CN115359869A - Multi-objective optimization-based dietary nutrition collocation method - Google Patents
Multi-objective optimization-based dietary nutrition collocation method Download PDFInfo
- Publication number
- CN115359869A CN115359869A CN202211181987.2A CN202211181987A CN115359869A CN 115359869 A CN115359869 A CN 115359869A CN 202211181987 A CN202211181987 A CN 202211181987A CN 115359869 A CN115359869 A CN 115359869A
- Authority
- CN
- China
- Prior art keywords
- food material
- recommended
- food
- user
- meal
- 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.)
- Withdrawn
Links
- 238000005457 optimization Methods 0.000 title claims abstract description 50
- 238000000034 method Methods 0.000 title claims abstract description 28
- 235000005911 diet Nutrition 0.000 title claims abstract description 27
- 235000016709 nutrition Nutrition 0.000 title claims abstract description 23
- 230000035764 nutrition Effects 0.000 title claims abstract description 20
- 230000000378 dietary effect Effects 0.000 title claims abstract description 16
- 235000013305 food Nutrition 0.000 claims abstract description 205
- 239000000463 material Substances 0.000 claims abstract description 194
- 235000012054 meals Nutrition 0.000 claims abstract description 47
- 235000015097 nutrients Nutrition 0.000 claims abstract description 38
- 230000037213 diet Effects 0.000 claims abstract description 11
- 230000007246 mechanism Effects 0.000 claims abstract description 9
- 238000007781 pre-processing Methods 0.000 claims abstract description 5
- 238000012163 sequencing technique Methods 0.000 claims description 10
- 230000015572 biosynthetic process Effects 0.000 claims description 6
- 238000010845 search algorithm Methods 0.000 claims description 6
- 235000021152 breakfast Nutrition 0.000 claims description 4
- 235000019577 caloric intake Nutrition 0.000 claims description 4
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 201000010099 disease Diseases 0.000 claims description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 3
- 230000002354 daily effect Effects 0.000 description 15
- 206010012601 diabetes mellitus Diseases 0.000 description 5
- 230000003203 everyday effect Effects 0.000 description 4
- 240000008042 Zea mays Species 0.000 description 3
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 description 3
- 235000002017 Zea mays subsp mays Nutrition 0.000 description 3
- 235000005822 corn Nutrition 0.000 description 3
- 210000001835 viscera Anatomy 0.000 description 3
- 241000272525 Anas platyrhynchos Species 0.000 description 2
- CIWBSHSKHKDKBQ-JLAZNSOCSA-N Ascorbic acid Chemical compound OC[C@H](O)[C@H]1OC(=O)C(O)=C1O CIWBSHSKHKDKBQ-JLAZNSOCSA-N 0.000 description 2
- 235000008534 Capsicum annuum var annuum Nutrition 0.000 description 2
- 240000008384 Capsicum annuum var. annuum Species 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 2
- HVYWMOMLDIMFJA-DPAQBDIFSA-N cholesterol Chemical compound C1C=C2C[C@@H](O)CC[C@]2(C)[C@@H]2[C@@H]1[C@@H]1CC[C@H]([C@H](C)CCCC(C)C)[C@@]1(C)CC2 HVYWMOMLDIMFJA-DPAQBDIFSA-N 0.000 description 2
- 235000020979 dietary recommendations Nutrition 0.000 description 2
- 235000013601 eggs Nutrition 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- OVBPIULPVIDEAO-LBPRGKRZSA-N folic acid Chemical compound C=1N=C2NC(N)=NC(=O)C2=NC=1CNC1=CC=C(C(=O)N[C@@H](CCC(O)=O)C(O)=O)C=C1 OVBPIULPVIDEAO-LBPRGKRZSA-N 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 235000006286 nutrient intake Nutrition 0.000 description 2
- FPIPGXGPPPQFEQ-UHFFFAOYSA-N 13-cis retinol Natural products OCC=C(C)C=CC=C(C)C=CC1=C(C)CCCC1(C)C FPIPGXGPPPQFEQ-UHFFFAOYSA-N 0.000 description 1
- 240000008574 Capsicum frutescens Species 0.000 description 1
- 235000002568 Capsicum frutescens Nutrition 0.000 description 1
- VYZAMTAEIAYCRO-UHFFFAOYSA-N Chromium Chemical compound [Cr] VYZAMTAEIAYCRO-UHFFFAOYSA-N 0.000 description 1
- 240000008067 Cucumis sativus Species 0.000 description 1
- 235000010799 Cucumis sativus var sativus Nutrition 0.000 description 1
- ZZZCUOFIHGPKAK-UHFFFAOYSA-N D-erythro-ascorbic acid Natural products OCC1OC(=O)C(O)=C1O ZZZCUOFIHGPKAK-UHFFFAOYSA-N 0.000 description 1
- 235000002722 Dioscorea batatas Nutrition 0.000 description 1
- 235000006536 Dioscorea esculenta Nutrition 0.000 description 1
- 240000001811 Dioscorea oppositifolia Species 0.000 description 1
