Intelligent accounting method and device for water content of user's diet and computer equipment

Abstract

The application relates to a user's dietary water content intelligent accounting method and device and computer equipment. The method comprises the following steps: acquiring a multi-spectrum scan diagram of food, addition amount information and cooking treatment information, and identifying current material evaluation information of each material of the food based on the multi-spectrum scan diagram of the food; calculating the current material water content of each material through a water content accounting model based on the addition amount information of the food and the current material evaluation information of each material; identifying current interference data of each water content interference factor of the food based on the cooking treatment information of the food; calculating the current water content influence degree value of each material through a compensation factor calculation model based on the current interference data of each water content interference factor; and calculating the current target water content of each material based on the current water content influence degree value of each material and the current material water content of each material. The method can improve the calculation accuracy of the water content of solid food of cooked food.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence network technology, and in particular to a method, apparatus and computer equipment for intelligently calculating the water content of a user's diet. Background Technology

[0002] Recording patient intake and output in the intensive care unit is a crucial aspect of clinical nursing and medical management. Traditional methods of calculating intake rely on nurses manually weighing food, consulting food moisture content tables, and performing conversions, which is time-consuming and prone to errors; inaccurate calculations can affect doctors' treatment decisions; and existing smart devices cannot cover the calculation of moisture content in solid foods. Therefore, improving the accuracy of calculating the moisture content of solid foods is a current research focus.

[0003] Traditional techniques often involve staff setting up a moisture content comparison table, and then calculating the moisture content of each food item based on this table and the amount of food added to each item. However, due to different cooking methods and varying environments, a fixed moisture content comparison table often fails to accurately calculate the current moisture content of cooked food, resulting in low accuracy in calculating the moisture content of solid cooked food. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, device, computer equipment, computer-readable storage medium, and computer program product for intelligently calculating the water content of a user's diet, in response to the above-mentioned technical problems.

[0005] Firstly, this application provides a method for intelligently calculating the water content of a user's diet, including:

[0006] The multispectral scan image of the food, the amount of food added, and the cooking and processing information of the food are obtained. Based on the multispectral scan image of the food, the current ingredient evaluation information of each ingredient of the food is identified.

[0007] Based on the information on the amount of food added and the current food evaluation information of each ingredient, the current food moisture content of each ingredient is calculated using a moisture content calculation model. Based on the cooking and processing information of the food, the current interference data of each moisture content interference factor of the food is identified.

[0008] Based on the current interference data of each of the aforementioned moisture content interference factors, the current moisture content influence value of each of the aforementioned ingredients is calculated using a compensation factor calculation model. Based on the current moisture content influence value of each of the aforementioned ingredients and the current moisture content of each of the aforementioned ingredients, the current target moisture content of each of the aforementioned ingredients is calculated.

[0009] Optionally, the step of identifying the current ingredient evaluation information of each ingredient of the food based on the multispectral scan image of the food includes:

[0010] Based on the multispectral scan images of the food, the food image range of each food ingredient is identified through a food ingredient image segmentation network;

[0011] For each ingredient, based on the ingredient image range, an image feature recognition network is used to identify the environmental features of the environment in which the ingredient is located, as well as the ingredient features of the ingredient itself.

[0012] Based on the environmental characteristics of the environment in which the food is located, the environmental state of the food is identified, and based on the food characteristics of the food, the food state of the food is identified.

[0013] The environmental state and the food state of the food are used as the current food evaluation information.

[0014] Optionally, the step of calculating the current moisture content of each ingredient based on the information on the amount of food added and the current ingredient evaluation information of each ingredient, using a moisture content calculation model, includes:

[0015] Based on the amount of food added, the current weight of each ingredient is identified, and based on the environmental state and the state of each ingredient, the moisture content range of each ingredient is calculated by the moisture content calculation module.

[0016] Based on the image range of each ingredient, the target detection area of ​​each ingredient is filtered, and based on the target detection area of ​​the ingredient, the water content percentage of each ingredient is obtained through microwave resonance technology.

[0017] Based on the water content range and water content percentage of each ingredient, the current water content of each ingredient is calculated using a food water content algorithm.

[0018] Optionally, the step of identifying current interference data for various moisture content interference factors of the food based on the food's cooking and processing information includes:

[0019] Based on the cooking method, identify the current environmental impact data of each type of environmental impact of the food's environment, as well as the amount of interfering substances added to the food's moisture content.

[0020] Based on the current environmental impact data for each of the aforementioned environmental impact types, and the amount of interfering substances added to the moisture content of the food, current interference data for each of the aforementioned moisture content interference factors is generated through a data transformation strategy.

[0021] Optionally, based on the current interference data of each of the aforementioned moisture content interference factors, the degree of influence of the current moisture content of each of the ingredients is calculated using a compensation factor calculation model, including:

[0022] Obtain the water content interference fitting coefficient for each of the water content interference data;

[0023] Based on the current interference data of each of the aforementioned moisture content interference factors and the moisture content interference fitting coefficient of each of the aforementioned moisture content interference data, the influence value of the current moisture content of the food is calculated through the compensation factor calculation model.

[0024] Based on the influence value of the current moisture content of the food, the environmental state of each ingredient, and the ingredient state of each ingredient, the influence value of the current moisture content of each ingredient is identified.

[0025] Optionally, calculating the current target moisture content of each ingredient based on the influence value of the current moisture content of each ingredient and the current moisture content of each ingredient includes:

[0026] Based on the influence value of the current moisture content of each ingredient and the current moisture content of each ingredient, calculate the initial target moisture content of each ingredient.

