Diet suggestion recommendation method, control device and storage medium

Abstract

The invention relates to a diet suggestion recommendation method, a control device and a storage medium. The method comprises the following steps: acquiring food material information in a refrigerator; food residue information collected based on a biosensor in the dish washing machine is obtained; and generating diet suggestions based on the food material information and the food residue information. According to the method, the food material information in the refrigerator and the food residue information collected based on the biosensor in the dish washing machine are obtained, the diet behavior and nutrition intake of the user are analyzed in real time, and therefore personalized diet adjustment suggestions can be given immediately when the diet behavior of the user occurs. Therefore, not only can the user be helped to understand own diet habits and improve own understanding of healthy diet, but also own diet structure can be managed and improved more effectively, and life quality is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of dietary nutrition management, and specifically provides a method for recommending dietary advice, a control device and a storage medium. Background Art

[0002] With the increase in the types of diets and the improvement of dietary standards, individual users have more and more demands on food and beverages. For example, users pay attention to whether the food and beverages are healthy and nutritionally balanced. At present, there are already some methods and technologies for healthy diet.

[0003] There are two main methods and technologies for healthy diet: the first one is to make an overall evaluation of the user's diet in the past period of time and give the user some suggestions on reasonable diet and exercise based on the evaluation results. However, the above methods and technologies summarize the user's diet in the past period of time and make suggestions on the diet in the next period of time. The user can only see whether the diet in the past period of time is healthy and how to adjust the diet in the next period of time. It is impossible to adjust their diet in time, resulting in a poor user experience.

[0004] Accordingly, the art needs a new dietary advice recommendation method to solve the above problems. Summary of the invention

[0005] In order to overcome the above-mentioned defects, the present invention is proposed to provide a solution or at least partially solve the problem that the diet recommendation method in the prior art cannot provide real-time diet adjustment suggestions, thereby affecting the user experience.

[0006] In a first aspect, the present invention provides a method for recommending dietary advice, the method obtaining food information in a refrigerator; obtaining food residue information collected by a biosensor in a dishwasher; and generating dietary advice based on the food information and the food residue information.

[0007] As an alternative or supplement to the above solution, in a method according to an embodiment of the present invention, the food residue information includes nutritional components in the food residue and the content of the nutritional components.

[0008] As an alternative or supplement to the above scheme, in a method according to an embodiment of the present invention, obtaining food information in the refrigerator includes: obtaining image information collected by an image acquisition device in the refrigerator; and obtaining food information in the refrigerator based on the image information, wherein the food information includes food types and food quantities.

[0009] As an alternative or supplement to the above scheme, in a method according to an embodiment of the present invention, the generating of dietary recommendations based on the ingredient information and the food residue information includes: judging the types of ingredients consumed by the user within a time period and the corresponding quantities of ingredients based on the ingredient information; and generating dietary recommendations based on the types of ingredients consumed by the user within the time period, the corresponding quantities of ingredients and the food residue information.

[0010] As an alternative or supplement to the above solution, in a method according to an embodiment of the present invention, the dietary advice includes a dietary recommendation recipe.

[0011] As an alternative or supplement to the above scheme, in a method according to an embodiment of the present invention, the dishwasher uses water to flush food residues on the surface of the tableware to form a liquid sample to be tested, and the biosensor identifies the liquid sample to be tested, the nutritional components and the content of the nutritional components.

[0012] As an alternative or supplement to the above scheme, in a method according to an embodiment of the present invention, obtaining the food information in the refrigerator based on the image information includes: preprocessing the image information; identifying the type of food based on the image information; and identifying the quantity of corresponding food based on the image information.

[0013] As an alternative or supplement to the above solution, in a method according to an embodiment of the present invention, the method of identifying the type of food based on image information includes: extracting features using a neural network model, and classifying the food based on the extracted features.

[0014] In a second aspect, a control device is provided, which includes a processor and a storage device, wherein the storage device is suitable for storing multiple computer programs, and the computer programs are suitable for being loaded and run by the processor to execute the dietary advice recommendation method described in any one of the technical solutions of the dietary advice recommendation method mentioned above.