- 235000003416 Dioscorea oppositifolia Nutrition 0.000 description 1
- OVBPIULPVIDEAO-UHFFFAOYSA-N N-Pteroyl-L-glutaminsaeure Natural products C=1N=C2NC(N)=NC(=O)C2=NC=1CNC1=CC=C(C(=O)NC(CCC(O)=O)C(O)=O)C=C1 OVBPIULPVIDEAO-UHFFFAOYSA-N 0.000 description 1
- BUGBHKTXTAQXES-UHFFFAOYSA-N Selenium Chemical compound [Se] BUGBHKTXTAQXES-UHFFFAOYSA-N 0.000 description 1
- 240000003768 Solanum lycopersicum Species 0.000 description 1
- FPIPGXGPPPQFEQ-BOOMUCAASA-N Vitamin A Natural products OC/C=C(/C)\C=C\C=C(\C)/C=C/C1=C(C)CCCC1(C)C FPIPGXGPPPQFEQ-BOOMUCAASA-N 0.000 description 1
- 229930003270 Vitamin B Natural products 0.000 description 1
- 229930003268 Vitamin C Natural products 0.000 description 1
- HCHKCACWOHOZIP-UHFFFAOYSA-N Zinc Chemical compound [Zn] HCHKCACWOHOZIP-UHFFFAOYSA-N 0.000 description 1
- FPIPGXGPPPQFEQ-OVSJKPMPSA-N all-trans-retinol Chemical compound OC\C=C(/C)\C=C\C=C(/C)\C=C\C1=C(C)CCCC1(C)C FPIPGXGPPPQFEQ-OVSJKPMPSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 235000021466 carotenoid Nutrition 0.000 description 1
- 150000001747 carotenoids Chemical class 0.000 description 1
- 235000012000 cholesterol Nutrition 0.000 description 1
- 239000011651 chromium Substances 0.000 description 1
- 229910052804 chromium Inorganic materials 0.000 description 1
- 235000020940 control diet Nutrition 0.000 description 1
- 238000010411 cooking Methods 0.000 description 1
- 235000021316 daily nutritional intake Nutrition 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000013325 dietary fiber Nutrition 0.000 description 1
- 235000019007 dietary guidelines Nutrition 0.000 description 1
- 229960000304 folic acid Drugs 0.000 description 1
- 235000019152 folic acid Nutrition 0.000 description 1
- 239000011724 folic acid Substances 0.000 description 1
- 235000012631 food intake Nutrition 0.000 description 1
- 230000037406 food intake Effects 0.000 description 1
- 235000012907 honey Nutrition 0.000 description 1
- 230000007794 irritation Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 102000004169 proteins and genes Human genes 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 150000003839 salts Chemical class 0.000 description 1
- 150000004671 saturated fatty acids Chemical class 0.000 description 1
- 239000011669 selenium Substances 0.000 description 1
- 229910052711 selenium Inorganic materials 0.000 description 1
- 235000021139 traditional diet Nutrition 0.000 description 1
- 235000019155 vitamin A Nutrition 0.000 description 1
- 239000011719 vitamin A Substances 0.000 description 1
- 235000019156 vitamin B Nutrition 0.000 description 1
- 239000011720 vitamin B Substances 0.000 description 1
- 235000019154 vitamin C Nutrition 0.000 description 1
- 239000011718 vitamin C Substances 0.000 description 1
- 229940045997 vitamin a Drugs 0.000 description 1
- 239000011701 zinc Substances 0.000 description 1
- 229910052725 zinc Inorganic materials 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/60—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to nutrition control, e.g. diets
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Primary Health Care (AREA)
- Mathematical Analysis (AREA)
- Public Health (AREA)
- General Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Epidemiology (AREA)
- Operations Research (AREA)
- Nutrition Science (AREA)
- Algebra (AREA)
- Software Systems (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a multi-objective optimization-based dietary nutrition collocation method, which comprises the following steps: acquiring user data and preprocessing the user data; setting constraint conditions and an objective function of the multi-objective optimization function; constructing a food material scoring mechanism for selecting food materials; solving the selected food materials by using a multi-objective optimization algorithm to obtain a food material recommendation scheme; according to the method, personalized diet recommendation is provided for the user according to the diet pagoda, and the food material recommendation and the menu recommendation are combined, so that a reasonable and healthy nutritional catering meeting the element requirements of the user is provided for the user; whether meals are edible or not and recommending meals for different users can be judged through basic information of the users, preferences of the users and requirements of the users on nutrients.