[0027] Based on the initial target moisture content of each ingredient, the moisture content ratio table of each ingredient is queried, the current calculated weight value of each ingredient is identified, and the current food weight value of the food is collected.

[0028] Calculate the current weight value of the food and the deviation value between it and the current calculated weight value of each ingredient. If the deviation value is greater than a preset deviation threshold, re-acquire the multispectral scan image of the food.

[0029] The new multispectral scan image replaces the existing multispectral scan image, and the process returns to the step of identifying the current ingredient evaluation information of each ingredient of the food based on the multispectral scan image of the food, until the deviation value is not greater than a preset deviation threshold. Then, the initial target moisture content of each ingredient obtained in the last iteration is used as the current target moisture content of each ingredient.

[0030] Secondly, this application also provides a smart device for calculating the water content of a user's diet, comprising:

[0031] The acquisition module is used to acquire the multispectral scan image of the food, the amount of food added, and the cooking and processing information of the food, and based on the multispectral scan image of the food, to identify the current ingredient evaluation information of each ingredient of the food.

[0032] The identification module is used to calculate the current moisture content of each ingredient based on the amount of food added and the current ingredient evaluation information of each ingredient, through a moisture content calculation model, and to identify the current interference data of each moisture content interference factor of the food based on the cooking and processing information of the food.

[0033] The calculation module is used to calculate the degree of influence of the current moisture content of each ingredient based on the current interference data of each moisture content interference factor, through a compensation factor calculation model, and to calculate the current target moisture content of each ingredient based on the degree of influence of the current moisture content of each ingredient and the current moisture content of each ingredient.

[0034] Optionally, the acquisition module is specifically used for:

[0035] Based on the multispectral scan images of the food, the food image range of each food ingredient is identified through a food ingredient image segmentation network;

[0036] For each ingredient, based on the ingredient image range, an image feature recognition network is used to identify the environmental features of the environment in which the ingredient is located, as well as the ingredient features of the ingredient itself.

[0037] Based on the environmental characteristics of the environment in which the food is located, the environmental state of the food is identified, and based on the food characteristics of the food, the food state of the food is identified.

[0038] The environmental state and the food state of the food are used as the current food evaluation information.

[0039] Optionally, the identification module is specifically used for:

[0040] Based on the amount of food added, the current weight of each ingredient is identified, and based on the environmental state and the state of each ingredient, the moisture content range of each ingredient is calculated by the moisture content calculation module.

[0041] Based on the image range of each ingredient, the target detection area of ​​each ingredient is filtered, and based on the target detection area of ​​the ingredient, the water content percentage of each ingredient is obtained through microwave resonance technology.

[0042] Based on the water content range and water content percentage of each ingredient, the current water content of each ingredient is calculated using a food water content algorithm.

[0043] Optionally, the identification module is specifically used for:

[0044] Based on the cooking method, identify the current environmental impact data of each type of environmental impact of the food's environment, as well as the amount of interfering substances added to the food's moisture content.

[0045] Based on the current environmental impact data for each of the aforementioned environmental impact types, and the amount of interfering substances added to the moisture content of the food, current interference data for each of the aforementioned moisture content interference factors is generated through a data transformation strategy.

[0046] Optionally, the computing module is specifically used for:

[0047] Obtain the water content interference fitting coefficient for each of the water content interference data;

[0048] Based on the current interference data of each of the aforementioned moisture content interference factors and the moisture content interference fitting coefficient of each of the aforementioned moisture content interference data, the influence value of the current moisture content of the food is calculated through the compensation factor calculation model.

[0049] Based on the influence value of the current moisture content of the food, the environmental state of each ingredient, and the ingredient state of each ingredient, the influence value of the current moisture content of each ingredient is identified.

[0050] Optionally, the computing module is specifically used for:

[0051] Based on the influence value of the current moisture content of each ingredient and the current moisture content of each ingredient, calculate the initial target moisture content of each ingredient.

[0052] Based on the initial target moisture content of each ingredient, the moisture content ratio table of each ingredient is queried, the current calculated weight value of each ingredient is identified, and the current food weight value of the food is collected.

[0053] Calculate the current weight value of the food and the deviation value between it and the current calculated weight value of each ingredient. If the deviation value is greater than a preset deviation threshold, re-acquire the multispectral scan image of the food.

[0054] The new multispectral scan image replaces the existing multispectral scan image, and the process returns to the step of identifying the current ingredient evaluation information of each ingredient of the food based on the multispectral scan image of the food, until the deviation value is not greater than a preset deviation threshold. Then, the initial target moisture content of each ingredient obtained in the last iteration is used as the current target moisture content of each ingredient.

[0055] Thirdly, this application provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method described in any one of the first aspects.

