Method and equipment for detecting nutrient substances in cod intestines based on machine learning

Abstract

The invention discloses a cod intestine nutrient substance detection method and cod intestine nutrient substance detection equipment based on machine learning, and relates to the technical field of food detection. Comprising the following steps: sample acquisition: acquiring a cod intestine sample and sample information, and detecting the nutrient substance concentration of the cod intestine sample by adopting a gas chromatographic method. According to the present invention, the target process meeting the user demand for detecting the target substance is provided for the user by matching the user demand with the matching adjustment method, and the target process is matched with the gas chromatography to detect the concentration of the target substance so as to obtain the target chromatogram after the detection; the concentration of the target substance is obtained according to the target chromatogram through the set matching recognition model and is fed back to a user, manual analysis of researchers is not needed for judging the concentration of the target substance, the error of a detection result is reduced, and the efficiency is improved; the substance detection time is shortened by actively outputting the detection process and automatically identifying the concentration of the target substance, so that the cod intestine nutrient substance detection efficiency and the accuracy of the detection result are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of food detection, and in particular to a method and device for detecting nutrients in cod intestines based on machine learning. Background Art

[0002] Cod intestines are rich in various nutrients, such as fatty acids, amino acids, etc., and have high nutritional value. In order to support the product development of cod intestines, meet regulatory requirements, study functional characteristics, monitor raw material quality and promote scientific research, it is often necessary to test cod intestines.

[0003] Patent publication number CN118378731A is a method for predicting water pollutant concentration based on IML-GIS coupling, including obtaining water quality data at precise points in the study area; obtaining natural geographic parameter data sets shared in the study area; using ArcGIS to fuse all prediction variable data set bands; converting the fused data set image into an array recognizable by the python language; establishing an integrated machine learning model; training the integrated machine learning model, establishing a mathematical connection between the measured data set and the fused data set; predicting the continuous pollutant concentration values ​​in the entire geographic space of the study area. This method eliminates the tedious and complex process of field sampling and routine laboratory water quality testing, and is well suited for the prediction of pollutant concentrations of different types of water bodies in large-scale basin spaces, especially for complex and special water bodies such as groundwater that are difficult to observe in the field, and realizes effective prediction of water quality evolution trends at a spatial scale.

[0004] The material component detection based on the above and similar principles adopts an image-based method to detect the material component. This material component detection method relies on image acquisition. If there are errors or inaccuracies in the image acquisition, it will lead to the disadvantage of inaccurate detection results. When researchers in a food health research center need to regularly monitor the nutritional components of cod intestines to evaluate their adaptability to a specific diet, based on the above scenario, the material detection method based on the above and similar principles cannot accurately provide the results of food nutritional component detection. In the prior art, when gas chromatography is used to detect food nutrients, the content or concentration of the target component is usually analyzed manually through the chromatogram, which takes a long time and involves subjective judgment and human errors, which easily leads to errors in the detection results and low efficiency in analyzing the detection results, which is not conducive to improving the efficiency and accuracy of overall nutritional component detection. Therefore, the present invention is proposed. Summary of the invention

[0005] The purpose of the present invention is to provide a method and device for detecting nutrients in cod intestines based on machine learning to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solution: a method for detecting nutrients in cod intestines based on machine learning, the method comprising: Sample acquisition: obtaining cod intestine samples and sample information, and using gas chromatography to detect the nutrient concentration of the cod intestine samples; Information processing: based on the sample information, the actual weight of the sample is obtained, and the detection items and sample weight are preset. The detection items are nutrients. Based on the detection items and gas chromatography, the detection process acquisition method is used to optimize the preprocessing process of the traditional detection process to obtain the detection process and data relationship; Establishing a test catalog: Based on the test process and data relationship and the sample weight, the test process under different sample weights is generated through the test derivation method to obtain the derived process. The test items, test process, sample weight and derived process are integrated to obtain the test set, and a test catalog is established to store the test set. Process output: Obtain user needs and user address information, obtain target substances based on user needs, select the corresponding process in the detection catalog based on user needs, match the actual weight of the sample and the data relationship through the matching adjustment method, and adjust to obtain the target process; Reference establishment and target substance detection: Based on the detection items, a reference library for matching and identifying nutrient concentrations is established through a reference establishment method. Based on the target substance and target process, the target substance is detected on the cod intestine sample by gas chromatography to obtain a chromatogram; Matching output: Find the chromatographic peak corresponding to the target substance in the chromatogram to obtain the target chromatographic peak, mark the target chromatographic peak in the chromatogram to obtain the target chromatogram, import the target chromatogram into the matching recognition model to obtain the concentration of the target substance, and feed back the concentration of the target substance to the user based on the user address information; The reference establishment method includes: presetting a target concentration, obtaining a cod intestine sample with a detection item of the target concentration to obtain a reference sample, detecting the detection item concentration of the reference sample based on gas chromatography to obtain a reference chromatogram, establishing a correlation between the target concentration and the chromatogram, integrating the target concentration and the chromatogram to obtain a sub-reference, and establishing a reference library for storing the sub-reference.

