CN115862814A - Accurate meal management method based on intelligent health data analysis - Google Patents
Accurate meal management method based on intelligent health data analysis Download PDFInfo
- Publication number
- CN115862814A CN115862814A CN202211619302.8A CN202211619302A CN115862814A CN 115862814 A CN115862814 A CN 115862814A CN 202211619302 A CN202211619302 A CN 202211619302A CN 115862814 A CN115862814 A CN 115862814A
- Authority
- CN
- China
- Prior art keywords
- food
- user
- nutrient
- intake
- calculating
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000007726 management method Methods 0.000 title claims abstract description 20
- 230000036541 health Effects 0.000 title claims abstract description 18
- 238000007405 data analysis Methods 0.000 title claims abstract description 16
- 235000012054 meals Nutrition 0.000 title claims description 19
- 235000013305 food Nutrition 0.000 claims abstract description 108
- 235000015097 nutrients Nutrition 0.000 claims abstract description 79
- 235000005911 diet Nutrition 0.000 claims abstract description 40
- 230000037213 diet Effects 0.000 claims abstract description 34
- 238000000034 method Methods 0.000 claims abstract description 33
- 230000008569 process Effects 0.000 claims abstract description 18
- 235000006286 nutrient intake Nutrition 0.000 claims abstract description 15
- 230000003203 everyday effect Effects 0.000 claims abstract description 14
- 238000005457 optimization Methods 0.000 claims abstract description 12
- 235000021049 nutrient content Nutrition 0.000 claims abstract description 7
- 235000016709 nutrition Nutrition 0.000 claims description 22
- 230000035764 nutrition Effects 0.000 claims description 18
- 230000006870 function Effects 0.000 claims description 17
- 230000002354 daily effect Effects 0.000 claims description 12
- 238000003709 image segmentation Methods 0.000 claims description 9
- 230000000378 dietary effect Effects 0.000 claims description 6
- 238000013135 deep learning Methods 0.000 claims description 5
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 3
- 235000012631 food intake Nutrition 0.000 abstract description 4
- 230000037406 food intake Effects 0.000 abstract description 4
- 230000001143 conditioned effect Effects 0.000 abstract 1
- 239000003925 fat Substances 0.000 description 12
- 230000002068 genetic effect Effects 0.000 description 11
- 235000019577 caloric intake Nutrition 0.000 description 10
- 108090000623 proteins and genes Proteins 0.000 description 9
- 150000004671 saturated fatty acids Chemical class 0.000 description 9
- 150000004665 fatty acids Chemical class 0.000 description 6
- 210000000349 chromosome Anatomy 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 102000004169 proteins and genes Human genes 0.000 description 4
- 235000014633 carbohydrates Nutrition 0.000 description 3
- 150000001720 carbohydrates Chemical class 0.000 description 3
- 235000006694 eating habits Nutrition 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 230000035772 mutation Effects 0.000 description 3
- 241000209094 Oryza Species 0.000 description 2
- 235000007164 Oryza sativa Nutrition 0.000 description 2
- 235000018823 dietary intake Nutrition 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 235000009566 rice Nutrition 0.000 description 2
- 238000005303 weighing Methods 0.000 description 2
- 235000016795 Cola Nutrition 0.000 description 1
- 244000228088 Cola acuminata Species 0.000 description 1
- 235000011824 Cola pachycarpa Nutrition 0.000 description 1
- 235000020881 DASH diet Nutrition 0.000 description 1
- 241000287828 Gallus gallus Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 235000013339 cereals Nutrition 0.000 description 1
- 235000013330 chicken meat Nutrition 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 208000019622 heart disease Diseases 0.000 description 1
- 239000003446 ligand Substances 0.000 description 1
- 235000013372 meat Nutrition 0.000 description 1
- 235000021274 meat intake Nutrition 0.000 description 1
- 230000004060 metabolic process Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 208000024335 physical disease Diseases 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 235000014347 soups Nutrition 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 235000018648 unbalanced nutrition Nutrition 0.000 description 1
- 238000002562 urinalysis Methods 0.000 description 1
Images
Abstract
The invention relates to an accurate diet management method based on intelligent health data analysis. The technical scheme is as follows: acquiring body index data of a user and a food image of the user; segmenting a food image of a user; calculating nutrient elements required to be taken by a user every day according to body index data of the user; performing data analysis based on the segmented food image to obtain the actual ingested nutrient content, comparing the actual ingested nutrient content with the recommended ingested amount, and improving the existing food intake of the user based on a target planning model to obtain an optimal diet recommendation scheme; the method adopts the target optimization model to process the nutrient elements ingested every day and the segmented food image so as to determine the optimal nutrient intake amount for every day, and the optimal nutrient intake amount for every day is used for diet management according to the optimal nutrient intake amount for every day, so that the body health of the user is conditioned.
