CN114203281A - Meal recommendation method and meal recommendation device - Google Patents
Meal recommendation method and meal recommendation device Download PDFInfo
- Publication number
- CN114203281A CN114203281A CN202210081626.4A CN202210081626A CN114203281A CN 114203281 A CN114203281 A CN 114203281A CN 202210081626 A CN202210081626 A CN 202210081626A CN 114203281 A CN114203281 A CN 114203281A
- Authority
- CN
- China
- Prior art keywords
- preset
- theoretical
- nutrient
- meal
- information
- 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
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
- 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
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Primary Health Care (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Nutrition Science (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The embodiment of the invention discloses a diet recommending method and a diet recommending device, wherein the method comprises the following steps: determining a theoretical nutrient intake associated with the user; acquiring dish information, and determining dish nutrition information corresponding to the dish information; constructing an analysis model based on the theoretical nutrient intake and the dish nutrient information; obtaining a preset multi-order model solving rule; and processing the analysis model based on the preset multi-order model solving rule to generate a meal recommendation result. In the process of meal configuration, the existing meal configuration result is adjusted by combining the personal information of the user, the meal configuration of the user is analyzed by adopting a multi-order model, and the optimal solution is solved for the multi-order model by a least square method, so that the optimal solution for the non-linear coefficient multi-order model in the meal configuration scene is realized, the personalized optimal meal recommendation of the user is realized, and the rationality of the meal configuration and the accuracy of the meal recommendation are improved.
Description
Technical Field
The present invention relates to the field of information processing technologies, and in particular, to a meal recommendation method, a meal recommendation apparatus, and a computer-readable storage medium.
Background
Along with the continuous development of economy, the living standard of people is continuously improved, correspondingly, people put forward higher requirements on diet in life, and the diet concept of people is continuously changed.
In the conversion process, people tend to eat more nutritious food, but more dietary health problems are caused in the process of adopting more nutritious food, such as overnutrition, induction of chronic diseases and even death events can be caused due to unreasonable diet of people, and the annual increase of dietary disease events also makes people put higher requirements on the intake structure of diet.
In the existing dietary structure, according to the published documents or related dietary guidelines, the nutrition intake of general population often has a fixed proportion, however, in the practical application process, the prior art has at least the following technical problems:
on one hand, since the dietary intake is difficult to calculate accurately, the result of manual calculation may result in excessive intake of a certain nutrient element, such as excessive intake of carbohydrate or fat; in another case, after the establishment of the menu is completed, the actual requirements cannot be met no matter how the intake is adjusted;
on the other hand, it is difficult for a person to accurately adjust each person's intake amount because each person's theoretical intake amount is related to factors such as sex, labor intensity/work, height, weight, etc.
Disclosure of Invention
In order to solve the technical problems in the prior art, embodiments of the present invention provide a method for recommending a meal, which provides a more accurate and reasonable meal configuration for a user based on user information and a multi-order analysis model based on an existing meal configuration method, and recommends the meal configuration to the user, thereby improving the rationality of the meal configuration of the user, improving the accuracy of meal recommendation, and satisfying the actual needs of the user.
In order to achieve the above object, an embodiment of the present invention provides a recommendation method for a meal, including: determining a theoretical nutrient intake associated with the user; acquiring dish information, and determining dish nutrition information corresponding to the dish information; constructing an analysis model based on the theoretical nutrient intake and the dish nutrient information; obtaining a preset multi-order model solving rule; and processing the analysis model based on the preset multi-order model solving rule to generate a meal recommendation result.
Preferably, the determining a theoretical nutrient intake associated with the user comprises: acquiring user information; determining a corresponding theoretical intake caloric value based on the user information; generating a theoretical nutrient intake for the user based on preset nutrient calculation rules and the theoretical caloric intake, the theoretical nutrient intake comprising theoretical intake values for a plurality of nutrient elements.
Preferably, the vegetable nutrition information includes contents of different nutrient elements in the vegetable, and the constructing an analysis model based on the theoretical nutrient intake and the vegetable nutrition information includes: acquiring the recommended quantity of preset dishes; determining configuration weight representation information of different dishes based on the preset recommended quantity of the dishes; constructing a multi-order model based on the configured weight representation information of different dishes, the theoretical nutrient intake and the content of each nutrient element in different dishes, wherein the order of the multi-order model corresponds to the number of the nutrient elements to be analyzed; using the multi-order model as the analysis model.
