449 results about "Food sample" patented technology

The invention relates to the technical field of food component analysis, in particular to a food quality component analysis method and system based on a near infrared spectrum technology, and the method comprises the following steps: obtaining a food sample set, and obtaining original near infrared spectrum data based on the food sample set, combining the original near infrared spectrum data to form an original infrared spectrum matrix; preprocessing the original infrared spectrum matrix to generate a processed spectrum matrix; and extracting the characteristic wavelength of the near infrared spectrum information based on the processed spectrum matrix, constructing a food quality quantitative analysis model according to the characteristic wavelength in combination with a partial least squares regression algorithm, and outputting a component content predicted value according to the food quality quantitative analysis model. And generating a quality component analysis report of the to-be-detected food based on the component content predicted value. The method has the advantages that food quality and ingredients can be quickly, nondestructively and accurately detected, and detection precision and accuracy are improved.

The invention relates to a food safety risk analysis method and system based on big data. The method comprises the steps of collecting food full-life-cycle key data through Internet of Things equipment and a data platform, and completing data format standardization to form a structured data set; key risk factors are extracted through the structured data set, a risk factor weight matrix is constructed, and a primary risk value of the food sample is calculated; establishing a time sequence prediction model by using the primary risk value and historical time sequence data, calculating a risk change trend, and predicting a future risk fluctuation condition; calculating a food risk grade according to the primary risk value and the risk change trend, and generating a corresponding risk classification label; performing comparative analysis on the risk classification label and an actual supervision result, calculating a model deviation, and optimizing a risk calculation and trend prediction model based on a deviation result; the optimized analysis results are integrated, the risk level and the change trend are displayed through a graphical interface, and intelligent early warning prompts and intervention decision suggestions are provided.

The invention provides a food heavy metal pollution detection system based on plasma emission spectrum analysis, and aims to realize rapid and accurate detection of heavy metal elements in a food sample. The system comprises a sample processing module, an excitation module, a spectrum detection module, a signal processing module, a data analysis module and an output module. The sample processing module converts a food sample into an aerosol or steam state. The spectrum detection module is used for extracting spectrum characteristic information of heavy metal elements. And the signal processing module adopts an AI-driven spectrum denoising algorithm to remove background noise and interference signals. And the data analysis module calculates the concentration of each element based on the characteristic peak intensity and generates heavy metal pollution data. And the output module is used for visually displaying the detection result. According to the method, complex sample pretreatment steps are reduced, the detection efficiency and sensitivity are improved, and the method is suitable for food safety detection scenes and particularly has remarkable advantages in field rapid detection application of agricultural products, drinking water and processed food.

The invention discloses an improved food sensory quality evaluation method and system based on a fuzzy mathematical method, and relates to the technical field of food inspection and detection. Performing a single-factor test on the improved food sample, and performing a response surface test on the basis of the single-factor test; performing comprehensive sensory evaluation on each sample in the response surface test by adopting a fuzzy mathematical analysis method; and physical and chemical indexes of the improved food under the optimal process are determined. According to the invention, the technology of the improved food is optimized, and the physicochemical indexes of the improved food with the optimized response surface are measured; a single-factor test and a response surface test are carried out in sequence, sensory scores are taken as evaluation standards, and factors influencing the quality of the improved food are determined; the optimal formula of the improved food is finally determined through a verification experiment; a fuzzy mathematics comprehensive sensory evaluation model is established for the improved food, and the obtained sensory evaluation result is used for response surface optimization evaluation.

The invention relates to a food reserved sample quality monitoring method based on machine learning, and the method specifically comprises the following steps: deploying a sensor array in a food reserved sample environment, collecting reserved sample multi-dimensional physicochemical characteristic data in real time, constructing a training set through historical normal and degraded batch data, and marking a state; the method comprises the following steps: constructing a machine learning model for food reserved sample quality monitoring, inputting sample data in a training set into the model, sequentially passing through a dynamic distribution alignment module, a physical constraint confrontation enhancement module and a multi-scale residual space-time network, and performing dynamic attention mechanism enhancement by utilizing physical constraint and environment modulation. And finally, outputting a quality category probability by the multi-modal classifier. Then calculating model loss, and carrying out iterative training on the model to obtain a trained model; and deploying the trained model at a reserved sample monitoring terminal, inputting newly collected monitoring data, and predicting the quality state of the food reserved sample. According to the invention, high-efficiency and real-time quality monitoring on the quality of the reserved food sample can be realized.

