Intelligent analysis system for nutritional ingredients of functional food

Abstract

The invention discloses an intelligent analysis system for nutritional ingredients of functional food. The intelligent analysis system is characterized in that a sample is extracted from food through a configured sampler; carrying out pretreatment on the extracted sample; carrying out nondestructive testing on the treated sample by adopting a spectrum technology to obtain spectrum information of the sample; analyzing the spectral information, and identifying nutritional ingredients in the sample; analyzing the identified nutritional ingredients to obtain the composition and the corresponding content of the nutritional ingredients; and outputting and uploading an analysis result of the primary data analysis module. Nondestructive testing is carried out by adopting a spectrum technology, the spectrum information of the sample is rapidly obtained, and the analysis speed is increased; the spectral information is subjected to nutritional ingredient identification by using an intelligent algorithm, so that the analysis accuracy is improved; and according to two data analysis, a quantitative detection result under a specific function is output, the quantitative accuracy is high, and the problem that the nutritional values of various foods are difficult to intuitively quantify in an existing food nutritional value display mode is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of food analysis, and in particular to an intelligent analysis system for the nutritional components of functional foods. Background Art

[0002] With the rapid development of social economy, people's quality of life has gradually improved, and their concern for food safety and healthy eating has become increasingly serious.

[0003] In the food market, the dazzling array of goods is overwhelming. Usually, the ingredients and nutritional ratios of foods are displayed on the packaging, but this information often confuses consumers when choosing foods, and it is difficult to intuitively quantify the nutritional value of various foods.

[0004] In view of this phenomenon, it is important to develop a food nutritional analysis system with a high level of intelligence, which will help consumers understand and evaluate the nutritional content of food more deeply, make wise purchasing decisions based on quantitative indicators, and improve their quality of life. Summary of the invention

[0005] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0006] In view of the problems existing in the above-mentioned existing food nutritional value display methods, the present invention is proposed.

[0007] Therefore, the technical problem solved by the present invention is to solve the problem that the existing food nutritional value display method is difficult to intuitively quantify the nutritional value of various foods.

[0008] To solve the above technical problems, the present invention provides the following technical solutions: a functional food nutrient intelligent analysis system, comprising the following components: a sampling module, which extracts samples from food through a configured sampler; a sample processing module, which performs pre-processing on the samples extracted by the sampling module; a spectral detection module, which uses spectral technology to perform non-destructive testing on the processed samples to obtain spectral information of the samples; a nutrient identification module, which analyzes the spectral information to identify the nutrients in the sample; a primary data analysis module, which analyzes the identified nutrients to obtain the composition and corresponding content of the nutrients; and a result output module, which outputs and uploads the analysis results of the primary data analysis module.

[0009] As a preferred solution of the intelligent analysis system of functional food nutritional components described in the present invention, the sampler is a needle sampler or a spoon.

[0010] As a preferred solution of the functional food nutrient component intelligent analysis system described in the present invention, the pre-treatment performed by the sample processing module specifically includes grinding and solvent dissolution.

[0011] As a preferred solution of the functional food nutritional component intelligent analysis system described in the present invention, it also includes a secondary data analysis module. After the primary data analysis module obtains the composition and corresponding content of the nutritional components, the secondary data analysis module constructs a comprehensive analysis model, inputs the corresponding content of each nutritional component into each item of the model, and outputs a comprehensive analysis value. The result output module synchronously uploads the analysis result of the primary data analysis module and the comprehensive analysis value.

[0012] As a preferred embodiment of the intelligent analysis system for the nutritional components of functional foods described in the present invention, the nutritional components included in constructing the comprehensive analysis model specifically include: protein, fat, carbohydrates, vitamins and minerals, antioxidants, dietary fiber, probiotics and prebiotics, and amino acids.

