Extraction system for antioxidant substances in plantain herb

Abstract

The invention relates to the technical field of substance and component extraction, and discloses a plantain herb antioxidant substance extraction system which comprises a data extraction module, a first data acquisition module and a prediction antioxidant module. The antioxidant substances in the plantain herb are extracted under the assistance of ultrasonic waves, and the extract is subjected to antioxidant activity evaluation and main component analysis. Through antioxidant activity evaluation and main component analysis, antioxidant experiment records are obtained from a plantain molecular experiment database, classification is performed according to an antioxidant determination method, and an antioxidant data dichotomy database is constructed. And constructing an osteoarthritis simulation model based on the osteoarthritis data, training the osteoarthritis simulation model by using the data in the anti-oxidation dichotomy database, and predicting the influence of the plantain herb anti-oxidation data on the osteoarthritis. The method is used for extracting the antioxidant substances in the plantain herb, greatly saves the separation and purification period, and effectively evaluates the potential influence of the antioxidant substances in the plantain herb on the osteoarthritis treatment effect.

Description

Technical Field

[0001] The invention relates to the technical field of material and component extraction, and in particular to a system for extracting antioxidant substances from plantain. Background Art

[0002] The phenylethanol glycosides contained in plantain (such as ergosterol, isoergosterol and Plantamajoside) have significant antioxidant activity. These compounds can scavenge free radicals, reduce oxidative stress, and thus protect joint tissues from damage. In addition, plantain produced in northwest Yunnan showed strong antioxidant activity in in vitro experiments, and its 95% ethanol extract was particularly effective in scavenging DPPH and ABTS free radicals. Plantain also contains flavonoids, which also have anti-inflammatory and antioxidant effects. For example, polysaccharides and flavonoids in plantain can inhibit the release of inflammatory mediators, reduce inflammatory reactions around joints, and relieve joint pain. In addition, plantain ethanol extract can also increase the activity of superoxide dismutase, further achieving anti-apoptosis, anti-oxidative stress and anti-inflammatory effects. The antioxidant substances in plantain can effectively treat osteoarthritis, reduce joint pain and inflammatory reactions by scavenging free radicals, inhibiting the release of inflammatory mediators, and enhancing the activity of antioxidant enzymes, thereby improving patients' symptoms and quality of life.

[0003] Prior art 1, Chinese patent, application number 202410062455.X discloses a composite preparation of plantain extract with protective effect against alcoholic liver damage, its preparation method and application. The present invention belongs to the field of biomedicine technology. Experiments have proved that the composite preparation provided by the present invention can improve liver function and lipid metabolism by inhibiting the ALT, AST activity and TG content in serum; reduce the liver index of mice and the MDA content in liver tissue, effectively reduce the deposition of fat in the liver; increase the SOD, CAT activity and T-GSH content in mice, although it reduces the degree of lipid peroxidation and oxidative stress response, restores the balance of the body's oxidation and antioxidant systems, and thus plays a protective role against acute liver damage caused by alcohol; but the efficiency and purity of plantain are poor.

[0004] Prior art 2, Chinese patent, application number 202410715720.X discloses an antioxidant composition and a preparation method thereof, the composition comprising the following components in parts by weight: 0.2-0.8 parts of Milo wood extract, 1-5 parts of Rhodiola rosea extract, 0.01-0.04 parts of ergothioneine, 1-5 parts of Camellia extract, and 0.5-1 parts of Plantain extract. By adopting a combination of Milo wood extract, Rhodiola rosea extract, ergothioneine, Camellia extract and Plantain extract, their joint action exerts a significant antioxidant effect. The free radical scavenging rate of the composition was tested to reach 74.6%, which is significantly better than the composition prepared in the comparative example; however, the selective extraction is poor and the antioxidant mechanism is unclear.

[0005] Prior art three, Chinese patent, application number 202410919996.X discloses a method for extracting ursolic acid from plantain by dialysis freeze-drying, which relates to the technical field of effective ingredient extraction of Chinese herbal medicine, including the following steps: crushing plantain into powder, adding anhydrous ethanol to the plantain powder, soaking for a period of time, and then ultrasonic extraction; adding activated carbon to the solution after ultrasonic extraction, mixing and shaking, standing, after the upper clear liquid is clear and transparent without any color, decompressing and filtering, and using a rotary evaporator to concentrate the filtrate; dialyzing the concentrated solution, a dialysis bag with a molecular weight cutoff of 300 is placed on the outer layer of a dialysis bag with a molecular weight cutoff of 500, and the concentrated solution is added to a dialysis bag with a molecular weight cutoff of 500 for dialysis; the dialysate between the two dialysis bags is collected and freeze-dried to obtain a white powder. A cold temperature technology, although the whole process will not lose the activity of the extracted molecular drug, it can also save the separation and purification cycle on a large scale, and has low requirements for laboratory conditions and operator level; but the extraction efficiency and purity are poor.

[0006] At present, the existing technologies 1, 2 and 3 have the problems of poor efficiency and purity of plantain, poor selective extraction and unclear antioxidant mechanism. To solve the above problems, the present invention provides an antioxidant substance extraction system in plantain. Summary of the invention

[0007] The main purpose of the present invention is to provide a system for extracting antioxidant substances from plantain to solve the problems of poor efficiency and purity of plantain, poor selective extraction and unclear antioxidant mechanism in the prior art.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] A system for extracting antioxidant substances from plantain, comprising:

[0010] The data extraction module is used for ultrasonic-assisted extraction of antioxidant substances from plantain, antioxidant activity evaluation of the extracted antioxidant substances, main component analysis of the evaluation results, and formation of antioxidant experimental records; the antioxidant experimental records are input into the plantain molecular experimental database;

[0011] The first data acquisition module is used to obtain antioxidant experimental records from the plantain molecular experimental database; the antioxidant experimental records are classified according to the antioxidant determination method, and the antioxidant analysis is classified into antioxidant molecules and non-antioxidant molecules based on the experimental results, so as to construct a binary classification database of antioxidant data with different antioxidant properties;

[0012] The predictive antioxidant module is used to obtain user osteoarthritis data, build an osteoarthritis simulation model based on the osteoarthritis data, and train the osteoarthritis simulation model with data from the antioxidant binary classification database; predict the impact of plantain antioxidant data on bones and joints. If it is less than the preset impact value, the antioxidant data is deemed qualified; if it is greater than the preset impact value, ultrasonic assistance is used to continue to purify the antioxidant data.

[0013] As a further improvement of the present invention, the data extraction module includes:

[0014] The extraction submodule is used to extract antioxidant substances using an ultrasonic generator with a set frequency of 20kHz, a processing time of 3 seconds, a pause of 7 seconds, and an output power of 30%; the extraction time is 45 minutes, and the extract is filtered using a 0.45μm injection filter; and the total phenol content and total flavonoid content are determined by measuring at 765nm and 510nm, respectively, and a calibration curve is created to determine the TPC and TFC concentrations of the extract;

[0015] The evaluation submodule is used to determine the antioxidant activity of the extract, measuring at 517 nm and 734 nm respectively; measuring the absorbance change of the mixture, and drawing a standard curve of Trolox concentration and absorbance based on Trolox standard solutions of different concentrations; and calculating the Trolox equivalent unit based on the absorbance change and the standard curve;

[0016] The first analysis submodule is used to perform data preprocessing and feature extraction on the Trolox equivalent unit value if it is greater than a preset value, and to perform principal component analysis on the processed data, and input the analysis results into the Plantago asiatica molecular experimental database to form experimental data.