The invention provides a food pollution detection method based on multi-wavelength spectrophotometry, and the method comprises the steps: transmitting light in a series of wavelength ranges to a food sample through a tunable multi-wavelength light source system, generating spectral response, collecting the spectral response through a high-resolution spectrometer, and forming a multi-dimensional spectral image, a deep learning algorithm is used for analyzing, identifying and distinguishing subtle spectral differences between natural components and potential pollutants in a food sample, a preliminary identification result is obtained, a self-adaptive wavelength selection mechanism is implemented, wavelength output of a light source is dynamically adjusted, spectral response data is obtained, and the spectral response data is compared with a preset food safety standard database. According to the technical scheme provided by the invention, natural components and potential pollutants in a food sample are efficiently and accurately recognized, and the sensitivity, specificity and accuracy of pollutant detection are remarkably improved.

The invention relates to a food sampling inspection decision-making method based on a graph attention network and Crack-Topsis, and belongs to the technical field of food safety. Firstly, data are preprocessed; then, constructing a graph attention network model, inputting the preprocessed data into a GAT model for training, and predicting the number of sampling inspection times of each node by extracting node features and calculating association weights among the nodes; and finally, decision-making is carried out on the sampling inspection sequence of different hazardous substances by adopting a Crimic-Topsis method, the sampling inspection sequence of the hazardous substances is determined according to the closeness degree of the hazardous substances, and the sampling inspection efficiency and effect are improved. Through the method, a more scientific and reasonable food sampling inspection plan can be realized, the food safety is guaranteed, the decision-making efficiency of a supervision department is improved, and the waste of sampling inspection resources is reduced.

The invention provides a D-A type organic fluorescent small molecule, a preparation method and application of the D-A type organic fluorescent small molecule in detection of nitrofuran antibiotics, and belongs to the technical field of fluorescent sensing. The D-A type organic fluorescent micromolecule is composed of 2-(2-aminophenyl) benzothiazole and an electron-donating group, the excitation spectrum of the D-A type organic fluorescent micromolecule is obviously overlapped with the absorption spectrum of nitrofuran antibiotics, and fluorescence quenching response can be shown through the inner filter effect; the trace nitrofuran antibiotics can be detected in a liquid phase in an ultrafast, high-sensitivity, excellent-selectivity and strong-anti-interference manner. According to the invention, a quantitative evaluation system can be constructed in combination with a smart phone, the RGB value of the image of the liquid-phase fluorescence sensor is output in real time, and rapid, accurate and visual quantitative detection of nitrofuran antibiotics in a real food sample or a water source is realized. In addition, the filter paper fluorescence sensor has the advantages of being portable and easy to prepare, and nitrofuran antibiotics can be rapidly identified on site in an actual scene.

The invention provides a food component analysis method and system based on a near infrared spectrum. The method comprises the following steps: acquiring a near infrared spectrum signal through a food sample, and generating a sample near infrared spectrum signal by adopting an intelligent sampling method; based on the near infrared spectrum signal of the sample, automatically focusing a key area by using an attention mechanism enhanced convolutional neural network, and combining a spectrum characteristic selection technology to screen spectrum characteristics, and generating sample component and content information; based on the sample component and content information, evaluating the human body metabolism influence degree by applying a gradient boosting decision tree algorithm, analyzing a biological mechanism by combining a bioinformatics analysis technology, and generating a sample influence evaluation report; and based on the sample influence evaluation report, adopting natural language processing to generate a food component analysis report. According to the technical scheme provided by the invention, high-precision and automatic food component analysis is realized, the analysis accuracy and efficiency are improved, and an influence mechanism of food components on human metabolism is deeply analyzed.

