Soup component rapid detection method and spectrum analyzer thereof

Abstract

The invention discloses a rapid detection method for soup components. The rapid detection method comprises the following steps: S1, pretreating a to-be-detected soup; s2, carrying out data acquisition on the preprocessed soup, wherein the data acquisition comprises acquisition of multichannel spectral data, conductivity data and / or temperature data of the soup; s3, according to the multi-channel spectral data, the conductivity data and / or the temperature data, analyzing the soup by adopting a soup analysis model to generate an analysis result; the analysis result comprises a qualitative analysis result and a semi-quantitative analysis result. Laboratory-level preprocessing is not needed, and the method can be used at any time in life scenes; the non-destructive test does not affect the soup quality; the content levels of purine, protein, fat and salinity in the soup can be tested; mutual interference of components on the same characteristics is eliminated by using big data and an AI model; and the difference of the components on different physical quantities is utilized to carry out correction and adjustment, so that the test reliability and accuracy are improved.

Description

Technical Field

[0001] This application relates to the field of soup detection technology, and in particular to a rapid detection method for soup components and its spectroscopic analyzer. Background Technology

[0002] In the vast ocean of Chinese cuisine, soup undoubtedly occupies an important place. Soup is a common type of dish in daily life. During the continuous simmering process, as the cell walls of tissues break down and a large amount of nucleotides dissolve into the soup, the concentration of purines continues to rise. Fat and protein undergo an emulsification reaction, making the fat distribution more even and less prone to separation. Furthermore, as evaporation occurs, the concentration of various components in the soup further increases.

[0003] Traditional laboratory methods for analyzing soup components require specialized equipment, reagents, and specialized procedures for pretreatment. The reliance on single measurement methods also leads to interference between different components, hindering rapid, non-destructive on-site testing and making them unsuitable for everyday residential settings. With rising living standards and health awareness, coupled with an aging population, especially among individuals with underlying conditions such as high uric acid, high cholesterol, and high blood pressure, it is crucial to control excessive intake of purines, protein, fat, and salt in the diet.

[0004] When analyzing purines, proteins, fats, and salinity in soups in the laboratory, methods such as high-performance liquid chromatography (HPLC) for purines, Kjeldahl and Coomassie brilliant blue methods for proteins, and Soxhlet extraction for fats all require specialized reagents and equipment, making them cumbersome and unsuitable for non-destructive testing at home. Refractometers and conductivity meters for salinity are also susceptible to interference from substances like oils. While single-channel sensors can respond to some indicators, they lack interference immunity. In developing appliances with soup-making functions, using time and temperature to control purine levels is inadequate for adapting to the differences in various ingredients and cannot accurately determine the final soup's state. Using cameras for observation, however, lacks a light source, leading to deficiencies in measurement accuracy and inter-device consistency. Summary of the Invention

[0005] The purpose of this application is to overcome the shortcomings of the prior art and provide a rapid detection method for soup components and a spectrometer thereof.

[0006] To achieve the above objectives, this application provides the following technical solutions: The first aspect of this application provides a rapid detection method for soup components, including the following steps: S1. Pre-treat the soup sample to be tested; the pre-treatment includes filtration, adsorption and / or reverse osmosis. S2. Data acquisition is performed on the pretreated soup, including the acquisition of multi-channel spectral data, conductivity data and / or temperature data of the soup. S3. Based on the multi-channel spectral data, conductivity data, and / or temperature data, the soup is analyzed using a soup analysis model to generate analysis results; the analysis results include qualitative analysis results and semi-quantitative analysis results.