[0015] In a third aspect, a computer-readable storage medium is provided, wherein a plurality of computer programs are stored therein, wherein the computer programs are suitable for being loaded and run by a processor to execute the dietary advice recommendation method described in any one of the technical solutions of the dietary advice recommendation method described above.

[0016] The above one or more technical solutions of the present invention have at least one or more of the following Beneficial effects:

[0017] In the technical solution of the present invention, by acquiring the food information in the refrigerator and the food residue information collected by the biosensor in the dishwasher, the user's eating behavior and nutritional intake are analyzed in real time, so that personalized dietary adjustment suggestions can be given immediately when the user's eating behavior occurs. In this way, it can not only help users understand their eating habits and improve their understanding of healthy eating, but also more effectively manage and improve their dietary structure and improve their quality of life. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The disclosure of the present invention will become more easily understood with reference to the accompanying drawings. It will be readily understood by those skilled in the art that these drawings are only for illustrative purposes and are not intended to limit the scope of protection of the present invention. In addition, similar numbers in the drawings represent similar components, wherein:

[0019] Figure 1 is a flowchart of main steps of a method for recommending dietary advice according to an embodiment of the present invention;

[0020] Figure 2 is a flowchart of the secondary steps of a method for recommending dietary advice according to an embodiment of the present invention;

[0021] Figure 3 is a flowchart of the secondary steps of a method for recommending dietary advice according to an embodiment of the present invention;

[0022] Figure 4 1 is a flowchart of the main steps of a method for recommending dietary advice according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] Some embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0024] In the description of the present invention, "module" and "processor" may include hardware, software or a combination of the two. A module may include hardware circuits, various suitable sensors, communication ports, and memories, and may also include software parts, such as computer programs, or a combination of software and hardware. The processor may be a central processing unit, a microprocessor, an image processor, a digital signal processor, or any other suitable processor. The processor has data and / or signal processing functions. The processor may be implemented in software, hardware, or a combination of the two. Non-temporary computer-readable storage media include any suitable medium that can store computer programs, such as magnetic disks, hard disks, optical disks, flash memory, read-only memory, random access memory, etc. The term "A and / or B" means all possible combinations of A and B, such as only A, only B, or A and B. The term "at least one A or B" or "at least one of A and B" has a similar meaning to "A and / or B", and may include only A, only B, or A and B. The singular terms "one" and "the" may also include plural forms.

[0025] See attached Figure 1 , Figure 1 FIG. 1 is a flow chart showing the main steps of a method for recommending dietary advice according to an embodiment of the present invention. Figure 1 As shown, the method for recommending dietary advice in the embodiment of the present invention mainly includes the following steps S10 to S30.

[0026] Step S10: Obtain food information in the refrigerator.

[0027] In this embodiment, the food information refers to the types and quantities of various food stored in the refrigerator. This information is collected by an image acquisition device (such as a camera) installed in the refrigerator. After collection, this information will be sent to the cloud platform through a network connection.

[0028] In one embodiment, the data uploading process can be real-time or periodic. Real-time uploading means that whenever the image acquisition device captures a new image, the image is immediately uploaded to the cloud platform. Periodic uploading means that the images collected within a period of time are uploaded together after a set time interval (such as every hour, every day, etc.).

[0029] The data uploaded to the cloud platform includes not only image information, but may also include other relevant information, such as collection time, refrigerator temperature, etc. This information can provide more contextual information and help the cloud platform understand the storage and use of ingredients more accurately.

[0030] In this embodiment, the food information in the refrigerator is obtained through steps S101 to S102. Figure 2 shown.

[0031] Step S101: Acquire image information collected by an image acquisition device in the refrigerator.

[0032] In one embodiment, the image acquisition device uses a high-resolution camera to obtain sufficiently clear images of the food. The image acquisition device is equipped with appropriate lighting equipment or uses a long exposure method to ensure that the image of the food can be clearly captured even when the refrigerator door is closed and the internal light is dim.

[0033] In this embodiment, the image acquisition device is set to start working under certain circumstances, such as when the refrigerator door is opened, or when a set timer is reached. After the image acquisition device captures the image, the image information will be collected by the refrigerator controller or built-in computer, and then uploaded to the cloud platform through a network connection (such as Wi-Fi).

[0034] Step S102: Obtaining food information in the refrigerator based on the image information.