Description
Technical Field
The invention belongs to the technical field of health management, and particularly relates to an accurate diet management method based on intelligent health data analysis.
Background
The life activities of the human body require nutrition to provide energy, including self metabolism and energy consumed by work and exercise. If the daily intake of energy by human body is insufficient, the body can utilize self-stored energy and even consume self-tissue to meet the requirements of life activities. With the improvement of living standard of people, various food layers are continuously generated, and the imbalance of diet is a common phenomenon at present. People often suffer from various physical diseases due to excessive diet, excessive energy in the body, unbalanced nutrition caused by monophagia and independent diet, and even sub-health caused by diet. Although there are some suggestions to the user on diet, such as the balance of five cereals consumed per meal, the control of meat intake, etc. However, this is only to recommend some conventional suggestions and does not recommend the actual situation of the individual, resulting in inaccurate food recommendation. Moreover, the traditional meal survey methods such as weighing method take more than 1 hour (every time) to implement the process according to the established flow steps, and the use of weighing tools is not always accompanied with the process of daily meals, and the comprehensive factors make the traditional methods have low efficiency. In order to improve the quality and efficiency of the diet survey, the invention provides an accurate diet management method based on intelligent health data analysis.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides an accurate diet management method based on intelligent health data analysis, which comprises the following steps: : acquiring body index data of a user and a food image of the user; segmenting the food image of the user, and calculating nutrient elements actually ingested by the user according to the segmented food image; calculating nutrient elements required to be ingested by the user every day according to body index data of the user; and inputting the nutrient elements actually taken by the user and the nutrient elements required to be taken by the user every day into a target optimization model to obtain an optimal diet recommendation scheme.
Preferably, the process of segmenting the food image of the user comprises: acquiring a horizontal 360-degree covered three-direction standardized food image; calibrating and preprocessing the food image; establishing a deep learning network based on food image segmentation; inputting the calibrated and preprocessed graph into a food image segmentation deep learning network for food identification and segmentation processing to obtain different food images; extracting nutrients of different foods, and calculating the difference of the space ratio of the foods before and after the foods are eaten by the user to obtain the content of the nutrients in each food; the dietary nutrients are output according to the content of the nutrients in each food.
Preferably, the process of calculating the daily intake of the nutritional elements required by the user comprises: acquiring food data of a user, wherein the food data comprises a type of food and a weight of the food; and calculating the content of the nutrient elements required to be ingested by the user according to the food data.
Preferably, the processing of the daily nutrient elements and the segmented food image using the objective optimization model includes: inputting the data determined by dividing the food image into a food database, and calculating the nutrient content of each food; comparing the nutrient components ingested by the user with the recommended nutrient intake of the medical advice, and calculating the difference between the nutrient components ingested by the user and the recommended intake of the medical advice; inputting the difference data with the advice recommendation into a target planning model, and calculating the food to be supplemented or the food to be reduced; making a diet recommendation based on the existing diet structure according to the calculated result; comparing the diet recommendation results with a database, checking whether the daily nutrition is within the required range; if not, updating the data and adjusting the diet recommendation result; this process is repeated until the daily nutrition is within the required range.
The invention has the beneficial effects that:
the method adopts a target optimization model to process nutrient elements ingested every day and a segmented food image so as to determine the optimal nutrient intake for every day, and carries out diet management according to the optimal nutrient intake for every day so as to condition the body health of a user; compared with the previous fuzzy suggestion on the user in the aspect of diet, the method provided by the invention can be close to the diet nutrition intake scheme of the doctor advice, and can effectively realize individual accurate health management.
