64 results about "Food category" patented technology

The invention provides a food material feature recognition model construction and classification method, system and device, and a medium. The food material feature recognition model construction method comprises the steps of obtaining target sample image data of a plurality of sample food materials; wherein the target sample image data comprises visible light image data and infrared image data; constructing a training sample data set based on the target sample image data and food material category data corresponding to the target sample image data; and inputting the training sample data set into a preset model to construct a food material feature recognition model. According to the method, the food material feature recognition model is constructed, so that the feature vectors of the food materials under different environments, different illumination conditions or different angles can be effectively recognized, comprehensive and diversified food material features are extracted, and then the types of the food materials are accurately recognized; the food materials can be accurately classified under different environments, different illumination conditions or different angles, and the universality and coverage of food material classification are improved.

The invention relates to the technical field of medical health monitoring and evaluation, and discloses a method and system for evaluating and monitoring the nutrition risk of a cancer palliative treatment patient, and the method comprises the steps: obtaining a daily diet image of the cancer patient through an image device, recognizing the type of food in the daily diet image, recognizing the weight of food in the daily diet image, and calculating the nutrition risk of the cancer palliative treatment patient; analyzing diner actions in the daily diet image; the daily diet condition of the cancer patient is analyzed according to the food category, the food weight, the diner action and the target food, the nutrition change item of the initial nutrition condition is determined according to the daily diet condition, and the nutrition risk condition of the cancer patient is identified according to the nutrition change item; determining target monitoring equipment of the cancer patient from non-image equipment; and constructing a nutrition risk sequence of the nutrition risk level, analyzing the nutrition risk trend of the cancer patient by using the nutrition risk sequence, and determining a nutrition risk monitoring result of the cancer patient. The convenience of nutrition risk assessment of the patient can be improved.

The invention discloses a personalized recipe recommendation system, a recommendation method and an interaction system, and relates to the technical field of diet recommendation, the system comprises a user data collection module, a food image recognition module and a personalized recommendation module, the user data collection module is used for obtaining health data and diet preference data of a user, the health data comprises basic information, health conditions and exercise habits, the basic information comprises regions, the health conditions comprise allergen lists, chronic diseases and diet targets, and the food image recognition module is used for obtaining food photos uploaded by a user, recognizing the food photos to obtain food recognition results and sending the food recognition results to the user. The food identification result comprises a food type corresponding to the food photo, and the personalized recommendation module is used for determining a recommended recipe recommended to the user based on the health data, the diet preference data and the food identification result. By considering more comprehensive influence factors, a more suitable and personalized recipe can be recommended to the user.

The invention provides a food classification component identification method and system based on multi-scale feature attention synergy, and the method comprises the steps: constructing a multi-task neural network model, sequentially inputting a food image into a global feature module and a progressive local feature module, and respectively extracting global semantic information and refined local features of different scales; feature interaction between food category identification and component analysis tasks is promoted through a cross attention cooperation module, and key areas and important component information in images are dynamically selected; gradually activating different depth levels of the network by adopting a staged end-to-end training strategy, and introducing a KL divergence constraint to enhance the difference between feature scales; and simultaneously generating prediction results of food categories and component labels through a multi-task classifier. The technical problems of food identification and component analysis task splitting, insufficient local feature expression and insufficient cross-task information complementation are solved.

The invention discloses a human-in-the-loop diet monitoring robot based on body intelligence. The human-in-the-loop diet monitoring robot at least comprises a food information acquisition module, a food identification module, a human-computer interaction module, an identification model incremental learning module, a diet recording module and a diet analysis module. The system obtains food information, and performs real-time identification and recording in combination with a machine learning algorithm. Besides, the man-machine interaction module provides an intelligent diet accompanying function by utilizing cue word engineering and improves the diet experience of the user, and the diet analysis module carries out nutritional ingredient analysis on diet records through an image-text interaction deep fusion technology based on a multi-modal large model and generates personalized diet suggestions according to the diet condition of the user. The system is combined with a healthy diet recording and analyzing function to ensure data synchronization and analysis. According to the method, the adaptability of new food types is remarkably improved, and reliable technical support is provided for intelligent diet monitoring, diet accompanying and healthy diet analysis.