[0035] In this embodiment, the relevant information of the food ingredients is extracted from the collected image of the interior of the refrigerator through image processing and analysis technology.

[0036] In one embodiment, the food information in the refrigerator is obtained through steps S102-1 to S102-3, such as Figure 3 As shown, the details are as follows:

[0037] Step S102-1: pre-process the image information.

[0038] In this embodiment, in order to facilitate the subsequent recognition of image information, the image is first pre-processed.

[0039] In one embodiment, first, a cropping step is selectively performed according to the needs, wherein the image is cropped to distinguish the food inside the refrigerator and remove irrelevant background and edge parts. This step can be completed by setting a fixed cropping area or dynamically determining the cropping area through image segmentation technology.

[0040] The image is then enhanced to improve the visual effect and contrast and clarity of the image. Image enhancement methods include histogram equalization, contrast stretching, gamma transformation, etc. This step can help deal with the problem of the dark part of the image being too dark or the bright part being too bright due to the different lighting conditions inside the refrigerator.

[0041] Finally, the image is filtered to remove noise and interference in the image. Image filtering methods include mean filtering, median filtering, Gaussian filtering, etc. This step can help deal with the hardware noise of the camera, or interference such as dust and water stains inside the refrigerator.

[0042] The preprocessed images will be more conducive to subsequent image recognition and analysis.

[0043] Step S102-2: Identify the type of food based on the image information.

[0044] In this embodiment, various food ingredients are identified from the image using computer vision technology.

[0045] In one embodiment, the image information is first input into a trained neural network model for feature extraction. The function of feature extraction is to convert the image into a feature vector that can express the image content. Common feature extraction methods include SIFT (scale invariant feature transform), SURF (speeded up robust features), HOG (histogram vector), and deep learning models such as convolutional neural networks (CNN). These features can represent the color, texture, shape and other information of the image to a certain extent, providing a basis for subsequent food identification.

[0046] Based on the extracted feature vectors, the ingredients are classified. This step is usually performed using machine learning or deep learning models, such as support vector machines (SVM), random forests, logistic regression, or deep learning models such as convolutional neural networks (CNN). These models need to be trained to learn the ability to recognize different ingredients.

[0047] The recognition result is then output, which usually includes the type and probability of the food. The probability indicates the confidence of the model in the recognition result, and the higher the value, the higher the confidence.

[0048] In this embodiment, preferably, a deep learning model, i.e., a convolutional neural network (CNN), is used as a feature extraction method, and a CNN-based classification method is used to identify ingredients.

[0049] First, feature extraction is performed. In food identification, convolutional neural networks (CNN) are a very effective method. The CNN model contains multiple convolutional layers and pooling layers. Each convolutional layer can extract a feature of the image, while the pooling layer can reduce the dimension and complexity of the feature. For example, the first few convolutional layers may extract low-level features such as edges, colors, and textures of the image, while the subsequent convolutional layers may extract higher-level features such as shapes and partial structures. These features will be used to distinguish different ingredients.

[0050] The hypothetical refrigerator camera captures an image containing apples and bananas, and the CNN model will extract various features from this image, such as color, shape, texture, etc. These features will be used in subsequent classification tasks.

[0051] Then, we will classify the ingredients. Based on the feature extraction, we will use a pre-trained CNN model for classification. This model is trained on a large number of labeled food images and learns how to distinguish different ingredients based on their features.

[0052] During the training process, the CNN model will model each ingredient and learn the characteristic distribution of the ingredient. In the prediction phase, the model will calculate the probability of each ingredient based on the input characteristics and take the ingredient with the highest probability as the prediction result.

[0053] In the example, the pre-trained CNN model will determine that the most likely ingredients in this image are apples and bananas based on the extracted features. Then, the prediction result is uploaded to the cloud.

[0054] Step S102 - 3 : Identify the quantity of corresponding ingredients based on the image information.

[0055] In this embodiment, the quantity of the ingredients indicates the amount of the ingredients. In this embodiment, the quality of the ingredients is used to indicate the quantity of the ingredients.