Drawings
FIG. 1 is a flow chart of a method for intelligent meal management based on data analysis according to the present invention;
FIG. 2 is a flow chart of image segmentation according to the present invention;
FIG. 3 is a flow chart of a bid planning algorithm of the present invention;
FIG. 4 is a flowchart of the present invention for solving an optimal meal plan based on genetic algorithm;
FIG. 5 is a schematic diagram of a genetic algorithm population of the present invention;
FIG. 6 is a schematic diagram of a genetic algorithm selection operation of the present invention;
FIG. 7 is a schematic diagram of the genetic algorithm crossover operation of the present invention;
FIG. 8 is a diagram of the genetic algorithm variation of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
An accurate meal management method based on intelligent health data analysis comprises the steps of obtaining body index data of a user and food images of the user; segmenting a food image of a user; calculating the nutrient elements required to be taken by the user every day (medical advice, namely recommended intake amount which should be taken under ideal conditions) according to the physical index data of the user; and performing data analysis on the segmented food image, comparing the segmented food image with the recommended nutrient intake of the medical advice, and inputting the data into a target optimization model based on the comparison result data to obtain an optimal diet recommendation scheme.
In the process of segmenting the food image, the proportion p% of each nutrient in the image needs to be identified, food data (the type and the quality of food) segmented from the food image is input into a food database for analysis according to the food data, and the total amount of each component (the nutrient content in the food is in a linear relation with the weight of the food) can be calculated based on the proportion of the nutrient contained in the food, namely: mp%.
The specific image segmentation process comprises the steps of inputting a standardized user dining chart, wherein images in an image data set comprise images of different foods; and preprocessing the data in the food image data set, dividing the preprocessed food image, completing food recognition by a deep learning-based food image recognition model, and calculating the nutrient content in different types of food sub-images to obtain the nutrient intake of the user based on the meal.
Taking the extraction of fat, saturated fatty acid index and the like as an example, a user provides a standardized diet picture, positioning and identification are carried out based on a database, and food segmentation is completed to obtain food types such as glutinous rice balls, colas, rice, soup, chicken steaks, meat and the like; weight of intake x 1 、x 2 、x 3 、x 4 、x 5 、x 6 And the fat content m is obtained according to the content ratio of the fat and the saturated fatty acid 11 、m 21 、m 31 、m 41 、m 51 、m 61 Etc. saturated fatty acid content m 12 、m 22 、m 32 、m 42 、m 52 、m 62 And so on.
An embodiment of a method for precise meal management based on intelligent health data analysis comprises the following steps: the aim of constructing the model is to recommend an improvement scheme based on the existing dietary structure of the patient, so as to achieve the closest dietary nutrition intake scheme to the medical advice and realize the individual accurate health management. The model obtains clinical data information and dietary information for a patient's condition (a particular disease species, such as heart disease). The clinical data information comprises LIS data (such as urinalysis and physical examination reports) of a clinical trial information system, clinical diet medical orders (such as DASH diet scheme) and the like; the diet information obtains data from the food image segmentation system and evaluates the composition, quality and weight of the diet. Calculating the distance between the food and the medical advice diet scheme by the clinical data information and the diet information data through a target optimization model, judging whether the optimal scheme is the optimal scheme or not according to the calculation result, wherein the optimal scheme (the near term) does not need to be improved, and if the optimal scheme is not the optimal scheme, calculating and judging the optimal scheme through the target optimization model, and recommending the optimal scheme to the patient. The objective optimization model provides a scientific scheme for preventing and controlling diseases by supplementing additional food or reducing the intake of certain food on the premise of self dietary habits to meet the pre-specified nutritional requirements and preventing unreasonable intake of nutrient elements.
In this embodiment, determining the content of the nutrient element ingested by the user comprises: and inputting data determined by food image segmentation into a database, calculating nutrient components in the package, comparing the nutrient components with the recommended nutrient intake of the medical advice, and judging whether the package is good or bad so as to improve the package.