The invention provides a model-based finished dish nutrient content accurate real-time calculation method. The food raw materials and cooking data are obtained through front-end interaction, the nutrient intake is accurately calculated in real time, the nutrient intake is compared with a recommended value of a dietary pagoda for evaluation, food category intake is counted in a classified mode, and prompts are generated. The requirement of modern healthy diet for accurate evaluation of nutritional ingredients of dishes is met, and healthy catering development is promoted.

The invention relates to the technical field of diet recommendation, in particular to a nutrition intake recommendation method, device and system based on a diet structure and a medium. The method comprises the following steps: obtaining element information of various foods, and carrying out diet structure quantitative modeling on various food types to obtain a diet structure quantitative and quantitative model; converting quantitative information of various food categories into multi-dimensional vectors, and inputting numerical values generated by various food element information into an analysis model to obtain nutritional ingredient analysis data; processing intake data of a user based on cross analysis, clustering and classification technologies of diet data and user health data, identifying intake deviation, and analyzing the intake deviation; according to the health target data of the user, dynamically adjusting various parameters in the diet structure quantification and quantification model, generating personalized nutrition intake suggestions, and displaying the suggestions through a user interaction interface; according to the invention, a personalized and dynamic nutrition intake optimization scheme can be provided in combination with the health condition of the user.

The invention discloses a diet metering and recording system for gestational diabetes mellitus patients. The diet metering and recording system comprises a food containing structure; a food weighing structure; a food shooting structure; an information storage module; an analysis and control module; and a display structure. The information storage module is used for storing corresponding relations between food pictures and food categories; the signal receiving and transmitting module receives food category information and corresponding weight information of each meal. The analysis and control module is used for acquiring the pictures of the food in each food containing structure and the weight information of the weighed food one by one, and comparing the pictures and the weight information to obtain the names and the categories of the food; finally, comparing the obtained real food category and food weight information with the received food category and corresponding weight information, and outputting single ending information when the real food category and food weight information are matched with the received food category and corresponding weight information; when all matching is carried out, all ending information is output; the display structure receives the food category information and the corresponding weight information of each meal; and a timing and blood glucose monitoring module is arranged to obtain a 2h blood glucose value. The whole process is high in automation degree, and few events need to be memorized.

According to the daily diet nutrition analysis method based on the wireless weighing record, the intelligent nutrition scale can collect the food weight and conduct peeling calculation, and the net diet weight is accurately obtained. Through peeling calculation, weight interference of non-food parts such as containers can be eliminated, it is ensured that data uploaded to a cloud analysis background is the real food weight, and a foundation is laid for follow-up accurate nutrition analysis. The cloud analysis background can record the data in time and bind the data with the user ID, so that the diet data of each user can be independently stored and managed, and subsequent personalized nutrition analysis and health management for the user are facilitated. After the cloud analysis background records the data, a nutrition analysis notice or a food type selection input notice is sent to the user terminal in time. The timely notification mechanism can improve the participation degree and the response speed of the user, and ensures that the whole nutrition analysis process is efficiently carried out. The user can quickly log in the cloud analysis background to perform subsequent operation according to the notification, and waiting time is shortened.