Preferably, the preset multi-order model solution rule is a least square method, and the processing the analysis model based on the preset multi-order model solution rule to generate the meal recommendation result includes: acquiring a preset constraint condition; solving the analysis model based on the least square method and the preset constraint condition to generate the configuration weights of different dishes under the preset dish recommended quantity; generating a corresponding meal recommendation based on the configured weight.
Preferably, the method further comprises: after the meal recommendation result is generated, acquiring a preset optimization rule; determining corresponding optimization parameters based on the preset optimization rules; and optimizing the diet recommendation result based on the optimization parameters to generate an optimized recommendation result.
Preferably, the preset optimization rule is an accumulated error calculation rule, the optimization parameter is an accumulated error corresponding to the meal recommendation result, and the optimizing the meal recommendation result based on the optimization parameter to generate an optimized recommendation result includes: acquiring a preset error threshold; judging whether the accumulated error is larger than the preset error threshold value or not; and if so, reconstructing the analysis model, and generating an optimized recommendation result based on the reconstructed analysis model.
Correspondingly, the invention also provides a recommendation device for meals, which comprises: a first determination unit for determining a theoretical nutrient intake associated with a user; the second determining unit is used for acquiring the dish information and determining the dish nutrition information corresponding to the dish information; the model construction unit is used for constructing an analysis model based on the theoretical nutrient intake and the dish nutrient information; the solving rule obtaining unit is used for obtaining a preset multi-order model solving rule; and the recommending unit is used for processing the analysis model based on the preset multi-order model solving rule to generate a diet recommending result.
Preferably, the first determination unit includes: the user information acquisition module is used for acquiring user information; an intake calorie determination module for determining a corresponding theoretical intake calorie based on the user information; a theoretical intake determination module to generate a theoretical nutrient intake for the user based on a preset nutrient calculation rule and the theoretical ingested calories, the theoretical nutrient intake comprising theoretical ingested values of a plurality of nutrient elements.
Preferably, the dish nutrition information includes contents of different nutrient elements in the dish, and the model construction unit includes: the quantity obtaining module is used for obtaining the recommended quantity of preset dishes; the configuration weight determining module is used for determining configuration weight representation information of different dishes based on the preset recommended quantity of the dishes; the model building module is used for building a multi-order model based on the configured weight representation information of different dishes, the theoretical nutrient intake and the content of each nutrient element in the different dishes, and the order of the multi-order model corresponds to the number of the nutrient elements to be analyzed; a model determination module for using the multi-order model as the analysis model.
Preferably, the preset multi-order model solution rule is a least square method, and the recommending unit includes: the constraint condition acquisition module is used for acquiring a preset constraint condition; the model solving module is used for solving the analysis model based on the least square method and the preset constraint condition to generate the configuration weights of different dishes under the preset dish recommended quantity; and the recommending module is used for generating a corresponding diet recommending result based on the configured weight.
Preferably, the apparatus further comprises an optimization unit, the optimization unit being specifically configured to: after the meal recommendation result is generated, acquiring a preset optimization rule; determining corresponding optimization parameters based on the preset optimization rules; and optimizing the diet recommendation result based on the optimization parameters to generate an optimized recommendation result.
Preferably, the preset optimization rule is an accumulated error calculation rule, the optimization parameter is an accumulated error corresponding to the meal recommendation result, and the optimizing the meal recommendation result based on the optimization parameter to generate an optimized recommendation result includes: acquiring a preset error threshold; judging whether the accumulated error is larger than the preset error threshold value or not; and if so, reconstructing the analysis model, and generating an optimized recommendation result based on the reconstructed analysis model.
In another aspect, the present invention also provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the method provided by the present invention.
Through the technical scheme provided by the invention, the invention at least has the following technical effects:
by improving the existing meal recommendation method, in the process of meal configuration, the existing meal configuration result is adjusted by combining personal information of the user, the meal configuration of the user is analyzed by adopting a multi-order model, and the optimal solution is solved for the multi-order model by the least square method, so that the optimal solution for the non-linear coefficient multi-order model under the meal configuration scene is realized, the personalized optimal meal recommendation of the user is realized, the rationality of the meal configuration is improved, and the accuracy of the meal recommendation is improved.