[0007] Preferably, the data collection for the pretreated soup specifically includes the following steps: S21. Place the spectrometer directly into the pretreated soup; the spectrometer includes a processing module, an emission light source, and a photoelectric receiver; the optical path length of the acquisition optical path between the emission light source and the photoelectric receiver is 3mm~6mm; S22. The light source of the spectral analyzer emits ultraviolet-visible-near-infrared light, and the photodetector receives the ultraviolet-visible-near-infrared light that penetrates the soup. S23. The processing module analyzes and processes the ultraviolet-visible-near-infrared light received by the photoelectric receiver according to the soup analysis model to obtain the multi-channel spectral data, conductivity data and / or temperature data.

[0008] Preferably, the center frequencies of the multi-channel spectral data acquisition include 260nm, 280nm, 360nm, 530nm, 890nm±10nm, 400nm, 930nm, 1160nm, 1200nm, 1400nm, 1500nm, and 1600nm±10nm.

[0009] Preferably, the steps for constructing the soup analysis model include: S100, Sample library preparation, wherein the sample library contains multiple standard solution samples, mixed solution samples and real soup samples of different gradients, and each sample is labeled accordingly, and each sample is prepared in parallel; the standard solution samples include purine, protein, fat and sodium chloride solutions; S200. Data acquisition and labeling are performed on each sample in the sample library. The data acquisition includes acquiring multi-channel spectral data, conductivity data and / or temperature data of the soup. S300, Perform data quality control and data cleaning on the data; S400. The cleaned data is fed into the regression model for training. A mapping model is established using supervised learning algorithms, with multi-channel spectral, conductivity, and temperature data as inputs and protein concentration, purine concentration, fat concentration, and sodium chloride concentration as outputs. S500. Based on the training of the regression model, set qualitative analysis thresholds and semi-quantitative analysis thresholds. For the obtained regression model, the regression is converted to qualitative analysis through a decision transformation layer, and qualitative and semi-quantitative analyses are performed.

[0010] Preferably, the algorithm includes a multilayer perceptron regressor, an elastic regression network, a minimum absolute shrinkage and selection operator, and linear and nonlinear support vector regression.

[0011] Preferably, the data quality control and data cleaning of the data specifically involves: removing invalid bad samples, including those with missing data, missing labels, repeated collection of a single sample, and / or excessive volatility.

[0012] Preferably, the steps for preparing the authentic soup sample include: S101. Take the middle layer of the soup liquid; S102. Filter out particulate impurities and floating oil from the soup using a 100-400 mesh filter. S103. Laboratory analysis yielded the concentration values ​​of purines, proteins, fats, and salinity in the soup.

[0013] Preferably, the analytical methods used in the laboratory analysis include high performance liquid chromatography, Kjeldahl nitrogen determination, acid hydrolysis, silver nitrate titration, and conductivity measurement methods.

[0014] Preferably, the qualitative analysis results include qualified and unqualified; the semi-quantitative analysis results include low, medium and high.

[0015] The second aspect of this application provides a spectrometer, comprising: a processing module, an emission light source, and a photoelectric receiver; The processing module includes a memory and one or more processors; The memory is used to store one or more computer programs, and the one or more processors are used to execute the one or more computer programs stored in the memory, so that the one or more processors perform the rapid detection method for soup ingredients described above.

[0016] Implementing one of the above-mentioned technical solutions of this application has the following advantages or beneficial effects: This application does not require laboratory-level pretreatment and can be used at any time in daily life scenarios; it is a non-destructive test that does not affect the quality of soup; it can test the levels of purine, protein, fat, and salinity in soup; it uses big data and AI models to eliminate mutual interference between components on the same characteristics; and it uses the differences of components in different physical quantities to perform correction and adjustment, thereby improving the reliability and accuracy of the test. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings: Figure 1 This is a flowchart illustrating the rapid detection method for soup components according to an embodiment of this application; Figure 2 This is a flowchart illustrating the steps involved in constructing the soup analysis model according to an embodiment of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, various exemplary embodiments described below will be referenced to the accompanying drawings, which form part of the exemplary embodiments and depict various exemplary embodiments that may be adopted to implement this application. Unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. It should be understood that they are merely examples of processes, methods, and apparatuses consistent with some aspects of this application disclosed as detailed in the appended claims, and other embodiments may be used, or structural and functional modifications may be made to the embodiments listed herein without departing from the scope and spirit of this application.