The invention relates to pure microalgae cheese. The pure microalgae cheese comprises microalgae milk, an acidifying agent and chymosin, the microalgae milk is pure microalgae milk prepared from microalgae raw materials, wherein protein accounts for 40-60% of the dry weight of cells, grease accounts for 8-16% of the dry weight of the cells, and starch accounts for 20-30% of the dry weight of the cells. The pure microalgae milk is adopted as a raw material to prepare the cheese, exogenous starch, fat or protein is not added, a pure microalgae cheese product which is comparable with traditional cheese in flavor and sensory characteristics can be obtained, and the pure microalgae cheese product is good in processing performance and excellent in storage stability; the technical problems that traditional plant-based cheese must be supplemented with a large amount of exogenous starch, fat or protein to adjust the composition structure of raw materials, and the plant-based cheese has a large gap with animal cheese in the characteristics of taste, stretching, melting property, stability and the like are solved. According to the invention, rich high-protein nutritional products are provided for lactose intolerance, animal protein allergy and vegetarians, and the technical blank of the food type of microalgae cheese is filled. The whole microalgae enters the cheese, so that the flavor level of the cheese is enriched, and the comprehensive health-care function of the cheese product is enhanced.

The invention relates to a freezing control method and device, freezing equipment and a storage medium. The method comprises the following steps: determining adaptive target freezing parameters based on food characteristics of different food types in the freezing equipment and detection parameters in the freezing equipment, and controlling an ultrasonic generator in the freezing equipment according to target output power and target operation frequency so as to dynamically adjust the generation condition of ice crystals in combination with the food characteristics, the instant freezing temperature requirements of different food characteristics are met, and therefore the problem that the instant freezing effect is poor due to the fact that different instant freezing modes cannot be adopted in combination with the food characteristics in an existing instant freezing technology is solved.

The invention provides a food recognition and calorie estimation method and system based on a YOLOv8 model, and the method comprises the steps: inputting a food image, detecting food in the image in real time based on the YOLOv8 model, recognizing the type of the food, combining the cooking mode and component information of the food, and dynamically calculating the calorie content. The functions of accurately identifying the food in the meal scene and efficiently estimating the calorie are realized. According to the method, the detection precision is greatly improved while the advantage of detection speed is reserved, and the problems that a traditional target detection method is prone to background interference and low in recognition accuracy in meal recognition are effectively solved. According to the method, the practical application capability of the model in a specific scene is greatly improved, and a reliable basis is provided for subsequent calorie estimation and personalized health intervention. The method has high robustness, transportability and real-time performance, is suitable for various intelligent terminals and edge computing platforms, can be widely applied to the fields of intelligent restaurants, nutrition analysis, health management and the like, and has good popularization prospects and industrialization value.

The application provides a food image segmentation method based on a discrete wavelet attention network, and first, in view of the problems of multiple food categories, irregular distribution, inconsistent size and fuzzy boundary information in the food image, a Food2K-ResNet trained on Food2K and obtained through transfer learning is used to extract food image features, a discrete wavelet attention network and a residual channel attention network are combined to form a double-branch network, spatial domain and frequency domain feature processing is performed, spatial features and channel features are obtained from the spatial dimension and the channel dimension respectively, and the feature dimension of the food image is highlighted and enriched; finally, a segmentation head network is constructed, different scale features processed through the two branches are subjected to convolution, feature fusion and up-sampling operations, so that the size of the finally obtained features is consistent with the size of the input image, and a high-quality and highly detailed segmentation result is obtained.

The embodiment of the invention relates to a method, a device, equipment and a computer program product for determining freshness. The method includes acquiring input data associated with a target food. The method further includes determining a food category based on the input data. In addition, the method further comprises the steps that based on the food category and the input data, the freshness is determined through a freshness detection model, and a feature extraction module in the freshness detection model extracts food features based on the food category and the input data; a freshness determination module in the freshness detection model is configured to determine freshness based on the food category and the food characteristics. Therefore, according to the embodiment of the invention, the food category is firstly determined, and then the food category is used as the input feature to extract the food feature and determine the food freshness, so that the number of output categories of the freshness detection model can be greatly reduced, the training effect of the model is improved, and the accuracy of freshness detection is improved.

