Intelligent dinner plate for infants and working method of intelligent dinner plate

Abstract

The invention relates to an infant intelligent dinner plate and a working method thereof, the infant intelligent dinner plate comprises a dinner plate body, a weight acquisition module arranged in the dinner plate body, a control module electrically connected with the weight acquisition module, a shooting module connected with the control module, and a cloud server in signal connection with the control module, and the cloud server is in signal connection with a mobile terminal. The weight acquisition module is used for acquiring the weight of food, the shooting module is used for acquiring an image of the food, and the cloud server is used for identifying food types and calculating nutrition intake. According to the intelligent dinner plate for the infants and the working method of the intelligent dinner plate, the nutritional requirements of the infants can be calculated according to the conditions of the infants, the types of food can be recognized, the appropriate meal amount can be recommended, and healthy growth of the infants is guaranteed.

Description

Technical Field

[0001] The present invention belongs to the technical field related to smart meals, and in particular relates to a smart meal plate for infants and a working method thereof. Background Art

[0002] Generally, young children including infants (hereinafter, "infants and young children" is used to express the concept including infants and young children) use toddler plates not only in group meal services such as daycare centers and kindergartens, but also in ordinary households.

[0003] In recent years, with the rapid development of the economy and society and the change of lifestyle, the dietary structure of Chinese residents has changed greatly. A balanced diet is the fundamental way to achieve reasonable nutrition and is the core concept of the dietary guidelines of countries around the world. However, because it is too general and abstract, it is difficult for ordinary people to directly apply it to their daily dietary behavior. At present, there is a lack of a scientific and simple tool to help people, especially to help infants and young children achieve the nutritional principles of a balanced diet in their daily dietary behavior. Traditional dinner plates have a simple structure and a single function. They do not consider nutritional balance and cannot guide infants and young children to scientific and nutritious diets. In addition, since each infant and young child has different personal conditions, their nutritional needs need to be calculated. Therefore, there is a need for a device that can calculate the nutritional needs of infants and young children according to their own conditions and automatically measure the appropriate amount of food. The present invention solves this technical problem. Summary of the invention

[0004] The present invention provides an intelligent meal plate for infants and young children and a working method thereof, which can calculate the nutritional needs of infants and young children based on their own conditions, identify the types of food, and recommend appropriate meal amounts to ensure the healthy growth of infants and young children.

[0005] A smart meal plate for infants and young children comprises a meal plate body, a weight collection module arranged inside the meal plate body, a control module electrically connected to the weight collection module, a shooting module connected to the control module, and a cloud server connected to the control module via signals, wherein the cloud server is connected to a mobile terminal via signals, the weight collection module is used to collect the weight of food, the shooting module is used to collect images of food, and the cloud server is used to identify the type of food and calculate the nutritional intake.

[0006] Furthermore, the weight collection module includes a sensor component for collecting food weight, and the sensor component is connected to the control module.

[0007] Furthermore, the dinner plate body is rotatably connected to the upper cover, the shooting module includes a camera connected to the upper cover, and the camera is electrically connected to the control module.

[0008] A working method of an infant smart dinner plate, based on the above-mentioned infant smart dinner plate, comprises the following steps:

[0009] S1. Calculate the required nutritional intake based on the height, weight and age of infants and young children;

[0010] S2. Calculate the required nutritional intake based on the activity level of infants and young children;

[0011] S3, identifying the type of food in the plate;

[0012] S4. Determine the nutritional content data of the food;

[0013] S5, collecting weight information of food in the plate;

[0014] S6. Calculate the nutrient content of the food at this weight.

[0015] S7. Recommend nutrition-related content through mobile terminals.

[0016] Furthermore, the step S1 specifically includes the following steps:

[0017] S11. Calculate the basal metabolic rate (BMR) of infants and young children;

[0018] S12. When the infant is a boy:

[0019] BMR = 88.362 + (13.397 × weight in kg) + (4.799 × height in cm) - (5.677 × age);

[0020] S13. When the infant is a girl:

[0021] BMR=447.593+(9.247×weight in kg)+(3.098×height in cm)-(4.330×age).