[0013] As a preferred solution of the functional food nutrient component intelligent analysis system of the present invention, the comprehensive analysis model constructed is specifically:

[0014]

[0015] Wherein, δ is the comprehensive analysis value, α is the percentage of vitamins and minerals, β is the percentage of antioxidants, λ is the percentage of protein, ε is the percentage of fat, μ is the percentage of carbohydrates, θ is the percentage of dietary fiber, ω is the percentage of probiotics and prebiotics, is the percentage of amino acid, 1.84, 1.69, 1.257, 1.22, 1.03, 1.306, 1.06, 1.281, 1.19 and 1.04 are adjustment constants, and dx is the integral operation.

[0016] As a preferred solution of the functional food nutrient intelligent analysis system described in the present invention, when the comprehensive analysis value is higher than 2.997, the specific function test result of the current functional food is defined as qualified; when the comprehensive analysis value is higher than 4.005, the specific function test result of the current functional food is defined as high-quality; the result output module (600) synchronously outputs and uploads the analysis result of the primary data analysis module (500), the comprehensive analysis value and the test result.

[0017] The present invention provides an intelligent analysis system for the nutritional components of functional foods, which has the following beneficial effects:

[0018] 1. Use spectral technology for non-destructive testing, quickly obtain spectral information of samples, and improve analysis speed;

[0019] 2. Use intelligent algorithms to identify nutrients based on spectral information to improve analysis accuracy;

[0020] 3. Based on the secondary data analysis, the quantitative test results under specific functions are output with high quantification accuracy, which solves the problem that the existing food nutritional value display method is difficult to intuitively quantify the nutritional value of various foods. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0022] Figure 1 This is an overall system flow chart of the functional food nutritional component intelligent analysis system provided by the present invention. DETAILED DESCRIPTION

[0023] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0024] In the food market, the dazzling array of goods is overwhelming. Usually, the ingredients and nutritional ratios of foods are displayed on the packaging, but this information often confuses consumers when choosing foods, and it is difficult to intuitively quantify the nutritional value of various foods.

[0025] Therefore, the present invention provides a functional food nutritional component intelligent analysis system, comprising the following components:

[0026] The sampling module 100 extracts samples from food through a configured sampler;

[0027] The sample processing module 200 performs pre-processing on the sample extracted by the sampling module 100;

[0028] The spectrum detection module 300 uses spectrum technology to perform non-destructive testing on the processed samples to obtain spectrum information of the samples;

[0029] The nutrient component identification module 400 analyzes the spectral information and identifies the nutrient components in the sample;

[0030] A primary data analysis module 500 analyzes the identified nutrients to obtain the composition and corresponding content of the nutrients;

[0031] The result output module 600 outputs and uploads the analysis result of the primary data analysis module 500.

[0032] Specifically, the sampler is a needle sampler or a spoon.

[0033] Specifically, the pre-processing performed by the sample processing module 200 includes: grinding and dissolving with a solvent.

[0034] It should be noted that:

[0035] 1. The sampling module is an important part of the intelligent analysis system for functional food nutrients. Its main function is to accurately and quickly extract representative samples from food for subsequent component analysis and testing. The technical details of the sampling module are as follows:

[0036] ① Sampler selection: The sampler is the core component of the sampling module, and its selection directly affects the quality of the sample and the accuracy of the analysis results. In the intelligent analysis system of functional food nutrients, commonly used samplers include needle samplers and spoons.

[0037] Needle sampler: Needle samplers are usually made of stainless steel and have excellent corrosion resistance. They are compact and small in size, making them easy to sample in various food packages. The working principle of the needle sampler is to insert the sampling needle into the food by rotating or manually operating it to absorb a certain amount of sample. The sampling needle should be designed to minimize damage to the food during the sampling process to maintain the original state of the sample.

[0038] Spoon: A spoon is a simple and practical sampler suitable for sampling bulk food or solid food. The spoon should be made of food-grade stainless steel or ceramic to avoid contamination of the sample. The spoon should be sampled evenly to ensure that the sample is representative.