The user selects n kinds of alternative food as food of one day (determined by the user's eating habits), and records the selected alternative food as R 1 ,R 2 ,…,R n Weight is Rm 1 ,Rm 2 ,…,Rm n, The alternative food is derived from the eating habit of the user and is obtained based on image segmentationThe weight of (1) for food is recorded as m 1 ,m 2 ,…m n (ii) a The content of j nutrients (e.g. fat and saturated fatty acid index) in 100g of i food was recorded as x ij (i=1,2,..,i;j
=1,2,. J). For convenience, each nutrient content is related to the weight of food (including actual food intake, food alternative) m n 、Rm n Viewed as a linear relationship, the linear equations may be listed in turn as follows.
(1) Energy objective function
Let x 1 ,x 2 ,...,x n The unit energy content in the food is respectively e 1 ,e 2 ,...,e n Ideally, the following relationship is obtained by recommending the meal energy as the optimal intake according to the medical advice:
x 1 ×e 1j +x 2 ×e 2j +...x n ×e nj =RENI j
however, accurate energy intake is an impossible goal in real life, and an objective function is defined as the minimization of the energy intake on the premise that the recommended intake of the doctor is satisfied as much as possible, i.e., the daily required energy is satisfied. The energy objective function is then:
(2) Nutrient objective function
Under the ideal condition, the nutrient elements contained in the food ingested by the user are equal to the recommended ingested amount, and the expression is as follows:
x 1 ×k 1j +x 2 ×k 2j +...x n ×k nj =RNI j
wherein, the RNI is the recommended intake of the medical advice, and x is the weight of the food in the alternative food.
However, in a real situation, there is a certain gap between the food nutrition ANI actually taken by the user and the target recommended amount RNI. A deviation SNI is now introduced and must be present, representing the difference between the actual intake and the recommended intake. Wherein SNI j + The fraction indicating that the actual intake exceeds the recommended intake, i.e. the required reduction of the nutritional content of the intake, the SNI in the target plan j + ≥0;SNI j - Part representing that the actual intake does not reach the recommended intake, SNI in the target plan j - Not less than 0; recording the actual intake of j nutrition as ANI j 。
With respect to RNI j The positive deviation amount of (d) is:
with respect to RNI j The negative deviation amount of (d) is:
SNI j - ×SNI j + =0
since the recommended intake of each nutrient (such as fat and saturated fatty acid index) of the user is not a fixed value, a deviation variable is introduced according to the actual situation. Assuming a positive deviation variable d + Indicating that the actual value exceeds the target value, in the target plan d + Not less than 0; assuming a negative offset variable d - Indicating that the actual value has not reached the target value, target plan d - Is more than or equal to 0. In this example, a priority factor is set between the nutrients. There are many kinds of nutrients in food, and the number of nutrients needed by human body is more than tens or even hundreds, and the importance degree of different nutrients (such as fat and saturated fatty acid index) is different. When the set meal is judged to be good or bad, the set meal which preferentially meets the needs of important nutrients is better, and on the basis that the target of preferential nutrients is met, the condition that the corresponding nutrients with lower priorities are met is considered, such as the priorities of three nutrients of carbohydrate, fat and protein are higher. Priority factor, also called priority level, by P l Is represented by, and p l >>p l+1 L =1,2.. L. For distinguishing between nutrients having the same priority factor. For example, the carbohydrates, the fats and the proteins have the same priority, but the importance degrees of the carbohydrates, the fats and the proteins are different, and the weight coefficient W is used lj Represents P l The weight coefficient, j =1,2.. J, of each nutrient (e.g., fat and saturated fatty acid index) to which the priority factor corresponds. Since the objective planning is aimed at approaching the established target values as closely as possible, i.e. at minimizing the associated deviation variables, the objective function can only be minimized. In this example, each deviation variable is made as close as possible to the target recommended nutritional intake.