The invention discloses a food safety risk prediction method and device based on a heterogeneous graph neural network, and the method comprises the steps: evaluating the food safety risk: firstly, training a classification model to distinguish the qualified state and the unqualified state of a food sample; then, explaining the model by using an SHAP value, and calculating influence weights of various dopants on food qualification; finally, through weight integration, calculating an overall risk value for each sample, and taking the overall risk value as a prediction label; food safety map representation learning: capturing a complex relationship in a food sample, and identifying a potential risk mode: constructing a heterogeneous food safety map, and representing various entities and mutual relationships thereof; processing graph data by using a heterogeneous graph neural network HGNN fusing a meta-path context, and generating an embedded vector of a food sample node; and risk prediction: classifying the food samples by using the prediction labels and the embedded vectors of the food sample nodes, and dynamically evaluating the food safety risk. According to the method, the dopant feature contribution weight can be accurately calculated, and more accurate data support is provided for risk prediction.

A system for detecting microbial contamination in food processing environments, comprising: a sensor array with a variety of biosensors for detecting microbial markers that indicate a specific microbial contamination; a microfluidic analysis unit operatively coupled to the sensor array, the microfluidic unit comprising microchannels that direct environmental or food sample fluids through a series of analyzable stages, including sample concentration, enrichment, and pathogen identification; and a central processing unit (CPU) communicatively connected to the sensor array and the microfluidic device, the CPU being configured to receive and process real-time data from the sensor array, apply machine learning techniques to detect microbial contamination, and trigger an automated response based on predetermined contamination severity thresholds, the system being designed to continuously monitor microbial contamination at various stages of food processing, providing operators with real-time feedback and enabling immediate corrective action.

The invention relates to the technical field of food detection, in particular to a GC-IMS-based food freshness detection method, device and equipment, and the method comprises the following steps: obtaining headspace sampling gas of a to-be-detected food sample; according to the type of the to-be-detected food sample, automatically matching preset chromatographic conditions and ion mobility spectrometry conditions from a graded food type database; the headspace sampling gas is injected into GC-IMS, analysis is carried out based on matched chromatographic conditions and ion mobility spectrometry conditions, and a volatile organic compound fingerprint spectrum of the sample is obtained; and extracting preset key feature information from the fingerprint spectrum, and inputting the key feature information into a food freshness evaluation model to obtain a freshness evaluation result of the to-be-detected food sample. Therefore, the problems that in the prior art, detection parameter curing lacks adaptability, key feature analysis is not accurate, and model prediction accuracy is insufficient are solved.

The invention discloses a moisture fluorescence probe based on a D-pi-A structure as well as a preparation method and application of the moisture fluorescence probe. The preparation method specifically comprises the following steps: dissolving WP in a solvent, reacting with BF3. Et2O under the protection of nitrogen, filtering, washing and drying to obtain a red target product WP-BF3. According to the present invention, the change of the microenvironment moisture content can be responded, the significant fluorescence signal response can be generated at the 487 nm position, the quantitative analysis detection of the moisture content in the organic solvent and the food sample can be achieved, the response is rapid, the sensitivity is good, and the accuracy is high.

The application relates to the field of food detection, and discloses a sample pretreatment device for food safety detection, which comprises a shell, a crushing mechanism, a centrifugal mechanism, a material distribution mechanism, a solid-phase extraction mechanism and a nitrogen blowing mechanism are arranged in the shell; juice is obtained after the food sample is crushed, and the juice is subjected to centrifugal treatment in the centrifugal mechanism; the supernatant after centrifugation is temporarily stored and distributed in the material distribution mechanism; the multiple samples after distribution are subjected to solid-phase extraction in the solid-phase extraction mechanism; and the nitrogen blowing mechanism cooperates with the solid-phase extraction mechanism to complete nitrogen blowing work. Through structural innovation and function integration, the crushing, centrifugal, material distribution, extraction and nitrogen blowing concentration five function modules are integrated in the same equipment, the equipment floor area is reduced, the operation process is optimized, the manual intervention frequency is reduced, and the efficiency and reliability of the food safety detection sample pretreatment are remarkably improved.

The invention discloses a food colony detection and analysis method and system based on artificial intelligence, and the method comprises the steps: carrying out gradient elution-layered filtration pretreatment on a to-be-detected food sample to generate an impurity-removed colony sample; synchronously performing bacterial colony microscopic image acquisition and near infrared spectrum data acquisition on the impurity-removed bacterial colony sample to generate initial multi-modal data; performing space-time calibration processing on the initial multi-modal data to generate multi-modal data after space-time calibration; performing multi-dimensional bacterial colony feature extraction and screening processing on the multi-modal data after space-time calibration to generate a strong correlation feature subset; performing AI double-branch attention fusion analysis processing on the strong correlation feature subset to generate a bacterial colony classification result and a bacterial colony concentration estimated value; and performing multi-reference-system correction processing on the bacterial colony classification result and the bacterial colony concentration estimation value to generate a corrected detection result. According to the invention, the timeliness and reliability of the detection result are improved.