Additional features and advantages of embodiments of the invention will be set forth in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the embodiments of the invention without limiting the embodiments of the invention. In the drawings:
fig. 1 is a flowchart of a specific implementation of a method for recommending a meal according to an embodiment of the present invention;
FIG. 2 is a flowchart of an embodiment of building an analysis model in a meal recommendation method according to an embodiment of the present invention;
fig. 3 is a flowchart illustrating a specific implementation of generating a recommendation result of a meal in a recommendation method for a meal according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a meal recommendation device provided by an embodiment of the invention.
Detailed Description
In order to solve the technical problems in the prior art, embodiments of the present invention provide a method for recommending a meal, which performs targeted intelligent analysis and calculation according to actual personal information of a user on the basis of an existing method for recommending a meal by using a manual calculation manner or a method for determining meal recommendation according to a fixed calculation manner, thereby providing a more accurate meal recommendation result, improving recommendation accuracy, satisfying the actual needs of the user, and improving the rationality of meal matching.
The following detailed description of embodiments of the invention refers to the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating embodiments of the invention, are given by way of illustration and explanation only, not limitation.
The terms "system" and "network" in embodiments of the present invention may be used interchangeably. The "plurality" means two or more, and in view of this, the "plurality" may also be understood as "at least two" in the embodiments of the present invention. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" generally indicates that the preceding and following related objects are in an "or" relationship, unless otherwise specified. In addition, it should be understood that the terms first, second, etc. in the description of the embodiments of the invention are used for distinguishing between the descriptions and are not intended to indicate or imply relative importance or order to be construed.
Referring to fig. 1, an embodiment of the present invention provides a method for recommending a meal, including:
s10) determining a theoretical nutrient intake associated with the user;
s20) acquiring dish information, and determining dish nutrition information corresponding to the dish information;
s30) constructing an analysis model based on the theoretical nutrition intake and the dish nutrition information;
s40) obtaining a preset multi-order model solving rule;
s50) processing the analysis model based on the preset multi-order model solution rule to generate a meal recommendation result.
In order to provide healthier diet recommendation for users, the existing diet recommendation method is improved, because the general nutrient intake requirements for Chinese residents are recorded in the existing public data, such as Chinese resident diet guidelines:
1) carbohydrate intake for three meals: 3:4: 3;
2) caloric intake ratio of three meals: 3:4: 3;
3) the calorie accounts for the three nutrient elements which are taken in are respectively as follows: 50-65% of carbohydrate, 10-15% of protein and 20-30% of fat.
The above disclosure can perform rapid preliminary determination on the dietary intake of each user, and compared with the conventional manual determination method, the method can effectively improve the efficiency and accuracy of dietary recommendation and reduce the influence caused by subjective deviation, so in a possible implementation manner, first determining a theoretical nutritional intake related to the user, for example, in an embodiment of the present invention, the determining the theoretical nutritional intake related to the user includes: acquiring user information; determining a corresponding theoretical intake caloric value based on the user information; generating a theoretical nutrient intake for the user based on preset nutrient calculation rules and the theoretical caloric intake, the theoretical nutrient intake comprising theoretical intake values for a plurality of nutrient elements.
Specifically, first, user information is obtained, where the user information includes, but is not limited to, height, weight, sex, labor intensity, and the like of the user, and then, the theoretical intake calorie of the user is determined according to the user information, the determination process may be determined according to a public calorie calculation formula, and at this time, the theoretical intake calorie of the user is further determined according to a preset nutrition calculation rule and the theoretical intake calorie calculation, for example, the preset nutrition calculation rule may be characterized as:
the amount of protein (g) ideally taken per day is 15%/4 of the calorie ideally taken;
ideal intake of fat per day (g) ═ ideal intake of calories 25%/9;
ideal intake of carbohydrate per day (g) ═ ideal intake of calories 60%/4;
the remaining micronutrients may be empirically assigned a corresponding desired intake comprising theoretical intakes of a plurality of nutrient elements including, but not limited to, calories, carbohydrates, proteins, fats, vitamins, cellulose, calcium, iron, and the like. At this time, the nutritional information of the dish to be ingested is further determined.