[0019] In the description of this application, it should be understood that the terms "center," "longitudinal," "lateral," etc., indicate the orientation or positional relationship based on the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the referred element must have a specific orientation, or be constructed and operated in a specific orientation. The terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. The term "multiple" means two or more. The terms "connected" and "linked" should be interpreted broadly, for example, they can be fixed connections, detachable connections, integral connections, mechanical connections, electrical connections, communication connections, direct connections, indirect connections through an intermediate medium, and can be the internal connection of two elements or the interaction relationship between two elements. The term "and / or" includes any and all combinations of one or more of the related listed items. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0020] Molecular absorption spectroscopy is an objective physical property of molecules. When electromagnetic radiation (light) of continuous wavelength irradiates and passes through a specific substance, the groups or electrons inside the molecule are excited by radiation of a specific frequency, transitioning from a low-energy state to a high-energy state, thus causing the emitted light to exhibit energy intensity attenuation in a specific wavelength band. For example, the highest absorption peak of purine bases (adenine A and guanine G) released by DNA cleavage is located around 260 nm; protein molecules usually exist in a clustered form, absorbing light around 280 nm (because of the presence of aromatic amino acids such as tryptophan, tyrosine, and phenylalanine) but not light around 350 nm; the classical absorption peak of fat molecules is around 930 nm, while there is also a second-order overtone absorption of the CH2 group in fat molecules around 1210 nm. Large, uneven particles in soup can block the light measurement window and should be filtered out. For solid suspensions with smaller particle sizes (less than 1.2 μm), most food pigments (such as paprika and chlorophyll in soup) have very weak molecular absorption in the near-infrared region around 860 nm. Using this wavelength can effectively eliminate interference with the color of the soup.

[0021] Although salt (NaCl) is the main electrolyte in soup, conductivity measurement is the total conductivity of all charged ions in the solution. Organic acids in the soup (such as vinegar and tomato acid) produce H+ ions, and alkaline substances produce OH- ions, all of which have extremely high molar conductivity. The potassium (from soy sauce or low-sodium salt), calcium, and magnesium ions in seasonings, as well as ions produced by monosodium glutamate (MSG), and the hardness (residual ions) of the cooking water itself, also contribute to the final result. Temperature affects the form and viscosity of substances in the soup, thus influencing the absorption spectrum and conductivity characteristics, necessitating temperature compensation.

[0022] To illustrate the technical solutions described in this application, specific embodiments are provided below, showing only the parts related to the embodiments of this application.

[0023] like Figure 1 As shown, this application discloses an embodiment of a rapid detection method for soup components. This method is a non-destructive rapid detection method that can directly contact the soup to achieve rapid on-site qualitative and semi-quantitative analysis of purines, proteins, fats, and salinity in the soup. The specific steps include: S1. Pre-treat the soup sample to be tested; the pre-treatment includes filtration, adsorption, and / or reverse osmosis to reduce the selectivity of the signal during data acquisition. Specifically, a suitable filter can be selected for filtration to remove oil and residue from the soup sample, and then the sample should be left to stand at room temperature.

[0024] S2. Data acquisition is performed on the pretreated soup, including the acquisition of multi-channel spectral data, conductivity data and / or temperature data of the soup.

[0025] S3. Based on the multi-channel spectral data, conductivity data, and / or temperature data, the soup is analyzed using a soup analysis model to generate analysis results; the analysis results include qualitative analysis results and semi-quantitative analysis results.