The invention relates to a food sensory evaluation method and device based on an attention mechanism, equipment and a medium. The method comprises the following steps: acquiring sensory information such as vision, smell, taste and touch of a food sample through multi-modal data acquisition equipment, and performing standardization processing to obtain a sensory feature matrix; generating a sensory feature vector set by using a pre-established multi-modal feature extraction model; modeling each sensory dimension relationship by means of an attention layer in a deep learning network, and calculating to obtain an attention weight of each sensory feature; and performing weighted combination on the sensory feature vector set based on the weight to generate a comprehensive sensory feature basic representation. According to the method, the association among the multi-modal sensory characteristics is effectively modeled through an attention mechanism, and a scientific and efficient solution is provided for food sensory evaluation.

The invention provides an intelligent veterinary drug residue detection system and method based on multi-dimensional spectral characteristics, and relates to the technical field of veterinary drug residue detection, spectral response data of a to-be-detected sample solution in a visible light band and a near-infrared band is collected, and the residue discrimination degree of veterinary drug residues under any wavelength when the concentration dependence change exists is determined; abnormal wave band combinations with quantitative response to veterinary drug residues are screened out from the visible light wave band and the near-infrared wave band respectively, the residual peak deviation of the veterinary drug residues in the region of interest of the spectrum is determined according to the abnormal wave band combinations, and trace residue marks in the multiple spectrum intensity distribution modes are determined; and performing in-situ nondestructive screening on veterinary drug residues in the to-be-detected animal-derived food sample according to the residue discrimination and the trace residue mark. According to the method, on the premise that the dual-band spectrum collaborative response is enhanced, the veterinary drug residue characteristics can be directionally distinguished and detected, so that the veterinary drug residue screening accuracy is improved.

The application provides a preparation method of a functionalized phage probe and application of the functionalized phage probe in detection of escherichia coli. The functionalized phage is a recombinant phage (M13KO7@SaBP) in which streptavidin binding peptide (SaBP) is fused and expressed at the N terminal of the main capsid protein P8 protein of M13K07 phage. In the application, the gene encoding SaBP (MDVEAWLGAR) is inserted into the N terminal of the P8 protein gene of M13K07 phage by site-directed mutagenesis to prepare M13K07@SaBP. The stable signal amplification is realized by using the abundant P8 protein (about 2700) of M13 phage and the super strong binding force of biotin-streptavidin, the interference of food sample matrix is reduced by combining the magnetic separation technology, and a detection method of escherichia coli with high sensitivity and small sample matrix interference is constructed.

The invention belongs to the field of detection, and particularly relates to an electrochemical sensing platform for detecting lead ions and malathion as well as a preparation method and a detection method of the electrochemical sensing platform. The preparation method of the electrochemical sensing platform comprises the steps of designing a three-chain DNA compound, preparing a gold nanoparticle electrode, preparing the electrochemical sensing platform and the like. The electrochemical sensing platform realizes dual detection of lead ions (in a signal enhancement mode) and malathion (in a signal weakening mode) through specific recognition of DNAzyme and an aptamer on the basis of a three-chain DNA compound and a gold nanoparticle electrode. The method has the advantages of no label, high sensitivity (the detection limits respectively reach 5.42 pM and 0.34 pM), strong anti-interference capability and good stability, and is suitable for rapid detection of trace pollutants in environment and food samples.

The invention discloses a bidirectional coupling numerical simulation method for a translation heating process of regular or irregular food in a microwave cavity, and belongs to the technical field of microwave heating. According to the invention, liquid nitrogen is adopted for freezing and homogenizing food samples, so that the accuracy of food electric heating characteristic parameters can be improved; the prediction precision of microwave heating numerical simulation can be improved by adopting a bidirectional coupling translational motion mode. The method for accurate modeling of regular food and platform or round corner approximate modeling of irregular food corners can effectively conform to the finite element and finite time domain difference principle. Aiming at microwave-assisted heating models of various heat sources, the fluid power grid division mode provided by the invention can effectively reduce false cooling phenomena occurring at the initial stage of heating translational motion operation, and is more suitable for the actual microwave-assisted heating treatment process. According to the invention, the time and economic cost of sample testing can be greatly reduced, and accurate prediction of microwave processing temperature changes of regular food and irregular food can be realized.