[0017] As a further improvement of the present invention, the evaluation submodule includes:

[0018] A variation unit is used to measure the absorbance variation of the mixture at 517 nm and 734 nm respectively, the extract is mixed with the free radical solution, and the absorbance is measured at a wavelength of 517 nm; the extract is mixed with the free radical cation, and the absorbance is measured at a wavelength of 734 nm;

[0019] A drawing unit is used to draw a standard curve between Trolox concentration and absorbance using Trolox standard solutions of different concentrations; a standard curve is drawn by measuring the absorbance at 734 nm using Trolox solutions in the range of 0-15 μm;

[0020] The first calculation unit is used to calculate the Trolox equivalent unit of the sample according to the absorbance change and the standard curve; by measuring the absorbance change at 517nm and 734nm, combined with the standard curve, the Trolox concentration corresponding to the extract is obtained. If it is greater than the preset value, it is judged that the antioxidant capacity meets the standard.

[0021] As a further improvement of the present invention, the first analysis submodule includes:

[0022] A preprocessing unit is used to preprocess the data whose antioxidant capacity meets the standard; wherein the preprocessing includes operations such as data cleaning, missing value processing, outlier processing and standardization;

[0023] The second calculation unit is used to calculate the standardized data to obtain a correlation matrix and a covariance matrix, and obtain the linear relationship between the variables through the covariance matrix; and evaluate the correlation between the variables through the correlation matrix;

[0024] The second analysis unit is used to perform eigenvalue decomposition on the covariance matrix or the correlation matrix to obtain eigenvalues ​​and corresponding eigenvectors; select the number of principal components according to the size of the eigenvalues, select the principal components whose contribution values ​​exceed the preset contribution rates, project the original data onto the selected principal components, and obtain a new low-dimensional data representation.

[0025] As a further improvement of the present invention, the first data acquisition module includes:

[0026] The second data acquisition submodule is used to retrieve antioxidant experimental records from the Plantain Experiment Database, extract relevant antioxidant analysis, screen the retrieved data, and capture information related to small molecule antioxidants; wherein the information related to small molecule antioxidants includes chemical structure, antioxidant determination method, determination results, determination target and references;

[0027] The classification submodule is used to classify the time records according to the antioxidant determination method; analyze the test results under each classification, calculate the concentration and content of each antioxidant component, and perform data analysis;

[0028] Among them, they are classified according to hydrogen atom transfer reaction, electron transfer reaction, lipid peroxide inhibition, and Nrf2 antioxidant response element signaling pathway;

[0029] A database submodule is constructed to classify antioxidant analysis into antioxidant molecules and non-antioxidant molecules according to the antioxidant assay results; an antioxidant threshold is set. If the antioxidant threshold is exceeded, the compounds with antioxidant activity are classified as antioxidant molecules; if the threshold is lower than the threshold, the compounds with antioxidant activity are classified as non-antioxidant molecules; a binary classification database is constructed based on the classified data.

[0030] As a further improvement of the present invention, the prediction anti-oxidation module comprises:

[0031] The third data acquisition submodule is used to obtain the user's bone and joint data, clean the bone and joint data, remove missing values, etc., convert categorical variables into virtual variables, and remove data values ​​in numerical data; build an osteoarthritis simulation model based on the preprocessed data;

[0032] The first simulation submodule is used to retrieve the antioxidant data of plantain from the antioxidant binary database to form a data set, and divide the data set into a training set and a test set; train the osteoarthritis simulation model according to the training set, and input the extracted antioxidant data of plantain into the osteoarthritis simulation model for simulation;

[0033] The result output submodule is used to obtain the impact value of plantain oxidation data on bone joints according to the simulation results. If it is greater than the preset impact value, the antioxidant data will continue to be purified; if it is less than the preset impact value, the antioxidant data purification is deemed qualified.

[0034] As a further improvement of the present invention, the simulation submodule includes:

[0035] A data retrieval unit is used to retrieve the antioxidant data of plantain from the database to form a data set; divide the data set into a training set and a test set; and perform preprocessing operations on the data set such as removing outliers, balancing data distribution, converting categorical variables, and standardizing numerical variables;

[0036] The model training unit is used to train the osteoarthritis simulation model using the training set; during the training process, the antioxidant data of plantain and the historical bone and joint treatment data of the user are analyzed to obtain the relationship between the antioxidant data of plantain and the historical bone and joint treatment data of the user, and the relationship is learned;

[0037] The result analysis unit is used to recursively screen variables after the training is completed. Based on the results of each training of the osteoarthritis simulation model, the variables with a smaller value than the preset value are gradually eliminated. According to the final training results of the osteoarthritis simulation model, the variables that contribute most to the simulation results are extracted. The extracted plantain antioxidant data is input into the osteoarthritis simulation model for simulation.

[0038] As a further improvement of the present invention, the model training unit includes:

[0039] An analysis subunit is used to collect a node set of plantain antioxidant data and a user's historical bone and joint treatment data, analyze the output data and characteristics of each node in the node set, and analyze the dependency relationship between nodes based on the characteristic analysis results of the node input data and output data;

[0040] A dependency matrix subunit is used to construct a dependency matrix between nodes according to the dependency relationship, calculate the similarity between the output data of the first node and the output data of the second node, and determine the dependency relationship between the output data of the first node and the data of the second node according to a threshold value between the similarities;

[0041] The optimization analysis subunit is used to identify the node configuration information that can be optimized, as well as the potential parallel execution sets and sequential execution sets between nodes; according to the identified parallel execution sets and sequential execution sets, the configuration execution order of the optimized acquisition tasks is reordered.

[0042] As a further improvement of the present invention, the result analysis unit comprises:

[0043] The variable screening subunit is used to gradually eliminate variables less than the threshold based on each training result of the osteoarthritis simulation model, and extract the variable value that contributes the most to the simulation result according to the final training result of the osteoarthritis simulation model; and obtain the final bone and joint simulation model

[0044] The second simulation subunit is used to input the plantain extraction data into the bone and joint simulation model, simulate the input plantain extraction data, and obtain the treatment effect of the user's osteoarthritis; and compare the treatment effect of the user's osteoarthritis with the preset treatment effect;

[0045] The comparison subunit is used to evaluate according to the comparison results, obtain the impact value of the antioxidant data of plantain on the user's bones and joints, verify the simulation results with the verification set, evaluate with the preset verification value, and adjust the bone and joint simulation model according to the evaluation results.

[0046] As a further improvement of the present invention, the result output submodule comprises:

[0047] A determination unit is used to determine the impact value of the oxidation data of plantain on the bone joints according to the simulation result. If it is greater than the preset impact value, the antioxidant data is further purified. If it is less than the preset impact value, the antioxidant data purification is deemed qualified.

[0048] The adjustment unit is used to analyze the antioxidant data of the simulation results to obtain the antioxidant capacity; compare the preset influence value with the simulation result to obtain the data gap between the preset influence value and the simulation result, and adjust the ultrasonic auxiliary parameters according to the data gap;

[0049] The qualified unit is used to further purify the antioxidant data with the adjusted ultrasonic-assisted parameters, input the purified data into the osteoarthritis simulation model, and re-simulate the prediction; it is iterated in sequence until the antioxidant data is purified to be qualified.