(1) Required to just reach the target nutrient recommended intake. In this case, it is undesirable to decide whether the nutrient intake exceeds or falls short of the target nutrient recommended intake, and so there are
(2) The target nutrient recommended intake is required not to be exceeded, but is allowed to be insufficient. At this time, it is not desirable that the decision-making nutrient intake exceeds the target nutrient recommended intake, and therefore there are
(3) It is required not to fall below the target nutrition recommended intake but to be allowed to exceed the target nutrition recommended intake. At this point, it is undesirable to make a decision on nutrient intake less than the target nutrient recommended intake, and so there are
According to the above concept, a nutrient objective function is determined:
obtaining a nutrition discrimination model of the package according to the objective function, wherein the expression of the model is as follows:
the multi-objective planned nutritional formula of the present invention combines minimization of energy intake while meeting recommended intake as much as possible, and minimization of the distance between each nutritional intake and the recommended intake. Combining the energy constraint and the nutrient constraint together, the following constraint multi-target planning model can be obtained:
and converting the multi-objective programming problem into a problem solved by single objective programming. In the above it can be seen that the objective function and constraints regarding caloric intake can be translated into constraints, translating a reasonably recommended range of caloric intake into one constraint of nutrient intake.
Thus, the objective function of each nutrient can be converted into a single constraint without influencing the value, namely the constraint condition that the nutrient intake is closest to the recommended intake of the medical advice, and the redundant energy intake can be consumed in a proper motion mode under the condition that the daily required energy requirement is met.
Thus, after converting the multi-target linear programming into the single-target linear programming, the mathematical expression of the model is as follows:
the model sets the intake of various nutrients (such as fat and saturated fatty acid index) and takes the order as the optimal recommended intake, which is used as the standard to improve diet. Meanwhile, the range constraint of the total intake of each nutrient (such as fat and saturated fatty acid index) and the total intake constraint of energy are added, so that the minimum energy intake required every day is ensured, and the condition that the model discrimination is closer to the nutrient condition of an actual diet set is ensured.
In the process of determining the food scheme of the user, the existing dietary structure needs to be improved continuously, and the specific steps comprise:
step 1: dividing the image into determined food types and qualities, and calculating the actual nutrition and energy intake of the user;
step 2: inputting the nutrition and energy intake of the user into the multi-target planning model;
and step 3: an intelligent optimization algorithm, such as a genetic algorithm, solves the multi-target plan, and judges whether the nutrition and energy intake scheme is optimal or not, namely, the requirement of medical advice is met to the maximum extent;
and 4, step 4: if the solution is an effective solution of the model, an intelligent optimized nutrition recommendation scheme is adopted; otherwise, adding food alternatives, and returning to the step 1 for subsequent operation.
As shown in fig. 3, the data of nutrient and energy supply obtained by image segmentation can be used as input of a target optimization model of the precise meal management method. And optimizing food intake by adopting a genetic algorithm, and meeting the matching scheme with the minimum distance from the medical advice when the recommended nutrients and energy of the medical advice are met as much as possible.
As shown in fig. 4, the process of optimizing food intake using genetic algorithm includes:
step 1: and acquiring a user food scheme, and obtaining the food type, weight, content of each nutrient and energy content by segmenting the food image.
Step 2: setting parameters including initial population size M, maximum iteration number T and basic variation probability P b And cross probability P c 。
As shown in fig. 5, setting parameters includes: in the process of encoding nutrients and energy and initial population generation, since the de-encoding is the key to the genetic algorithm, the phenotype and genotype are interconverted by the way of the encoding. Selecting binary coding mode to code nutrient and energy, wherein x represents protein, fat and other nutrient and energy units, and is regarded as a gene segment, so that x 1 …x n The combination of (a) constitutes a chromosome, i.e. an individual. The system generates M feasible solutions, namely a set of individuals, which is an initial community, genes, namely various nutrients and energy, in the initial community are determined by alternative food schemes, and the contents of the nutrients and the energy are obtained by segmenting food images.
And step 3: calculating a fitness function of each individual in the population; the fitness function can be directly replaced by an objective function, and the expression is as follows:
in the genetic algorithm, the degree of goodness and badness of each individual is evaluated according to the fitness of the individual, so that the genetic chance of the individual is determined. The smaller the algorithm fitness function value is, the higher the fitness of the group of genes is, and the better the nutrient and energy collocation is; and the larger the fitness function value is, the lower the fitness of the group of genes is, the lower the probability of inheritance to the next generation is, the easier the group of genes is to be eliminated, and the more the nutrient and energy collocation needs to be improved.