The invention relates to the technical field of intelligent detection, and discloses an intelligent detection method and system for illegal food addition and a storage medium. The method comprises the following steps: preparing a multi-target SERS substrate for inhibiting interference; a food sample is extracted and injected into the substrate, and a multi-dimensional spectrum is obtained through three-wavelength laser scanning; performing noise reduction and alignment on the spectral data to extract characteristic peak fingerprints to form a unique identification matrix; and training a multi-path parallel attention network, and simultaneously identifying various additives and concentrations through feature fusion. The method solves the problem of insufficient detection sensitivity and specificity caused by the influence of interfering substances such as citrate in food safety detection in the SERS technology, and breaks through the technical bottleneck that a traditional method is difficult to detect various illegal food additives at the same time; the problem of low accuracy and efficiency of a detection result caused by lack of intelligent data processing in the prior art is solved.

The utility model discloses a food inspection filtering device, which relates to the field of food detection and comprises a mounting plate, a filtering tank is rotatably arranged on the mounting plate, and a rotating component is arranged on the mounting plate and used for rotating the filtering tank; a storage tank is arranged at the bottom of the mounting plate, a metal filter screen is arranged on the side wall of the filtering tank, and the storage tank is matched with the mounting plate to cover the metal filter screen of the filtering tank; a backwashing mechanism is arranged on the mounting plate and is used for cleaning residues in the filtering tank and on the surface of the metal filtering net; the backwashing mechanism comprises a water pump I, a pipeline, a water pump II and a spray pipe, and the water pump I is matched with the pipeline to pump out residues in the filtering tank. The solid-liquid separation device has the beneficial effects that the filtering tank is rotated through the rotating assembly, solid-liquid separation is performed on a food sample and a solution under the action of centrifugal force, the separation speed is remarkably increased, the food sample is retained in the filtering tank, and the solution can penetrate through the filtering tank to be collected into the storage tank so as to be conveniently collected.

The present disclosure reveals the method for the quantitative determination of ethylene oxide (EO) and 2-chloroethanol (2CE) as contaminants in food products. The method is based on concentrated hydrochloric acid-mediated derivatization of the processed samples under specific treatment conditions, which provides the quantitative conversion of EO to 2CE, followed by the quantitative determination of thus formed 2CE with gas chromatography coupled with mass spectrometry (GC / MS-MS). The method enables a highly accurate procedure for the analysis of EO and 2CE in food samples at the concentration range from 0.019-0.19 mg / kg.

The invention relates to the field of food detection, and discloses a sample pretreatment device for food safety detection.The sample pretreatment device comprises a shell, a crushing mechanism, a centrifugal mechanism, a material distributing mechanism, a solid-phase extraction mechanism and a nitrogen blowing mechanism are arranged in the shell, and after a food sample is crushed by the crushing mechanism, juice enters the centrifugal mechanism to be subjected to centrifugal treatment; the material separation mechanism is used for temporarily storing and separating centrifuged supernate, the solid-phase extraction mechanism is used for carrying out solid-phase extraction on a plurality of separated samples, and the nitrogen blowing mechanism and the solid-phase extraction mechanism are matched to complete nitrogen blowing work. Through structural innovation and function integration, five functional modules including crushing, centrifuging, material separation, extraction and nitrogen blowing concentration are integrated into the same equipment; the occupied area of the equipment is reduced, the operation process is optimized, the manual intervention frequency is reduced, and the pretreatment efficiency and reliability of the food safety detection sample are remarkably improved.

The invention discloses a rapid component detection system based on food additives, and relates to the technical field of food safety detection.A food sample is collected, matrix information of the food sample is obtained, an additive fingerprint feature group is extracted based on a reference model, sample response signals are collected through multi-channel detection, and feature matching analysis is carried out; outputting additive existence judgment and a matching degree score; when the matching degree score is lower than a preset threshold value, abnormal response features are extracted, feature vectors of the components to be verified are constructed and compared with the high-risk component template data, and suspected illegal added components are marked; by fusing spectrum, fluorescence and electrochemical multi-dimensional detection channels, the method has the characteristics of broad spectrum, rapidness and high adaptability, can realize intelligent identification and early warning of unknown or illegal additives, and is suitable for mobile detection and risk screening in various food scenes.