[0056] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0057] Fifthly, this application provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0058] The aforementioned intelligent calculation method, device, and computer equipment for the moisture content of a user's diet acquires multispectral scan images of the food, information on the amount of food added, and information on the cooking and processing of the food. Based on the multispectral scan images of the food, it identifies the current ingredient evaluation information of each ingredient. Based on the information on the amount of food added and the current ingredient evaluation information of each ingredient, it calculates the current moisture content of each ingredient using a moisture content calculation model. Based on the cooking and processing information of the food, it identifies the current interference data of each moisture content interference factor. Based on the current interference data of each moisture content interference factor, it calculates the degree of influence of each ingredient's current moisture content using a compensation factor calculation model. Based on the degree of influence of each ingredient's current moisture content and the current moisture content of each ingredient, it calculates the current target moisture content of each ingredient. This solution assesses and analyzes the moisture content of food from multiple perspectives, including multispectral analysis, dosage, and cooking methods, effectively improving the accuracy of moisture content assessment. Furthermore, it quantifies the current moisture content of different ingredients and various factors that interfere with moisture content, allowing for the calculation of both the food's inherent moisture content and the degree of interference and influence during cooking and processing. This significantly enhances the accuracy of real-time moisture content assessment. In conclusion, this solution provides a comprehensive analysis of real-time moisture content and environmental interference from multiple angles and levels, avoiding the bias issues associated with relying on single tables and effectively improving the accuracy of calculating the moisture content of cooked solid foods. Attached Figure Description

[0059] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0060] Figure 1This is a flowchart illustrating a method for intelligently calculating the water content of a user's diet in one embodiment.

[0061] Figure 2 This is a flowchart illustrating an example of intelligent calculation of a user's dietary water content in one embodiment;

[0062] Figure 3 This is a structural block diagram of a user's intelligent calculation device for dietary water content in one embodiment;

[0063] Figure 4 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0064] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0065] The intelligent calculation method for the moisture content of a user's food provided in this application embodiment can be applied to an intelligent calculation system for the moisture content of a user's food. This system can be applied to a terminal, which can be, but is not limited to, various personal computers, laptops, mid-range computers, etc. Specifically, the terminal evaluates and analyzes the moisture content of food from the perspectives of multispectral images, added amounts, and cooking methods, effectively improving the accuracy of moisture content assessment. Furthermore, when assessing the moisture content of food, this solution performs quantitative analysis from the perspectives of current ingredient assessment information for different ingredients and various moisture content interference factors. This allows for the calculation of not only the moisture content of the food itself but also the degree of moisture content interference and influence during cooking and processing, effectively improving the accuracy of real-time moisture content assessment. In summary, this solution comprehensively analyzes the real-time moisture content of food and environmental moisture content interference from multiple angles and levels, avoiding the bias problems of relying on single-table verification and effectively improving the accuracy of calculating the moisture content of cooked solid food.

[0066] In one exemplary embodiment, such as Figure 1 As shown, a method for intelligently calculating the water content of a user's diet is provided. Taking the application of this method to a terminal as an example, the method includes the following steps S101 to S103. Wherein:

[0067] Step S101: Obtain the multispectral scan image of the food, the amount of food added, and the cooking and processing information of the food, and based on the multispectral scan image of the food, identify the current ingredient evaluation information of each ingredient of the food.

[0068] In this embodiment, the terminal uses a multispectral image acquisition device to perform image acquisition and processing on the food, obtaining a multispectral scan image of the food. This multispectral image acquisition device is capable of acquiring spectral images in the wavelength range of 900–2500 nm (near-infrared band). This multispectral scan image can be used to identify the moisture distribution, component differences, and texture of the food. Then, in response to the information upload operation by the staff, the terminal obtains the added weight values ​​of different ingredients in the food, obtaining the amount of food added, and also obtains data on environmental factors that can affect the moisture content of the food, such as the cooking method, exposure time in the environment, ambient temperature, ambient humidity, and ambient wind speed, as cooking and processing information. Then, based on the multispectral scan image of the food, the terminal identifies the current ingredient evaluation information of each ingredient. The current ingredient evaluation information includes the environmental state of the environment in which the ingredient is located and the ingredient state of the ingredient. The environmental state characterizes the food state of the food, which includes, but is not limited to, pure solid, semi-solid, and liquid states. The "food state" refers to the shape state of the food itself, which can be the original food shape, semi-separated food shape, fully separated food shape, or non-food shape state. Specifically, a semi-separated food state is one where the food has been broken down / cut into multiple components, each component being at least 1 / 5 of the original food volume. Examples include cutting eggplant into eggplant segments, corn into corn segments, and green beans into green bean segments. A fully separated food state is one where the food has been broken down / cut into multiple components, each component being less than 1 / 5 of the original food volume, and the food has not spoiled. Examples include cutting scallions into scallion flowers, potatoes into potato shreds, and radishes into radish shreds. A non-food shape state is one where the original form of the food has been altered (e.g., solid to liquid, liquid to solid) or its original biological characteristics have been changed. Examples include frying pork fat into crispy pork cracklings, frying potatoes into French fries, turning potatoes into mashed potatoes, and turning soy milk into tofu or dried bean curd sticks. The specific identification process will be explained in detail later.

[0069] Step S102: Based on the information on the amount of food added and the current food evaluation information of each ingredient, the current food moisture content of each ingredient is calculated through the moisture content calculation model, and based on the food cooking and processing information, the current interference data of each moisture content interference factor of the food is identified.

[0070] In this embodiment, the terminal calculates the current moisture content of each ingredient based on the amount of food added and the current ingredient evaluation information, using a moisture content calculation model. It also identifies the current interference data of various moisture content interference factors based on the food's cooking and processing information. The moisture content calculation model includes a moisture content calculation module and a food moisture content algorithm. The terminal first calculates the moisture content range of each ingredient by combining the ingredient weight, environmental conditions, and the ingredient's state. Then, it obtains the real-time moisture content percentage of each ingredient and, combining the percentage and range, queries the current moisture content of each ingredient using the food moisture content algorithm. This algorithm includes different moisture content ranges, moisture content percentage ranges, and comparisons with the actual moisture content of each ingredient. The terminal directly queries the moisture content of each ingredient by comparing the moisture content range and percentage with the aforementioned comparisons. The specific identification process will be explained in detail later. The various factors that interfere with the moisture content include environmental factors, cooking additives, and cooking methods that indirectly affect the moisture content of ingredients. For example, factors such as the amount of salt added, ambient temperature, ambient humidity, ambient airflow speed, boiling, frying, and stir-frying are all interfering factors.