[0039] ② Sampling module design: The sampling module should have the following technical features:

[0040] High degree of automation: The sampling module should have automatic control function to achieve precise control of the sampler and reduce errors caused by manual operation.

[0041] Fast sampling speed: The sampling module should be able to quickly complete sample extraction to meet the high efficiency requirements of modern food production.

[0042] High sampling accuracy: The sampling module should ensure the accuracy and uniformity of samples during the sampling process to improve the accuracy of the analysis results.

[0043] Sample protection: The sampling module should have a sample protection function to prevent the sample from being contaminated and deteriorated during sampling, transportation and storage.

[0044] Easy to clean and maintain: The sampling module should be designed with a structure that is easy to clean and maintain to ensure the cleanliness of the sampler and the stable operation of the sampling module.

[0045] 2. The sample processing module is a key part of the intelligent analysis system of functional food nutrients. Its function is to pre-process the samples extracted by the sampling module for subsequent spectral detection and nutrient analysis. The technical details of the sample processing module are as follows:

[0046] ① Grinding and crushing: Grinding and crushing is the first step in the sample processing module, and its purpose is to reduce the sample particles to a fine enough size for subsequent dissolution and analysis. Grinding and crushing technical details include:

[0047] Grinding equipment selection: Commonly used grinding equipment includes ball mill, vibration mill and high-speed stirring mill. Ball mill is suitable for large-scale production, vibration mill and high-speed stirring mill are suitable for laboratory and small-scale production.

[0048] Grinding media: The material and size of the grinding media have an important influence on the grinding effect. Usually stainless steel, zirconium oxide or glass beads are used, with a diameter between 0.1mm and 1mm.

[0049] Grinding time: Grinding time should be determined according to the nature of the sample and the required fineness, and is generally controlled between a few minutes to tens of minutes.

[0050] ②Solvent dissolution: Solvent dissolution is the second step in the sample processing module, and its purpose is to completely dissolve the ground sample for subsequent spectral detection and nutrient analysis. The technical details of solvent dissolution include:

[0051] Solvent selection: The choice of solvent should be determined according to the nature of the sample and the components to be analyzed. Commonly used solvents include methanol, acetonitrile, water, acetone, etc.

[0052] Dissolution conditions: Dissolution conditions include temperature, time and stirring speed, etc. The temperature should be controlled below the boiling point of the solvent to prevent the solvent from volatilizing; the dissolution time should be determined according to the sample amount and the properties of the solvent, generally controlled between a few minutes and tens of minutes; the stirring speed should be high enough to ensure uniform dissolution of the sample.

[0053] ③Design of sample processing module: The sample processing module should have the following technical features:

[0054] High degree of automation: The sample processing module should have automatic control function to achieve precise control of the grinding and dissolution process and reduce errors caused by manual operation.

[0055] Sample protection: The sample processing module should have a sample protection function to prevent the sample from being contaminated and deteriorated during the processing process.

[0056] Easy to clean and maintain: The sample processing module should be designed with a structure that is easy to clean and maintain to ensure the cleanliness and stable operation of the equipment.

[0057] 3. The spectrum detection module is a key part of the functional food nutrition component intelligent analysis system for obtaining sample spectrum information. This module uses spectral technology such as near infrared spectroscopy (NIR), Raman spectroscopy or Fourier transform infrared spectroscopy (FTIR) to achieve rapid and non-destructive detection of sample components. The technical details of the spectrum detection module are as follows:

[0058] ① Light source selection: The light source is the core component of the spectrum detection module, and its performance directly affects the sensitivity and accuracy of the detection. Commonly used light sources include halogen lamps, xenon lamps, LED lamps, etc. The choice of light source should be determined according to the specific requirements of the spectrum detection technology. For example, near-infrared spectroscopy technology usually uses LED lamps as the light source.