In the embodiment of the invention, the existing meal recommendation method is improved, the actually needed heat of the user is rapidly calculated by combining the existing nutrition calculation method according to the actual personal information of the user, and the theoretical nutrition intake of the user is further determined, so that the calculation accuracy of the nutrition intake of the user is effectively improved, the calculation result is more in line with the actual requirement of each user, the rationality of meal collocation is improved, and the meal health of the user is guaranteed.
Referring to fig. 2, in an embodiment of the present invention, the dish nutrition information includes contents of different nutrient elements in a dish, and the constructing an analysis model based on the theoretical nutrient intake and the dish nutrition information includes:
s21) acquiring the recommended quantity of preset dishes;
s22) determining configuration weight representation information of different dishes based on the preset recommended quantity of the dishes;
s23) constructing a multi-stage model based on the configured weight representation information of different dishes, the theoretical nutrient intake and the content of each nutrient element in different dishes, wherein the order of the multi-stage model corresponds to the number of the nutrient elements to be analyzed;
s24) using the multi-order model as the analytical model.
In a possible embodiment, the dish information is a set of all dishes that can be ingested by the user, the set of dishes can be provided by the user actively, or can be provided by a professional physician or a nutrition specialist after being evaluated according to the actual physical condition of the user, and the corresponding dish nutrition information is determined according to the dish information, specifically, the dish nutrition information includes the content of different nutrient elements in different dishes, for example, in an embodiment, the dish nutrition information is the weight (for example, g or mg) of each unit weight (for example, kg) of nutrient elements such as calorie, carbohydrate, protein, fat, vitamin a, vitamin B, vitamin C, cellulose, calcium, iron and the like in each dish, and then an analysis model is further constructed according to the theoretical nutrient intake and the dish nutrition information, namely in the embodiment of the present invention, and constructing a corresponding analysis model aiming at each user, thereby providing a meal recommendation result meeting the individual requirements of each user.
Specifically, a preset recommended number of dishes is first obtained, for example in one embodiment,the preset recommendation quantity of the dishes is 7, and further, the configuration weight representation information of different dishes is determined according to the preset recommended quantity of the dishes, for example, the configuration weight of each dish can be represented by x, wherein the configuration weight of the first dish can be represented by x1The second is x2… at this time, a multi-step model is constructed according to the weight characterization information, the theoretical nutrient intake and the content of each nutrient element, for example, in one embodiment, the recommended meal result corresponding to 4 nutrient elements needs to be determined for the user, and the theoretical intake of the 4 nutrient elements can be characterized as y1、y2、y3、y4Then the above multi-order model can be characterized as:
a1x1+a2x2+a3x3+a4x4+a5x5+a6x6+a7x7＝y1；
b1x1+b2x2+b3x3+b4x4+b5x5+b6x6+b7x7＝y2；
c1x1+c2x2+c3x3+c4x4+c5x5+c6x6+c7x7＝y3；
d1x1+d2x2+d3x3+d4x4+d5x5+d6x6+d7x7＝y4；
the a, b, c and d respectively represent the content of the elements in the 4 in the corresponding dishes, and it can be seen that in the actual calculation process, a model constructed according to the actual nutrition intake requirement of the user, the recommended quantity of the dishes and the theoretical nutrition intake is a multi-order model, and for those skilled in the art, it is easy to know that, for example, for the ternary-one-order problem, if three unknowns exist, three equations are correspondingly provided, then a unique solution can be solved; if the three unknowns correspond to two equations, an infinite solution exists; if there are four equations corresponding to the three unknowns (the coefficients of the equations are non-linear), then there is no solution. Therefore, the corresponding meal recommendation result cannot be calculated according to the actual demand of the user by adopting the traditional calculation method or the traditional solution method.
Referring to fig. 3, in an embodiment of the present invention, the preset multi-order model solution rule is a least square method, and the processing the analysis model based on the preset multi-order model solution rule to generate the meal recommendation result includes:
s51) acquiring preset constraint conditions;
s52) solving the analysis model based on the least square method and the preset constraint condition to generate the configuration weights of different dishes under the preset dish recommended quantity;
s53) generating a corresponding meal recommendation based on the configured weight.