[0071] Step S103: Based on the current interference data of each moisture content interference factor, calculate the current moisture content influence value of each ingredient through the compensation factor calculation model, and calculate the current target moisture content of each ingredient based on the current moisture content influence value of each ingredient and the current moisture content of each ingredient.

[0072] In this embodiment, the terminal calculates the degree of influence of the current moisture content of each ingredient based on the current interference data of each moisture content interference factor using a compensation factor calculation model. Based on the degree of influence and the current moisture content of each ingredient, the terminal calculates the current target moisture content of each ingredient. The compensation factor calculation model, constructed by the inventors of this solution, is a model for calculating the degree of influence of different moisture content interference factors on the moisture content of each ingredient. This model includes moisture content interference fitting coefficients for different moisture content interference factors. The terminal obtains the moisture content interference value of each interference factor by multiplying the current interference data by the fitting coefficient. Then, the terminal sums these moisture content interference values ​​to obtain the current degree of influence of the moisture content. This degree of influence value includes positive and negative signs. The specific calculation process will be explained in detail later. The current target moisture content is actually the sum of the influence of the current moisture content of each ingredient and the current moisture content of each ingredient.

[0073] Based on the above scheme, the moisture content of food is evaluated and analyzed from the perspectives of multispectral images, amount added, and cooking methods, effectively improving the accuracy of moisture content assessment. Secondly, when assessing the moisture content of food, this scheme quantifies the current ingredient assessment information and various moisture content interference factors. This allows for the calculation of both the moisture content of the food itself and the degree of moisture content interference and influence during cooking and processing, effectively improving the accuracy of real-time moisture content assessment. In summary, this scheme comprehensively analyzes the real-time moisture content of food and environmental moisture content interference from multiple angles and levels, avoiding the bias problems of relying on single-table verification and effectively improving the accuracy of calculating the moisture content of cooked solid foods.

[0074] Optionally, based on the multispectral scan image of the food, the current ingredient evaluation information of each ingredient is identified, including: based on the multispectral scan image of the food, identifying the ingredient image range of each ingredient through an ingredient image segmentation network; for each ingredient, based on the ingredient image range, identifying the environmental features of the environment in which the ingredient is located, and the ingredient features of the ingredient, through an image feature recognition network; identifying the environmental state of the ingredient based on the environmental features of the environment in which the ingredient is located, and identifying the ingredient state of the ingredient based on the ingredient features; and using the environmental state and the ingredient state of the ingredient as the current ingredient evaluation information of the ingredient.

[0075] In this embodiment, the terminal identifies the image range of each food ingredient based on its multispectral scan image using an ingredient image segmentation network. This image segmentation network is a convolutional neural network based on an edge detection algorithm. Since different ingredients vary in water content, structure, shape, and image color, the terminal uses this image segmentation network to identify image ranges with the same image color and identifies these ranges as the image range of the same ingredient. Next, the terminal presets a correspondence between each ingredient and its image color. Then, using this correspondence and the image color corresponding to each ingredient's image range, the terminal queries the ingredient corresponding to each ingredient's image range.

[0076] For each ingredient, the terminal, based on the ingredient's image range, uses an image feature recognition network to identify the environmental features of the ingredient's environment and the ingredient's own characteristics. This image feature recognition network is a neural network based on the improved Mask R-CNN algorithm constructed in this solution. This neural network can accurately identify the ingredient and food features of different ingredients, thereby accurately classifying the current ingredient and food features of each ingredient. The terminal presets one or more food features corresponding to different environmental states, and one or more ingredient features corresponding to different ingredient states. Then, through the identified ingredient features and the aforementioned correspondence, the terminal identifies the ingredient state corresponding to that ingredient feature. Similarly, the terminal identifies the environmental state corresponding to that ingredient feature. In this configuration, one ingredient feature corresponds to one ingredient state, and one food feature corresponds to one environmental state.

[0077] Finally, the terminal uses the environmental condition of the ingredients and the ingredient condition of the ingredients as the current ingredient assessment information.

[0078] Based on the above scheme, by using multispectral scanning images and the food image segmentation network and image feature recognition network constructed in this scheme, it is possible not only to accurately locate the range of each ingredient in mixed food, but also to comprehensively identify the ingredient features and food characteristics of each ingredient, thereby improving the accuracy of feature recognition of each ingredient in mixed food.

[0079] Optionally, based on the amount of food added and the current food assessment information of each ingredient, the current food moisture content of each ingredient is calculated using a moisture content calculation model. This includes: identifying the current weight of each ingredient based on the amount of food added, and calculating the moisture content range of each ingredient based on the environmental and food conditions of each ingredient using a moisture content calculation module; filtering the target detection area of ​​each ingredient based on the image range of each ingredient, and obtaining the moisture content percentage of each ingredient using microwave resonance technology based on the target detection area of ​​the ingredient; and calculating the current food moisture content of each ingredient based on the moisture content range and the moisture content percentage of each ingredient using a food moisture content algorithm.