Description
Technical Field
The invention relates to the field of recommendation and optimization, in particular to a multi-objective optimization-based dietary nutrition collocation method.
Background
With the rapid development of economy in China, people pay more and more attention to diet health, but the existing dietary nutrition recommendation method is difficult to meet the reasonable requirement of people on diet health, and the existing dietary recommendation scheme is either specific to a specific field, such as the medical field, and the dietary collocation scheme is strictly recommended according to the nutrient demand, but the nutrition collocation scheme capable of meeting the requirement is few, and the requirement of users on diversity is difficult to meet; or aiming at the common people, when the diversity of the nutrition scheme is satisfied, the daily intake of nutrients is not controlled enough, and the nutrition collocation is too loose.
Aiming at a diet recommendation method, the current mainstream method is divided into two methods, namely, on the basis of the constraint of nutrients, the food material recommendation is carried out by using algorithms such as multi-objective linear programming and the like; secondly, recipe collocation recommendation is carried out based on the recipes, but the quality of the recipe collocation recommendation is recommended to the food materials; the traditional diet recommendation method has the following defects: the recommended food materials cannot be matched into dishes in the actual eating process; inadequate control of daily food intake based on recipe recommendations; the dietary recommendation scheme is less in variety and difficult to meet the requirement of the diversity of the dietary varieties of the users; or the nutrition collocation scheme is too loose, and the patent provides a diet nutrition collocation mechanism based on multi-objective optimization aiming at the problems.
Disclosure of Invention
In order to solve the technical problems, the invention adopts a technical scheme that: the method for collocating the dietary nutrition based on the multi-objective optimization is characterized by comprising the following steps:
s100, acquiring user data and preprocessing the user data;
s200, setting constraint conditions and a target function of the multi-target optimization function;
s300, constructing a food material grading mechanism for selecting food materials;
s400, solving the selected food materials by using a multi-objective optimization algorithm to obtain a food material recommendation scheme.
Further, the user data includes: basic information, disease information and physical examination report results of a user, wherein the basic information comprises; user occupation, user preferences, and user territory;
the user data is obtained by actively uploading by a user;
the pretreatment comprises the following steps: analyzing the user data, giving a food material label for each food material in a standard food database, and calculating a recommended range of daily required energy and nutrients of the user;
the food material labels comprise a label suitable for eating and a label suitable for eating with caution;
the standard food database is obtained from the internet, the standard food database is wide in coverage range and comprises n types of food materials, each type of food material comprises d types of food materials, and n and d are positive integers larger than or equal to 1.
Further, the constraint conditions include:
the daily recommended food material category quality should be within the recommended range, as shown in formula (1):
wherein m represents the number of recommendable food materials,
indicating the recommended quality of the ith food material,
indicating whether the ith food material is recommended or not,
0 means no recommendation, 1 means recommendation,
represents the ith food material of the kth food material,
refers to the minimum recommended value of the kth food material,
the maximum recommended value of the kth food material is indicated;
the daily energy intake needs should be within the recommended range, as shown in equation (2):
wherein,
represents the energy contained in the ith food material per unit mass,
a minimum recommended value representing the user's energy per day,
a maximum recommended value representing a user's energy per day;
the daily nutrient elements should be within the recommended range, as shown in equation (3):
wherein,
represents the total content of jth nutrient elements in all food materials recommended on the day,
represents the mass of the jth nutrient contained in the ith food material per unit mass;
the recommended mass range of each food material is shown in formula (4):
wherein,
refers to the minimum recommended amount of the ith food material,
the maximum recommended amount of the ith food material is referred to;
the number of the food material types per day is not less than 12, as shown in formula (5):
the energy ratio of each meal is shown in formula (6):
wherein u represents a type of meal per day of
B represents breakfast, l represents Chinese meal, d represents dinner,
referring to the recommended energy proportion of the u-th meal;
according to the menu data, the probability of dish formation is counted, as shown in formula (7):
wherein,
refers to the recommended food material quantity of the u-th meal,
the number of food materials which can be used as a dish is recommended by the u th meal.