In order to further improve the accuracy of the final meal recommendation result, in a possible implementation manner, a preset constraint condition is obtained first, for example, in an embodiment of the present invention, according to the summary of the actual meal configuration experience, the weight of all dishes is constrained to be greater than 50g, that is, all x are greater than 50g, on the basis, the analysis model is further solved by using a least square method and the preset constraint condition to generate the configuration weights of different dishes in the preset dish recommendation number, and at this time, the corresponding dish recommendation result is generated according to the configuration weight of each dish.
In the embodiment of the invention, the multi-order model is solved by adopting the least square method, so that the corresponding optimal solution can be generated aiming at the nonlinear coefficient multi-order model solving process of the diet configuration, the technical effect of accurately recommending the diet for the user under the limited condition is effectively realized, and the actual requirements of the user are met.
However, in the actual application process, the solution obtained by the above solution method may not meet the actual needs of the user, that is, there may be a large deviation, so in order to further improve the accuracy of the meal configuration recommendation, it is also necessary to perform validity analysis on the recommendation result, and perform further optimization when the configuration is not reasonable, so as to improve the meal configuration accuracy.
In an embodiment of the present invention, the method further comprises: after the meal recommendation result is generated, acquiring a preset optimization rule; determining corresponding optimization parameters based on the preset optimization rules; and optimizing the diet recommendation result based on the optimization parameters to generate an optimized recommendation result.
Further, in this embodiment of the present invention, the preset optimization rule is an accumulated error calculation rule, the optimization parameter is an accumulated error corresponding to the meal recommendation result, and the optimizing the meal recommendation result based on the optimization parameter to generate an optimized recommendation result includes: acquiring a preset error threshold; whether the accumulated error is greater than the preset error threshold value; and if so, reconstructing the analysis model, and generating an optimized recommendation result based on the reconstructed analysis model.
In a possible embodiment, after solving the analysis model of the user by the least square method and obtaining the corresponding meal recommendation result, further obtaining a preset optimization rule, and determining the corresponding optimization parameter according to the preset optimization rule, for example, in an embodiment of the present invention, the optimization rule is a calculation rule for calculating an accumulated error of the meal recommendation result, for example, the configured weights of the dishes in 4 calculated according to the multi-step model are y1, y2, y3, and y4, respectively, then:
accumulated error (y1-y 1)2+(y2-y2*)2+(y3-y3*)2+(y4-y4*)2；
At this time, a preset error threshold is obtained, whether the calculated accumulated error is larger than the preset error threshold is judged, if yes, it can be determined that the analysis model needs to be reconstructed, for example, the intake of the dishes to be configured and each kind of dishes can be adjusted to obtain the optimized recommendation result again until the final recommendation result meets the optimization rule, so as to realize effective diet recommendation.
In the embodiment of the invention, after the diet recommendation is carried out, the effectiveness and the accuracy of the diet recommendation result are automatically monitored and optimized in time, so that the diet recommendation result recommended for the user is effectively ensured to meet the actual requirements of the user, the recommendation accuracy is improved, and the diet health degree of the user is improved.
The following describes a meal recommendation device provided by an embodiment of the invention with reference to the accompanying drawings.
Referring to fig. 4, based on the same inventive concept, an embodiment of the present invention provides a meal recommendation device, including: a first determination unit for determining a theoretical nutrient intake associated with a user; the second determining unit is used for acquiring the dish information and determining the dish nutrition information corresponding to the dish information; the model construction unit is used for constructing an analysis model based on the theoretical nutrient intake and the dish nutrient information; the solving rule obtaining unit is used for obtaining a preset multi-order model solving rule; and the recommending unit is used for processing the analysis model based on the preset multi-order model solving rule to generate a diet recommending result.
In an embodiment of the present invention, the first determining unit includes: the user information acquisition module is used for acquiring user information; an intake calorie determination module for determining a corresponding theoretical intake calorie based on the user information; a theoretical intake determination module to generate a theoretical nutrient intake for the user based on a preset nutrient calculation rule and the theoretical ingested calories, the theoretical nutrient intake comprising theoretical ingested values of a plurality of nutrient elements.