[0007] Furthermore, the detection process acquisition method includes: acquiring the process of detecting the detection item using gas chromatography to obtain a traditional process, extracting the part of the traditional process that inaccurately expresses the parameter data to obtain a processing process and a data relationship, the data relationship is the relationship between the sample weight and the parameter data, based on the processing process, supplementing the details of the parameter data in the processing process through an optimization method to obtain an optimized process, and replacing the processing process in the traditional process with the optimized process to obtain a detection process corresponding to the detection item.

[0008] Furthermore, the optimization method includes: splitting the data relationship to obtain several sub-data relationships, splitting the processing process to obtain several sub-processes, extracting parameters in the sub-processes to obtain parameters to be optimized, establishing an association relationship between the sub-data relationship and the sub-processes, obtaining target parameters based on sample weight and the sub-data relationship, determining the relationship between the target parameters and the parameters to be optimized based on the association relationship, replacing the parameters to be optimized with the target parameters in the sub-processes based on the relationship between the target parameters and the parameters to be optimized to obtain sub-optimization processes, and integrating the sub-optimization processes in order of the split processing processes to obtain an optimization process.

[0009] Furthermore, the detection derivation method includes: presetting a derivative unit, obtaining the weight of the sample in the previous sample detection information to obtain the previous weight information, judging whether the previous weight information is an integer to obtain a judgment result, when the judgment result feedback is that the previous weight information is an integer, the derivative unit is an integer, the derivative unit is cumulatively increased or reduced based on the sample weight to obtain the derived sample weight, based on the derived sample weight and data relationship to obtain the derivative parameters corresponding to the derived sample, the optimization parameters in the detection process are replaced with the derivative parameters to obtain the derived process, when the judgment result feedback is that the previous weight information is not an integer, the derivative unit is a decimal, the derivative unit is cumulatively increased or reduced based on the sample weight to obtain the derived sample weight, based on the derived sample weight and data relationship to obtain the derivative parameters corresponding to the derived sample, the optimization parameters in the detection process are replaced with the derivative parameters to obtain the derived process, when the judgment result feedback is that part of the previous weight information is an integer, then the process of judging the result feedback as the previous weight information being an integer and the judgment result feedback as the previous weight information not being an integer is performed and integrated to obtain the derivative process.

[0010] Furthermore, the matching adjustment method includes: retrieving the detection set corresponding to the target substance in the detection catalog based on the target substance to obtain a target set, selecting the detection process consistent with the actual weight of the sample in the target set based on the actual weight of the sample to obtain a selection result, when the selection result feedback is that there is a detection process consistent with the actual weight of the sample in the target set, then extracting the detection process consistent with the actual weight of the sample in the target set to obtain the target process, when the selection result feedback is that there is no detection process consistent with the actual weight of the sample in the target set, extracting the detection process in the target set that is closest to the actual weight of the sample to obtain a pre-process, obtaining the difference between the sample weight in the pre-process and the actual weight of the sample, and adjusting the optimization parameters in the pre-process based on the difference and data relationship to obtain the target process.