[0022] Furthermore, the step S2 specifically includes the following steps:

[0023] S21. According to the intensity of infants' activities, they are divided into: almost no exercise, light activity, moderate activity, high activity, and extreme activity;

[0024] S22. The obtained basal metabolic rate is further calculated according to the specific activity intensity:

[0025] Almost no exercise: BMR × 1.2;

[0026] Light activity: BMR × 1.375;

[0027] moderate activity: BMR × 1.55;

[0028] High activity: BMR × 1.725;

[0029] Extreme activity: BMR × 1.9.

[0030] Furthermore, the step S3 specifically includes the following steps:

[0031] S31. Construct a food recognition algorithm based on convolutional neural network;

[0032] S32, the camera photographs the food on the plate and uploads the obtained food image to the cloud server;

[0033] S33, identifying the type of food photographed by using a food recognition algorithm;

[0034] S34. Establish a food nutrient database, and find the nutrient content of the food per unit mass in the database.

[0035] Furthermore, the step S31 specifically includes the following steps:

[0036] S311, collecting images of several foods as a food dataset;

[0037] S312, dividing the food data set into a training set and a test set according to a certain ratio;

[0038] S313, using the sample images of the training set to train the convolutional neural network model, training a CNN feature extraction model, and obtaining food features of the corresponding training samples;

[0039] S314, training the Softmax classifier according to the learned features, when the number of training times reaches the set requirement, the iteration is terminated to obtain the Sofmax classifier model, otherwise, continue to input sample images to train the Softmax classifier;

[0040] S315. Input the test sample into the convolutional neural network, extract the food features of the corresponding test sample, and then input the obtained features into the trained Softmax classifier to identify the category of the food in the image and obtain the recognition status of each food.

[0041] Furthermore, the step S6 specifically includes the following steps:

[0042] S61, comparing the weight of the food on the plate with the unit mass of the food to obtain a corresponding ratio;

[0043] S62: Calculate the nutrient content of the food on the current plate based on the nutrient content per unit mass of the food and the corresponding ratio.

[0044] The technical effects of the present invention are as follows

[0045] (1) The smart plate in this solution can not only be used to hold food, but also calculate the nutritional needs of infants and young children based on their age and amount of exercise. It can also identify the type of food and collect the weight of the food in the plate, thereby calculating the corresponding nutrient content, so that people can understand whether the nutrition provided by the food in the plate meets the nutritional needs of infants and young children, which is conducive to the healthy growth of infants and young children;

[0046] (2) This solution uses a camera to capture images of food, and uses a food recognition algorithm to identify the type of food captured, and then finds the nutrient content of the corresponding food per unit mass. The sensor can also be used to collect the weight of the food on the plate, and then the unit mass is compared with the actual mass, and the nutrient content of the food on the plate is calculated based on the ratio. The operation is simple and it is easy for people to understand the nutrient content of the food on the plate, so that they can judge whether the nutrient content of the food on the plate is sufficient based on the nutrient needs of infants and young children. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 The work flow diagram of the present invention is

[0048] Figure 2 The flowchart of the food recognition algorithm constructed in the present invention.

[0049] Figure 3 It is a structural block diagram of the present invention. DETAILED DESCRIPTION

[0050] The technical solution of the present invention will be clearly and completely described below in conjunction with specific implementations and drawings.

[0051] See also Figure 3 A smart meal tray for infants and young children includes a meal tray body, a weight collection module disposed inside the meal tray body, a control module electrically connected to the weight collection module, a shooting module connected to the control module, and a cloud server connected to the control module via a signal, wherein the cloud server is connected to a mobile terminal via a signal, the weight collection module is used to collect the weight of food, the shooting module is used to collect images of food, and the cloud server is used to identify the type of food and calculate the nutritional intake. The mobile terminal in this embodiment is a smart phone.

[0052] Furthermore, the weight collection module includes a sensor component for collecting the weight of food, and the sensor component is connected to the control module. The sensor component in this embodiment can be a weight sensor or a pressure sensor.

[0053] Furthermore, one side of the dinner plate body is rotatably connected to one side of the upper cover, the shooting module includes a camera connected to the upper cover, and the camera is electrically connected to the control module. The upper cover in this solution is used to cover the dinner plate to prevent dust from falling, and the camera on the upper cover can shoot the food in the dinner plate.