[0050] The present invention extracts antioxidant substances from plantain by ultrasound-assisted extraction, and performs antioxidant activity evaluation and main component analysis on the extract. The ultrasonic-assisted extraction technology can significantly improve the extraction rate of antioxidant substances, and at the same time, through antioxidant activity evaluation and main component analysis, the effectiveness and safety of the extract are ensured. Antioxidant experimental records are obtained from the plantain molecular experimental database, and classified according to the antioxidant determination method to construct a binary classification database of antioxidant data. Through classification and database construction, systematic management of antioxidant data is achieved. A simulation model is constructed based on osteoarthritis data, and the data training model in the antioxidant binary classification database is used to predict the effect of plantain antioxidant data on osteoarthritis. Through the training and prediction of the simulation model, the potential impact of plantain antioxidant substances on the effect of treating osteoarthritis can be effectively evaluated, providing a scientific basis for clinical application. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 A block diagram of an embodiment of a system for extracting flower-nourishing substances from plantain of the present invention;

[0052] Figure 2 This is a block diagram of a data extraction module of an embodiment of a system for extracting flower-nourishing substances from plantain of the present invention;

[0053] Figure 3 This is a block diagram of an evaluation submodule of an embodiment of the system for extracting flower-growing substances from plantain;

[0054] Figure 4 This is a block diagram of the first analysis submodule of an embodiment of a system for extracting flower-nourishing substances from plantain of the present invention;

[0055] Figure 5 This is a block diagram of a first data acquisition module of an embodiment of a system for extracting flower-nourishing substances from plantain of the present invention;

[0056] Figure 6 This is a block diagram of a prediction antioxidant module of an embodiment of a system for extracting flower-nourishing substances from plantain of the present invention;

[0057] Figure 7 This is a block diagram of the first simulation submodule of an embodiment of a system for extracting flower-nourishing substances from plantain of the present invention;

[0058] Figure 8 This is a block diagram of a model training unit of an embodiment of a system for extracting flower-nourishing substances from plantain of the present invention;

[0059] Fig. 9 This is a block diagram of a result analysis unit of an embodiment of a system for extracting flower-nourishing substances from plantain of the present invention;

[0060] Fig.10 This is a flow chart of the steps of an embodiment of the method for extracting flower-nourishing substances from plantain of the present invention;

[0061] Fig.11 It is a structural schematic diagram of an embodiment of an electronic device of the present invention;

[0062] Fig.12 It is a schematic structural diagram of an embodiment of the storage medium of the present invention. DETAILED DESCRIPTION

[0063] 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.

[0064] The terms "first", "second" and "third" in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Therefore, the features defined as "first", "second" and "third" can explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. All directional indications (such as up, down, left, right, front, back...) in the embodiments of the present invention are only used to explain the relative position relationship, movement, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication also changes accordingly. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices.

[0065] Reference to an "embodiment" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0066] like Figure 1 As shown, this embodiment provides an embodiment of a system for extracting antioxidant substances from plantain. In this embodiment, the system for extracting antioxidant substances from plantain comprises:

[0067] Data extraction module 1 is used for ultrasonic-assisted extraction of antioxidant substances from plantain, antioxidant activity evaluation of the extracted antioxidant substances, main component analysis of the evaluation results, and forming antioxidant experimental records; the antioxidant experimental records are input into the plantain molecular experimental database;

[0068] The first data acquisition module 2 is used to obtain antioxidant experimental records from the plantain molecular experimental database; the antioxidant experimental records are classified according to the antioxidant determination method, and the antioxidant analysis is classified into antioxidant molecules and non-antioxidant molecules based on the experimental results, and a binary classification database of antioxidant data with different antioxidant properties is constructed;

[0069] The antioxidant prediction module 3 is used to obtain the user's osteoarthritis data, build an osteoarthritis simulation model based on the osteoarthritis data, and train the osteoarthritis simulation model with data in the antioxidant binary classification database; predict the impact of plantain antioxidant data on bones and joints. If it is less than the preset impact value, the antioxidant data is qualified; if it is greater than the preset impact value, ultrasonic assistance is used to continue to purify the antioxidant data.

[0070] Preferably, in the data extraction module 1 of this embodiment, the antioxidant substances in plantain are extracted by ultrasound, and the antioxidant activity evaluation and main component analysis of the extract are performed; the use of ultrasound-assisted extraction technology can significantly improve the extraction rate of antioxidant substances, and at the same time, through antioxidant activity evaluation and main component analysis, the effectiveness and safety of the extract are ensured. The first data acquisition module 2 obtains antioxidant experimental records from the plantain molecular experimental database, and classifies them according to the antioxidant determination method to construct a binary classification database of antioxidant data; through classification and database construction, systematic management of antioxidant data is achieved. The prediction antioxidant module 3 constructs a simulation model based on osteoarthritis data, and uses the data training model in the antioxidant binary classification database to predict the effect of plantain antioxidant data on osteoarthritis; through the training and prediction of the simulation model, the potential effect of plantain antioxidant substances on the treatment of osteoarthritis can be effectively evaluated, providing a scientific basis for clinical application.

[0071] Therefore, this embodiment improves the efficiency of antioxidant extraction and evaluation, and provides new ideas and methods for the treatment of osteoarthritis through data management and model prediction.

[0072] Further, if Figure 2 As shown, the data extraction module 1 specifically includes:

[0073] The extraction submodule 11 is used to extract antioxidant substances using an ultrasonic generator, with a set frequency of 20 kHz, a processing time of 3 seconds, a pause of 7 seconds, and an output power of 30%; the extraction time is 45 minutes, and the extract is filtered using a 0.45 μm injection filter; and the total phenol content and total flavonoid content are measured at 765 nm and 510 nm, respectively, and a calibration curve is created to determine the TPC and TFC concentrations of the extract;

[0074] Among them, the expression of the ultrasonic generator optimizing its operating parameters is:

[0075]

[0076] In the formula, E represents the working efficiency of the ultrasonic generator, P represents the output power, expressed in percentage (such as 30%), T p Indicates the processing time in seconds (such as 3 seconds), T srepresents the pause time (Pause Time), the unit is seconds (such as 7 seconds), F represents the ultrasonic frequency, the unit is kHz (such as 20kHz), F0 represents the base frequency, the unit is kHz (such as 20kHz), T e Indicates the extraction time (Extraction Time), in minutes (such as 45 minutes), T f Indicates the filtering time (Filtering Time), in seconds (e.g., the filtering time is the time required for the extract to be filtered through a 0.45 μm syringe filter); P·T p represents the energy output during the processing time, It means that the effect of pause time on processing time is taken into account. The longer the pause time, the lower the efficiency. It means that the effect of frequency change on efficiency is taken into account. The higher the frequency, the higher the efficiency. It means that the effect of extraction time and filtration time on efficiency is taken into account. The longer the extraction time, the lower the efficiency; the longer the filtration time, the lower the efficiency; by adjusting parameters such as output power, processing time, pause time, frequency and filtration time, this expression can be optimized to improve the working efficiency of the ultrasonic generator. For example, increasing output power, shortening processing time, reducing pause time, increasing frequency or reducing filtration time can improve efficiency to a certain extent;

[0077] Evaluation submodule 12 is used to determine the antioxidant activity of the extract, measuring at 517 nm and 734 nm respectively; measuring the absorbance change of the mixture, and drawing a standard curve of Trolox concentration and absorbance according to Trolox standard solutions of different concentrations; and calculating the Trolox equivalent unit according to the absorbance change and the standard curve;

[0078] The first analysis submodule 13 is used to perform data preprocessing and feature extraction on the Trolox equivalent unit value if it is greater than a preset value, and to perform principal component analysis on the processed data, and input the analysis results into the Plantago asiatica molecular experimental database to form experimental data.