And 4, step 4: carrying out selection operation on the population;
as shown in fig. 6, performing the selection operation on the population includes: selecting a roulette method selection strategy, and calculating the sum sigma fi of the fitness of all individuals in a group; and secondly, calculating the relative fitness fi/sigma fi of each individual, namely the selected probability of each individual is in direct proportion to the fitness function value, so that the individual with a smaller fitness value is prevented from being directly eliminated.
And 5: and performing cross operation on the groups.
As shown in fig. 7, the specific process includes: adopting a single point crossing method, selecting two chromosomes by single point crossing to obtain a crossing probability P c And carrying out selective crossing, carrying out segmentation on the selected position points and exchanging the right part, and obtaining two different daughter chromosomes under the condition of causing small damage, namely generating a new collocation scheme on the basis of the original father nutrition energy collocation chromosome through crossing operation.
Step 6: and performing mutation operation on the population.
As shown in fig. 8, the specific process includes: adopting single point mutation method, the basic mutation probability P b Only one crossover point is randomly placed in the individual code string, and then the partial chromosomes of two individual ligands are interchanged at that point. The variation operation ensures the diversity of individuals, is not limited to the local optimal solution, and increases the possibility that the collocation of nutrition and energy is close to the optimal.
And 4, step 4: the algorithm is terminated to meet the following condition, and when the generated algebraic number reaches the value of the specified maximum iteration time T, the algorithm is stopped; in the time sequence of continuous propagation, if a new generation of individuals are not propagated for a long time, that is, under the condition of the current individual, the objective function cannot be improved, and when the maximum iteration number T is reached, the algorithm is stopped, the current individual is the final evolutionary result and is regarded as the optimal collocation scheme, so that the collocation of nutrients and energy is closest to the recommendation of medical advice.
The above-mentioned embodiments, which are further detailed for the purpose of illustrating the invention, technical solutions and advantages, should be understood that the above-mentioned embodiments are only preferred embodiments of the present invention, and should not be construed as limiting the present invention, and any modifications, equivalents, improvements, etc. made to the present invention within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (6)
1. An accurate meal management method based on intelligent health data analysis is characterized by comprising the following steps: acquiring body index data of a user and a food image of the user; segmenting the food image of the user, and calculating nutrient elements actually ingested by the user according to the segmented food image; calculating nutrient elements required to be taken by a user every day according to body index data of the user; and inputting the nutrient elements actually taken by the user and the nutrient elements required to be taken by the user every day into a target optimization model to obtain an optimal diet recommendation scheme.
2. The method for precise meal management based on intelligent health data analysis as claimed in claim 1, wherein the process of segmenting the food image of the user comprises: acquiring a horizontal 360-degree covered three-direction standardized food image; calibrating and preprocessing the food image; establishing a deep learning network based on food image segmentation; inputting the calibrated and preprocessed graph into a food image segmentation deep learning network for food identification and segmentation processing to obtain different food images; extracting nutrients of different foods, and calculating the difference of the space ratio of the foods before and after the foods are eaten by the user to obtain the content of the nutrients in each food; the dietary nutrients are output according to the content of the nutrients in each food.
3. The method for precise meal management based on intelligent health data analysis as claimed in claim 1, wherein the process of calculating the daily required nutrient elements for the user comprises: acquiring food data of a user, wherein the food data comprises a type of food and a weight of the food; and calculating the content of the nutrient elements required to be ingested by the user according to the food data.
4. The method for precise meal management based on intelligent health data analysis as claimed in claim 1, wherein the process of processing the daily intake of nutrient elements and the segmented food image by using the target optimization model comprises: inputting the data determined by dividing the food image into a food database, and calculating the nutrient content of each food; comparing the nutrient components ingested by the user with the recommended nutrient intake of the medical advice, and calculating the difference between the nutrient components ingested by the user and the recommended intake of the medical advice; inputting the difference data recommended by the medical advice into a target planning model, and calculating the food needing to be supplemented or the food needing to be reduced; making a diet recommendation based on the existing diet structure according to the calculated result; comparing the diet recommendation results with a database, checking whether the daily nutrition is within the required range; if the result does not meet the preset condition, updating the data and adjusting the diet recommendation result; this process is repeated until the daily nutrition is within the required range.