[0059] ② Spectrometer: The spectrometer is a key device in the spectrum detection module. Its function is to receive the spectrum signal emitted by the sample and convert it into an electrical signal. The design of the spectrometer should ensure high sensitivity and stability to meet the needs of different samples and different detection conditions.

[0060] ③ Sample pool design: The sample pool is the interface between the sample and the light source and spectrometer. Its design should ensure that the sample will not be contaminated or damaged during the detection process. The material of the sample pool should have high light transmittance and chemical stability to adapt to the detection of different samples.

[0061] ④Signal acquisition and processing: The signals generated during the spectrum detection process need to be processed by the signal acquisition and processing system to extract useful spectral information. The signal processing system should include noise suppression, signal smoothing, spectral feature extraction and other links to improve the accuracy and reliability of spectral analysis.

[0062] ⑤ Spectral analysis algorithm: The spectral analysis algorithm is the core software part of the spectral detection module. Its function is to analyze and process the collected spectral data to identify and quantify the nutrients in the sample. Commonly used spectral analysis algorithms include Multiple Linear Regression (MLR), Partial Least Squares (PLS), Principal Component Analysis (PCA), etc.

[0063] 4. The nutrient identification module is one of the core technologies in the functional food nutrient intelligent analysis system. Its function is to analyze the spectral information obtained by the spectrum detection module to identify the nutrients in the sample. The technical details of the nutrient identification module are as follows:

[0064] Spectral preprocessing: Spectral preprocessing is the first step in the nutrient identification module, and its purpose is to improve the quality of the spectrum and enhance the readability of the spectral information. Commonly used spectral preprocessing methods include smoothing, normalization, noise removal, and derivation.

[0065] Feature band selection: Feature band selection refers to selecting spectral regions that have a significant impact on the nutritional components of the sample from spectral data. Commonly used feature band selection methods include interval selection, partial least squares regression (PLS-DA), etc.

[0066] Spectral pattern recognition: Spectral pattern recognition is a key step in the nutrient identification module. Its purpose is to convert spectral data into representative patterns for subsequent component identification and quantitative analysis. Commonly used spectral pattern recognition methods include principal component analysis (PCA), partial least squares regression (PLS), support vector machine (SVM), etc.

[0067] Component identification and quantification: Component identification and quantification is to identify and quantify the nutrients in the sample based on the results of spectral pattern recognition. Commonly used component identification and quantification methods include multiple linear regression (MLR), partial least squares regression (PLS), principal component regression (PCR), etc.

[0068] Algorithm optimization and model training: In order to improve the accuracy and stability of the nutrient identification module, the algorithm needs to be optimized and the model needs to be trained. The goal of optimization is to minimize the prediction error and improve the prediction performance of the model. During the training process, the model needs to be trained using sample data with known ingredient content to improve its prediction accuracy.

[0069] Identification result verification: Identification result verification is the last step in the nutrient identification module. Its purpose is to verify the identification result to confirm its accuracy. Commonly used identification result verification methods include leave-one-out validation and cross-validation.

[0070] 5. The data analysis module is the core part of the intelligent analysis system of functional food nutrients. Its function is to conduct in-depth analysis on the output results of the nutrient identification module to obtain the composition and corresponding content of the nutrients in the sample. The specific technical details of the data analysis module are as follows:

[0071] Component composition analysis: Component composition analysis is the first step of the data analysis module, and its purpose is to analyze the nutritional composition of the sample. Commonly used component composition analysis methods include principal component analysis (PCA), partial least squares discriminant analysis (PLS-DA), orthogonal partial least squares discriminant analysis (OPLS-DA), etc. These methods can cluster samples to achieve composition analysis of nutritional components.

[0072] Content quantitative analysis: Content quantitative analysis is a key step in the data analysis module, and its purpose is to quantitatively analyze the nutrients in the sample. Commonly used content quantitative analysis methods include multiple linear regression (MLR), partial least squares regression (PLS), principal component regression (PCR), etc. These methods can establish a mathematical model between nutrients and spectral data, thereby achieving accurate prediction of the nutrient content in the sample.