[0079] Preferably, the extraction submodule 11 of this embodiment uses a differential acoustic wave generator for extraction, sets the frequency to 20kHz, the processing time to 3 seconds, the pause to 7 seconds, and the output power to 30%; the extraction time is 45 minutes, and the extract is filtered using a 0.45μm injection filter; and the total phenol content and total flavonoid content are measured, respectively, at 765nm and 510nm, and a calibration curve is created to determine the TPC and TFC concentrations of the extract; through ultrasonic-assisted extraction technology, the efficiency and the content of the bioactive components of the extract are improved. The evaluation submodule 12 sequentially determines the oxidative activity of the extract, measures at 517nm and 734nm, measures the absorbance change of the mixture, draws a Trolox concentration and absorbance standard curve, and calculates the Trolox equivalent unit according to the absorbance change and the standard curve; the antioxidant activity of the extract is proved by DPPH and ABTS tests, ensuring the accuracy and reliability of the evaluation; using Trolox as a standard, drawing a Trolox concentration and absorbance standard curve, ensuring the accuracy and consistency of the measurement. If the Trolox equivalent unit value is greater than the preset value, the analysis submodule 13 performs data preprocessing and feature extraction and other operations; performs principal component analysis on the processed data, and inputs the analysis results into the plantain molecular experimental database to form experimental data; improves the accuracy and efficiency of data analysis through data preprocessing and feature extraction, and inputs the analysis results into the plantain molecular experimental database.

[0080] Therefore, this example achieves a comprehensive evaluation and analysis of the bioactive components in plant extracts through ultrasound-assisted extraction technology, Trolox equivalent antioxidant capacity determination method and efficient data analysis method.

[0081] Further, if Figure 3 As shown, the evaluation submodule 12 specifically includes:

[0082] The variation unit 121 is used to measure the absorbance variation of the mixture at 517 nm and 734 nm respectively, the extract is mixed with the free radical solution, and the absorbance is measured at a wavelength of 517 nm; the extract is mixed with the free radical cation, and the absorbance is measured at a wavelength of 734 nm;

[0083] A drawing unit 122 is used to draw a standard curve between Trolox concentration and absorbance using Trolox standard solutions of different concentrations; a standard curve is drawn by measuring the absorbance at 734 nm using Trolox solutions in the range of 0-15 μm;

[0084] The first calculation unit 123 is used to calculate the Trolox equivalent unit of the sample according to the absorbance change and the standard curve; by measuring the absorbance change at 517nm and 734nm, combined with the standard curve, the Trolox concentration corresponding to the extract is obtained. If it is greater than a preset value, it is judged that the antioxidant capacity meets the standard.

[0085] Preferably, the variation unit 121 of this embodiment measures the absorbance variation of the mixture at 517nm and 734nm respectively. The extract is mixed with the free radical solution, and the absorbance is measured at a wavelength of 517nm; the extract is mixed with the free radical cation, and the absorbance is measured at a wavelength of 734nm; by measuring the absorbance at different wavelengths, the scavenging ability of the sample for DPPH free radicals and ABTS free radicals can be evaluated respectively; the drawing unit 122 uses Trolox standard solutions of different concentrations to draw a standard curve between Trolox concentration and absorbance; a Trolox solution in the range of 0-15μM is used to draw a standard curve by measuring the absorbance at 734nm; by constructing a standard curve, the scavenging ability of the sample for DPPH free radicals and ABTS free radicals can be evaluated respectively. The absorbance of the sample is converted into the corresponding Trolox concentration, so as to quantify the antioxidant capacity of the sample; the first calculation unit 123 calculates the Trolox equivalent unit of the sample according to the absorbance change and the standard curve; by measuring the absorbance change at 517nm and 734nm, combined with the standard curve, the Trolox concentration corresponding to the extract is obtained, and if it is greater than the preset value, it is judged that the antioxidant capacity meets the standard; by calculating the Trolox equivalent unit of the sample, the antioxidant capacity of the sample is quantitatively evaluated, and compared with the preset standard, so as to quickly screen out samples with significant antioxidant activity.

[0086] Therefore, this embodiment achieves efficient and accurate evaluation of the antioxidant capacity of the sample through multi-wavelength measurement, standard curve construction and quantitative calculation.

[0087] Further, if Figure 4 As shown, the first analysis submodule 13 specifically includes:

[0088] A preprocessing unit 131 is used to preprocess the data whose antioxidant capacity meets the standard; wherein the preprocessing includes operations such as data cleaning, missing value processing, outlier processing and standardization;

[0089] The second calculation unit 132 is used to calculate the standardized data to obtain a correlation matrix and a covariance matrix, obtain the linear relationship between the variables through the covariance matrix; and evaluate the correlation between the variables through the correlation matrix;

[0090] The second analysis unit 133 is used to perform eigenvalue decomposition on the covariance matrix or the correlation matrix to obtain eigenvalues ​​and corresponding eigenvectors; select the number of principal components according to the size of the eigenvalues, select the principal components whose contribution values ​​exceed the preset contribution rate, and project the original data onto the selected principal components to obtain a new low-dimensional data representation;

[0091] Among them, the expression for eigenvalue decomposition of the covariance matrix or correlation matrix is:

[0092]

[0093] In the formula, Λ represents the eigenvalue matrix, C represents the set of eigenvalues, ij Represents the element of the covariance matrix or correlation matrix, represents the element of the i-th row and j-th column, μ i represents the mean of the i-th variable, σ i represents the standard deviation of the i-th variable, and n represents the dimension of the matrix, that is, the number of variables; It means calculating the relationship between each element in the covariance matrix or correlation matrix and its corresponding mean and standard deviation, and summing them up; It means calculating the sum of the squares of each element in the covariance matrix or correlation matrix, summing them, and then taking the square root; standardizing the covariance matrix or correlation matrix so that its mean is 0 and its standard deviation is 1; performing eigenvalue decomposition on the standardized matrix to obtain the eigenvalue matrix and eigenvector matrix; selecting the number of principal components according to the size of the eigenvalue, and selecting the principal components whose contribution value exceeds the preset contribution rate; projecting the original data onto the selected principal components to obtain a new low-dimensional data representation. The expression comprehensively considers the elements, mean, standard deviation and the relationship between the matrix, and describes the process of eigenvalue decomposition through complex mathematical operations. By adjusting the elements, mean and standard deviation of the matrix, this expression can be optimized to better understand and process the eigenvalue decomposition of the covariance matrix or correlation matrix.

[0094] Preferably, the preprocessing unit 131 of this embodiment ensures data quality by identifying and correcting errors, missing or abnormal values, and uses deletion, interpolation and other methods to process missing values ​​to maintain the integrity and accuracy of the data set; identifies and processes outliers by methods such as standard deviation and box plot to avoid the influence of these extreme values ​​on the analysis results; converts data to a unified scale, eliminates dimensional differences, and makes the influence of different features on the principal components equal; standardization can improve the generalization ability and stability of the model. The second calculation unit 132 calculates the covariance matrix based on the standardized data to reflect the linear relationship between variables; the covariance matrix is ​​an important tool for measuring the degree of correlation between variables and reveals the potential structure in the data; the correlation between variables is evaluated by the correlation matrix, and the correlation coefficient is used to describe the strength and direction of the relationship between variables; the correlation matrix replaces the covariance matrix for PCA analysis, especially when the units of the variables are inconsistent. The analysis unit 133 is used to perform eigenvalue decomposition on the covariance matrix or the correlation matrix to obtain eigenvalues ​​and corresponding eigenvectors; the eigenvectors represent the directions of the principal components, and the eigenvalues ​​represent the variance of the data in these directions; the number of principal components is selected according to the eigenvalues, and several larger principal components are usually selected to retain the variance information of most of the data; the principal components whose contribution values ​​exceed the preset contribution rates are selected to reduce the data dimension and highlight important patterns; the original data is projected onto the selected principal components to obtain a new low-dimensional data representation. This embodiment simplifies the data set, removes noise, and discovers potential relationships, providing a basis for subsequent modeling and analysis.