5. The method of claim 4, wherein calculating the gap from the recommended intake of the order comprises:
the actual intake of the user is calculated by the following formula:
m 1 ×x 1j +m 2 ×x 2j +...m n ×x nj =ANI j
difference between actual intake and recommended intake
|ANI j -RNI j |=SNI j
Wherein m is n Denotes the weight of the nutrient element, x nj Represents a nutrient element in the food, ANI j Indicating the actual amount of nutrient elements, RNI, taken by the user j Indicates the recommended intake, SNI j Representing the difference between the actual intake and the recommended intake.
6. The intelligent health data analysis-based accurate meal management method according to claim 4, wherein the objective function is:
wherein L represents the rating for different nutrients; p l Denotes the priority factor, p l >>p l+1 L =1,2l; j represents a nutrient, and J represents a nutrient,is shown at P l A negative deviation weighting factor of the respective nutrient under the priority factor,. Beta.>Represents a negative offset variable, <' > is selected>Represents P l The positive deviation weight coefficient of each nutrient under the priority factor, device for selecting or keeping>Indicating a positive deviation variable. />
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211619302.8A CN115862814A (en) | 2022-12-14 | 2022-12-14 | Accurate meal management method based on intelligent health data analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211619302.8A CN115862814A (en) | 2022-12-14 | 2022-12-14 | Accurate meal management method based on intelligent health data analysis |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115862814A true CN115862814A (en) | 2023-03-28 |
Family
ID=85673417
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211619302.8A Pending CN115862814A (en) | 2022-12-14 | 2022-12-14 | Accurate meal management method based on intelligent health data analysis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115862814A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116884573A (en) * | 2023-09-08 | 2023-10-13 | 北京逯博士行为医学科技研究院有限公司 | Dietary nutrition configuration method based on optimal carbon technology |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107680652A (en) * | 2017-09-13 | 2018-02-09 | 天津大学 | A kind of nutrition dietary based on machine learning recommends and evaluation method |
CN108364675A (en) * | 2018-01-23 | 2018-08-03 | 明纳信息技术深圳有限公司 | A kind of identification method of food weight and nutrient content based on image recognition |
CN109273070A (en) * | 2018-09-06 | 2019-01-25 | 北京好价网络科技有限公司 | Dietetic nutrition analysis system and method |
CN110097946A (en) * | 2019-03-01 | 2019-08-06 | 西安电子科技大学 | A kind of dietary recommendations continued method based on Analysis of Nutritive Composition |
CN111063419A (en) * | 2019-12-27 | 2020-04-24 | 南京舜国宸智能科技有限公司 | Intelligent healthy diet management system |
CN111161839A (en) * | 2019-12-25 | 2020-05-15 | 天津大学 | Method for recommending diet of diabetic through food nutrients |
CN111402996A (en) * | 2020-03-19 | 2020-07-10 | 珠海格力电器股份有限公司 | Diet recipe recommendation method and system and storage medium |
CN112071400A (en) * | 2020-09-21 | 2020-12-11 | 中山大学 | Food material quantitative selection method based on disease knowledge base |
CN114203279A (en) * | 2021-12-17 | 2022-03-18 | 浙江华园紫杭教育科技有限公司 | Intelligent diet nutrition blending and optimizing method and device and electronic equipment |
CN114550018A (en) * | 2022-02-25 | 2022-05-27 | 重庆邮电大学 | Nutrition management method and system based on deep learning food image recognition model |
CN114974512A (en) * | 2022-05-30 | 2022-08-30 | 中国银行股份有限公司 | Recommendation method and device for meal information |
CN115292607A (en) * | 2022-08-26 | 2022-11-04 | 温州医科大学 | Nutrient bidding judgment and diet recommendation system based on open type personalized diet database |
-
2022
- 2022-12-14 CN CN202211619302.8A patent/CN115862814A/en active Pending
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107680652A (en) * | 2017-09-13 | 2018-02-09 | 天津大学 | A kind of nutrition dietary based on machine learning recommends and evaluation method |
CN108364675A (en) * | 2018-01-23 | 2018-08-03 | 明纳信息技术深圳有限公司 | A kind of identification method of food weight and nutrient content based on image recognition |
CN109273070A (en) * | 2018-09-06 | 2019-01-25 | 北京好价网络科技有限公司 | Dietetic nutrition analysis system and method |