[0011] Furthermore, the process of finding the chromatographic peak corresponding to the target substance in the chromatogram to obtain the target chromatographic peak is as follows: based on the reference library, a chromatogram with a known detection item concentration is obtained to obtain a comparison chromatogram, the peak residence time in the comparison chromatogram is recorded to obtain the comparison time, a correspondence between the comparison time and the detection item is established, a comparison library is established to store the comparison time, the detection item and the correspondence, the residence time of the chromatographic peak in the chromatogram is recorded to obtain the target time, the detection item consistent with the target substance is retrieved from the comparison library to obtain the comparison item, the comparison time corresponding to the comparison item is extracted based on the correspondence to obtain the reference time, and the chromatographic peak with the same target time and reference time is selected to obtain the target chromatographic peak.

[0012] Furthermore, the method for establishing the matching recognition model includes: Acquisition of training data: Split the sub-references in the reference library to obtain the target concentration and chromatogram, mark the chromatographic peaks corresponding to the target concentration in the chromatogram, and integrate the target concentration and the marked chromatogram to obtain training data; Model selection and training: Select a suitable deep learning model as the model matrix, import the training data into the model matrix for the model to learn and obtain the initial model; Model adjustment and output: preset test data and test concentration, the test data is a chromatogram with marked chromatographic peaks, the test data is imported into the initial model to obtain the result concentration, the difference between the result concentration and the test concentration is determined to obtain the result information, and the initial model is optimized and adjusted based on the result information to obtain a matching recognition model.

[0013] A cod intestine nutrient detection device based on machine learning uses the above-mentioned cod intestine nutrient detection method based on machine learning.

[0014] Compared with the prior art, the present invention has the following beneficial effects: The cod intestine nutrient detection method and device based on machine learning monitors user needs and provides users with a target process for detecting target substances that meets user needs in accordance with the matching adjustment method according to the user needs. The target process is combined with gas chromatography to detect the concentration of the target substance. After the target chromatogram is obtained, the concentration of the target substance is obtained according to the target chromatogram through the set matching recognition model and fed back to the user. The process of judging the concentration of the target substance does not require manual analysis by researchers, thereby reducing errors in the detection results and improving efficiency. The time for substance detection is shortened by actively outputting the detection process and automatically identifying the concentration of the target substance, thereby improving the efficiency of cod intestine nutrient detection and the accuracy of the detection results.

[0015] At the same time, through the set monitoring process acquisition method, the specific process of using gas chromatography to detect the concentration of the detection item can be obtained, and the specific process can be optimized to obtain the detection process, so as to match the operation of the adjustment method, and the detection process under different sample weights is derived through the set detection derivation method to obtain a derived process, and a detection directory is established to store the detection set to increase the data volume of the detection set in the detection directory, so as to facilitate the subsequent rapid output of the target process that meets the user's needs according to user needs, extract the parameters in the sub-processing process to obtain the parameters to be optimized, and extract a single parameter to facilitate multi-threaded separate supplementary optimization of the parameters to be optimized and integrate them after optimization to improve the efficiency of the optimization process.

[0016] At the same time, the detection derivative method calculates the possible unit form of the weight of future samples based on the weight of the samples in the previous sample detection information, and provides corresponding response methods. When the judgment result feedback is that the previous weight information is an integer, but the actual weight of the subsequent sample is not an integer, it is fed back to the detection derivative method for further derivation and supplement. It is also possible to select one of the three methods as the main derivation process of the detection derivative method according to actual use needs, or the above situation can be used as the main derivation process of the detection derivative method. The specific selection needs to be formulated by researchers according to actual usage. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of the overall upper half of the process structure of the present invention; Figure 2 It is a schematic diagram of the overall lower half process structure of the present invention; Figure 3 A schematic diagram of the matching recognition model establishment and operation structure of the present invention; Figure 4 It is a schematic diagram of the structure of the detection derivation method of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] Testing the nutrients in cod intestines helps to evaluate their nutritional value, ensure food safety, and meet consumer needs. It can also detect the protein, fat, carbohydrates, vitamins, minerals and other nutrients in cod intestines, ensure that the nutritional information on product labels is accurate, and avoid false advertising. The results of nutrient testing of cod intestines provide important scientific basis for manufacturers, consumers and research institutions, and have broad application value.