In an embodiment of the present invention, the dish nutrition information includes contents of different nutrient elements in a dish, and the model building unit includes: the quantity obtaining module is used for obtaining the recommended quantity of preset dishes; the configuration weight determining module is used for determining configuration weight representation information of different dishes based on the preset recommended quantity of the dishes; the model building module is used for building a multi-order model based on the configured weight representation information of different dishes, the theoretical nutrient intake and the content of each nutrient element in the different dishes, and the order of the multi-order model corresponds to the number of the nutrient elements to be analyzed; a model determination module for using the multi-order model as the analysis model.
In an embodiment of the present invention, the predetermined multi-order model solution rule is a least square method, and the recommendation unit includes: the constraint condition acquisition module is used for acquiring a preset constraint condition; the model solving module is used for solving the analysis model based on the least square method and the preset constraint condition to generate the configuration weights of different dishes under the preset dish recommended quantity; and the recommending module is used for generating a corresponding diet recommending result based on the configured weight.
In an embodiment of the present invention, the apparatus further includes an optimization unit, where the optimization unit is specifically configured to: after the meal recommendation result is generated, acquiring a preset optimization rule; determining corresponding optimization parameters based on the preset optimization rules; and optimizing the diet recommendation result based on the optimization parameters to generate an optimized recommendation result.
In an embodiment of the present invention, the preset optimization rule is an accumulated error calculation rule, the optimization parameter is an accumulated error corresponding to the meal recommendation result, and the optimizing the meal recommendation result based on the optimization parameter to generate an optimized recommendation result includes: acquiring a preset error threshold; judging whether the accumulated error is larger than the preset error threshold value or not; and if so, reconstructing the analysis model, and generating an optimized recommendation result based on the reconstructed analysis model.
Further, an embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the method of the present invention.
Although the embodiments of the present invention have been described in detail with reference to the accompanying drawings, the embodiments of the present invention are not limited to the details of the above embodiments, and various simple modifications can be made to the technical solutions of the embodiments of the present invention within the technical idea of the embodiments of the present invention, and the simple modifications all belong to the protection scope of the embodiments of the present invention.
It should be noted that the various features described in the above embodiments may be combined in any suitable manner without departing from the scope of the invention. In order to avoid unnecessary repetition, the embodiments of the present invention do not describe every possible combination.
Those skilled in the art will understand that all or part of the steps in the method according to the above embodiments may be implemented by a program, which is stored in a storage medium and includes several instructions to enable a single chip, a chip, or a processor (processor) to execute all or part of the steps in the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In addition, any combination of various different implementation manners of the embodiments of the present invention is also possible, and the embodiments of the present invention should be considered as disclosed in the embodiments of the present invention as long as the combination does not depart from the spirit of the embodiments of the present invention.
Claims (13)
1. A method for recommending meals, said method comprising:
determining a theoretical nutrient intake associated with the user;
acquiring dish information, and determining dish nutrition information corresponding to the dish information;
constructing an analysis model based on the theoretical nutrient intake and the dish nutrient information;
obtaining a preset multi-order model solving rule;
and processing the analysis model based on the preset multi-order model solving rule to generate a meal recommendation result.
2. The method of claim 1, wherein determining a theoretical nutrient intake associated with the user comprises:
acquiring user information;
determining a corresponding theoretical intake caloric value based on the user information;
generating a theoretical nutrient intake for the user based on preset nutrient calculation rules and the theoretical caloric intake, the theoretical nutrient intake comprising theoretical intake values for a plurality of nutrient elements.
3. The method of claim 1, wherein the meal nutritional information comprises content of different nutrient elements in a meal, and wherein constructing an analytical model based on the theoretical nutrient intake and the meal nutritional information comprises:
acquiring the recommended quantity of preset dishes;
determining configuration weight representation information of different dishes based on the preset recommended quantity of the dishes;
constructing a multi-order model based on the configured weight representation information of different dishes, the theoretical nutrient intake and the content of each nutrient element in different dishes, wherein the order of the multi-order model corresponds to the number of the nutrient elements to be analyzed;
using the multi-order model as the analysis model.