[0026] In one embodiment, the data collection of the pretreated soup specifically includes the following steps: S21. Place the spectrometer directly into the pretreated soup; the spectrometer includes a processing module, an emission light source, and a photoelectric receiver; the optical path length of the acquisition optical path between the emission light source and the photoelectric receiver is 3mm~6mm; S22. The light source of the spectral analyzer emits ultraviolet-visible-near-infrared light, and the photodetector receives the ultraviolet-visible-near-infrared light that penetrates the soup. S23. The processing module analyzes and processes the ultraviolet-visible-near-infrared light received by the photoelectric receiver (penetrating the soup) according to the soup analysis model, and obtains the multi-channel spectral data, conductivity data and / or temperature data.

[0027] In one embodiment, the spectrometer includes a processing module, an emission light source, and a photodetector; the optical path length of the emission light source and the photodetector is 3mm to 6mm. Specifically, the emission light source and the photodetector are separated by two pieces of quartz glass; alternatively, a sample collection chamber can be used, with a size not exceeding 25mm. 25mm 35mm.

[0028] In one embodiment, the center frequencies of the multi-channel spectral data acquisition include 260nm, 280nm, 360nm, 530nm, 890nm±10nm, 400nm, 930nm, 1160nm, 1200nm, 1400nm, 1500nm, and 1600nm±10nm.

[0029] In one embodiment, the analysis results include qualitative analysis results and semi-quantitative analysis results. Specifically, the qualitative analysis results include qualified and unqualified; the semi-quantitative analysis results include low, medium, and high. Specifically, the threshold for qualitative judgment can be set according to the testing requirements of different population groups. For example, in 100ml of soup, for normal individuals, a suitable standard is designed as salinity 0.3%~0.6%, purine 50~150mg, fat 1.0~3.0g, and protein 0.5~2.0g. Below this range is considered low, and above this range is considered high. For individuals with hypertension, hyperlipidemia, and hyperglycemia, and those with gout, the salinity threshold can be lowered to 0.4%, and the purine threshold to 75mg, etc. This personalized configuration can be done manually or provided through preset settings and online upgrades.

[0030] During testing, data can be uploaded to a cloud server via a communication link, calculated, and then sent back. Alternatively, edge or terminal computing power can be used locally. Specifically, the communication link includes, but is not limited to, Bluetooth, USB, serial port, Wi-Fi, wired network, and wireless network.

[0031] In one embodiment, such as Figure 2 As shown, the steps for constructing the soup analysis model include: S100, Sample library preparation, wherein the sample library contains multiple standard solution samples, mixed solution samples and real soup samples of different gradients, and each sample is labeled accordingly, and each sample is prepared in parallel (i.e. each preparation has at least one copy); the standard solution samples include purine, protein, fat and sodium chloride solution, etc.

[0032] Specifically, the preparation steps of the real soup sample include: S101. Take the middle layer of the soup; S102. Use a 100-400 mesh filter to remove particulate impurities and floating oil from the soup. It should be noted that the mesh size of the filter used in actual use needs to be consistent with that used in modeling to improve data consistency.

[0033] S103. Laboratory analysis was conducted to obtain the concentration values ​​of purines, proteins, fats, and salinity in the soup. The analytical methods used included, but were not limited to, high performance liquid chromatography, Kjeldahl nitrogen determination, acid hydrolysis, and silver nitrate titration.

[0034] S200. Data acquisition and labeling are performed on each sample in the sample library. The data acquisition includes acquiring multi-channel spectral data, conductivity data, and / or temperature data of the soup.

[0035] S300. Perform data quality control and data cleaning on the data; remove invalid or bad samples, including data with missing data, missing labels, repeated sampling of a single sample, and / or excessive volatility. Specifically, data quality control methods may include: collecting data multiple times (at least 3 times) to determine data consistency, calculating the variance of each channel, and setting a rejection threshold, such as 5%~15%. Weights can also be designed based on the contribution of each channel to the model, and a comprehensive judgment can be made for multiple channels. Alternatively, multi-channel molecular fingerprints can be used to determine the consistency between the input data and the model data, rejecting obvious outliers.