[0020] like Figure 1-Figure 4 As shown, the present invention provides a technical solution: a method for detecting nutrients in cod intestines based on machine learning, the method comprising: Sample acquisition: obtaining cod intestine samples and sample information, and using gas chromatography to detect the nutrient concentration of the cod intestine samples; Information processing: based on the sample information, the actual weight of the sample is obtained, and the detection items and sample weight are preset. The detection items are nutrients. Based on the detection items and gas chromatography, the detection process acquisition method is used to optimize the preprocessing process of the traditional detection process to obtain the detection process and data relationship; Establishing a test catalog: Based on the test process and data relationship and the sample weight, the test process under different sample weights is generated through the test derivation method to obtain the derived process. The test items, test process, sample weight and derived process are integrated to obtain the test set, and a test catalog is established to store the test set. Process output: Obtain user needs and user address information, obtain target substances based on user needs, select the corresponding process in the detection catalog based on user needs, match the actual weight of the sample and the data relationship through the matching adjustment method, and adjust to obtain the target process; Reference establishment and target substance detection: Based on the detection items, a reference library for matching and identifying nutrient concentrations is established through a reference establishment method. Based on the target substance and target process, the target substance is detected on the cod intestine sample by gas chromatography to obtain a chromatogram; Matching output: Find the chromatographic peak corresponding to the target substance in the chromatogram to obtain the target chromatographic peak, mark the target chromatographic peak in the chromatogram to obtain the target chromatogram, import the target chromatogram into the matching recognition model to obtain the concentration of the target substance, and feed back the concentration of the target substance to the user based on the user address information; It should be noted that during the sample acquisition stage, the cod intestine sample is directly obtained from the cod intestine to be tested. The sample information includes but is not limited to the actual weight of the sample. For example, the sample information may also include the content information of the cod intestine, so as to facilitate subsequent comparison to determine whether the cod intestine is qualified or whether there is false propaganda, etc. The nutrient concentration of the cod intestine sample is detected by gas chromatography, which can distinguish the components in the complex mixture and meet the needs of high-throughput detection to ensure the detection rate while obtaining accurate detection results. That is, by optimizing the pre-treatment technology in gas chromatography (such as derivatization and solid phase extraction), the interferences such as protein and salt in the cod intestine can be effectively removed, and the detection accuracy of the target substance can be improved. For example, the fatty acids in the cod intestine can be converted into fatty acid methyl esters, and the elimination In order to eliminate matrix interference and improve detection sensitivity, during the information processing stage, the detection items and sample weights are set by the researchers according to actual usage. The detection items need to cover all nutrients present in cod intestines. The specific process of using gas chromatography to detect the concentration of the detection items can be obtained through the set monitoring process acquisition method, and the specific process is optimized to obtain the detection process and data relationship. The data relationship is the relationship between sample weight and parameter data. For example, a specific dose of solvent needs to be added to the sample weight during the reaction. During the detection catalog establishment stage, the detection process under different sample weights is derived through the set detection derivation method to obtain the derived process, and a detection catalog is established to store the detection set to improve the data of the detection set in the detection catalog. The amount is convenient for the subsequent rapid output of the target process that meets the user's needs. In the process output stage, the user's needs and user address information can be obtained by the user. The user's needs are the specific nutrients that need to be detected, and the user's address information is the address information for feeding back the test results to the user, including but not limited to email and telephone number. The corresponding test process is selected from the test catalog according to the user's needs through the set matching adjustment method and adjusted to obtain the target process. In the reference establishment and target substance detection stages, a reference library for matching and identifying the concentration of nutrients is established through the set reference establishment method, so as to facilitate the subsequent identification of the concentration of the target substance. The target substance concentration of the cod intestine sample is detected by gas chromatography through the target process to obtain a chromatogram, and the matching In the output stage, the chromatographic peak corresponding to the target substance in the chromatogram is found and marked to obtain the target chromatogram, the target chromatogram is imported into the matching recognition model to obtain the concentration of the target substance, and the concentration of the target substance is fed back to the user based on the user address information. The present invention monitors the user's needs and provides the user with a target process for detecting the target substance that meets the user's needs in accordance with the matching adjustment method according to the user's needs. The target process is combined with gas chromatography to detect the concentration of the target substance. After the target chromatogram is obtained, the concentration of the target substance is obtained according to the target chromatogram through the set matching recognition model and fed back to the user. The process of judging the concentration of the target substance does not require manual analysis by the researchers, thereby reducing the error in the detection result and improving the efficiency.By actively outputting the detection process and automatically identifying the concentration of target substances, the time for substance detection is shortened to improve the efficiency of cod intestine nutrient detection and the accuracy of the detection results.