[0073] Result verification and optimization: In order to improve the accuracy of the analysis results, the data analysis module also needs to verify and optimize the results. This includes cross-validation of the established mathematical model, parameter optimization, etc. Through these methods, the accuracy and reliability of the analysis results can be ensured.

[0074] Obtaining the ingredients and content in food through spectral information is a mature application of existing spectral technology and will not be elaborated on here.

[0075] Furthermore, it also includes a secondary data analysis module 700. After the primary data analysis module 500 obtains the composition and corresponding content of the nutrients, the secondary data analysis module 700 constructs a comprehensive analysis model, inputs the corresponding content of each nutrient into each number of the model, and outputs a comprehensive analysis value. The result output module 600 simultaneously outputs and uploads the analysis results and comprehensive analysis values ​​of the primary data analysis module 500.

[0076] Specifically, when constructing a comprehensive analysis model, the nutrients included include: protein, fat, carbohydrates, vitamins and minerals, antioxidants, dietary fiber, probiotics and prebiotics, and amino acids.

[0077] It should be noted that the detection process of the above nutrients is specifically as follows:

[0078] 1. Protein detection:

[0079] Near infrared spectroscopy (NIR) technology: By analyzing the absorption spectrum of the sample in the near infrared wavelength range, the protein content can be predicted. NIR technology is suitable for rapid and non-destructive sample analysis, especially for solid or semi-solid samples.

[0080] 2. Fat detection:

[0081] Fourier transform infrared spectroscopy (FTIR) technology: FTIR can detect the characteristic absorption peaks of fatty acids in fat, such as the vibration absorption peaks of methyl and methylene, to estimate the fat content.

[0082] 3. Carbohydrate detection:

[0083] Near-infrared spectroscopy (NIR) technology: NIR can be used to predict the content of total carbohydrates and different types of carbohydrates (such as sugars, starches and fibers) in food.

[0084] 4. Vitamin and mineral testing:

[0085] Raman spectroscopy: Raman spectroscopy can be used to detect vitamins and minerals in food. Raman spectroscopy identifies ingredients by analyzing the vibrational patterns of the sample's molecular structure.

[0086] Near infrared spectroscopy (NIR) technology: NIR can also be used to predict the vitamin and mineral content in food, especially trace elements.

[0087] 5. Antioxidant detection:

[0088] Ultraviolet-visible spectroscopy (UV-Vis) technology: By analyzing the absorbance of a sample at a specific wavelength, the content of antioxidants such as vitamin C and polyphenols can be detected.

[0089] 6.Dietary fiber testing:

[0090] Near-infrared spectroscopy (NIR) technology: NIR can be used to predict the total dietary fiber content and the composition of different types of dietary fiber (such as soluble and insoluble fiber) in food.

[0091] 7. Probiotics and prebiotics testing:

[0092] Near-infrared spectroscopy (NIR) technology: NIR can be used to predict the number of probiotics and the chemical composition of prebiotics in food.

[0093] 8. Amino acid detection:

[0094] Fourier Transform Infrared Spectroscopy (FTIR) Technology: FTIR can be used to detect amino acids in food, especially by analyzing the secondary structure of proteins.

[0095] Furthermore, the comprehensive analysis model constructed is as follows:

[0096]

[0097] Among them, δ is the comprehensive analysis value, α is the percentage of vitamins and minerals, β is the percentage of antioxidants, λ is the percentage of protein, ε is the percentage of fat, μ is the percentage of carbohydrates, θ is the percentage of dietary fiber, and ω is the percentage of probiotics and prebiotics. is the percentage of amino acid, 1.84, 1.69, 1.257, 1.22, 1.03, 1.306, 1.06, 1.281, 1.19 and 1.04 are adjustment constants, and dx is the integral operation.