[0054] See also Figure 1 , Figure 2 A working method of an infant smart dinner plate, based on the above-mentioned infant smart dinner plate, comprises the following steps:

[0055] S1. Calculate the required nutritional intake based on the height, weight and age of infants and young children;

[0056] S2. Calculate the required nutritional intake based on the activity level of infants and young children;

[0057] S3, identifying the type of food in the plate;

[0058] S4. Determine the nutritional content data of the food;

[0059] S5, collecting weight information of food in the plate;

[0060] S6. Calculate the nutrient content of the food at this weight.

[0061] S7. Recommend nutrition-related content through mobile terminals.

[0062] Furthermore, step S1 specifically includes the following steps:

[0063] S11. Calculate the basal metabolic rate (BMR) of infants and young children;

[0064] S12. When the infant is a boy:

[0065] BMR = 88.362 + (13.397 × weight in kg) + (4.799 × height in cm) - (5.677 × age);

[0066] S13. When the infant is a girl:

[0067] BMR=447.593+(9.247×weight in kg)+(3.098×height in cm)-(4.330×age).

[0068] Further, step S2 specifically includes the following steps:

[0069] S21. According to the intensity of infants' activities, they are divided into: almost no exercise, light activity, moderate activity, high activity, and extreme activity;

[0070] S22. The obtained basal metabolic rate is further calculated according to the specific activity intensity:

[0071] Almost inactive (sedentary, almost no exercise): BMR × 1.2;

[0072] Light activity (normal exercise 1-3 days per week): BMR × 1.375;

[0073] Moderate activity (normal exercise 3-5 days per week): BMR × 1.55;

[0074] Highly active (normal exercise 6-7 days per week): BMR × 1.725;

[0075] Extreme activity (very strenuous physical work): BMR × 1.9.

[0076] Among them, the above levels can be divided specifically according to the activity time and activity intensity of infants and young children.

[0077] Further, step S3 specifically includes the following steps:

[0078] S31. Construct a food recognition algorithm based on convolutional neural network;

[0079] S32, the camera photographs the food on the plate and uploads the obtained food image to the cloud server;

[0080] S33, identifying the type of food photographed by using a food recognition algorithm;

[0081] S34. Establish a food nutrient database, and find the nutrient content of the food per unit mass in the database.

[0082] Further, step S31 specifically includes the following steps:

[0083] S311, collecting images of several foods as a food dataset;

[0084] S312, dividing the food data set into a training set and a test set according to a certain ratio;

[0085] S313, using the sample images of the training set to train the convolutional neural network model, training a CNN feature extraction model, and obtaining food features of the corresponding training samples;

[0086] S314, training the Softmax classifier according to the learned features, when the number of training times reaches the set requirement, the iteration is terminated to obtain the Sofmax classifier model, otherwise, continue to input sample images to train the Softmax classifier;

[0087] S315. Input the test sample into the convolutional neural network, extract the food features of the corresponding test sample, and then input the obtained features into the trained Softmax classifier to identify the category of the food in the image and obtain the recognition status of each food.

[0088] Further, step S6 specifically includes the following steps:

[0089] S61, comparing the weight of the food on the plate with the unit mass of the food to obtain a corresponding ratio;

[0090] S62: Calculate the nutrient content of the food on the current plate based on the nutrient content per unit mass of the food and the corresponding ratio.

[0091] The working process of the present invention is as follows:

[0092] First, input the age, gender, activity time and other data of the infant or child through a smartphone. The cloud server will automatically calculate the corresponding nutritional intake based on the input data. Then, put the food on the plate, and the camera will take a picture of the food on the plate. The collected image will be uploaded to the cloud server, and the cloud server will use the food recognition algorithm to identify the type of food on the plate. After identifying the corresponding type, the content of the nutritional elements of the corresponding food per unit mass can be found in the database. The sensor component will upload the weight information of the food to the cloud server through the control module. The cloud server can calculate the ratio of the current food weight to the unit weight, and calculate the amount of nutrients contained in the food per unit mass through the above ratio. The guardian of the infant or child can compare the nutritional intake required by the child with the nutrient content contained in the current food, so as to determine whether the current food can meet the nutritional needs of the child.