[0021] like Figure 1 As shown, the reference establishment method includes: presetting a target concentration, obtaining a cod intestine sample with a detection item of the target concentration to obtain a reference sample, detecting the detection item concentration of the reference sample based on gas chromatography to obtain a reference chromatogram, establishing a correlation between the target concentration and the chromatogram, integrating the target concentration and the chromatogram to obtain a sub-reference, and establishing a reference library for storing the sub-reference.

[0022] It should be noted that the target concentration is set by the researchers according to actual usage. The reference sample is the test item and the target concentration. The test item here refers to various nutrients, that is, one of multiple nutrients. When the reference sample is tested to obtain a reference chromatogram, the corresponding test process can be matched through the matching adjustment method, and then the reference sample is tested through the test process in conjunction with gas chromatography to obtain a reference chromatogram. The reference library is used to store sub-references. The more sub-references, the better. The number of sub-references is determined based on actual usage.

[0023] like Figure 1 As shown, the method for acquiring the detection process includes: acquiring the process of detecting the detection item using gas chromatography to obtain a traditional process, extracting the part of the traditional process that inaccurately expresses the parameter data to obtain a processing process and a data relationship, the data relationship is the relationship between the sample weight and the parameter data, based on the processing process, supplementing the details of the parameter data in the processing process through an optimization method to obtain an optimized process, and replacing the processing process in the traditional process with the optimized process to obtain a detection process corresponding to the detection item.

[0024] It should be noted that the traditional process can be obtained from the information of the detection items previously detected by gas chromatography, and the part of the parameter data that is not accurately expressed in the traditional process is extracted to obtain the processing process and data relationship. The part of the parameter data that is not accurately expressed is the part that adjusts the sample weight to cause the solvent that reacts with the sample or the time and temperature for heating the sample to be adjusted. The data relationship is the data on how the solvent dosage or the time and temperature for heating the sample will change due to the change in the reaction sample weight. The details of the parameter data are supplemented and optimized through the set optimization method to obtain the optimization process, so as to directly match the target process corresponding to the actual weight of the sample according to the actual weight of the sample, so as to improve the efficiency of target substance detection.

[0025] The optimization method includes: splitting a data relationship to obtain a number of sub-data relationships, splitting a processing process to obtain a number of sub-processing processes, extracting parameters in the sub-processing process to obtain parameters to be optimized, establishing an association relationship between the sub-data relationship and the sub-processing process, obtaining a target parameter based on sample weight and the sub-data relationship, determining the relationship between the target parameter and the parameter to be optimized based on the association relationship, replacing the parameter to be optimized with the target parameter in the sub-processing process based on the relationship between the target parameter and the parameter to be optimized to obtain a sub-optimization process, and integrating the sub-optimization processes in sequence based on the split processing process to obtain an optimization process.

[0026] It should be noted that the process of extracting the parameters in the sub-process to obtain the parameters to be optimized, that is, extracting the parameters that are not clearly expressed in the processing process to obtain the parameters to be optimized, is to facilitate multi-threaded separate supplementary optimization of the parameters to be optimized and integrate them after optimization to improve the efficiency of the optimization process.

[0027] like Figure 1 and Figure 4 As shown, the detection derivation method includes: presetting a derivative unit, obtaining the weight of the sample in the previous sample detection information to obtain the previous weight information, judging whether the previous weight information is an integer to obtain a judgment result, when the judgment result feedback is that the previous weight information is an integer, the derivative unit is an integer, the derivative unit is cumulatively increased or reduced based on the sample weight to obtain the derived sample weight, based on the derived sample weight and data relationship to obtain the derivative parameters corresponding to the derived sample, the optimization parameters in the detection process are replaced with the derivative parameters to obtain the derivative process, when the judgment result feedback is that the previous weight information is not an integer, the derivative unit is a decimal, the derivative unit is cumulatively increased or reduced based on the sample weight to obtain the derived sample weight, based on the derived sample weight and data relationship to obtain the derivative parameters corresponding to the derived sample, the optimization parameters in the detection process are replaced with the derivative parameters to obtain the derivative process, when the judgment result feedback is that part of the previous weight information is an integer, then the judgment result feedback is that the previous weight information is an integer and the judgment result feedback is that the previous weight information is not an integer. The process is performed and integrated to obtain the derivative process.