[0036] S400. The cleaned data is fed into the regression model for training. Specifically, a mapping model is established using supervised learning algorithms, taking multi-channel spectral, conductivity, and temperature data as inputs and protein concentration, purine concentration, fat concentration, and sodium chloride concentration as outputs. The algorithms used include, but are not limited to, Multi-Layer Perceptron Regressor (MLPRS), Elastic Net, Lasso (Least Absolute Shrinkage and Selection Operator), and Linner / nonlinear Support Vector Regression (SVR).

[0037] S500. Based on the training of the regression model, set qualitative analysis thresholds and semi-quantitative analysis thresholds. Specifically, for the obtained regression model, the regression is converted to qualitative analysis through a decision transformation layer, and the application layer makes judgments to perform qualitative and semi-quantitative analysis.

[0038] For the issue of thick soups that partially solidify at low temperatures, this application only requires that the temperature be consistent during modeling and use. In practice, a detection optical path specifically designed for soups that can solidify can be designed to ensure consistency between modeling and use.

[0039] This application's spectrometer employs a miniature multi-channel spectrometer chip with a very small sampling space. It utilizes multispectral data, conductivity, and temperature data for joint modeling, employing a regression model and qualitative analysis layer separation, and can be customized for individual users. Furthermore, this application requires no laboratory-level preprocessing and can be used immediately in everyday scenarios; it is a non-destructive test that does not affect the quality of soups; it can test the levels of protein, purines, fat, and salinity in soups; it utilizes big data and AI models to eliminate mutual interference between components for the same characteristics; and it uses the differences in components across different physical quantities for correction and adjustment, improving system reliability.

[0040] Those skilled in the art will understand that all or part of the features / steps of the above-described method embodiments can be implemented by methods, data processing systems, or computer programs. These features may be implemented without hardware, entirely in software, or in a combination of hardware and software. The aforementioned computer program may be stored in one or more computer-readable storage media. When the computer program is executed (e.g., by a processor), it performs the steps of the above-described rapid detection method embodiments for soup components.

[0041] The aforementioned storage media capable of storing program code include: static hard disks, solid-state hard disks, random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), optical storage devices, magnetic storage devices, flash memory, magnetic disks or optical disks, and / or combinations of the above devices, that is, they can be implemented by any type of volatile or non-volatile storage devices or combinations thereof.

[0042] This application also provides an embodiment of a spectrometer, including: a processing module, an emission light source, and a photodetector; the processing module includes a memory and one or more processors; wherein the memory is used to store one or more computer programs, and the one or more processors are used to execute the one or more computer programs stored in the memory, so that the processors execute the features / steps of the above-described rapid detection method embodiment for soup components. Specifically, the optical path length of the acquisition optical path between the emission light source and the photodetector is 3mm~6mm; the emission light source emits ultraviolet-visible-near-infrared light, and the photodetector receives the ultraviolet-visible-near-infrared light penetrating the soup; the processing module analyzes and processes the ultraviolet-visible-near-infrared light received by the photodetector according to the soup analysis model to obtain the multi-channel spectral data, conductivity data, and / or temperature data.

[0043] The above description is merely a preferred embodiment of this application. Those skilled in the art will understand that various changes or equivalent substitutions can be made to these features and embodiments without departing from the spirit and scope of this application. Furthermore, under the teachings of this application, these features and embodiments can be modified to adapt to specific situations and materials without departing from the spirit and scope of this application. Therefore, this application is not limited to the specific embodiments disclosed herein, and all embodiments falling within the scope of the claims of this application are within the protection scope of this application.

Claims

1. A rapid detection method for soup components, characterized in that, include: S1. Pre-process the soup to be tested; The pretreatment includes filtration, adsorption, and / or reverse osmosis; S2. Data acquisition is performed on the pretreated soup, including the acquisition of multi-channel spectral data, conductivity data and / or temperature data of the soup. S3. Based on the multi-channel spectral data, conductivity data, and / or temperature data, the soup is analyzed using a soup analysis model to generate analysis results; the analysis results include qualitative analysis results and semi-quantitative analysis results.