[0095] Therefore, this embodiment achieves the goals of data cleaning, standardization, dimensionality reduction and feature extraction through the preprocessing unit, the second computing unit and the analysis unit, thereby improving the accuracy and efficiency of data analysis.

[0096] Further, if Figure 5 As shown, the first data acquisition module 2 specifically includes:

[0097] The second data acquisition submodule 21 is used to retrieve antioxidant experimental records from the Plantain Experiment Database, extract relevant antioxidant analysis, screen the retrieved data, and capture information related to small molecule antioxidants; wherein the information related to small molecule antioxidants includes chemical structure, antioxidant determination method, determination results, determination target and references;

[0098] The classification submodule 22 is used to classify the time records according to the antioxidant determination method; analyze the test results under each classification, calculate the concentration and content of each antioxidant component, and perform data analysis;

[0099] Among them, they are classified according to hydrogen atom transfer reaction, electron transfer reaction, lipid peroxide inhibition, and Nrf2 antioxidant response element signaling pathway;

[0100] A database construction submodule 23 is used to classify antioxidant analysis into antioxidant molecules and non-antioxidant molecules according to the antioxidant assay results; set an antioxidant threshold, if it exceeds the antioxidant threshold, the antioxidant active compound is classified as an antioxidant molecule; if it is below the threshold, the antioxidant active compound is classified as a non-antioxidant molecule; and construct a binary classification database based on the classified data;

[0101] Among them, the relevant information of antioxidant molecules and non-antioxidant molecules includes chemical structure, determination method and determination results.

[0102] Preferably, the second data acquisition submodule 21 of this embodiment extracts antioxidant experimental records from the plantain experimental database, screens information related to small molecule antioxidants; collects chemical structures, antioxidant determination methods, determination results, determination antioxidant points and references of small molecule antioxidants; generates two-dimensional and three-dimensional chemical structures of antioxidants using software, and performs data analysis; captures all relevant information related to small molecule antioxidants, including chemical structures and antioxidant determination methods. The chemical structure generated by the software in this embodiment can intuitively display the molecular characteristics of antioxidants, which is convenient for subsequent analysis and research; and provides basic data for classification and construction of database submodules. The classification submodule 22 classifies the time records according to the antioxidant determination method; analyzes the test results under each classification and calculates the concentration and content of each antioxidant component; classifies according to hydrogen atom transfer reaction, electron transfer reaction, lipid peroxide inhibition, Nrf2 antioxidant response oxidative signaling pathway, etc.; classifies the time records by different antioxidant determination methods to ensure the accuracy of the classification; calculates the concentration and content of each antioxidant component and provides detailed data analysis results; provides data support for research and application based on the test results under different classifications. The database construction submodule 23 classifies the antioxidant analysis into antioxidant molecules and non-antioxidant molecules according to the antioxidant determination results; classifies the antioxidant analysis into antioxidant molecules and non-antioxidant molecules according to the antioxidant determination results; constructs a two-category database based on the classified data, including relevant information of antioxidant molecules and non-antioxidant molecules; the database contains relevant information of all antioxidant molecules and non-antioxidant molecules, including chemical structure, antioxidant determination method and determination results; by setting the antioxidant threshold, compounds with significant antioxidant activity can be quickly screened out, which is convenient for subsequent research and application; the constructed database can provide important data support for drug development, food additives and other fields.

[0103] Therefore, this embodiment realizes the whole process from data acquisition, classification to database construction through different technical means. Each module has its unique technical characteristics and expected technical effects, and together constitutes a complete antioxidant research system; through the application of these modules, the relevant data of antioxidants can be effectively screened, analyzed and utilized, providing strong support for research and application in related fields.

[0104] Furthermore, if Figure 6 As shown, the prediction antioxidant module 3 specifically includes:

[0105] The third data acquisition submodule 31 is used to acquire the bone and joint data of the user, clean the bone and joint data, remove missing values, etc., convert categorical variables into virtual variables, and remove data values ​​in numerical data; and construct an osteoarthritis simulation model based on the preprocessed data;

[0106] The first simulation submodule 32 is used to retrieve the antioxidant data of plantain from the antioxidant binary database to form a data set, and divide the data set into a training set and a test set; train the osteoarthritis simulation model according to the training set, and input the extracted antioxidant data of plantain into the osteoarthritis simulation model for simulation;

[0107] The result output submodule 33 is used to obtain the impact value of the plantain oxidation data on the bone joints according to the simulation results. If it is greater than the preset impact value, the antioxidant data will continue to be purified; if it is less than the preset impact value, the antioxidant data purification is deemed qualified.

[0108] Preferably, the third data acquisition submodule 31 of this embodiment mainly involves the acquisition and preprocessing of bone and joint data. Specifically, it includes operations such as cleaning bone and joint data, removing missing values, converting categorical variables into virtual variables, and removing outliers in numerical data; through the preprocessing steps, the quality and reliability of the data can be improved, and a more accurate data basis can be provided for subsequent model construction. This embodiment improves the accuracy and stability of the osteoarthritis simulation model. The simulation submodule 32 retrieves the plantain antioxidant data in the antioxidant binary database to form a data set, and divides it into a training set and a test set; then, the osteoarthritis simulation model is trained according to the training set, and the extracted plantain antioxidant data is input into the osteoarthritis simulation model for simulation; through simulation, the effect of plantain antioxidant data on osteoarthritis can be evaluated, thereby optimizing the purification process of antioxidant data; if the simulation results show that the impact value of antioxidant data on bone and joints is greater than the preset impact value, then continue to purify; otherwise, the purification is deemed qualified. The result output submodule 33 obtains the impact value of the antioxidant data of plantain on bone joints according to the simulation results, and judges whether it is necessary to continue purification or determine that the purification is qualified according to the impact value; through the judgment mechanism, the quality of the antioxidant data can be effectively controlled to ensure its safety and effectiveness in application. This embodiment improves the reliability and applicability of the antioxidant data in practical applications.

[0109] Therefore, this embodiment achieves in-depth analysis and optimization of the factors affecting osteoarthritis through steps such as data preprocessing, model training, and simulation evaluation, thereby improving the application effect of antioxidant data in the treatment of osteoarthritis.

[0110] Furthermore, the third data acquisition submodule 31 specifically includes:

[0111] The result combination unit is used to select features related to osteoarthritis from the preprocessed data, such as age, gender, weight and bone density, and divide the features into feature matrix and label vector as training data. The features will be used as the input of the model; the features are used to train the support vector machine and random forest models; the trained support vector machine and random forest are used to generate the prediction probability on the training set; the prediction probabilities of the support vector machine and random forest are combined to construct a new input matrix;

[0112] The result weighing unit is used to select logistic regression as the meta-model and train the logistic regression model using the input matrix and the labels of the original training set (i.e., the actual results of osteoarthritis); the logistic regression model will learn how to weigh the prediction results of the support vector machine and the random forest;

[0113] The model validation unit is used to evaluate the performance of the model using 5-fold cross validation and optimize the parameters of the support vector machine and random forest through grid search.