[0028] It should be noted that the derived units are integers or decimals, and the specific values ​​are determined by the user according to actual usage. The detection derivation method calculates the possible unit form of the weight of future samples based on the weight of the samples in the previous sample detection information, and provides corresponding response methods. When the judgment result feedback is that the previous weight information is an integer, but the actual weight of the subsequent sample is not an integer, it is fed back to the detection derivation method for further derivation and supplement. At the same time, one of the three methods can be selected as the main derivation process of the detection derivation method according to actual usage needs, or the above situation can be used as the main derivation process of the detection derivation method. The specific selection needs to be made by researchers according to actual usage.

[0029] like Figure 2 As shown, the matching adjustment method includes: retrieving the detection set corresponding to the target substance in the detection catalog based on the target substance to obtain the target set, selecting the detection process consistent with the actual weight of the sample in the target set based on the actual weight of the sample to obtain the selection result, when the selection result feedback is that there is a detection process consistent with the actual weight of the sample in the target set, then extracting the detection process consistent with the actual weight of the sample in the target set to obtain the target process, when the selection result feedback is that there is no detection process consistent with the actual weight of the sample in the target set, extracting the detection process closest to the actual weight of the sample in the target set to obtain the pre-process, obtaining the difference between the sample weight and the actual weight of the sample in the pre-process, and adjusting the optimization parameters in the pre-process based on the difference and data relationship to obtain the target process.

[0030] It should be noted that, through the set matching adjustment method, the substance whose concentration needs to be detected is determined according to user needs to obtain the target substance, the target substance is traversed through the detection directory to obtain the detection set corresponding to the target substance to obtain the target set, and the detection process consistent with the sample weight is selected in the detection set to obtain the target process. In this process, the deviation range can also be added to the actual weight of the sample. When the sample weight is within the deviation range added to the actual weight of the sample, the detection process is selected to obtain the target process. The researchers decide whether to use the deviation range or determine the specific value of the deviation range according to actual usage. When there is no sample in the target set that is consistent with the actual weight of the sample, a sample weight that is closer or farther from the actual weight of the sample is selected, and the difference between the two is obtained. According to the difference between the two and the data relationship, the optimization parameters of the pre-process are adjusted to obtain the target process. The specific optimization process is consistent with the detection process acquisition method.

[0031] The process of finding the chromatographic peak corresponding to the target substance in the chromatogram to obtain the target chromatographic peak is as follows: based on the reference library, a chromatogram with a known detection item concentration is obtained to obtain a comparison chromatogram, the peak residence time in the comparison chromatogram is recorded to obtain the comparison time, a correspondence between the comparison time and the detection item is established, a comparison library is established to store the comparison time, the detection item and the correspondence, the residence time of the chromatographic peak in the chromatogram is recorded to obtain the target time, the detection item consistent with the target substance is retrieved from the comparison library to obtain the comparison item, the comparison time corresponding to the comparison item is extracted based on the correspondence to obtain the reference time, and the chromatographic peak with the same target time and reference time is selected to obtain the target chromatographic peak.

[0032] It should be noted that the detection item and the target substance belong to the same substance. By comparing the chromatograms with known detection item concentrations, the relationship between the chromatographic peak in the chromatogram and the detection item can be reversely inferred, that is, the chromatographic peak corresponding to the detection item is extracted, and the comparison time is obtained by recording the residence time of the chromatographic peak. Then, the reference time consistent with the comparison time is extracted to determine the target chromatographic peak in the chromatogram corresponding to the target substance.