[0080] In this embodiment, the terminal identifies the current weight of each ingredient based on the amount of food added, and calculates the moisture content range of each ingredient using a moisture content calculation module, based on the environmental and physical conditions of each ingredient. Specifically, the calculation process of the moisture content calculation module is as follows: for each ingredient, the terminal identifies the applicable weight and the proportional relationship between the weight and moisture content based on the environmental and physical conditions of the ingredient. Then, the terminal inputs the current weight of the ingredient into the proportional relationship to generate the moisture content range of the ingredient. The aforementioned proportional relationship is set in the moisture content calculation module and includes proportional relationships corresponding to different ingredients under different environmental and physical conditions. This proportional relationship includes a range of proportional values ​​between the ingredient weight and its moisture content. The terminal multiplies the current weight of the ingredient by the proportional values ​​at both ends of this range to obtain the moisture content range of the ingredient.

[0081] The terminal filters the target detection area for each food ingredient based on its image range. Then, using microwave resonance technology, it obtains the percentage moisture content of each ingredient within that target detection area. The target detection area is the largest area within the food ingredient's image range. The terminal performs microwave resonance processing on the food using the corresponding resonant cavity, thereby monitoring the resonant frequency information returned by each target detection area. Then, according to a pre-set calibration model, the terminal identifies the moisture content corresponding to each target detection area based on its resonant frequency information, and uses this moisture content as the percentage moisture content of the food ingredient corresponding to each target detection area. The calibration model is of the same type and form as the food being tested, with 5–8 different moisture gradients (covering the detectable range, such as 5%–25%). The actual moisture content of each sample is accurately measured using the national standard drying method / Karl Fischer method. (True value), then, place each standard sample into the microwave device and record: attenuation A (dB), phase shift φ ( The resonant frequency f and bandwidth BW are given, along with temperature and density. Then, a fitting model (calculating coefficients) is used to combine multiple sets of data. Substitute into the formula and calculate using the least squares method. For example: linear fitting yields Specifically, before the actual testing, when testing the calibration model with samples that were not used in the calibration, the required error is... Only then can it be considered qualified.

[0082] Then, based on the moisture content range and percentage of each ingredient, the terminal calculates the current moisture content of each ingredient using a food moisture content algorithm. This algorithm works by multiplying the ingredient's weight by its moisture content percentage to obtain an initial moisture content value. If the initial moisture content value is outside the specified range, the terminal selects the closest value from those values ​​within that range as the current moisture content. If the initial moisture content value is within the specified range, the terminal uses that initial moisture content value as the current moisture content.

[0083] Based on the above scheme, by combining the environmental conditions, food conditions, and food weight of the ingredients, and through the water content calculation module and food water content algorithm, the current water content of each ingredient is calculated comprehensively, thereby improving the accuracy of real-time water content calculation for each ingredient.

[0084] Optionally, based on the food's cooking and processing information, current interference data of various moisture content interference factors of the food are identified, including: based on the cooking and processing method, current environmental impact data of various environmental impact types of the food's environment and the amount of interference substances added to the food's moisture content interference factors; based on the current environmental impact data of each environmental impact type and the amount of interference substances added to the food's moisture content interference factors, current interference data of each moisture content interference factor is generated through a data transformation strategy.

[0085] In this embodiment, the terminal identifies the current environmental impact data of each environmental impact type of the food's environment, as well as the amount of water content interfering substances added, based on the cooking method. The current environmental impact data for each environmental impact type includes, but is not limited to, ambient temperature, airflow velocity, humidity, and cooking time for each cooking method. Water content interfering substances include, but are not limited to, high-concentration solutes such as salt, oyster sauce, light soy sauce, and dark soy sauce.

[0086] Then, based on the current environmental impact data for each environmental impact type and the amount of interfering substances added to the food's moisture content, the terminal generates current interference data for each moisture content interference factor through a data transformation strategy. Specifically, each moisture content interference factor corresponds to one or more environmental impact types, or to all moisture content interfering substances. For example, the moisture content interference factor corresponding to ambient temperature is the moisture evaporation interference factor, the moisture content interference factor corresponding to ambient humidity is the moisture evaporation rate interference factor, the moisture content interference factor corresponding to ambient airflow is the moisture evaporation rate interference factor, and the moisture content interference factor corresponding to each moisture content interfering substance is the moisture content decay degree interference factor. This data transformation strategy includes the transformation relationship between the current environmental impact data for each environmental impact type and the current interference data for moisture content interference factors, or the transformation relationship between the amount of interfering substances added to each moisture content interfering substance and the current interference data for moisture content interference factors. Using the above transformation relationships, the terminal converts the current environmental impact data for each environmental impact type and the amount of interfering substances added to the food's moisture content into the current interference data for each moisture content interference factor, according to the above correspondence.

[0087] Based on the above scheme, by combining the environmental impact types related to different water content disturbance factors and water content disturbance substances, the current disturbance data of each water content disturbance factor is comprehensively analyzed, thereby improving the comprehensiveness of the identification of each water content disturbance factor.

[0088] Optionally, based on the current interference data of each moisture content interference factor, the influence value of the current moisture content of each ingredient is calculated using a compensation factor calculation model. This includes: obtaining the moisture content interference fitting coefficient of each moisture content interference data; calculating the influence value of the current moisture content of the food using a compensation factor calculation model based on the current interference data of each moisture content interference factor and the moisture content interference fitting coefficient of each moisture content interference data; and identifying the influence value of the current moisture content of each ingredient based on the influence value of the current moisture content of the food, the environmental state of each ingredient, and the ingredient state of each ingredient.