Further, the objective function includes: a daily nutrient element intake function, a food material dish forming probability function and a target optimization function;
the daily nutrient intake function means that various nutrient elements should meet the intake requirements of the user every day, as shown in formula (8):
wherein,
representing the weight of the user to the jth nutrient element on the current day;
the food material dish formation probability function means that the food material recommended by each meal needs to be cooked as much as possible, as shown in formula (9):
wherein,
representing the probability of the u meal for cooking;
the objective optimization function is shown in formula (10):
wherein,
、
the number of the coefficients is represented by,
。
further, the S300 includes:
s310, coarse recall: on the basis of the user data, respectively normalizing food material labels according to the occupation and the preference of the user, then giving different weights to different types of labels, calculating recall probabilities of all recommendable food materials by adopting a weighting method, and sequencing the recall probabilities in a descending order to obtain sequencing results;
s320, fine recall: and recalling food materials by combining a menu based on the sequencing result to obtain recalled food materials, judging whether the recalled food materials can become dishes according to the dish-forming probability, and selecting the food materials which can become dishes according to the judgment result.
Further, the S400 includes:
s410, selecting food materials by using different strategies through the food material grading mechanism, and recalling a plurality of groups of first recommended food materials;
s420, aiming at the multiple groups of first recommended food materials, on the basis that the constraint conditions are met, solving by using a multi-stage layer-by-layer optimization algorithm in the multi-objective optimization algorithm to obtain second recommended food materials;
and S430, summarizing the first recommended food material and the second recommended food material, creating a food material recommendation scoring rule to score the first recommended food material and the second recommended food material in a manual evaluation mode, and selecting the food material with the highest score to obtain an optimal diet recommendation scheme.
Further, the S420 includes:
s421, in an initialization stage, solving the objective optimization function by using a greedy algorithm to obtain a solution with the least number of violated hard rules and the maximum objective optimization function as an initial solution;
s422, in a nutrient element optimization stage, solving is carried out on the food material recommendation all day long, a daily nutrient element intake function is solved by taking formulas (1) to (5) as constraint conditions, and a global search algorithm is adopted to search in a global range to obtain the optimal solution of the current nutrient element;
s423, at a meal secondary optimization stage, solving energy calculation and dish forming probability of each meal, solving a food material dish forming probability function by taking formulas (6) to (7) as constraint conditions, and rapidly solving by adopting a local search algorithm to obtain the optimal solution of the current meal;
and S424, terminating the solution when the iteration times or the set time is reached, wherein the optimal solution of the current meal is the final optimal solution.
Further, the creating of the food material recommended scoring rule is to score the first recommended food material and the second recommended food material, and includes: hard rules and soft constraints, the hard rules including base constraints corresponding to equations (1) through (6), the hard rules being non-violatible; the soft constraints are that the first recommended food material and the second recommended food material are scored according to the rules of user occupation, user preference, current order, region, whether a single meal can be finished or not and the like.
In summary, due to the adoption of the technical scheme, the invention has the beneficial effects that:
according to the method, personalized diet recommendation is provided for the user according to the diet pagoda, and the food material recommendation and the recipe recommendation are combined, so that a reasonable and healthy nutritional catering meeting the element requirements of the user is provided for the user; whether meals are edible or not and recommending meals for different users can be judged through basic information of the users, preferences of the users and requirements of the users on nutrients.
Drawings
FIG. 1 is a flow chart of a dietary nutrition collocation method based on multi-objective optimization provided by the invention.
Detailed Description
The following detailed description of the preferred embodiments of the present invention, taken in conjunction with the accompanying drawings, will make the advantages and features of the present invention more comprehensible to those skilled in the art, and will thus provide a clear and concise definition of the scope of the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those described herein; it is to be understood that the embodiments described in this specification are only some embodiments of the invention, and not all embodiments.