[0114] Preferably, the result combination unit of this embodiment selects features related to osteoarthritis (such as age, gender, weight and bone density, etc.) from the preprocessed data to ensure that the data for model training is relevant and representative; the feature data is divided into a feature matrix and a label vector to provide structured input data for model training; the selected features are used to train the support vector machine (SVM) and random forest (Random Forest) models respectively to generate the prediction results of the basic model; the prediction probabilities of SVM and Random Forest are combined into a new input matrix to provide input for the training of the meta-model. Significance achieved: By selecting features related to the target, the prediction accuracy and relevance of the model are improved; by training two different basic models (SVM and Random Forest), the diversity of the model is enhanced, and more diverse prediction results are provided for subsequent integrated learning. The result weighing unit selects logistic regression as the meta-model, and uses its linear weighing ability to learn how to integrate the prediction results of SVM and Random Forest; the combined input matrix and the labels of the original training set are used to train the logistic regression model so that it can effectively weigh the prediction results of the basic model. Significance achieved: Through the trade-off of the logistic regression model, the advantages of SVM and Random Forest can be effectively combined to improve the prediction accuracy of the overall model; the logistic regression model is simple and easy to explain, which can simplify the complexity of the integrated model and facilitate model evaluation and application. The model validation unit uses 5-fold cross-validation to evaluate the performance of the model to ensure that the model performs consistently on different data subsets and avoid overfitting; the parameters of the support vector machine and random forest are optimized through the grid search method to find the best model configuration and improve the generalization ability of the model. Significance achieved: Through cross-validation, the model's performance on different data subsets is ensured to improve the robustness and stability of the model; through parameter optimization, the best model configuration is found, which further improves the model's prediction performance and generalization ability.

[0115] In summary, through the collaborative work of the result combination unit, the result weighing unit and the model verification unit, the third data acquisition submodule 31 in this embodiment realizes the complete process from data selection, model training, result weighing to model verification. It not only improves the prediction accuracy and relevance of the model, but also enhances the robustness and generalization ability of the model, providing a more reliable and effective tool for the diagnosis and prediction of osteoarthritis.

[0116] Furthermore, if Figure 7 As shown, the first simulation submodule 32 specifically includes:

[0117] The data retrieval unit 321 is used to retrieve the antioxidant data of plantain from the database to form a data set; divide the data set into a training set and a test set; perform preprocessing operations on the data set such as removing outliers, balancing data distribution, converting categorical variables, and standardizing numerical variables;

[0118] The model training unit 322 is used to train the osteoarthritis simulation model using the training set; during the training process, the plantain antioxidant data and the user's historical bone and joint treatment data are analyzed to obtain the relationship between the plantain antioxidant data and the user's historical bone and joint treatment data, and the relationship is learned;

[0119] The result analysis unit 323 is used to recursively screen variables after the training is completed. Based on each training result of the osteoarthritis simulation model, the variables that are less than the preset value are gradually eliminated. According to the final training result of the osteoarthritis simulation model, the variables that contribute the most to the simulation result are extracted; and the extracted plantain antioxidant data are input into the osteoarthritis simulation model for simulation.

[0120] Preferably, the data retrieval unit 321 of this embodiment retrieves the plantain auxiliary data from the database to form a data set; divides the data set into a training set and a test set; identifies and processes outliers that deviate from the entire data, adjusts the sample distribution, ensures the balance of the data set, converts categorical variables into numerical variables, facilitates the processing of the osteoarthritis simulation model, eliminates dimensional images, and ensures comparability between indicators; improves the quality of the data set and reduces noise interference in model training by removing outliers and balancing data distribution; standardization ensures the comparability between different features, accelerates model convergence, and improves model training efficiency; through categorical variable conversion and numerical variable standardization, the model can better understand and utilize data features and enhance the generalization ability of the model. The model training unit 322 uses the training set to train the osteoarthritis simulation model; analyzes the plantain auxiliary data and the user's historical treatment bone and joint data to obtain the relationship between the two; through analysis, learns the relationship between the plantain auxiliary data and the user's historical treatment bone and joint data; by analyzing and learning the relationship between the two, the model can better capture the association between the data and improve the prediction accuracy of the model; can find the potential association between the plantain auxiliary data and the user's historical treatment bone and joint data, and provide a basis for data analysis and model optimization. The result analysis unit 323 recursively screens variables, gradually eliminates variables less than the preset value, and extracts the variables that contribute most to the simulation results according to the final training results of the osteoarthritis simulation model; inputs the extracted plantain auxiliary data into the osteoarthritis simulation model for simulation; through variable screening, removes redundant variables, simplifies the model structure, and reduces the computational complexity; extracts the variables that contribute most to the simulation results, so that the model focuses more on key features and improves the prediction accuracy of the model. Simulation through the optimized model can more accurately reflect the actual situation and improve the reliability of the simulation.

[0121] Therefore, this embodiment realizes the automation and optimization of data preprocessing, model training and result analysis, significantly improving the efficiency of data processing and the performance of the model; through preprocessing operations such as outlier processing, data distribution balance, categorical variable conversion and numerical variable standardization, the quality of data and the stability of the model are ensured; through data analysis and relationship learning, the prediction ability of the model and data association discovery are improved; through variable screening and model optimization, the model structure is simplified and the accuracy of the simulation results is improved. This implementation constitutes an efficient and reliable osteoarthritis simulation system.

[0122] Furthermore, if Figure 8 As shown, the model training unit 322 specifically includes:

[0123] The analysis subunit 3221 is used to collect the node set of plantain antioxidant data and the user's historical bone and joint treatment data, analyze the output data and characteristics of each node in the node set, and analyze the dependency relationship between the nodes according to the characteristic analysis results of the node input data and output data;

[0124] The dependency matrix subunit 3222 is used to construct a dependency matrix between nodes according to the dependency relationship, calculate the similarity between the output data of the first node and the output data of the second node, and determine the dependency relationship between the output data of the first node and the data of the second node according to the threshold value between the similarities;

[0125] The optimization analysis subunit 3223 is used to identify the node configuration information that can be optimized, as well as the potential parallel execution sets and sequential execution sets between nodes; and re-order the configuration execution order of the optimized acquisition task according to the identified parallel execution sets and sequential execution sets.

[0126] Preferably, the analysis subunit 3221 of this embodiment collects the node set of plantain antioxidant data and the user's historical treatment bone and joint data, analyzes the output data and its features of each node; uses the feature extraction unit to extract features in the interaction data, and calculates the similarity between these features through the similarity calculation unit, so as to judge the dependency relationship between the nodes. The dependency matrix subunit 3222 constructs the dependency matrix between the nodes, and calculates the similarity between the output data of the first node and the output data of the second node. The optimization analysis subunit 3223 identifies the node configuration information that can be optimized, and reorders the configuration execution order of the optimized acquisition task according to the parallel execution set and the forward execution set.

[0127] Therefore, this embodiment improves the accuracy and robustness of data analysis, optimizes the data processing flow, improves task execution efficiency, and enhances the scalability and flexibility of the system.