[0089] In this embodiment, the terminal acquires the moisture content interference fitting coefficients for each moisture content interference data. Then, based on the current interference data for each moisture content interference factor and the moisture content interference fitting coefficients for each moisture content interference data, the terminal calculates the degree of influence of the current moisture content of the food using a compensation factor calculation model. Specifically, the calculation formula for this compensation factor calculation model is as follows:

[0090]

[0091] In the above formula, Factors interfering with the rate of water evaporation; Factors affecting moisture evaporation; Factors affecting the degree of moisture content decline; : These are the fitting coefficients for each moisture content interference factor. The ellipsis above also includes other moisture content interference factors and their corresponding fitting coefficients, which will not be elaborated upon here.

[0092] Finally, based on the current moisture content impact value of the food, the environmental state of each ingredient, and the ingredient state of each ingredient, the terminal identifies the current moisture content impact value of each ingredient. Specifically, the terminal presets the ratio between the environmental state of each ingredient, the ingredient state of each ingredient, and the moisture content impact value. The terminal multiplies the current moisture content impact value of the food by the corresponding ratio value for each ingredient to obtain the current moisture content impact value of each ingredient.

[0093] Based on the above scheme, by comprehensively calculating the various factors that interfere with the moisture content of food, the influence value of the current moisture content of the food can be identified. Then, from the perspectives of the environmental state and food state of each ingredient, the influence value of the current moisture content of each ingredient is comprehensively analyzed, thereby improving the accuracy of identifying the influence value of the current moisture content of each ingredient.

[0094] Optionally, based on the influence value of the current moisture content of each ingredient and the current moisture content of each ingredient, the current target moisture content of each ingredient is calculated, including: calculating the initial target moisture content of each ingredient based on the influence value of the current moisture content of each ingredient and the current moisture content of each ingredient; based on the initial target moisture content of each ingredient, querying the ingredient moisture content ratio table of each ingredient, identifying the current calculated weight value of each ingredient, and collecting the current food weight value; calculating the current food weight value of the food and the deviation value between it and the current calculated weight value of each ingredient, and if the deviation value is greater than a preset deviation threshold, re-collecting the multispectral scan image of the food; replacing the multispectral scan image with the new multispectral scan image, and returning to execute the step of identifying the current ingredient evaluation information of each ingredient of the food based on the multispectral scan image of the food, until the deviation value is not greater than the preset deviation threshold, and using the initial target moisture content of each ingredient obtained in the last iteration as the current target moisture content of each ingredient.

[0095] In this embodiment, the terminal calculates the initial target moisture content of each ingredient based on the influence value of the current moisture content of each ingredient and the current moisture content of each ingredient. The initial target moisture content is the moisture content obtained by summing the influence value of the current moisture content with the current moisture content of the ingredient.

[0096] Then, based on the initial target moisture content of each ingredient, the terminal queries the ingredient moisture content ratio table for each ingredient, identifies the current calculated weight value of each ingredient, and collects the current food weight value. Next, the terminal calculates the deviation between the current food weight value and the current calculated weight value of each ingredient. If the deviation value exceeds a preset deviation threshold, the terminal re-collects a multispectral scan image of the food. Then, the terminal replaces the previous multispectral scan image with the new one and returns to execute the step of identifying the current ingredient evaluation information of each ingredient based on the food's multispectral scan image, until the deviation value is no greater than the preset deviation threshold. Finally, the initial target moisture content of each ingredient obtained in the last iteration is used as the current target moisture content of each ingredient.

[0097] Based on the above scheme, the target moisture content of each identified ingredient is corrected by calculating the moisture content deviation value, thereby improving the accuracy of the target moisture content identification.

[0098] This application also provides an example of intelligent calculation of a user's dietary water content, such as... Figure 2 As shown, the specific processing procedure includes the following steps:

[0099] Step S201: Obtain the multispectral scan image of the food, the amount of food added, and the cooking and processing information of the food.

[0100] Step S202: Based on the multispectral scan image of the food, the food image range of each food is identified through the food image segmentation network.

[0101] Step S203: For each ingredient, based on the ingredient image range, an image feature recognition network is used to identify the environmental features of the environment in which the ingredient is located, as well as the ingredient features of the ingredient.

[0102] Step S204: Based on the environmental characteristics of the environment in which the ingredients are located, identify the environmental state of the ingredients, and based on the ingredients' characteristics, identify the ingredients' food state.

[0103] Step S205: The environmental state of the ingredients and the ingredient state of the ingredients are used as the current ingredient evaluation information.

[0104] Step S206: Based on the information on the amount of food added, identify the current weight of each ingredient, and calculate the moisture content range of each ingredient based on the environmental state and the state of each ingredient through the moisture content calculation module.

[0105] Step S207: Based on the image range of each ingredient, the target detection area of ​​each ingredient is selected, and based on the target detection area of ​​the ingredient, the water content percentage of each ingredient is obtained through microwave resonance technology.

[0106] Step S208: Based on the water content range and water content percentage of each ingredient, calculate the current water content of each ingredient using a food water content algorithm.

[0107] Step S209: Based on the cooking method, identify the current environmental impact data of each type of environmental impact of the food's environment, as well as the amount of interfering substances added to the food's moisture content.

[0108] Step S210: Based on the current environmental impact data of each type of environmental impact and the amount of added interfering substances for the moisture content of food, the current interference data of each moisture content interfering factor is generated through a data transformation strategy.

[0109] Step S211: Obtain the water content interference fitting coefficients for each water content interference data.

[0110] Step S212: Based on the current interference data of each moisture content interference factor and the moisture content interference fitting coefficient of each moisture content interference data, the influence value of the current moisture content of the food is calculated through the compensation factor calculation model.