Fig. 1 is a flowchart of a multi-objective optimization-based dietary nutrition collocation method provided by an embodiment of the invention, and the method comprises the following steps:
s100, acquiring user data and preprocessing the user data;
further, the user data includes: basic information, disease information and physical examination report results of a user, wherein the basic information comprises; user occupation, user preferences, and user territory;
the user data is obtained by actively uploading by a user;
the pretreatment comprises the following steps: analyzing the user data, giving a food material label for each food material in a standard food database, and calculating a recommended range of daily required energy and nutrients of the user;
the food material labels comprise a label suitable for eating and a label suitable for eating with caution;
the standard food database is obtained from the internet, the standard food database is wide in coverage range and comprises n types of food materials, each type of food material comprises d types of food materials, and n and d are positive integers larger than or equal to 1.
S200, setting constraint conditions and a target function of a multi-target optimization function;
further, the constraint conditions include:
the recommended food material category quality should be within the recommended range every day, and according to the Chinese resident dietary guidelines, it can be known that different groups have different energy intakes all day, and different types of food intakes corresponding to different groups every day are different, as shown in formula (1):
wherein m represents the number of recommendable food materials,
indicating the recommended quality of the ith food material,
indicating whether the ith food material is recommended or not,
0 means not recommended, 1 means recommended,
indicates the ith food material of the kth food material,
refers to the minimum recommended value of the kth food material,
the maximum recommended value of the kth food material is indicated;
the daily energy intake needs should be within the recommended range, as shown in equation (2):
wherein,
represents the energy contained in the ith food material per unit mass,
a minimum recommended value representing the user's energy per day,
a maximum recommended value representing a user's energy per day;
the daily nutrient elements should be within the recommended range, as shown in equation (3):
wherein,
represents the total content of the jth nutrient element in all the food materials recommended in the day,
represents the mass of the jth nutrient contained in the ith food material per unit mass;
the recommended quality range of each food material is shown in formula (4):
wherein,
refers to the minimum recommended amount of the ith food material,
the maximum recommended amount of the ith food material;
the number of the food material types per day is not less than 12, as shown in formula (5):
the energy ratio of each meal is shown in formula (6):
wherein u represents a type of meal per day of
B represents breakfast, l represents Chinese meal, d represents dinner,
the recommended energy proportion of the u-th meal is indicated;
according to the menu data, the probability of dish formation is counted, as shown in formula (7):
wherein,
refers to the recommended food material quantity of the u-th meal,
the number of food materials which can be used as a dish is recommended by the u th meal.
Further, the objective function includes: a daily nutrient element intake function, a food material dish forming probability function and a target optimization function;
the daily nutrient intake function means that various nutrient elements should meet the intake requirements of the user every day, as shown in formula (8):
wherein,
representing the weight of the user to the jth nutrient element on the current day;
the food material dish formation probability function means that the food material recommended by each meal needs to be cooked as much as possible, as shown in formula (9):
wherein,
representing the probability of the u-th meal becoming a dish;
the objective optimization function is shown in formula (10):
wherein,
、
the number of the coefficients is represented by,
。
s300, constructing a food material scoring mechanism for selecting food materials;
further, the S300 includes:
s310, coarse recall: on the basis of the user data, normalizing food material labels respectively according to the occupation and the user preference of the user, then giving different weights to different types of labels, calculating recall probabilities of all recommendable food materials by adopting a weighting method, and sequencing the recall probabilities in a descending order to obtain a sequencing result;
s320, recall of essence: and recalling food materials by combining a menu based on the sequencing result to obtain recalled food materials, judging whether the recalled food materials can become dishes according to the dish-forming probability, and selecting the food materials which can become dishes according to the judgment result.
S400, solving the selected food materials by using a multi-objective optimization algorithm to obtain a food material recommendation scheme.
Further, the S400 includes:
s410, selecting food materials by using different strategies through the food material grading mechanism, and recalling a plurality of groups of first recommended food materials;
s420, aiming at the multiple groups of first recommended food materials, on the basis that the constraint conditions are met, a multi-stage layer-by-layer optimization algorithm in the multi-objective optimization algorithm is used for solving to obtain second recommended food materials.