[0056] In one embodiment, a deep learning-based target detection and segmentation algorithm (such as MaskR-CNN) is used to detect and segment the food in the refrigerator image. After segmentation, image regions are generated one by one, and each region corresponds to a food object. After that, the shape and size of each segmented food object are analyzed. For example, the size of the food can be estimated by counting the number of pixels in the food area in the image. Combined with the known shape of the food (such as assuming that some food is a standard shape, such as spherical, cylindrical, etc.), the volume of the food can be calculated.

[0057] Then, by combining the volume of the food and its density (the average density of each food stored in the database in advance), the mass of the food can be estimated.

[0058] In this embodiment, taking an apple in a refrigerator as an example, object recognition is first performed, and the object in the image is determined to be an apple through a deep learning model.

[0059] Next, we use deep learning object detection and segmentation algorithms, such as Mask R-CNN, to detect and segment the apples in the image. The result of the detection will be an image region containing the apple.

[0060] After that, the shape and size of the segmented apples are analyzed. By counting the number of pixels in the apple image area, the two-dimensional size of the apple in the image can be estimated. Since most apples can be assumed to be approximately spherical, the three-dimensional size of the apple can be calculated by combining the two-dimensional size of the image with the shooting distance and angle of the camera (known or calculated through the camera parameters and the physical arrangement of the camera and the refrigerator), and then the volume of the apple can be estimated.

[0061] Finally, the mass of the apple can be calculated by combining the volume and density of the apple. The density of the apple is pre-stored in the database. For example, the average density of the apple can be assumed to be 0.9 g / cm 3 . Assume that, if the calculated volume of the apple is 100cm 3 , then its mass can be estimated to be 90g.

[0062] In addition, if there are multiple apples in the camera's field of view, they need to be detected and estimated separately, and then the mass of each apple needs to be added together to get the total mass of the apples.

[0063] The above is the process of estimating the quality of food in the refrigerator through image acquisition device and deep learning technology.

[0064] Finally, the results of recognition and counting are integrated to generate ingredient information. The ingredient information includes the type and quantity of each ingredient. This information will be helpful for the subsequent generation of dietary advice and health management functions.

[0065] Step S20: Acquire food residue information collected by the biosensor in the dishwasher.

[0066] In this embodiment, the food residue information includes the nutrients in the food residue and the content of the nutrients. The biosensor is a special sensor designed to detect and analyze various components in the food residue.

[0067] In one embodiment, when collecting food residue information, the food residue is first washed down with water through a dishwasher. The purpose of this process is to wash the food residue from the tableware and convert it into a form that can be analyzed by the sensor, that is, to form a liquid sample to be tested. These food residues contain various chemical substances produced during the cooking process. After analysis, the nutritional component information in the food residues is obtained, that is, the nutritional components and the content of the nutritional components are obtained. These components may include proteins, amino acids, sugars, organic acids, phenols, vitamins, mineral elements, cholesterol, etc.

[0068] This flushing fluid sample is then passed to the biosensor for analysis.

[0069] In a biosensor, the liquid sample will be processed through various chemical analysis methods. These analysis methods include gas chromatography, liquid chromatography or mass spectrometry. These analysis methods are used to determine the type and content of specific chemicals in the sample. For example, gas chromatography can analyze volatile organic compounds in the sample; liquid chromatography can analyze non-volatile compounds in the sample; mass spectrometry can accurately determine the type and content of various elements and compounds in the sample.

[0070] After these analysis processes are completed, the biosensor converts the analysis results into electronic data and sends these data to the dishwasher's control system or the cloud. In this way, the process of obtaining food residue information collected by the biosensor in the dishwasher is completed.

[0071] In this step, the dishwasher uses a biosensor to collect food residue information. Combining the biosensor with the dishwasher, a common and frequently used household appliance in daily life, makes subsequent judgments more convenient and accurate.

[0072] Step S30: Generate dietary recommendations based on the food material information and the food residue information.

[0073] In this embodiment, dietary advice refers to opinions or suggestions on improving the user's diet, generated based on the user's food consumption and nutritional information in food residues.

[0074] In one embodiment, dietary recommendations include: intake recommendations and dietary menu recommendations. The intake recommendations are mainly recommendations for adjusting the intake of ingredients. For example, if the analysis finds that the user's protein intake is too low, the user will be advised to increase the intake of meat or soy products; if the user's sugar intake is found to be too high, the user will be advised to reduce the intake of sweets. These recommendations are based on the user's actual eating habits and nutritional intake, and are intended to help users balance their diets and improve the scientificity and health of nutritional intake.