[0111] Step S213: Based on the influence value of the current moisture content of the food, the environmental state of each ingredient, and the ingredient state of each ingredient, identify the influence value of the current moisture content of each ingredient.

[0112] Step S214: Calculate the initial target moisture content of each ingredient based on the influence value of the current moisture content of each ingredient and the current moisture content of each ingredient.

[0113] Step S215: Based on the initial target moisture content of each ingredient, query the moisture content ratio table of each ingredient, identify the current calculated weight value of each ingredient, and collect the current food weight value.

[0114] Step S216: Calculate the current weight value of the food and the deviation value between it and the current calculated weight value of each ingredient. If the deviation value is greater than the preset deviation threshold, re-acquire the multispectral scan image of the food.

[0115] Step S217: Replace the multispectral scan image with the new multispectral scan image, and return to the step of performing food-based multispectral scan image to identify the current ingredient evaluation information of each ingredient of the food until the deviation value is not greater than the preset deviation threshold. Then, take the initial target moisture content of each ingredient obtained in the last iteration as the current target moisture content of each ingredient.

[0116] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0117] Based on the same inventive concept, this application also provides a user's intelligent dietary moisture content calculation device for implementing the aforementioned intelligent calculation method for user's dietary moisture content. The solution provided by this device is similar to the implementation described in the above method. Therefore, the specific limitations of one or more user's intelligent dietary moisture content calculation device embodiments provided below can be found in the limitations of the user's intelligent dietary moisture content calculation method described above, and will not be repeated here.

[0118] In one exemplary embodiment, such as Figure 3 As shown, a smart device for calculating the water content of a user's diet is provided, comprising: an acquisition module 310, an identification module 320, and a calculation module 330, wherein:

[0119] The acquisition module 310 is used to acquire the multispectral scan image of the food, the amount of food added, and the cooking and processing information of the food, and based on the multispectral scan image of the food, identify the current ingredient evaluation information of each ingredient of the food.

[0120] The identification module 320 is used to calculate the current moisture content of each ingredient based on the amount of food added and the current ingredient evaluation information of each ingredient, through a moisture content calculation model, and to identify the current interference data of each moisture content interference factor of the food based on the cooking and processing information of the food.

[0121] The calculation module 330 is used to calculate the current moisture content influence value of each ingredient based on the current interference data of each moisture content interference factor through a compensation factor calculation model, and to calculate the current target moisture content of each ingredient based on the current moisture content influence value of each ingredient and the current moisture content of each ingredient.

[0122] Optionally, the acquisition module 310 is specifically used for:

[0123] Based on the multispectral scan images of the food, the food image range of each food ingredient is identified through a food ingredient image segmentation network;

[0124] For each ingredient, based on the ingredient image range, an image feature recognition network is used to identify the environmental features of the environment in which the ingredient is located, as well as the ingredient features of the ingredient itself.

[0125] Based on the environmental characteristics of the environment in which the food is located, the environmental state of the food is identified, and based on the food characteristics of the food, the food state of the food is identified.

[0126] The environmental state and the food state of the food are used as the current food evaluation information.

[0127] Optionally, the identification module 320 is specifically used for:

[0128] Based on the amount of food added, the current weight of each ingredient is identified, and based on the environmental state and the state of each ingredient, the moisture content range of each ingredient is calculated by the moisture content calculation module.

[0129] Based on the image range of each ingredient, the target detection area of ​​each ingredient is filtered, and based on the target detection area of ​​the ingredient, the water content percentage of each ingredient is obtained through microwave resonance technology.

[0130] Based on the water content range and water content percentage of each ingredient, the current water content of each ingredient is calculated using a food water content algorithm.

[0131] Optionally, the identification module 320 is specifically used for:

[0132] Based on the cooking method, identify the current environmental impact data of each type of environmental impact of the food's environment, as well as the amount of interfering substances added to the food's moisture content.

[0133] Based on the current environmental impact data for each of the aforementioned environmental impact types, and the amount of interfering substances added to the moisture content of the food, current interference data for each of the aforementioned moisture content interference factors is generated through a data transformation strategy.

[0134] Optionally, the computing module 330 is specifically used for:

[0135] Obtain the water content interference fitting coefficient for each of the water content interference data;

[0136] Based on the current interference data of each of the aforementioned moisture content interference factors and the moisture content interference fitting coefficient of each of the aforementioned moisture content interference data, the influence value of the current moisture content of the food is calculated through the compensation factor calculation model.

[0137] Based on the influence value of the current moisture content of the food, the environmental state of each ingredient, and the ingredient state of each ingredient, the influence value of the current moisture content of each ingredient is identified.

[0138] Optionally, the computing module 330 is specifically used for:

[0139] Based on the influence value of the current moisture content of each ingredient and the current moisture content of each ingredient, calculate the initial target moisture content of each ingredient.

[0140] Based on the initial target moisture content of each ingredient, the moisture content ratio table of each ingredient is queried, the current calculated weight value of each ingredient is identified, and the current food weight value of the food is collected.

[0141] Calculate the current weight value of the food and the deviation value between it and the current calculated weight value of each ingredient. If the deviation value is greater than a preset deviation threshold, re-acquire the multispectral scan image of the food.

[0142] The new multispectral scan image replaces the existing multispectral scan image, and the process returns to the step of identifying the current ingredient evaluation information of each ingredient of the food based on the multispectral scan image of the food, until the deviation value is not greater than a preset deviation threshold. Then, the initial target moisture content of each ingredient obtained in the last iteration is used as the current target moisture content of each ingredient.