The invention provides a pretreatment method for detecting various vitamins in food, and relates to the technical field of vitamin detection. Comprising the following steps: a) mixing a food sample with a sodium acetate buffer solution according to a volume ratio of 1: (1-5), adding a combined enzyme for enzymolysis to obtain enzymatic hydrolysate, and collecting filtrate after filtering a membrane; the combined enzyme comprises neutral protease and lipase; the mass volume ratio of the combined enzyme to the sodium acetate buffer solution is 24-32%; b) adding a mixed solvent of normal hexane and acetonitrile into the filtrate, carrying out vortex mixing, centrifuging, and separating to obtain an upper-layer normal hexane phase or a lower-layer acetonitrile phase; and c) transferring the upper-layer normal hexane phase or the lower-layer acetonitrile phase, adding silanized magnetic nanoparticles, oscillating and adsorbing for 15-20 minutes, and removing the silanized magnetic nanoparticles to obtain a sample to be detected. The pretreatment method disclosed by the invention can meet the requirements of detecting various vitamins in different foods, and is high in detection accuracy and precision.

The utility model discloses a food additive detection device which comprises a shell, the shell is of a hollow cylinder structure, a feeding hopper is arranged on the upper surface of the shell in a penetrating mode, a box body is fixedly connected to one side of the shell, a chromatographic column is arranged in the box body, an analyzer is fixedly arranged in the box body, and a detection module is arranged in the analyzer. An analyzer is fixedly mounted on the upper surface of the box body, the analyzer is connected with the chromatographic column, a control panel is fixedly mounted on the upper surface of the box body, the control panel is connected with the analyzer, a sample treatment structure is arranged in the shell, and the sample treatment structure is provided with a multi-stage treatment mode to treat food into sample liquid to be detected. According to the food additive detection device, the crushing cylinder, the stirring cylinder and the filtering cylinder are sequentially arranged in the shell, a food sample to be detected is pretreated, the food detection efficiency is improved, and treatment structures in the crushing cylinder, the stirring cylinder and the filtering cylinder are connected to the output end of the same motor through the rotating cylinder, so that the energy consumption of the device is reduced.

1. Name of the designed product: sample scale. 2. Use of the designed product: weighing, food sample, data recording and transmission. 3. Design points of the designed product: in shape. 4. Picture or photo that best shows the design points: perspective view.

The invention discloses a food risk prediction visual analysis method and device based on meta-path selection, and the method comprises the steps: carrying out the cleaning and preprocessing of food detection data, and distributing a risk level label for each sample based on a detection value of a pollutant and a legal threshold value; food attribute features are preprocessed, a heterogeneous graph is constructed for different types of nodes and relationships thereof, a suitable meta-path is designed in combination with domain knowledge, and food table data preprocessed in the previous step are converted into a data format suitable for an HAN heterogeneous model; the method comprises the following steps: interactively adjusting the weight of a meta-path in a visualization system, calculating the embedding result of a food sample in real time, carrying out dimensionality reduction display on the embedding result of the food sample through an embedding result distribution view, providing a meta-path composition view, and designing an embedding comparison view; the combined influence of the display attributes on the food risk level is visually provided and serves as the basis of meta-path weight distribution; through model calculation, food risk grade prediction is generated based on the current meta-path composition, and a prediction result is displayed in a prediction probability form; meanwhile, attribute distribution in a prediction result self-defined interval is analyzed to serve as support for the prediction result.

To provide an allergic reaction test food which contains nuts as the only allergen, can be provided to infants without the risk of aspiration, and a method for producing the allergic reaction test food.SOLUTION: Provided is an allergic reaction test food product comprising a freeze-dried product of a predetermined shape that contains nuts, starch, and dextrin and does not contain any allergens other than those derived from nuts. The nuts are in a paste form, preferably with a maximum particle size of 900 μm or less, preferably with a nut content of 0.02 to 4.2 g per piece in terms of weight before freeze-drying, and preferably dissolved in water or hot water at the time of use to form a paste.SELECTED DRAWING: None