[0098] It should be noted that the comprehensive analysis model constructed is used to generate comprehensive analysis values ​​for functional sports drinks, with the percentage of vitamins and minerals and the percentage of antioxidants as the main basis. The comprehensive analysis model in the present invention is not suitable for processing other functional foods.

[0099] Furthermore, when the comprehensive analysis value is higher than 2.997, the specific function test result of the current functional food is defined as qualified; when the comprehensive analysis value is higher than 4.005, the specific function test result of the current functional food is defined as high-quality. The result output module 600 synchronously uploads the analysis result, comprehensive analysis value and test result of the data analysis module 500.

[0100] In order to verify the beneficial effects of the intelligent analysis system for functional food nutrients, the following data verification test was designed:

[0101] 1. Sample preparation: Select a certain number of functional foods as test samples, including samples of various nutrients such as protein, fat, carbohydrates, vitamins and minerals, antioxidants, dietary fiber, probiotics and prebiotics.

[0102] 2. Spectral detection: Use the spectral detection module of the functional food nutrient intelligent analysis system to perform non-destructive testing on each sample to obtain the spectral information of the sample.

[0103] 3. Nutrient identification: Use intelligent algorithms to identify nutrients based on spectral information to obtain the types and contents of nutrients in each sample.

[0104] 4. Data analysis: Based on the recognition results, secondary data analysis is performed to output quantitative detection results under specific functions.

[0105] 5. Verification test: Compare the quantitative test results obtained by the intelligent analysis system of functional food nutrients with the results obtained by traditional chemical analysis methods to verify the accuracy of the system.

[0106] 6. Statistical analysis: Conduct statistical analysis on the comparison results and calculate the accuracy, precision and other indicators of the system.

[0107] 7. Result output: Organize the results of the verification test into a table, including sample name, traditional chemical analysis results, intelligent analysis results, error analysis, etc.

[0108] Compared with the traditional chemical analysis results, the present invention adopts full spectrum for detection, and the generated data comparison table is shown in Table 1:

[0109] Table 1: Data comparison table

[0110] Protein samples 20.00％ 19.50％ ±0.50％ Fat samples 15.00％ 15.50％ ±0.50％ Carbohydrate samples 60.00％ 60.50％ ±0.50％ Vitamin samples 5.00mg / 100g 4.90mg / 100g ±0.10mg / 100g Mineral samples 100.00μg / 100g 99.50μg / 100g ±0.50μg / 100g Antioxidant samples 150.00mg / kg 149.00mg / kg ±1.00mg / kg Dietary fiber samples 10.00％ 10.50％ ±0.50％ Probiotic samples 1×10^9CFU / g 9.5×10^8CFU / g ±1×10^7CFU / g Amino Acid Samples 10.00g / 100g 10.50g / 100g ±0.50g / 100g

[0111] In the above data verification test table, traditional chemical analysis methods may include the following:

[0112] Kjeldahl method: used to determine protein content. The protein content is calculated by measuring the nitrogen content in the sample and then multiplying it by the nitrogen conversion factor of protein (usually 6.25).

[0113] Acid hydrolysis method: used to determine fat content, the sample is hydrolyzed with acid to convert fat into fatty acids and glycerol, followed by saponification, extraction and analysis to determine fat content.

[0114] Enzymatic method: used to determine carbohydrate content, using specific enzymes to hydrolyze carbohydrates and then analyzing the hydrolyzate to determine the carbohydrate content.

[0115] Atomic absorption spectrometry (AAS) or atomic fluorescence spectrometry (AFS): used to determine metal elements and some non-metal elements, such as iron, calcium, zinc, etc.

[0116] High Performance Liquid Chromatography (HPLC): used for the determination of monosaccharides, oligosaccharides and polysaccharides, as well as specific vitamins and organic acids.

[0117] Automatic amino acid analyzer: used to determine the amino acid composition and content in food.