Embodiments of the present disclosure relate to a method and an apparatus for determining freshness, a device, and a computer program product. The method includes obtaining input data associated with a target food. The method further includes determining a food category based on the input data. In addition, the method further includes determining freshness through a freshness detection model based on the food category and the input data. A feature extraction module in the freshness detection model extracts a food feature based on the food category and the input data. A freshness determining module in the freshness detection model is configured to determine the freshness based on the food category and the food feature. Therefore, according to the embodiments of the present disclosure, the food category is first determined, and then the food category is used as an input feature to extract the food feature and determine the food freshness. In this way, a quantity of output categories of the freshness detection model can be greatly reduced, thereby improving a training effect of the model and improving accuracy of freshness detection.

The invention provides a refrigeration storage fresh-keeping method and system and a refrigeration storage. The method comprises the steps that the VOCs concentration in a current storage cabin in the refrigeration storage is monitored in real time; measuring the moisture migration rate of the surface of the food in the current storage cabin in real time to obtain a corresponding measurement value; identifying the type of food stored in the current storage cabin; determining the odor intensity change rate at the current moment according to the VOCs concentration; according to the odor intensity change rate and the food category, obtaining a theoretical value of the surface moisture migration rate of the food in the current storage cabin; and according to the ratio of the measured value to the theoretical value of the food surface moisture migration rate at the current moment, making a corresponding fresh-keeping regulation and control strategy in combination with the odor intensity change rate. The system uses the method, and the refrigeration appliance comprises the system. The food fresh-keeping dynamic control method can accurately distinguish the corruption dynamic state, prolong the food fresh-keeping period, reduce the false triggering rate and solve the problem of food fresh-keeping dynamic control.

Provided are a shopping information providing method and a refrigerator using the method. Specifically, the method includes the operations of: identifying a category of displayed food items on a display stand in front of which a user is located in a store; generating shopping information related to stored food items included in the identified category among one or more food items stored in an in-house refrigerator; and transmitting the generated shopping information to a user terminal. The shopping information includes at least one of a list of the stored food items, locations of the stored food items, an internal image displaying the stored food items, a required list requiring purchase in the category, recipe information related to the displayed food items and the stored food items, and recommended storage location information related to where the displayed food items are to be stored in the refrigerator.

The present disclosure relates to a method, device, electronic device and storage medium for retrieving food images. The retrieval method includes: acquiring a food image; determining an initial retrieval result based on a matching result between the food image and a preset image in an image library; determining, based on the food image, at least one second food category corresponding to the food image and the confidence level of the food image for each second food category; and adjusting the initial retrieval result based on the confidence level, the correspondence between the first food category and the second food category to generate a final retrieval result. The embodiment of the present disclosure can reorder the initial retrieval results based on the confidence level of the second food category corresponding to each food image, so that the retrieved first food category is more consistent with the actual food category of the food image, thereby improving the classification accuracy of the food image and facilitating improving the final retrieval accuracy of the food image.

The application discloses a kind of food additive knowledge generation method and system based on multi-modal, it is related to food additive knowledge generation technical field, by regulation rule slot disassembly module and product scene slot construction module, regulation side and scene side are respectively transcribed into slot chain, so that regulation constraint object, food category, use condition, label requirement and other information and ingredient table, label identification, process specification, detection specification and question and answer target form the structure basis that can be aligned item by item, avoid only stay in the level of article original display or keyword hit.Multiple modal semantic module sorts out regulation text, ingredient table text, label image identification text, detection item specification, process specification text and question and answer request, so that subsequent processing is carried out under the same semantic fragment system, reduce the alignment fracture caused by the difference of expression from different sources, so that scene input has sustainable acceptance ability.

The application provides a dietary management method and system based on inflammatory dietary assessment and anti-inflammatory dietary plan pushing, which comprises the following steps: step 1, obtaining the intake amount of food of a surveyee each time; step 2, combining food categories and intake frequency, calculating the average daily intake amount of various foods of the surveyee; step 3, based on the dietary intake data of the surveyee, adopting principal component analysis for statistical analysis, obtaining a personalized food combination which can best represent the favorite of the surveyee; step 4, according to the full literature retrieval result, creating an inflammation score CDII of Chinese food, which is used to measure the dietary inflammation degree of Chinese people; and step 5, combining the inflammation effect score in the CDII and the personalized food combination, providing food replacement suggestions which can meet the dietary favorite of the surveyee and reduce dietary inflammation to the surveyee. The application can more easily reduce the chronic inflammation of the body on the basis of not changing the dietary habits, and from the inflammatory mechanism, the most fundamental and effective result of reducing the risk of chronic diseases is achieved.