[0093] The above embodiments are only preferred embodiments of the present invention. Those skilled in the art can derive other embodiments from the above embodiments without creative work. Therefore, this application is intended to protect not only the above embodiments, but also the scope consistent with the principles and features of this application.

Claims

1. A smart meal tray for infants, characterized in that: The invention comprises a dinner plate body, a weight collection module arranged inside the dinner plate body, a control module electrically connected to the weight collection module, a shooting module connected to the control module, and a cloud server connected to the control module via signals, wherein the cloud server is connected to a mobile terminal via signals, the weight collection module is used to collect the weight of food, the shooting module is used to collect images of food, and the cloud server is used to identify the type of food and calculate the nutritional intake.

2. The smart infant dinner plate according to claim 1, characterized in that: The weight collection module includes a sensor component for collecting the weight of food, and the sensor component is connected to the control module.

3. The smart infant dinner plate according to claim 2, characterized in that: The dinner plate body is rotatably connected to the upper cover, the shooting module includes a camera connected to the upper cover, and the camera is electrically connected to the control module.

4. A working method of an infant smart dinner plate, based on the infant smart dinner plate according to claim 3, characterized in that: The following steps are involved: S1. Calculate the required nutritional intake based on the height, weight and age of infants and young children; S2. Calculate the required nutritional intake based on the activity level of infants and young children; S3, identifying the type of food in the plate; S4. Determine the nutritional data of the food; S5, collecting weight information of food in the plate; S6. Calculate the nutrient content of the food at this weight; S7. Recommend nutrition-related content through mobile terminals.

5. The working method of the smart infant dinner plate according to claim 4, characterized in that: The step S1 specifically includes the following steps: S11. Calculate the basal metabolic rate (BMR) of infants and young children; S12. When the infant is a boy: BMR = 88.362 + (13.397 × weight in kg) + (4.799 × height in cm) - (5.677 × age); S13. When the infant is a girl: BMR=447.593+(9.247×weight in kg)+(3.098×height in cm)-(4.330×age).

6. The working method of the smart infant dinner plate according to claim 4, characterized in that: The step S2 specifically includes the following steps: S21. According to the intensity of infants' activities, they are divided into: almost no exercise, light activity, moderate activity, high activity, and extreme activity; S22. The obtained basal metabolic rate is further calculated according to the specific activity intensity: Almost no exercise: BMR × 1.2; Light activity: BMR × 1.375; moderate activity: BMR × 1.55; High activity: BMR × 1.725; Extreme activity: BMR × 1.

9.

7. The working method of the smart infant dinner plate according to claim 4, characterized in that: The step S3 specifically includes the following steps: S31. Construct a food recognition algorithm based on convolutional neural network; S32, the camera photographs the food on the plate and uploads the obtained food image to the cloud server; S33, identifying the type of food photographed by using a food recognition algorithm; S34. Establish a food nutrient database, and find the nutrient content of the food per unit mass in the database.

8. The working method of the smart infant dinner plate according to claim 7, characterized in that: The step S31 specifically includes the following steps: S311, collecting images of several foods as a food dataset; S312, dividing the food data set into a training set and a test set according to a certain ratio; S313, using the sample images of the training set to train the convolutional neural network model, training a CNN feature extraction model, and obtaining food features of the corresponding training samples; S314, training the Softmax classifier according to the learned features, when the number of training times reaches the set requirement, the iteration is terminated to obtain the Sofmax classifier model, otherwise, continue to input sample images to train the Softmax classifier; S315. Input the test sample into the convolutional neural network, extract the food features of the corresponding test sample, and then input the obtained features into the trained Softmax classifier to identify the category of the food in the image and obtain the recognition status of each food.

9. The working method of the smart infant dinner plate according to claim 4, characterized in that: The step S6 specifically includes the following steps: S61, comparing the weight of the food on the plate with the unit mass of the food to obtain a corresponding ratio; S62: Calculate the nutrient content of the food on the current plate based on the nutrient content per unit mass of the food and the corresponding ratio.

Images