[0075] Dietary recommendation recipes provide some recipes with reasonable combinations of ingredients to help users improve their eating habits and nutritional intake. For example, if there are chicken breasts and vegetables in the refrigerator, a recipe for "stir-fried chicken breasts with vegetables" can be provided. These recipe suggestions can not only help users make use of remaining ingredients, but also guide users to combine diets in a more scientific and healthy way.

[0076] In this embodiment, dietary recommendations are generated through steps S301-S302, such as Figure 4 As shown, the details are as follows:

[0077] Step S301: Determine the types of ingredients consumed by the user within a time period and the corresponding quantity of ingredients based on the ingredient information

[0078] In this embodiment, the acquired food information is sorted by time to form a time series food consumption record. Then, by comparing the food information at each time point, the food consumed by the user at each time point can be inferred.

[0079] For example, if at a certain time point, the food information in the refrigerator shows that there are 3 apples, and at the next time point, the food information in the refrigerator shows that there are only 2 apples, then it can be inferred that the user consumed one apple during this time period. Similarly, the types and quantities of other food consumed by the user during this time period can also be determined.

[0080] This step can accurately determine the types and quantities of food consumed by the user within a period of time, providing an important data basis for the subsequent generation of dietary recommendations.

[0081] Step S302: Generate dietary recommendations based on the types of food consumed by the user within a time period, the corresponding amounts of food, and food residue information.

[0082] In one embodiment, the cloud platform analyzes the nutrients in the food residue to understand the intake of nutrients in the user's diet. For example, if the cholesterol content in the food residue is too high, it may indicate that the user consumes too much high-cholesterol food. At the same time, combined with the food information, it can be understood which ingredients these nutrients come from. For example, if it is found that the food information shows that meat consumption is high, it may be that meat products cause excessive cholesterol intake. After understanding this information, the cloud platform can evaluate the user's diet to see whether it is nutritionally balanced and whether there is an excessive or insufficient intake of certain nutrients.

[0083] Based on the user's dietary status assessment results, the cloud platform will generate two parts of personalized dietary recommendations: intake recommendations and dietary recommendation recipes. In the intake recommendation section, the cloud platform will refer to the user's dietary status. For example, if the assessment results show that the user's cholesterol intake is too high, the cloud platform may recommend that the user reduce the intake of high-cholesterol foods, such as certain meats, while increasing the intake of vegetables and fruits to balance nutrient intake and reduce cholesterol intake. In the dietary recommendation recipe section, the cloud platform will recommend suitable healthy recipes to users based on the remaining ingredients in the refrigerator. These recipes will not only help users utilize existing ingredients, but more importantly, they will help users consume food in a healthier and more nutritious way.

[0084] In this embodiment, preferably, the dietary recommendations also include an intake ingredient detail, which is calculated based on the ingredients that the user takes out through the refrigerator and produces residues in the dishwasher within a certain period of time. It should be noted that since some ingredients may not pass through the refrigerator and dishwasher, such as ingredients taken directly from the storage room, etc., the intake ingredient details can only reflect the nutritional components of some ingredients ingested by the user through the refrigerator and dishwasher. Despite this, the intake ingredient details can still provide users with a reference to help them understand and grasp their own dietary status and better judge whether the dietary recommendations generated by the cloud platform are appropriate.

[0085] The detailed list of intake ingredients is designed to increase users' transparency into their own dietary nutritional status, allowing them to be more clear about their dietary goals and adjust their eating habits more specifically.

[0086] It should be pointed out that although the various steps in the above embodiments are described in a specific order, those skilled in the art can understand that in order to achieve the effects of the present invention, different steps do not have to be performed in such an order. They can be performed simultaneously (in parallel) or in other orders. These changes are within the scope of protection of the present invention.

[0087] It is understood by those skilled in the art that the present invention implements all or part of the processes in the method of the above embodiment, and can also be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of each of the above method embodiments when executed by the processor. Among them, the computer program includes a computer program, and the computer program can be in source code form, object code form, executable file or some intermediate form. The computer-readable storage medium may include: any entity or device, medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory, random access memory, electric carrier signal, telecommunication signal and software distribution medium that can carry the computer program. It should be noted that the content contained in the computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable storage media do not include electric carrier signals and telecommunication signals.