[0118] Fiber Analyzer: Used to determine dietary fiber content, especially using the enzymatic-gravimetric method.

[0119] Microbial count method: used to determine the number of probiotics, such as the plate count method.

[0120] Mass spectrometry (MS): Used to determine the structure and molecular weight of specific compounds, such as antioxidants and prebiotics.

[0121] These traditional chemical analysis methods usually require professional laboratory equipment and technicians to operate. The analysis process is relatively complicated and time-consuming. The functional food nutritional component intelligent analysis system uses spectral technology to achieve fast and non-destructive sample detection and processes data through intelligent algorithms, thereby improving analysis efficiency and accuracy.

[0122] The present invention provides an intelligent analysis system for the nutritional components of functional foods, which has the following beneficial effects:

[0123] 1. Use spectral technology for non-destructive testing, quickly obtain spectral information of samples, and improve analysis speed;

[0124] 2. Use intelligent algorithms to identify nutrients based on spectral information to improve analysis accuracy;

[0125] 3. Based on the secondary data analysis, the quantitative test results under specific functions are output with high quantification accuracy, which solves the problem that the existing food nutritional value display method is difficult to intuitively quantify the nutritional value of various foods.

[0126] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A functional food nutritional component intelligent analysis system, characterized in that: Includes the following components: A sampling module (100) extracts samples from food through a configured sampler; A sample processing module (200) performs pre-processing on the sample extracted by the sampling module (100); A spectrum detection module (300) uses spectrum technology to perform non-destructive testing on the processed sample to obtain spectrum information of the sample; A nutrient component identification module (400) analyzes the spectral information to identify the nutrient components in the sample; A primary data analysis module (500) analyzes the identified nutrients to obtain the composition and corresponding content of the nutrients; The result output module (600) outputs and uploads the analysis result of the primary data analysis module (500).

2. The functional food nutritional component intelligent analysis system according to claim 1, characterized in that: The sampler is a needle sampler or a spoon.

3. The functional food nutritional component intelligent analysis system according to claim 2, characterized in that: The pre-treatment performed by the sample processing module (200) specifically includes: grinding and dissolving with a solvent.

4. The functional food nutritional component intelligent analysis system according to claim 3, characterized in that: It also includes a secondary data analysis module (700). After the primary data analysis module (500) obtains the composition and corresponding content of the nutrients, the secondary data analysis module (700) constructs a comprehensive analysis model, inputs the corresponding content of each nutrient into each number in the model, and outputs a comprehensive analysis value. The result output module (600) simultaneously outputs and uploads the analysis result of the primary data analysis module (500) and the comprehensive analysis value.

5. The functional food nutritional component intelligent analysis system according to claim 4, characterized in that: When constructing the comprehensive analysis model, the nutrients included specifically include: protein, fat, carbohydrates, vitamins and minerals, antioxidants, dietary fiber, probiotics and prebiotics, and amino acids.

6. The functional food nutritional component intelligent analysis system according to claim 5, characterized in that: The comprehensive analysis model constructed is specifically: Wherein, δ is the comprehensive analysis value, α is the percentage of vitamins and minerals, β is the percentage of antioxidants, λ is the percentage of protein, ε is the percentage of fat, μ is the percentage of carbohydrates, θ is the percentage of dietary fiber, ω is the percentage of probiotics and prebiotics, is the percentage of amino acid, 1.84, 1.69, 1.257, 1.22, 1.03, 1.306, 1.06, 1.281, 1.19 and 1.04 are adjustment constants, and dx is the integral operation.

7. The intelligent analysis system for nutritional components of functional foods according to claim 6, characterized in that: When the comprehensive analysis value is higher than 2.997, the specific function test result of the current functional food is defined as qualified; when the comprehensive analysis value is higher than 4.005, the specific function test result of the current functional food is defined as high-quality; the result output module (600) synchronously outputs and uploads the analysis result of the primary data analysis module (500), the comprehensive analysis value and the test result.

Images