[0128] Further, if Fig. 9 As shown, the result analysis unit 323 specifically includes:

[0129] The variable screening subunit 3231 is used to gradually eliminate variables less than a threshold value based on each training result of the osteoarthritis simulation model, and extract the variable value that contributes the most to the simulation result according to the final training result of the osteoarthritis simulation model, so as to obtain the final bone joint simulation model;

[0130] The second simulation subunit 3232 is used to input the plantain extraction data into the bone and joint simulation model, simulate the input plantain extraction data, and obtain the treatment effect of the user's osteoarthritis; and compare the treatment effect of the user's osteoarthritis with the preset treatment effect;

[0131] The comparison subunit 3233 is used to evaluate based on the comparison results, obtain the impact value of the plantain antioxidant data on the user's bones and joints, use the verification set to verify the simulation results, evaluate with the preset verification value, and adjust the bone and joint simulation model according to the evaluation results.

[0132] Preferably, the variable screening subunit 3231 of this embodiment gradually eliminates variables less than the threshold value based on each training result of the osteoarthritis simulation model, and extracts the variable value that contributes the most to the simulation result; by effectively screening variables, the model complexity is reduced, overfitting or underfitting is avoided, and the prediction accuracy and generalization ability of the model are improved. The simulation subunit 3232 inputs the plantain extraction data into the bone and joint simulation model for simulation to obtain the osteoarthritis treatment effect of the user; similar to the feature extraction and model prediction process in machine learning, simulation is performed by inputting specific data to evaluate the treatment effect; through the simulation model, the potential efficacy of different treatment methods on osteoarthritis patients can be predicted, providing a scientific basis for clinical decision-making. At the same time, the simulation method of this embodiment can simulate real treatment scenarios to help doctors better understand the effects of treatment plans. The comparison subunit 3233 compares the osteoarthritis treatment effect of the user with the preset treatment effect, and uses the verification set to verify the simulation results; similar to the cross-validation and model evaluation in machine learning, by comparing the actual results with the expected results, the accuracy and reliability of the model are evaluated; through comparative analysis, the impact value of plantain antioxidant data on the user's bones and joints can be obtained, and the bone and joint simulation model can be adjusted according to the evaluation results; it is helpful to optimize the model parameters and improve the prediction accuracy and applicability of the model.

[0133] Therefore, this embodiment improves the accuracy and practicality of the osteoarthritis simulation model through technical means such as variable screening, simulation and comparative analysis, and provides strong support for clinical treatment.

[0134] Furthermore, if Fig.10 As shown, the result output submodule 33 specifically includes:

[0135] A determination unit 331 is used to determine the impact value of the oxidation data of plantain on the bone joints according to the simulation result. If it is greater than the preset impact value, the antioxidant data is further purified. If it is less than the preset impact value, the antioxidant data purification is deemed qualified.

[0136] The adjustment unit 332 is used to analyze the antioxidant data of the simulation results to obtain the antioxidant capacity; compare the preset influence value with the simulation result to obtain the data gap between the preset influence value and the simulation result, and adjust the ultrasonic auxiliary parameters according to the data gap;

[0137] The qualified unit 333 is used to further purify the antioxidant data with the adjusted ultrasound-assisted parameters, input the purified data into the osteoarthritis simulation model, and re-simulate the prediction; iterates in sequence until the antioxidant data is purified to be qualified.

[0138] Preferably, the determination unit 331 of this embodiment obtains the impact value of the antioxidant data of plantain on the bone joints through the simulation results, and compares it with the preset impact value; if the impact value is greater than the preset value, the antioxidant data is continued to be purified; if it is less than the preset value, the antioxidant data purification is deemed qualified; by accurately evaluating the impact of the antioxidant data on the bone joints, the antioxidant data is determined to be qualified only when it reaches a certain threshold. The adjustment unit 332 analyzes the antioxidant data of the simulation results to obtain the antioxidant capacity, and compares the preset impact value with the simulation results to calculate the data gap between the two; adjusts the ultrasonic auxiliary parameters according to the gap. By adjusting the ultrasonic auxiliary parameters, the purified antioxidant data is purified for the second time, so that the antioxidant capacity is closer to the preset impact value. The qualified unit 333 uses the adjusted ultrasonic auxiliary parameters to continue to purify the antioxidant data, input the purified data into the osteoarthritis simulation model, and re-simulate the prediction; through the iterative process until the antioxidant data is purified and qualified; through multiple iterations and optimizations, the antioxidant data meets the qualified standards in multiple simulation predictions.

[0139] Therefore, this embodiment constitutes a complete antioxidant data purification and verification process, which ensures that the final antioxidant data can effectively reflect its effects on bones and joints through precise data analysis and parameter adjustment, and maintains high quality and high standards in multiple iterations.

[0140] like Fig.11 As shown, this embodiment provides an embodiment of an electronic device. In this embodiment, the electronic device 4 includes a processor 41 and a memory 42 coupled to the processor 41.

[0141] The memory 42 stores program instructions for implementing the system for extracting antioxidant substances from plantain according to any of the above embodiments.

[0142] The processor 41 is used to execute the program instructions stored in the memory 42 to extract the antioxidant substances from the plantain.

[0143] The processor 41 may also be referred to as a CPU (Central Processing Unit). The processor 41 may be an integrated circuit chip having signal processing capabilities. The processor 41 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0144] Further, Fig.12 The schematic diagram of the structure of the storage medium of an embodiment of the present application is that the storage medium 5 of the embodiment of the present application stores program instructions 51 that can implement all the above methods, wherein the program instructions 51 can be stored in the above storage medium in the form of a software product, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or terminal devices such as a computer, a server, a mobile phone, and a tablet.

[0145] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0146] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of software functional units. The above is only an implementation mode of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly used in other related technical fields, is also included in the patent protection scope of the present invention.

[0147] The specific implementation methods of the invention are described in detail above, but they are only examples, and the invention is not limited to the specific implementation methods described above. For those skilled in the art, any equivalent modification or substitution of the invention is also within the scope of the invention, therefore, the equalization, modification, improvement, etc. made without departing from the spirit and principle of the invention should be included in the scope of the invention.

Claims

1. A system for extracting antioxidant substances from plantain, characterized in that: The system for extracting antioxidant substances from plantain comprises: The data extraction module is used for ultrasonic-assisted extraction of antioxidant substances from plantain, antioxidant activity evaluation of the extracted antioxidant substances, main component analysis of the evaluation results, and formation of antioxidant experimental records; the antioxidant experimental records are input into the plantain molecular experimental database; The first data acquisition module is used to obtain antioxidant experimental records from the plantain molecular experimental database; the antioxidant experimental records are classified according to the antioxidant determination method, and the antioxidant analysis is classified into antioxidant molecules and non-antioxidant molecules based on the experimental results, so as to construct a binary classification database of antioxidant data with different antioxidant properties; The predictive antioxidant module is used to obtain user osteoarthritis data, build an osteoarthritis simulation model based on the osteoarthritis data, and train the osteoarthritis simulation model with data from the antioxidant binary classification database; predict the impact of plantain antioxidant data on bones and joints. If it is less than the preset impact value, the antioxidant data is deemed qualified; if it is greater than the preset impact value, ultrasonic assistance is used to continue to purify the antioxidant data.