[0143] The various modules in the aforementioned intelligent calculation device for the user's dietary water content can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0144] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 4As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a method for intelligently calculating the water content of a user's diet. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0145] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0146] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of a method for intelligently calculating the water content of a user's diet.

[0147] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program being executed by a processor to implement the steps of a method for intelligently calculating the water content of a user's diet.

[0148] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of a method for intelligently calculating the water content of a user's diet.

[0149] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0150] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0151] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0152] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for intelligently calculating the water content of a user's diet, characterized in that, The method includes: The multispectral scan image of the food, the amount of food added, and the cooking and processing information of the food are obtained. Based on the multispectral scan image of the food, the current ingredient evaluation information of each ingredient of the food is identified. Based on the information on the amount of food added and the current food evaluation information of each ingredient, the current food moisture content of each ingredient is calculated using a moisture content calculation model. Based on the cooking and processing information of the food, the current interference data of each moisture content interference factor of the food is identified. Based on the current interference data of each of the aforementioned moisture content interference factors, the current moisture content influence value of each of the aforementioned ingredients is calculated using a compensation factor calculation model. Based on the current moisture content influence value of each of the aforementioned ingredients and the current moisture content of each of the aforementioned ingredients, the current target moisture content of each of the aforementioned ingredients is calculated.

2. The method according to claim 1, characterized in that, The process of identifying the current ingredient evaluation information of each ingredient in the food based on the multispectral scan image of the food includes: Based on the multispectral scan images of the food, the food image range of each food ingredient is identified through a food ingredient image segmentation network; For each ingredient, based on the ingredient image range, an image feature recognition network is used to identify the environmental features of the environment in which the ingredient is located, as well as the ingredient features of the ingredient itself. Based on the environmental characteristics of the environment in which the food is located, the environmental state of the food is identified, and based on the food characteristics of the food, the food state of the food is identified. The environmental state and the food state of the food are used as the current food evaluation information.

3. The method according to claim 2, characterized in that, Based on the information on the amount of food added and the current food evaluation information of each ingredient, the current food moisture content of each ingredient is calculated using a moisture content calculation model, including: Based on the amount of food added, the current weight of each ingredient is identified, and based on the environmental state and the state of each ingredient, the moisture content range of each ingredient is calculated by the moisture content calculation module. Based on the image range of each ingredient, the target detection area of ​​each ingredient is filtered, and based on the target detection area of ​​the ingredient, the water content percentage of each ingredient is obtained through microwave resonance technology. Based on the water content range and water content percentage of each ingredient, the current water content of each ingredient is calculated using a food water content algorithm.

4. The method according to claim 1, characterized in that, The method of identifying current interference data for various moisture content interference factors of the food based on the food's cooking and processing information includes: Based on the cooking method, identify the current environmental impact data of each type of environmental impact of the food's environment, as well as the amount of interfering substances added to the food's moisture content. Based on the current environmental impact data for each of the aforementioned environmental impact types, and the amount of interfering substances added to the moisture content of the food, current interference data for each of the aforementioned moisture content interference factors is generated through a data transformation strategy.

5. The method according to claim 3, characterized in that, Based on the current interference data of each of the aforementioned moisture content interference factors, the degree of influence of the current moisture content of each of the aforementioned ingredients is calculated using a compensation factor calculation model, including: Obtain the water content interference fitting coefficient for each of the water content interference data; Based on the current interference data of each of the aforementioned moisture content interference factors and the moisture content interference fitting coefficient of each of the aforementioned moisture content interference data, the influence value of the current moisture content of the food is calculated through the compensation factor calculation model. Based on the influence value of the current moisture content of the food, the environmental state of each ingredient, and the ingredient state of each ingredient, the influence value of the current moisture content of each ingredient is identified.

6. The method according to claim 1, characterized in that, The calculation of the current target moisture content of each ingredient based on the influence value of the current moisture content of each ingredient and the current moisture content of each ingredient includes: Based on the influence value of the current moisture content of each ingredient and the current moisture content of each ingredient, calculate the initial target moisture content of each ingredient. Based on the initial target moisture content of each ingredient, the moisture content ratio table of each ingredient is queried, the current calculated weight value of each ingredient is identified, and the current food weight value of the food is collected. Calculate the current weight value of the food and the deviation value between it and the current calculated weight value of each ingredient. If the deviation value is greater than a preset deviation threshold, re-acquire the multispectral scan image of the food. The new multispectral scan image replaces the existing multispectral scan image, and the process returns to the step of identifying the current ingredient evaluation information of each ingredient of the food based on the multispectral scan image of the food, until the deviation value is not greater than a preset deviation threshold. Then, the initial target moisture content of each ingredient obtained in the last iteration is used as the current target moisture content of each ingredient.

7. A smart device for calculating the water content of a user's diet, characterized in that, The device includes: The acquisition module is used to acquire the multispectral scan image of the food, the amount of food added, and the cooking and processing information of the food, and based on the multispectral scan image of the food, to identify the current ingredient evaluation information of each ingredient of the food. The identification module is used to calculate the current moisture content of each ingredient based on the amount of food added and the current ingredient evaluation information of each ingredient, through a moisture content calculation model, and to identify the current interference data of each moisture content interference factor of the food based on the cooking and processing information of the food. The calculation module is used to calculate the degree of influence of the current moisture content of each ingredient based on the current interference data of each moisture content interference factor, through a compensation factor calculation model, and to calculate the current target moisture content of each ingredient based on the degree of influence of the current moisture content of each ingredient and the current moisture content of each ingredient.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images