4. The method of claim 3, wherein the predetermined multi-step model solution rule is a least squares method, and wherein processing the analytical model based on the predetermined multi-step model solution rule to generate the meal recommendation comprises:
acquiring a preset constraint condition;
solving the analysis model based on the least square method and the preset constraint condition to generate the configuration weights of different dishes under the preset dish recommended quantity;
generating a corresponding meal recommendation based on the configured weight.
5. The method of claim 4, further comprising:
after the meal recommendation result is generated, acquiring a preset optimization rule;
determining corresponding optimization parameters based on the preset optimization rules;
and optimizing the diet recommendation result based on the optimization parameters to generate an optimized recommendation result.
6. The method of claim 5, wherein the preset optimization rule is an accumulated error calculation rule, the optimization parameter is an accumulated error corresponding to the meal recommendation result, and the optimizing the meal recommendation result based on the optimization parameter to generate an optimized recommendation result comprises:
acquiring a preset error threshold;
judging whether the accumulated error is larger than the preset error threshold value or not;
and if so, reconstructing the analysis model, and generating an optimized recommendation result based on the reconstructed analysis model.
7. A recommendation device for a meal, the device comprising:
a first determination unit for determining a theoretical nutrient intake associated with a user;
the second determining unit is used for acquiring the dish information and determining the dish nutrition information corresponding to the dish information;
the model construction unit is used for constructing an analysis model based on the theoretical nutrient intake and the dish nutrient information;
the solving rule obtaining unit is used for obtaining a preset multi-order model solving rule;
and the recommending unit is used for processing the analysis model based on the preset multi-order model solving rule to generate a diet recommending result.
8. The apparatus according to claim 7, wherein the first determining unit comprises:
the user information acquisition module is used for acquiring user information;
an intake calorie determination module for determining a corresponding theoretical intake calorie based on the user information;
a theoretical intake determination module to generate a theoretical nutrient intake for the user based on a preset nutrient calculation rule and the theoretical ingested calories, the theoretical nutrient intake comprising theoretical ingested values of a plurality of nutrient elements.
9. The apparatus of claim 7, wherein the dish nutrition information comprises contents of different nutrient elements in a dish, and the model construction unit comprises:
the quantity obtaining module is used for obtaining the recommended quantity of preset dishes;
the configuration weight determining module is used for determining configuration weight representation information of different dishes based on the preset recommended quantity of the dishes;
the model building module is used for building a multi-order model based on the configured weight representation information of different dishes, the theoretical nutrient intake and the content of each nutrient element in the different dishes, and the order of the multi-order model corresponds to the number of the nutrient elements to be analyzed;
a model determination module for using the multi-order model as the analysis model.
10. The apparatus of claim 9, wherein the predetermined multi-order model solution rule is a least squares method, and the recommending unit comprises:
the constraint condition acquisition module is used for acquiring a preset constraint condition;
the model solving module is used for solving the analysis model based on the least square method and the preset constraint condition to generate the configuration weights of different dishes under the preset dish recommended quantity;
and the recommending module is used for generating a corresponding diet recommending result based on the configured weight.
11. The apparatus according to claim 10, further comprising an optimization unit, the optimization unit being specifically configured to:
after the meal recommendation result is generated, acquiring a preset optimization rule;
determining corresponding optimization parameters based on the preset optimization rules;
and optimizing the diet recommendation result based on the optimization parameters to generate an optimized recommendation result.
12. The apparatus of claim 11, wherein the preset optimization rule is an accumulated error calculation rule, the optimization parameter is an accumulated error corresponding to the meal recommendation result, and the optimizing the meal recommendation result based on the optimization parameter to generate an optimized recommendation result comprises:
acquiring a preset error threshold;
judging whether the accumulated error is larger than the preset error threshold value or not;
and if so, reconstructing the analysis model, and generating an optimized recommendation result based on the reconstructed analysis model.
13. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210081626.4A CN114203281A (en) | 2022-01-24 | 2022-01-24 | Meal recommendation method and meal recommendation device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210081626.4A CN114203281A (en) | 2022-01-24 | 2022-01-24 | Meal recommendation method and meal recommendation device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114203281A true CN114203281A (en) | 2022-03-18 |
Family
ID=80658788
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210081626.4A Pending CN114203281A (en) | 2022-01-24 | 2022-01-24 | Meal recommendation method and meal recommendation device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114203281A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020230123A1 (en) * | 2019-05-12 | 2020-11-19 | Makesense Digital Health Technologies Ltd. | A system and a method for health and diet management and nutritional monitoring |
| CN112148969A (en) * | 2020-08-24 | 2020-12-29 | 毛端中 | Meal recommendation method and device, computer equipment and storage medium |
| US20210319887A1 (en) * | 2015-05-20 | 2021-10-14 | Amuseneering Technologies, Llc | Method of treating diabetes informed by social determinants of health |
| CN113903430A (en) * | 2021-10-29 | 2022-01-07 | 武汉宇科天创网络科技有限公司 | Method and system for recommending healthy meals |
-
2022
- 2022-01-24 CN CN202210081626.4A patent/CN114203281A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210319887A1 (en) * | 2015-05-20 | 2021-10-14 | Amuseneering Technologies, Llc | Method of treating diabetes informed by social determinants of health |
| WO2020230123A1 (en) * | 2019-05-12 | 2020-11-19 | Makesense Digital Health Technologies Ltd. | A system and a method for health and diet management and nutritional monitoring |
| CN112148969A (en) * | 2020-08-24 | 2020-12-29 | 毛端中 | Meal recommendation method and device, computer equipment and storage medium |
| CN113903430A (en) * | 2021-10-29 | 2022-01-07 | 武汉宇科天创网络科技有限公司 | Method and system for recommending healthy meals |
Non-Patent Citations (1)
| Title |
|---|
| 丁振良主编: "《误差理论与数据处理》", 28 February 2015 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Guyomard et al. | Eating patterns and food systems: critical knowledge requirements for policy design and implementation | |
| CN101373486B (en) | A Personalized Summary System Based on User Interest Model | |
| CN108806770A (en) | A kind of diet recommendation method based on user | |
| CN112786154A (en) | Recipe recommendation method and device, electronic equipment and storage medium | |
| CN103577671A (en) | Method and system for generating personalized meal schemes | |
| BRPI0918261B1 (en) | process for selecting a food product based on the effect of the food product on the health of a human being, data processing system for selecting a food product based on the effect of the food product on the health of a human being, and process for controlling body weight in a human being | |
| JP6410069B1 (en) | Recipe information providing apparatus, recipe information providing method, and recipe information providing program | |
| Chen et al. | A smart kitchen for nutrition-aware cooking | |
| CN113140287A (en) | Recipe recommendation method and device and electronic equipment | |
| JP2019133624A (en) | Recipe information provision apparatus, recipe information provision method, and recipe information provision program | |
| CN117976145A (en) | A personal long-term dietary recommendation supervision method, system, terminal and storage medium | |
| CN110762571A (en) | Recipe recommendation method based on cooking oil smoke and range hood | |
| CN110853735A (en) | Method and device for analyzing intake of dietary component, computer device and storage medium | |
| JP2012203834A (en) | Menu presentation system and menu presentation method and program | |
| JP4237695B2 (en) | Recipe customization support system and method | |
| EP2787459A1 (en) | Method of monitoring nutritional intake by image processing | |
| CN114203281A (en) | Meal recommendation method and meal recommendation device | |
| Probst et al. | First-stage development and validation of a web-based automated dietary modeling tool: using constraint optimization techniques to streamline food group and macronutrient focused dietary prescriptions for clinical trials | |
| CN118800401A (en) | Intelligent nutrition assessment and dietary intervention system for people with hypertension and hyperglycemia | |
| CN112133434A (en) | Dietary habit-based hyperlipidemia auxiliary diagnosis system, device and storage medium | |
| Rajikan et al. | Construction of healthy and palatable diet for low socioeconomic female adults using linear programming | |
| CN111009307A (en) | Recipe data recommendation method and system and household appliance | |
| CN117786202A (en) | Method and device for recommending diet and refrigerator | |
| CN112102922B (en) | Information recommendation method and device | |
| Sobralske | Olakino Maika’i: health care in Pacific Island culture |
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 |