[0033] like Figure 3 As shown, the method for establishing the matching recognition model includes: Acquisition of training data: Split the sub-references in the reference library to obtain the target concentration and chromatogram, mark the chromatographic peaks corresponding to the target concentration in the chromatogram, and integrate the target concentration and the marked chromatogram to obtain training data; Model selection and training: Select a suitable deep learning model as the model matrix, import the training data into the model matrix for the model to learn and obtain the initial model; Model adjustment and output: preset test data and test concentration, the test data is a chromatogram with marked chromatographic peaks, the test data is imported into the initial model to obtain the result concentration, the difference between the result concentration and the test concentration is determined to obtain the result information, and the initial model is optimized and adjusted based on the result information to obtain a matching recognition model.

[0034] It should be noted that in the training data acquisition stage, the training data is obtained through the reference library established by the reference establishment method, and the more sub-references there are in the reference library, the more training data there will be. The process of marking the chromatographic peak corresponding to the target concentration in the chromatogram can be determined by finding the chromatographic peak corresponding to the target substance provided in the matching output stage. The chromatographic peak corresponding to the target concentration can be determined by marking the chromatographic peak and providing the target concentration. The training data can be obtained by marking the chromatographic peak and providing the target concentration. In the model selection and training stage, the deep learning model selects the corresponding model as the model matrix according to the actual use requirements, such as a convolutional neural network. Specifically, the image processing model can be selected as the model matrix, and the initial model is obtained by importing the training data into the model matrix for learning. In the model adjustment and output stage, the preset test data and test concentration are used as the data for testing the initial model, and the result concentration is obtained by importing the test data into the initial model. Then, according to the difference between the result concentration and the test concentration, it is decided whether the initial model is put into use. When the target chromatogram is identified by the matching recognition model, it is necessary to pre-process the target chromatogram in advance, such as image clarity, denoising, etc., to improve the accuracy of the output results of the matching recognition model.

[0035] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is limited by the attached embodiments and their equivalents.

Claims

1. A method for detecting nutrients in cod intestines based on machine learning, characterized in that: The method comprises: Sample acquisition: obtain cod intestine samples and sample information, use gas chromatography with matching recognition model to detect the nutrient concentration of cod intestine samples, and obtain the actual weight of the samples based on the sample information; Information processing: preset test items and sample weights, and optimize the test process based on the test items through the test process acquisition method to obtain the test process and data relationship; Establishing a test catalog: Based on the test process and data relationship and the sample weight, the test process under different sample weights is generated through the test derivation method to obtain the derived process. The test items, test process, sample weight and derived process are integrated to obtain the test set, and a test catalog is established to store the test set. Process output: Obtain user needs, obtain target substances based on user needs, select corresponding processes in the detection catalog through matching adjustment methods based on user needs, and adjust to obtain target processes; Reference establishment and target substance detection: A reference library for matching and identifying nutrient concentrations was established through a reference establishment method, and a chromatogram was obtained by detecting target substances in cod intestine samples by gas chromatography based on a target process; Matching output: Find and mark the chromatographic peaks corresponding to the target substance in the chromatogram to obtain the target chromatogram, and import the target chromatogram into the matching recognition model to obtain the concentration of the target substance; The method for establishing the matching recognition model includes: Acquisition of training data: Split the reference library to obtain the target concentration and chromatogram, mark the chromatographic peaks corresponding to the target concentration in the chromatogram, and integrate the target concentration and the marked chromatogram to obtain training data; Model selection and training: Select a suitable deep learning model as the model matrix, import the training data into the model matrix for the model to learn and obtain the initial model; Model adjustment and output: preset test data and test concentration, the test data is a chromatogram with chromatographic peaks marked, the test data is imported into the initial model to obtain the result concentration, the difference between the result concentration and the test concentration is determined to obtain the result information, and the initial model is optimized and adjusted based on the result information to obtain a matching recognition model.

2. The method for detecting nutrients in cod intestines based on machine learning according to claim 1, characterized in that: The detection process acquisition method includes: acquiring the process of detecting the detection item using gas chromatography to obtain a traditional process, extracting the part of the traditional process that inaccurately expresses the parameter data to obtain a processing process and a data relationship, the data relationship is the relationship between the sample weight and the parameter data, based on the processing process, supplementing the details of the parameter data in the processing process through an optimization method to obtain an optimized process, and replacing the processing process in the traditional process with the optimized process to obtain a detection process corresponding to the detection item.

