaller than the difference evaluation value, determining that the secondary verification result is inconsistent with the initial result;

[0150] The third difference absolute value is the absolute value of the difference between the number of explicit divisions of the secondary verification and the number of implicit divisions of the secondary verification.

[0151] Specifically, the process of determining whether the first verification result and the second verification result are consistent, and outputting the actual origin tracing result based on the consistency of each verification result includes: if the first verification result and the second verification result are both consistent with the initial or inconsistent with the initial, determining that the division is accurate, and outputting the actual origin tracing result; if the first verification result and the second verification result are one consistent with the initial and one inconsistent with the initial, determining that the division is inaccurate, and not outputting the actual origin tracing result;

[0152] In this embodiment, successive verification can reduce the error that may be caused by a single division and improve the accuracy of classification through multiple divisions and comparisons. By comparing the results of different verification steps, the consistency and stability of the classification standard can be checked. If the results of multiple verifications are consistent, it means that the division result is accurate. If the two verification results are consistent, the actual origin traceability result is output. The specific output process is: according to the initial division result, the database corresponding to the standard soybean origin and characteristics is compared, and the feature identifier of each sample cluster is matched with the record in the database to output the actual origin traceability result.

[0153] Specifically, the embodiments of the present invention can significantly improve the accuracy of soybean origin traceability and reduce the errors that may be introduced by a single division by successively verifying and comparing the results of different verification steps. Multiple verifications ensure the consistency and stability of the classification standards, thereby enhancing the reliability of the overall classification system. By adjusting the classification standards, the classification can be made more detailed and the resolution of the classification can be improved. By comparing the results of the first verification and the second verification, the misjudgment in the classification process can be effectively identified and reduced. By comparing the results of different verification steps, the consistency of the data can be ensured, which is crucial for establishing a reliable traceability system. Taking the two characteristics into consideration, the samples can be evaluated more comprehensively and the comprehensiveness of the classification can be improved.

[0154] Specifically, in this embodiment, based on the separate verification mode, the first category division result and the second category division result are separately verified to obtain the first category verification result and the second category verification result, and the process of determining whether to output the actual origin tracing result according to the first category verification result and the second category verification result includes:

[0155] Reanalyze the samples in the first sample cluster to confirm whether their dominant characteristics are consistent with the initial markings. Review the dominant characteristics of soybean shape, size, color, and texture through visual inspection, instrument measurement, or other verification methods. Check the stability of the dominant characteristics in each sample cluster to ensure that there are no misclassified samples. Perform chemical analysis on the samples in the second sample cluster, re-measure the recessive characteristics of their mineral content, compare the re-measured data with the initial marking results, check whether there are significant differences, and evaluate whether the sample cluster based on recessive characteristics is stable.

[0156] After verification, there are no significant differences in the results of each Class I sample cluster divided based on dominant characteristics, indicating that the Class I sample cluster accurately reflects the dominant characteristics of soybeans; after verification, there are no significant differences in the results of each Class II sample cluster divided based on recessive characteristics, indicating that the Class II sample cluster accurately reflects the recessive characteristics of soybeans. If there are no significant differences in the Class I verification results and the Class II verification results, indicating that the sample cluster division is accurate and stable, then the division result is considered to be reliable, and the verified sample characteristics are matched with the standard soybean origin and characteristic database. According to the matching results, the actual origin traceability information of each sample is output, that is, the actual origin traceability result is output; if one of the Class I verification results and the Class II verification results is significantly different, then the division result is considered to be unreliable.

[0157] Specifically, the embodiments of the present invention can ensure the accuracy of classification results and reduce classification errors by reanalyzing and verifying the explicit and implicit features of samples. By individually verifying the explicit and implicit features of each sample cluster, the stability and reliability of classification results can be verified, and the accuracy of traceability can be improved. By checking the stability of features within the sample cluster, the stability of the classification results can be evaluated, providing a basis for the output of the final traceability results, thereby ensuring the accuracy and reliability of the traceability results.

[0158] See also Figure 4 The present invention also provides an agricultural product origin identification and tracing system based on feature fingerprints, comprising:

[0159] A sample collection module, which is used to collect soybean samples according to a preset initial sample volume to obtain a target sample set;

[0160] An explicit feature analysis module, which is used to perform explicit feature analysis on the target sample set to obtain an explicit feature fingerprint;

[0161] A latent feature analysis module, which is used to perform latent feature analysis on the target sample set to obtain a latent feature fingerprint;

[0162] A partitioning and clustering module, which is used to perform one-category partitioning and two-category partitioning on samples according to each characteristic fingerprint, so as to obtain a number of one-category sample clusters and a number of two-category sample clusters;

[0163] A verification mode selection module, which is used to compare the first-class division result and the second-class division result to determine whether to adopt a successive verification mode or a separate verification mode;

[0164] A successive verification module, which is used to perform multiple divisions through multiple verifications to obtain each verification result, and decide whether to output the actual origin traceability result according to each verification result;

[0165] A separate verification module is used to independently verify the first-category classification results and the second-category classification results respectively, and combine the two types of verification results to determine whether to output the actual origin traceability results.