The present invention discloses an intelligent fresh-keeping system and method for food refrigeration equipment, comprising: firstly, collecting an initial image of a target food through an image sensor; then processing the image through a food category recognition model to obtain the appearance and type of the food to be monitored, and determining a key monitoring area; finally, collecting image data of the key area, combining the food type matching preset library to obtain the current fresh-keeping strategy and sending it to a central control chip for execution, so as to realize intelligent and accurate fresh-keeping of food.

The present disclosure relates to the field of image recognition and artificial intelligence technology, and provides a method, device and equipment for intelligent monitoring and reminder of patient dietary behavior, the method comprising: collecting patient dietary image data containing calibrated tableware, and preprocessing the dietary image data; extracting at least three types of local invariant feature descriptors from the preprocessed dietary image data; normalizing the extracted various feature descriptors and performing feature fusion to generate a fused feature vector; inputting the fused feature vector into a pre-trained deep neural network model for feature classification, and outputting a food category label; calculating the patient's dietary intake based on the dietary image data, the food category label and the size of the calibrated tableware; and performing intelligent personalized reminders based on the food category label, the patient's case data and the patient's dietary intake, thereby solving the problems of insufficient accuracy, high computational complexity and weak personalized services in the current process of dietary behavior recognition and intervention for cancer patients.

A method of processing an image, the method comprising: receiving image data from a subject at a remote location; and analyzing the image data to identify therein content related to the food category. A set of subject descriptor features specific to the subject is obtained, and a trained machine learning program is applied to the identified food category and the set of features to provide a score describing a response of the subject to the food category. The method generates processed image data including a score superimposed on at least a portion of the received image data, and transmits the image data to a display device viewable by the subject at the remote location.

The invention provides a food detection method and system based on computer vision, and the method comprises the steps: carrying out the adaptive noise removal and image segmentation of a food image, obtaining a standard food image, and extracting the food morphological characteristics of the standard food image; performing block feature extraction and global feature fusion on the standard food image to obtain food global features, and performing category analysis on the standard food image to obtain food category information; performing multi-scale feature sampling and dynamic defect scoring on the standard food image according to the food type information to obtain food defect information; performing aging drift detection and freshness analysis on the standard food image to obtain food freshness information; identifying food label information from the standard food image, and performing multi-source data fusion on the food type information, the food defect information, the food freshness information and the food label information to obtain a food detection report.

The application provides a cold storage preservation method, a system and a cold storage. The method comprises the following steps: monitoring the VOCs concentration in a current storage cabin of the cold storage in real time; measuring the moisture migration rate of food surface in the current storage cabin in real time to obtain a corresponding measurement value; identifying the food category stored in the current storage cabin; determining the odor intensity change rate at the current time according to the VOCs concentration; obtaining the theoretical value of the moisture migration rate of food surface in the current storage cabin according to the odor intensity change rate and the food category; and formulating a corresponding preservation control strategy according to the ratio of the measurement value and the theoretical value of the moisture migration rate of food surface at the current time, and combining the odor intensity change rate. The system uses the method, and the refrigeration appliance comprises the system. The application can accurately distinguish the corruption dynamics, improve the food preservation period, reduce the false triggering rate, and solve the problem of food preservation dynamic control.