Further, the S420 includes:
s421, in an initialization stage, solving the objective optimization function by using a greedy algorithm to obtain a solution with the least number of violated hard rules and the maximum objective optimization function as an initial solution;
s422, in a nutrient element optimization stage, solving is carried out aiming at the daily food material recommendation, a daily nutrient element intake function is solved by taking formulas (1) to (5) as constraint conditions, and a global search algorithm is adopted to carry out searching in a global range to obtain the optimal solution of the current nutrient element;
s423, at a meal secondary optimization stage, solving energy calculation and dish forming probability of each meal, solving a food material dish forming probability function by taking formulas (6) to (7) as constraint conditions, and rapidly solving by adopting a local search algorithm to obtain the optimal solution of the current meal;
and S424, terminating the solution when the iteration times or the set time is reached, wherein the optimal solution of the current meal is the final optimal solution.
S430, summarizing the first recommended food material and the second recommended food material, creating a food material recommendation scoring rule to score the first recommended food material and the second recommended food material in a manual evaluation mode, and selecting the food material with the highest score to obtain an optimal diet recommendation scheme.
Further, the creating of the food material recommended scoring rule is to score the first recommended food material and the second recommended food material, and includes: hard rules and soft constraints, the hard rules including base constraints corresponding to equations (1) through (6), the hard rules being non-violatible; the soft constraints are that the first recommended food material and the second recommended food material are scored according to rules such as occupation, user preference, current order, region and whether a single meal can be finished or not.
The features and properties of the present invention are described in further detail below in connection with example 1.
Taking a diabetic as an example, scientific research shows that the diabetic needs to control diet, eat less and eat more, and the diabetic is recommended to take six meals, namely breakfast, lunch, dinner and dinner, wherein the energy proportion of each meal is recommended to be 21%, 10%, 28%, 10%, 21% and 10%.
S100, acquiring user data and preprocessing the user data;
according to the user data, the diabetic should eat: low GI, low GL, high dietary fiber, high vitamin C, high vitamin B, high folic acid, high carotenoid, high vitamin A, high zinc, high selenium, high chromium, high quality protein and other types of food; with cautions: high GL, high energy, high fat, high saturated fatty acid, high cholesterol, high GI, high sugar, irritation, viscera, high salt and other types of food; the label is updated for each food material by combining the content of the nutrient elements of the food materials, and the label is eaten with caution, so that the diabetic patients can eat the food materials such as cucumber, corn, chinese yam, green pepper and the like with caution and eat the food materials such as duck eggs, hot pepper, honey, animal viscera and the like with caution;
and calculating the single-day energy range, the nutrient element range, the mass range of each type of food material and the like according to the basic information of the user.
S200, setting constraint conditions and a target function of the multi-target optimization function;
s300, constructing a food material grading mechanism for selecting food materials;
food material filtering: filtering food materials eaten with caution according to the food material labels, for example, food materials such as duck eggs and animal viscera are not recommended for diabetics;
food material rough recall: respectively normalizing food material labels based on the user data, then giving different weights to different types of labels, calculating recall probabilities of all recommendable food materials by adopting a weighting method according to the current time, the region to which the food materials belong, the common food materials, the professional attributes of the user and the preference of the user, and finally performing descending ordering on the recall probabilities to obtain ordering results as shown in a table;
| (Times) | region of origin | Whether it is common or not | Occupational attributes | User preferences | ··· | |
| Corn (corn) | 1 | 1 | 1 | 0 | 1 | ··· |
| Tomato plant | 1 | 1 | 1 | 0 | 0 | ··· |
| Green pepper | 1 | 1 | 1 | 0 | 0 | ··· |
| ··· | ··· | ··· | ··· | ··· | ··· | ··· |
Food material recall: and recalling food materials by combining a menu based on the sequencing result to obtain recalled food materials, judging whether the recalled food materials can become dishes according to the dish-forming probability, and selecting the food materials which can become dishes according to the judgment result.
S400, solving the selected food materials by using a multi-objective optimization algorithm to obtain a food material recommendation scheme.
And counting all recommendation schemes, and selecting an optimal recommendation scheme.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. A multi-objective optimization-based dietary nutrition collocation method is characterized by comprising the following steps:
s100, acquiring user data and preprocessing the user data;
s200, setting constraint conditions and a target function of a multi-target optimization function;
s300, constructing a food material grading mechanism for selecting food materials;
s400, solving the selected food materials by using a multi-objective optimization algorithm to obtain a food material recommendation scheme.