[0166] The calculation compensation parameters and the calculation adjustment parameters described in the present invention have two functions: one is to balance the left and right dimensions of the formula, and the other is to adjust the numerical results. No specific assignment is performed in this embodiment. In addition, the calculation formulas in this embodiment are used to intuitively reflect the adjustment relationship between the numerical values, such as positive correlation and negative correlation. Unless otherwise specified, the parameter values ​​that are not specifically limited to numerical values ​​are all positive.

[0167] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0168] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. The method for identifying and tracing the origin of agricultural products based on characteristic fingerprints includes: Collecting target agricultural product samples with a preset initial sample capacity to obtain a target sample set; According to the dominant characteristics of the target agricultural product, the target sample set is marked with a dominant characteristic fingerprint to obtain a dominant marking result, and the target sample set is divided into one category according to the dominant marking result to obtain a plurality of one-category sample clusters; According to the latent characteristics of the target agricultural product, the target sample set is marked with latent characteristic fingerprints to obtain latent marking results, and the target sample set is divided into two categories according to the latent marking results to obtain a number of two-category sample clusters; Compare the first-category classification result and the second-category classification result to determine whether to start the successive verification mode or the individual verification mode; Based on the successive verification mode, obtaining each verification result, and determining whether to output the actual origin tracing result according to each verification result; Based on the separate verification mode, the first category division results and the second category division results are respectively verified separately to obtain the first category verification results and the second category verification results, and it is determined whether to output the actual origin traceability results based on the first category verification results and the second category verification results.

2. The method for identifying and tracing the origin of agricultural products based on characteristic fingerprints according to claim 1 is characterized in that: The process of performing explicit feature fingerprint marking on the target sample set according to the explicit features of the target agricultural product to obtain an explicit marking result, and classifying the target sample set into one category according to the explicit marking result to obtain a plurality of one-category sample clusters includes: Determine each explicit feature vector according to the explicit features of the target agricultural product, and perform explicit feature fingerprint marking on each target sample point according to each explicit feature vector to determine the explicit identifier of each target sample point; Based on the explicit identifier, each target sample point is classified into one category according to the initial explicit classification standard to obtain each sample cluster corresponding to different origin types; The target sample set includes a number of target sample points; and the sample cluster includes a number of target sample points with explicit identifiers.

3. The method for identifying and tracing the origin of agricultural products based on characteristic fingerprints according to claim 2 is characterized in that: The process of performing implicit feature fingerprint marking on the target sample set according to the implicit features of the target agricultural product to obtain an implicit marking result, and dividing the target sample set into two categories according to the implicit marking result to obtain a plurality of two-category sample clusters includes: Determine a latent feature vector according to the latent feature of the target agricultural product, and perform invisible feature fingerprint marking on each target sample point according to the latent feature vector to determine the latent identifier of each target sample point; Based on the implicit identifier, each target sample point is divided into two categories according to the initial implicit classification standard to obtain two-category sample clusters corresponding to different origin types; The second type of sample clusters include a number of target sample points with implicit identifiers.

4. The method for identifying and tracing the origin of agricultural products based on characteristic fingerprints according to claim 3 is characterized in that: The process of comparing the first-category classification result and the second-category classification result to determine to start the successive verification mode or the individual verification mode includes: Identify a class of partitions to determine the number of class of partitions and the capacity of each class of sample clusters; Identify the two-class partitions to determine the number of two-class partitions and the capacity of each two-class sample cluster; Perform a comparison based on the number of the first-category division and the number of the second-category division to determine whether to start a supplementary comparison mode; Based on starting the supplementary comparison mode, performing a secondary comparison according to the capacity of each type one sample cluster and the capacity of each type two sample cluster, and determining to start the successive verification mode or the separate verification mode according to the secondary comparison result; The one-category division result includes: the number of the one-category divisions and the capacity of each one-category sample cluster; the two-category division result includes: the number of the two-category divisions and the capacity of each two-category sample cluster.