The invention discloses a food inspection information sharing method and system based on a block chain, and particularly relates to the technical field of food safety information management.The method comprises the steps that after food inspection data is generated, a priority index is calculated based on a risk level dimension, a time urgency dimension and a cross-domain sharing dimension; and a priority label is generated by adopting a dual-threshold mechanism of'static baseline + dynamic correction ', and a grading result is written into an on-chain index. And the transaction aggregator performs ordered aggregation and de-duplication on the records in the same sliding window according to the priority labels, and sorts the records in a descending order according to the priority indexes. The alliance chain network is divided into a plurality of logic channels according to food categories, different channels are provided with differentiated block output parameters and are sequenced and packaged in the channels according to priority indexes, and high-priority transactions enter a priority queue. A main channel maintains a global batch index and a cross-channel mapping table, and efficient, safe and traceable sharing of cross-mechanism and cross-region food inspection data is realized.

The invention discloses a food processing and quality control system based on artificial intelligence, and the system comprises a processing technology configuration center which is used for calling a corresponding standardized technological process template according to food category information, and generating a target technological process structural body; the loss prediction engine is used for outputting a loss rate prediction result set by adopting the improved quantile regression forest model; the quick detection system docking module is used for quickly detecting all batches of food to be delivered, generating a quick detection result, and comparing the quick detection result with a food safety standard library threshold value to obtain item-by-item qualification judgment; the ex-warehouse interception controller is used for performing joint verification on the loss rate prediction result set and the fast detection result, generating an ex-warehouse permission result or an ex-warehouse interception result, and generating an alarm log; and the quality log recorder is used for recording quality log data. According to the invention, an improved quantile regression forest model is adopted, and intelligent quality control of food processing is realized.

The invention belongs to the technical field of meal delivery system matching, and particularly relates to a food nutritional ingredient analysis method for a catering system. Comprising the following steps: establishing a food identification network model; food image samples are obtained to serve as training data to train a food recognition network model, and a fusion feature database of various kinds of food is generated; acquiring a real-time dinner plate image of the meal delivery system, inputting the dinner plate image into the food identification network model, and identifying the food category in the dinner plate; searching a food corresponding region in the feature map by using a sliding window based on a region suggestion network, and determining region coordinates; three-dimensional information is established based on image processing and pixel point matching, material object component analysis is completed, and nutritional ingredient data is obtained. The method is used for automatically analyzing and judging the component and the category of the food by acquiring the visual information of the food, a technical scheme is provided for automatic detection and output of nutritional ingredients of an automatic meal delivery system, and a technical basis is provided for subsequent work such as suggestion of the nutritional ingredients.

A method of operating a food categorization engine includes extracting features from each text description of a training food data set to generate a feature set. The feature set is analyzed to determine sets of food categorization features that correlate to one or more food categories, wherein the sets of food categorization features are defined by a plurality of category vectors. Individual words and / or characters of a text description of a food item received from a user are then analyzed in order to generate a numerical vector representative thereof. The numerical vector is multiplied by a matrix defined by the plurality of category vectors. One or more food categories with which to associate the received food item are automatically selected based at least in part on the multiplication, and the data record associated with the food item is amended to include the selected food categories.

The invention discloses a sample processing method for detecting neotame content in food, which is characterized by comprising the following steps: 1) preparing a sample to be tested; 2) extracting the sample: 2.1) adding the sample into a container, adding an extracting solution, and adjusting the pH value to 4-5; the addition amounts of the sample and the extracting solution satisfy the following ratio: 1 g: 5-10 mL; 2.2) heating the sample in a water bath at 50-70° C., adding n-hexane, centrifuging, and discarding the n-hexane layer; the addition amounts of the sample and n-hexane satisfy the following ratio: 1 g: 0.8-1.2 mL; 2.3) adding an 80-100 g / L potassium ferrocyanide aqueous solution and a 150-200 g / L zinc acetate aqueous solution, centrifuging, and transferring the supernatant; the addition amounts of the sample, potassium ferrocyanide aqueous solution, and zinc acetate aqueous solution satisfy the following ratio: 1 g: 0.1 mL-0.4 mL: 0.1 mL-0.4 mL. This sample pretreatment method is suitable for testing a variety of food matrices, covering the 14 major food categories specified in GB 2760-2014. It is highly versatile and improves detection accuracy and efficiency. The recovery rate of Niutian is 80% to 110%.