2. The multi-objective optimization-based meal nutrition collocation method according to claim 1, wherein the user data comprises: basic information, disease information and physical examination report results of a user, wherein the basic information comprises; user occupation, user preferences, and user territory;
the user data is obtained by actively uploading by a user;
the pretreatment comprises the following steps: analyzing the user data, giving a food material label for each food material in a standard food database, and calculating the recommended range of daily required energy and nutrients of the user;
the food material labels comprise a label suitable for eating and a label suitable for eating with caution;
the standard food database is obtained from the Internet, the standard food database is wide in coverage range and comprises n types of food materials, each type of food material comprises d types of food materials, and n and d are positive integers more than or equal to 1.
3. The multi-objective optimization-based dietary nutrition collocation method of claim 1, wherein the constraints comprise:
the daily recommended food material category quality should be within the recommended range, as shown in formula (1):
wherein m represents the number of recommendable food materials,
indicating the recommended quality of the ith food material,
indicating whether the ith food material is recommended or not,
0 means not recommended, 1 means recommended,
indicates the ith food material of the kth food material,
refers to the minimum recommended value of the kth food material,
the maximum recommended value of the kth food material is indicated;
the daily energy intake needs should be within the recommended range, as shown in equation (2):
wherein,
represents the energy contained in the ith food material per unit mass,
a minimum recommended value representing the user's energy per day,
a maximum recommended value representing a user's energy per day;
the daily nutrient elements should be within the recommended range, as shown in equation (3):
wherein,
represents the total content of jth nutrient elements in all food materials recommended on the day,
represents the mass of the jth nutrient contained in the ith food material per unit mass;
the recommended quality range of each food material is shown in formula (4):
wherein,
refers to the minimum recommended amount of the ith food material,
the maximum recommended amount of the ith food material;
the number of the food material types per day is not less than 12, as shown in formula (5):
the energy ratio of each meal is shown in formula (6):
wherein u represents a type of meal per day of
B represents breakfast, l represents Chinese meal, d represents dinner,
referring to the recommended energy proportion of the u-th meal;
according to the menu data, the probability of dish formation is counted, as shown in formula (7):
wherein,
indicate the u th meal to pushThe recommended number of the food materials is determined,
the number of food materials which can be used as a dish is recommended by the u th meal.
4. The multi-objective optimization-based dietary nutrition collocation method of claim 1, wherein the objective function comprises: a daily nutrient element intake function, a food material dish forming probability function and a target optimization function;
the daily nutrient element intake function means that various nutrient elements in each day meet the intake requirements of users, and is shown in a formula (8):
wherein,
representing the weight of the user to the jth nutrient element on the day;
the food material dish formation probability function means that the food material recommended by each meal needs to be cooked as much as possible, as shown in formula (9):
wherein,
representing the probability of the u-th meal becoming a dish;
the objective optimization function is shown in formula (10):
wherein,
、
the number of the coefficients is represented by,
。
5. the multi-objective optimization-based dietary nutrition collocation method according to claim 1 or 4, wherein the S300 comprises:
s310, coarse recall: on the basis of the user data, normalizing food material labels respectively according to the occupation and the user preference of the user, then giving different weights to different types of labels, calculating recall probabilities of all recommendable food materials by adopting a weighting method, and sequencing the recall probabilities in a descending order to obtain a sequencing result;
s320, recall of essence: and recalling food materials by combining a menu based on the sequencing result to obtain the recalled food materials, judging whether the recalled food materials can be used as a dish according to the dish-forming probability, and selecting the food materials which can be used as a dish according to the judgment result.
6. The multi-objective optimization-based meal nutrition collocation method according to claim 1 or 4, wherein the S400 comprises:
s410, selecting food materials by using different strategies through the food material grading mechanism, and recalling a plurality of groups of first recommended food materials;
s420, aiming at the multiple groups of first recommended food materials, on the basis that the constraint conditions are met, solving by using a multi-stage layer-by-layer optimization algorithm in the multi-objective optimization algorithm to obtain second recommended food materials;
s430, summarizing the first recommended food material and the second recommended food material, creating a food material recommendation scoring rule to score the first recommended food material and the second recommended food material in a manual evaluation mode, and selecting the food material with the highest score to obtain an optimal diet recommendation scheme.