3. The method for detecting nutrients in cod intestines based on machine learning according to claim 2, characterized in that: The optimization method includes: splitting a data relationship to obtain a plurality of sub-data relationships, splitting a processing process to obtain a plurality of sub-processes, extracting parameters in the sub-processes to obtain parameters to be optimized, establishing an association relationship between the sub-data relationship and the sub-processes, obtaining a target parameter based on sample weight and the sub-data relationship, determining a relationship between the target parameter and the parameter to be optimized based on the association relationship, replacing the parameter to be optimized with the target parameter in the sub-processing process based on the relationship between the target parameter and the parameter to be optimized to obtain a sub-optimization process, and integrating the sub-optimization processes in sequence based on the split processing processes to obtain an optimization process.

4. The method for detecting nutrients in cod intestines based on machine learning according to claim 1, characterized in that: The detection derivation method includes: presetting a derivative unit, obtaining the weight of the sample in the previous sample detection information to obtain the previous weight information, judging whether the previous weight information is an integer to obtain a judgment result, when the judgment result feedback is that the previous weight information is an integer, the derivative unit is an integer, the derivative unit is cumulatively increased or reduced based on the sample weight to obtain the derived sample weight, based on the derived sample weight and data relationship to obtain the derivative parameters corresponding to the derived sample, the optimization parameters in the detection process are replaced with the derivative parameters to obtain the derivative process, when the judgment result feedback is that the previous weight information is not an integer, the derivative unit is a decimal, the derivative unit is cumulatively increased or reduced based on the sample weight to obtain the derived sample weight, based on the derived sample weight and data relationship to obtain the derivative parameters corresponding to the derived sample, the optimization parameters in the detection process are replaced with the derivative parameters to obtain the derivative process, and when the judgment result feedback is that part of the previous weight information is an integer, the process of judging that the previous weight information is fed back as an integer and the process of judging that the previous weight information is not an integer are performed and integrated to obtain the derivative process.

5. The method for detecting nutrients in cod intestines based on machine learning according to claim 1, characterized in that: The matching adjustment method includes: based on the target substance, searching the detection set corresponding to the target substance in the detection catalog to obtain the target set; based on the actual weight of the sample, selecting the detection process consistent with the actual weight of the sample in the target set to obtain the selection result; when the selection result feedback is that there is a detection process consistent with the actual weight of the sample in the target set, then extracting the detection process consistent with the actual weight of the sample in the target set to obtain the target process; when the selection result feedback is that there is no detection process consistent with the actual weight of the sample in the target set, extracting the detection process closest to the actual weight of the sample in the target set to obtain the pre-process, obtaining the difference between the sample weight and the actual weight of the sample in the pre-process, and adjusting the optimization parameters in the pre-process based on the difference and data relationship to obtain the target process.

6. The method for detecting nutrients in cod intestines based on machine learning according to claim 1, characterized in that: The process of finding the chromatographic peak corresponding to the target substance in the chromatogram to obtain the target chromatographic peak is as follows: based on the reference library, a chromatogram with a known detection item concentration is obtained to obtain a comparison chromatogram, the peak residence time in the comparison chromatogram is recorded to obtain the comparison time, a correspondence between the comparison time and the detection item is established, a comparison library is established to store the comparison time, the detection item and the correspondence, the residence time of the chromatographic peak in the chromatogram is recorded to obtain the target time, the detection item consistent with the target substance is retrieved from the comparison library to obtain the comparison item, the comparison time corresponding to the comparison item is extracted based on the correspondence to obtain the reference time, and the chromatographic peak with the same target time and reference time is selected to obtain the target chromatographic peak.

7. The method for detecting nutrients in cod intestines based on machine learning according to claim 1, characterized in that: The reference establishment method includes: presetting a target concentration, obtaining a cod intestine sample with a detection item of the target concentration to obtain a reference sample, detecting the detection item concentration of the reference sample based on gas chromatography to obtain a reference chromatogram, establishing a correlation between the target concentration and the chromatogram, integrating the target concentration and the chromatogram to obtain a sub-reference, and establishing a reference library for storing the sub-reference.

8. A cod intestine nutrient detection device based on machine learning, characterized in that: A method for detecting nutrients in cod intestines based on machine learning as described in any one of claims 1 to 7 is used.

Images