2. The system for extracting antioxidant substances from plantain according to claim 1, characterized in that: Data extraction module, including: An extraction submodule, which is used to extract antioxidant substances using an ultrasonic generator, determine the total phenolic content and total flavonoid content, and create a calibration curve to determine the TPC and TFC concentrations of the extract; The evaluation submodule is used to determine the antioxidant activity of the extract, measure the absorbance change of the mixture, draw a standard curve of Trolox concentration and absorbance based on Trolox standard solutions of different concentrations; and calculate the Trolox equivalent unit based on the absorbance change and the standard curve; The first analysis submodule is used to perform data preprocessing and feature extraction on the Trolox equivalent unit value if it is greater than a preset value, and to perform principal component analysis on the processed data, and input the analysis results into the Plantago asiatica molecular experimental database to form experimental data.

3. The system for extracting antioxidant substances from plantain according to claim 2, characterized in that: Evaluation submodules include: a change unit for measuring the absorbance change of a mixture, mixing the extract with a free radical solution, and measuring the absorbance of the extract with a free radical cation; A drawing unit is used to draw a standard curve between Trolox concentration and absorbance using Trolox standard solutions of different concentrations; and to draw a standard curve by measuring absorbance using Trolox solution; The first calculation unit is used to calculate the Trolox equivalent unit of the sample according to the absorbance change and the standard curve; by measuring the absorbance change and combining it with the standard curve, the Trolox concentration corresponding to the extract is obtained. If it is greater than the preset value, it is judged that the antioxidant capacity meets the standard.

4. The system for extracting antioxidant substances from plantain according to claim 2, characterized in that: The first analysis submodule includes: A preprocessing unit, used for preprocessing data whose antioxidant capacity meets the standard; wherein the preprocessing includes data cleaning, missing value processing, outlier processing and standardization operation; The second calculation unit is used to calculate the standardized data to obtain a correlation matrix and a covariance matrix, and obtain the linear relationship between the variables through the covariance matrix; and evaluate the correlation between the variables through the correlation matrix; The second analysis unit is used to perform eigenvalue decomposition on the covariance matrix or the correlation matrix to obtain eigenvalues ​​and corresponding eigenvectors; select the number of principal components according to the size of the eigenvalues, select the principal components whose contribution values ​​exceed the preset contribution rates, project the original data onto the selected principal components, and obtain a new low-dimensional data representation.

5. The system for extracting antioxidant substances from plantain according to claim 1, characterized in that: The first data acquisition module includes: The second data acquisition submodule is used to retrieve antioxidant experimental records from the Plantain Experiment Database, extract relevant antioxidant analysis, screen the retrieved data, and capture information related to small molecule antioxidants; wherein the information related to small molecule antioxidants includes chemical structure, antioxidant determination method, determination results, determination target and references; The classification submodule is used to classify the time records according to the antioxidant determination method; analyze the test results under each classification, calculate the concentration and content of each antioxidant component, and perform data analysis; Among them, they are classified according to hydrogen atom transfer reaction, electron transfer reaction, lipid peroxide inhibition, and Nrf2 antioxidant response element signaling pathway; A database submodule is constructed to classify antioxidant analysis into antioxidant molecules and non-antioxidant molecules according to the antioxidant assay results; an antioxidant threshold is set. If the antioxidant threshold is exceeded, the compounds with antioxidant activity are classified as antioxidant molecules; if the threshold is lower than the threshold, the compounds with antioxidant activity are classified as non-antioxidant molecules; a binary classification database is constructed based on the classified data.

6. The system for extracting antioxidant substances from plantain according to claim 1, characterized in that: Predictive antioxidant module, including: The third data acquisition submodule is used to obtain the user's bone and joint data, clean the bone and joint data, remove missing values, etc., convert categorical variables into virtual variables, and remove data values ​​in numerical data; build an osteoarthritis simulation model based on the preprocessed data; The first simulation submodule is used to retrieve the antioxidant data of plantain from the antioxidant binary database to form a data set, and divide the data set into a training set and a test set; train the osteoarthritis simulation model according to the training set, and input the extracted antioxidant data of plantain into the osteoarthritis simulation model for simulation; The result output submodule is used to obtain the impact value of plantain oxidation data on bone joints according to the simulation results. If it is greater than the preset impact value, the antioxidant data will continue to be purified; if it is less than the preset impact value, the antioxidant data purification is deemed qualified.

7. The system for extracting antioxidant substances from plantain according to claim 6, characterized in that: Simulation submodules include: A data retrieval unit is used to retrieve the antioxidant data of plantain from the database to form a data set; divide the data set into a training set and a test set; and perform preprocessing operations on the data set such as removing outliers, balancing data distribution, converting categorical variables, and standardizing numerical variables; The model training unit is used to train the osteoarthritis simulation model using the training set; during the training process, the antioxidant data of plantain and the historical bone and joint treatment data of the user are analyzed to obtain the relationship between the antioxidant data of plantain and the historical bone and joint treatment data of the user, and the relationship is learned; The result analysis unit is used to recursively screen variables after the training is completed. Based on the results of each training of the osteoarthritis simulation model, the variables with a smaller value than the preset value are gradually eliminated. According to the final training results of the osteoarthritis simulation model, the variables that contribute most to the simulation results are extracted. The extracted plantain antioxidant data is input into the osteoarthritis simulation model for simulation.

8. The system for extracting antioxidant substances from plantain according to claim 7, characterized in that: Model training unit, including: An analysis subunit is used to collect a node set of plantain antioxidant data and a user's historical bone and joint treatment data, analyze the output data and characteristics of each node in the node set, and analyze the dependency relationship between nodes based on the characteristic analysis results of the node input data and output data; A dependency matrix subunit is used to construct a dependency matrix between nodes according to the dependency relationship, calculate the similarity between the output data of the first node and the output data of the second node, and determine the dependency relationship between the output data of the first node and the data of the second node according to a threshold value between the similarities; The optimization analysis subunit is used to identify the node configuration information that can be optimized, as well as the potential parallel execution sets and sequential execution sets between nodes; according to the identified parallel execution sets and sequential execution sets, the configuration execution order of the optimized acquisition tasks is reordered.

9. The system for extracting antioxidant substances from plantain according to claim 7, characterized in that: Result analysis unit, including: The variable screening subunit is used to gradually eliminate variables less than the threshold based on each training result of the osteoarthritis simulation model, and extract the variable value that contributes the most to the simulation result according to the final training result of the osteoarthritis simulation model; and obtain the final bone and joint simulation model The second simulation subunit is used to input the plantain extraction data into the bone and joint simulation model, simulate the input plantain extraction data, and obtain the treatment effect of the user's osteoarthritis; and compare the treatment effect of the user's osteoarthritis with the preset treatment effect; The comparison subunit is used to evaluate according to the comparison results, obtain the impact value of the antioxidant data of plantain on the user's bones and joints, verify the simulation results with the verification set, evaluate with the preset verification value, and adjust the bone and joint simulation model according to the evaluation results.

10. The system for extracting antioxidant substances from plantain according to claim 6, characterized in that: The result output submodule includes A determination unit is used to determine the impact value of the oxidation data of plantain on the bone joints according to the simulation result. If it is greater than the preset impact value, the antioxidant data is further purified. If it is less than the preset impact value, the antioxidant data purification is deemed qualified. An adjustment unit is used to analyze the antioxidant data of the simulation results to obtain the antioxidant capacity; Compare the preset impact value with the simulation result to obtain the data gap between the preset impact value and the simulation result, and adjust the ultrasonic auxiliary parameters according to the data gap; The qualified unit is used to further purify the antioxidant data with the adjusted ultrasonic-assisted parameters, input the purified data into the osteoarthritis simulation model, and re-simulate the prediction; it is iterated in sequence until the antioxidant data is purified to be qualified.

Images