7. The multi-objective optimization-based dietary nutrition collocation method of claim 6, wherein the S420 comprises:
s421, in an initialization stage, solving the objective optimization function by using a greedy algorithm to obtain a solution with the least number of violated hard rules and the maximum objective optimization function as an initial solution;
s422, in a nutrient element optimization stage, solving is carried out aiming at the daily food material recommendation, a daily nutrient element intake function is solved by taking formulas (1) to (5) as constraint conditions, and a global search algorithm is adopted to carry out searching in a global range to obtain the optimal solution of the current nutrient element;
s423, in a sub-optimal meal stage, solving is carried out on energy calculation and dish forming probability of each meal, formulas (6) to (7) are used as constraint conditions, a food material dish forming probability function is solved, a local search algorithm is adopted to carry out rapid solving, and a sub-optimal solution of the current meal is obtained;
and S424, terminating the solution when the iteration times or the set time is reached, wherein the optimal solution of the current meal is the final optimal solution.
8. The multi-objective optimization-based dietary nutritional collocation method of claim 6, wherein the creating a food material recommended scoring rule to score the first recommended food material and the second recommended food material comprises: hard rules and soft constraints, the hard rules including base constraints corresponding to equations (1) through (6), the hard rules being non-violatible; the soft constraints are that the first recommended food material and the second recommended food material are scored according to rules such as occupation, user preference, current order, region and whether a single meal can be finished or not.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211181987.2A CN115359869A (en) | 2022-09-27 | 2022-09-27 | Multi-objective optimization-based dietary nutrition collocation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211181987.2A CN115359869A (en) | 2022-09-27 | 2022-09-27 | Multi-objective optimization-based dietary nutrition collocation method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115359869A true CN115359869A (en) | 2022-11-18 |
Family
ID=84007961
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211181987.2A Withdrawn CN115359869A (en) | 2022-09-27 | 2022-09-27 | Multi-objective optimization-based dietary nutrition collocation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115359869A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118170969A (en) * | 2024-02-27 | 2024-06-11 | 安迪泰麟医疗科技(北京)有限公司 | Nutrient collocation recommendation method and system |
-
2022
- 2022-09-27 CN CN202211181987.2A patent/CN115359869A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118170969A (en) * | 2024-02-27 | 2024-06-11 | 安迪泰麟医疗科技(北京)有限公司 | Nutrient collocation recommendation method and system |
| CN118170969B (en) * | 2024-02-27 | 2024-08-27 | 安迪泰麟医疗科技(北京)有限公司 | Nutrient collocation recommendation method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109524084A (en) | A kind of intelligent nutrition catering system and method for personal health management | |
| CN110265114A (en) | Nutrition intelligent management system | |
| KR20190009405A (en) | Automation Method for supplying customized menu | |
| CN109461491A (en) | A kind of intelligent nutrition catering system and method for family health care management | |
| CN106682433A (en) | Student dietary behavior analysis method based on campus card data | |
| CN111261260B (en) | Diet recommendation system | |
| CN112786154A (en) | Recipe recommendation method and device, electronic equipment and storage medium | |
| CN112348692A (en) | Order agricultural system based on nutrient demand required by health of consumers | |
| Verkaik-Kloosterman et al. | Decreased, but still sufficient, iodine intake of children and adults in the Netherlands | |
| CN115359869A (en) | Multi-objective optimization-based dietary nutrition collocation method | |
| CN111161838A (en) | Reasonable diet method suitable for students, expert system and client | |
| CN103729572A (en) | Generation method of personal healthy dietary prescription | |
| CN111554379A (en) | Healthy food recipe recommendation method and device and computer readable storage medium | |
| Balakrishna et al. | Identifying nutrient patterns in south African foods to support national nutrition guidelines and policies | |
| CN116434915A (en) | Management method and system for guaranteeing balanced dietary nutrition of children | |
| CN117253612A (en) | Resident diet quality and chronic disease risk condition evaluation method based on scoring model | |
| CN116130058A (en) | Recipe recommendation method based on intelligent diet | |
| Tóth et al. | Characterization of the protein and carbohydrate related quality traits of a large set of spelt wheat genotypes | |
| Pochmann et al. | Multi-objective bilevel recommender system for food diets | |
| CN116682533A (en) | Renal patient nutrition management method and system based on machine learning | |
| Meherunnahar et al. | Development of novel foxtail millet-based nutri-rich instant noodles: Chemical and quality characteristics | |
| Jachimowicz et al. | Pasta as a Source of Minerals in the Diets of Poles; Effect of Culinary Processing of Pasta on the Content of Minerals | |
| Roumia et al. | Ancient wheats—a nutritional and sensory analysis review | |
| CN110838356B (en) | Data processing method and device and storage medium | |
| CN108242262B (en) | Intelligent restaurant nutrition catering recommendation method based on dynamic diet period right |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20221118 |