2. The rapid detection method for soup components according to claim 1, characterized in that, The data collection for the pretreated soup specifically includes the following steps: S21. Place the spectrometer directly into the pretreated soup; the spectrometer includes a processing module, an emission light source, and a photoelectric receiver; the optical path length of the acquisition optical path between the emission light source and the photoelectric receiver is 3mm~6mm; S22. The light source of the spectral analyzer emits ultraviolet-visible-near-infrared light, and the photodetector receives the ultraviolet-visible-near-infrared light that penetrates the soup. S23. The processing module analyzes and processes the ultraviolet-visible-near-infrared light received by the photoelectric receiver according to the soup analysis model to obtain the multi-channel spectral data, conductivity data and / or temperature data.

3. The rapid detection method for soup components according to claim 1, characterized in that, The center frequencies of the multi-channel spectral data acquisition include 260nm, 280nm, 360nm, 530nm, 890nm±10nm, 400nm, 930nm, 1160nm, 1200nm, 1400nm, 1500nm, and 1600nm±10nm.

4. The rapid detection method for soup components according to claim 1, characterized in that, The steps for constructing the soup analysis model include: S100, Sample library preparation, wherein the sample library contains multiple standard solution samples, mixed solution samples and real soup samples of different gradients, and each sample is labeled accordingly, and each sample is prepared in parallel; the standard solution samples include purine, protein, fat and sodium chloride solution; S200. Data acquisition and labeling are performed on each sample in the sample library. The data acquisition includes acquiring multi-channel spectral data, conductivity data and / or temperature data of the soup. S300, Perform data quality control and data cleaning on the data; S400. The cleaned data is fed into the regression model for training. A mapping model is established using supervised learning algorithms, with multi-channel spectral, conductivity, and temperature data as inputs and protein concentration, purine concentration, fat concentration, and sodium chloride concentration as outputs. S500. Based on the training of the regression model, set qualitative analysis thresholds and semi-quantitative analysis thresholds. For the obtained regression model, the regression is converted to qualitative analysis through a decision transformation layer, and qualitative and semi-quantitative analyses are performed.

5. The rapid detection method for soup components according to claim 4, characterized in that, The algorithm includes a multilayer perceptron regressor, an elastic regression network, a minimum absolute shrinkage and selection operator, and linear and nonlinear support vector regression.

6. The rapid detection method for soup components according to claim 4, characterized in that, The data quality control and data cleaning of the data specifically involves: removing invalid bad samples, including those with missing data, missing labels, repeated collection of a single sample, and / or excessive volatility.

7. The rapid detection method for soup components according to claim 4, characterized in that, The steps for preparing the actual soup sample include: S101. Take the middle layer of the soup liquid; S102. Filter out particulate impurities and floating oil from the soup using a 100-400 mesh filter. S103. Laboratory analysis yielded the concentration values ​​of purines, proteins, fats, and salinity in the soup.

8. The rapid detection method for soup components according to claim 7, characterized in that, The analytical methods used in the laboratory analysis include high performance liquid chromatography, Kjeldahl nitrogen determination, acid hydrolysis, silver nitrate titration, and conductivity measurement.

9. The rapid detection method for soup components according to claim 1, characterized in that, The qualitative analysis results include qualified and unqualified; the semi-quantitative analysis results include low, medium and high.

10. A spectrometer, characterized in that, include: Processing module, transmitting light source and photoelectric receiver; The processing module includes a memory and one or more processors; The memory is used to store one or more computer programs, and the one or more processors are used to execute the one or more computer programs stored in the memory to cause the one or more processors to perform the rapid detection method for soup ingredients as described in any one of claims 1-9.

Images