5. The method for identifying and tracing the origin of agricultural products based on characteristic fingerprints according to claim 4 is characterized in that: The process of performing secondary comparison according to the capacity of each first-class sample cluster and the capacity of each second-class sample cluster includes: Obtain the maximum sample capacity and the minimum sample capacity of each class of sample clusters; Obtain the maximum two-category sample capacity and the minimum two-category sample capacity in each two-category sample cluster capacity; Comparing the maximum sample size of the first category with the maximum sample size of the second category to obtain a maximum comparison result; Comparing the minimum sample size of the first category with the minimum sample size of the second category to obtain a minimum comparison result; The number of items in the maximum comparison result and the minimum comparison result that meet a single determination condition is determined.

6. The method for identifying and tracing the origin of agricultural products based on characteristic fingerprints according to claim 5 is characterized in that: The process of determining whether to output the actual origin traceability result according to each verification result includes: Based on the successive verification mode, adjusting the initial sample capacity according to a one-time verification standard to obtain a verification sample capacity; Performing a one-time verification division based on the verification sample capacity and the dominant characteristics and the invisible characteristics of the target agricultural product to obtain a number of one-time verification type one sample clusters and a number of one-time verification type two sample clusters; Determine the number of explicit divisions for one-time verification and the number of implicit divisions for one-time verification according to each one-time verification type one sample cluster and each one-time verification type two sample cluster; A verification result is determined according to the number of explicit divisions of the verification and the number of implicit divisions of the verification.

7. The method for identifying and tracing the origin of agricultural products based on characteristic fingerprints according to claim 6 is characterized in that: The process of determining whether to output the actual origin tracing result according to each verification result also includes: Based on the successive verification mode, adjusting the target classification standard according to the secondary verification standard to obtain the actual classification standard; Performing secondary verification division on the initial sample capacity to obtain a number of secondary verification type 1 sample clusters and a number of secondary verification type 2 sample clusters; Determine the number of explicit divisions of secondary verification and the number of implicit divisions of secondary verification according to each secondary verification type 1 sample cluster and each secondary verification type 2 sample cluster; Determine a secondary verification result according to the number of secondary verification explicit divisions and the number of secondary verification implicit divisions; Determine whether the first verification result is consistent with the second verification result, and output the actual origin tracing result based on the consistency of the verification results.

8. The method for identifying and tracing the origin of agricultural products based on characteristic fingerprints according to claim 7 is characterized in that: The process of determining a verification result according to the number of explicit divisions of the verification and the number of implicit divisions of the verification comprises: Determining whether the primary verification result is consistent with the initial result or inconsistent with the initial result according to the second difference absolute value combined with a preset difference evaluation value; Based on the absolute value of the second difference being greater than or equal to the difference evaluation value, determining that the first verification result is consistent with the initial result; Based on the absolute value of the second difference being smaller than the difference evaluation value, determining that the first verification result is inconsistent with the initial result; The second absolute value of the difference is the absolute value of the difference between the number of explicit divisions in the one-time verification and the number of implicit divisions in the one-time verification.

9. The method for identifying and tracing the origin of agricultural products based on characteristic fingerprints according to claim 8 is characterized in that: The process of determining the secondary verification result according to the number of secondary verification explicit divisions and the number of secondary verification implicit divisions includes: Determining whether the secondary verification result is consistent with the initial result or inconsistent with the initial result according to the third difference absolute value combined with the difference evaluation value; Based on the third difference absolute value being greater than or equal to the difference evaluation value, determining that the secondary verification result is consistent with the initial result; Based on the absolute value of the third difference being smaller than the difference evaluation value, determining that the secondary verification result is inconsistent with the initial result; The third difference absolute value is the absolute value of the difference between the number of explicit divisions of the secondary verification and the number of implicit divisions of the secondary verification.

10. A system for identifying and tracing the origin of agricultural products based on characteristic fingerprints, using a method for identifying and tracing the origin of agricultural products based on characteristic fingerprints as described in any one of claims 1 to 9, characterized in that: include: A sample collection module, which is used to collect target agricultural product samples according to a preset initial sample capacity to obtain a target sample set; An explicit feature analysis module, which is used to perform explicit feature analysis on the target sample set to obtain an explicit feature fingerprint; A latent feature analysis module, which is used to perform latent feature analysis on the target sample set to obtain a latent feature fingerprint; A partitioning and clustering module, which is used to perform one-category partitioning and two-category partitioning on samples according to each characteristic fingerprint, so as to obtain a number of one-category sample clusters and a number of two-category sample clusters; A verification mode selection module, which is used to compare the first-class division result and the second-class division result to determine whether to adopt a successive verification mode or a separate verification mode; A successive verification module, which is used to perform multiple divisions through multiple verifications to obtain each verification result, and decide whether to output the actual origin traceability result according to each verification result; A separate verification module is used to independently verify the first-category classification results and the second-category classification results respectively, and combine the two types of verification results to determine whether to output the actual origin traceability results.

Images