[0088] Furthermore, the present invention also provides a control device. In an embodiment of a control device according to the present invention, the control device includes a processor and a storage device, the storage device can be configured to store a program for executing a method for recommending dietary recommendations in the above method embodiment, and the processor can be configured to execute the program in the storage device, which includes but is not limited to a program for executing a method for recommending dietary recommendations in the above method embodiment. For ease of explanation, only the parts related to the embodiment of the present invention are shown. For specific technical details not disclosed, please refer to the method part of the embodiment of the present invention. The control device can be a control device device formed by various electronic devices.

[0089] Furthermore, the present invention also provides a computer-readable storage medium. In a computer-readable storage medium embodiment according to the present invention, the computer-readable storage medium can be configured to store a program for executing the dietary recommendation method of the above-mentioned method embodiment, and the program can be loaded and run by the processor to implement the above-mentioned dietary recommendation method. For ease of explanation, only the parts related to the embodiment of the present invention are shown. For specific technical details not disclosed, please refer to the method part of the embodiment of the present invention. The computer-readable storage medium can be a storage device formed by various electronic devices. Optionally, the computer-readable storage medium in the embodiment of the present invention is a non-temporary computer-readable storage medium.

[0090] Further, it should be understood that since the setting of each module is only for illustrating the functional units of the device of the present invention, the physical devices corresponding to these modules may be the processor itself, or a part of the software in the processor, a part of the hardware, or a part of the combination of software and hardware. Therefore, the number of each module in the figure is only schematic.

[0091] Those skilled in the art will appreciate that the modules in the device can be adaptively split or merged. Such splitting or merging of specific modules will not cause the technical solution to deviate from the principle of the present invention, and therefore, the technical solutions after splitting or merging will fall within the protection scope of the present invention.

[0092] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A method for recommending dietary advice, characterized in that: include: Get information about food in the refrigerator; Obtain food residue information collected by biosensors in dishwashers; Dietary recommendations are generated based on the food material information and the food residue information.

2. The method for recommending dietary advice according to claim 1, characterized in that: The food residue information includes the nutritional components in the food residue and the content of the nutritional components.

3. The method for recommending dietary advice according to claim 1, characterized in that: The obtaining of food information in the refrigerator includes: Acquire image information collected by an image acquisition device in the refrigerator; The food information in the refrigerator is obtained based on the image information, wherein the food information includes the type and quantity of the food.

4. The method for recommending dietary advice according to any one of claims 1 to 3, characterized in that: The generating of dietary advice based on the food material information and the food residue information comprises: Determining the types of ingredients consumed by the user within a time period and the corresponding quantities of ingredients based on the ingredient information; Dietary recommendations are generated based on the types of ingredients consumed by the user within the time period, the corresponding quantities of ingredients, and the food residue information.

5. The method for recommending dietary advice according to claim 1, characterized in that: The dietary advice includes dietary recommendation menus.

6. The method for recommending dietary advice according to claim 1, characterized in that: The dishwasher uses water to flush food residues on the surface of the tableware to form a liquid sample to be detected, and the biosensor identifies the liquid sample to be detected, the nutrient components and the content of the nutrient components.

7. The method for recommending dietary advice according to claim 3, characterized in that: The obtaining food information in the refrigerator based on the image information includes: Preprocess the image information; Identify food types based on image information; The quantity of the corresponding food is recognized based on the image information.

8. The method for recommending dietary advice according to claim 7, characterized in that: The method of identifying the type of food based on image information includes: The image information is input into a trained neural network model for feature extraction to obtain a feature vector. The food ingredients are classified based on the extracted feature vectors.

9. A control device, comprising a processor and a storage device, wherein the storage device is suitable for storing a plurality of computer programs, characterized in that: The computer program is suitable for being loaded and run by the processor to execute the dietary advice recommendation method according to any one of claims 1 to 8.

10. A computer-readable storage medium storing a plurality of computer programs, characterized in that: The computer program is suitable for being loaded and run by a processor to execute the dietary advice recommendation method according to any one of claims 1 to 8.

Images