CN110097946A (en) * | 2019-03-01 | 2019-08-06 | 西安电子科技大学 | A kind of dietary recommendations continued method based on Analysis of Nutritive Composition |
CN111161839A (en) * | 2019-12-25 | 2020-05-15 | 天津大学 | Method for recommending diet of diabetic through food nutrients |
CN111063419A (en) * | 2019-12-27 | 2020-04-24 | 南京舜国宸智能科技有限公司 | Intelligent healthy diet management system |
CN111402996A (en) * | 2020-03-19 | 2020-07-10 | 珠海格力电器股份有限公司 | Diet recipe recommendation method and system and storage medium |
CN112071400A (en) * | 2020-09-21 | 2020-12-11 | 中山大学 | Food material quantitative selection method based on disease knowledge base |
CN114203279A (en) * | 2021-12-17 | 2022-03-18 | 浙江华园紫杭教育科技有限公司 | Intelligent diet nutrition blending and optimizing method and device and electronic equipment |
CN114550018A (en) * | 2022-02-25 | 2022-05-27 | 重庆邮电大学 | Nutrition management method and system based on deep learning food image recognition model |
CN114974512A (en) * | 2022-05-30 | 2022-08-30 | 中国银行股份有限公司 | Recommendation method and device for meal information |
CN115292607A (en) * | 2022-08-26 | 2022-11-04 | 温州医科大学 | Nutrient bidding judgment and diet recommendation system based on open type personalized diet database |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116884573A (en) * | 2023-09-08 | 2023-10-13 | 北京逯博士行为医学科技研究院有限公司 | Dietary nutrition configuration method based on optimal carbon technology |
CN116884573B (en) * | 2023-09-08 | 2023-12-01 | 北京逯博士行为医学科技研究院有限公司 | Dietary nutrition configuration method based on optimal carbon technology |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104303185B (en) | System and method for user's particular adjustments of nutrients intake | |
CN111105860A (en) | Intelligent prediction, analysis and optimization system for accurate motion big data for chronic disease rehabilitation | |
CN117133407B (en) | Nutritional balance assessment method and system for multi-label neural network for children | |
CN116417115B (en) | Personalized nutrition scheme recommendation method and system for gestational diabetes patients | |
CN110890146A (en) | Bedside intelligent interaction system for intelligent ward | |
CN115862814A (en) | Accurate meal management method based on intelligent health data analysis | |
CN116665843B (en) | Dietary energy intake optimization method for tumor patients | |
CN116417114B (en) | Student healthy diet management system based on full life cycle | |
CN116682533A (en) | Renal patient nutrition management method and system based on machine learning | |
CN116434915A (en) | Management method and system for guaranteeing balanced dietary nutrition of children | |
US11145401B1 (en) | Systems and methods for generating a sustenance plan for managing genetic disorders | |
Ileri et al. | Advancing competitive position in healthcare: A hybrid metaheuristic nutrition decision support system | |
Shih et al. | Farm price prediction using case-based reasoning approach—A case of broiler industry in Taiwan | |
US20220171933A1 (en) | Methods and systems for personal recipe generation | |
Chen et al. | Multiobjective evolutionary algorithm with double-level archives for nutritional dietary decision problem | |
Segura et al. | A novel memetic algorithm with explicit control of diversity for the menu planning problem | |
CN110739045B (en) | Interactive evolution optimization method for personalized recipe design | |
US20230089697A1 (en) | Method for generating a composite nutritional index, and associated system | |
Bello et al. | Best compromise nutritional menus for childhood obesity | |
Chang et al. | Fuzzy multi-choice goal programming and artificial bee colony algorithm for triangular and trapezoidal membership functions | |
Tom | Computational intelligence using Fuzzy Multicriteria Decision Making for DIligenS: Dietary Intelligence System | |
US11887720B1 (en) | Apparatus and method for using a feedback loop to optimize meals | |
US11581085B1 (en) | Systems and methods for generating personalized nutrition prescriptions and modifying the personalized nutrition prescriptions based on feedback | |
US20240087719A1 (en) | Methods and systems for calculating an edible score in a display interface | |
CN112420159A (en) | Energy demand calculation processing method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230328 |