KR20240102200A - Method And Apparatus for Recommending Customized Diet by Using Personal Questionnaire Information - Google Patents

Abstract

A customized diet recommendation method and device using personal questionnaire information is disclosed.
In this embodiment, based on personal questionnaires (individual questions and answers), the recommended diet is divided into multiple groups and organized into categories, and the recommended diet is again recommended using personal information (gender, age, preference, etc.) based on the multiple groups. We provide a customized diet recommendation method and device using personal questionnaire information that can be used as basic data in an engine to generate recommended diets tailored to individual tendencies.

Description

Method and Apparatus for Recommending Customized Diet by Using Personal Questionnaire Information}

One embodiment of the present invention relates to a method and device for recommending a customized diet using personal questionnaire information.

The content described below simply provides background information related to this embodiment and does not constitute prior art.

Recently, personalized diets and foods have become popular, but the classification system for personalized diets is often fragmented and limited to regions, including genetic selection methods, age, gender, and region. However, with the development of transportation and the Internet, preference for foods from outside the region and tourist destinations is increasing, and the target of individual food preferences is broadening to a wider range than foods produced locally.

Conventionally, there are various methods for recommending an individual's preferred foods and healthy foods.

As the number of single-person households increases, a customized meal recommendation service for single-person households is becoming necessary. Food waste caused by leftover food ingredients is recognized as a social problem. Recently, in response to the expansion of O2O (Online to Offline)-based mobile shopping and the continuous increase in grocery and agricultural, livestock and marine product transactions on mobile devices, the need for food ingredient delivery services is increasing.

As we enter the aging era, the problem of low birth rate has begun to emerge as a social problem. Various support policies and social consideration policies for pregnant women are being implemented. Policy support measures can only be applied uniformly, but it is difficult to consider them as personal support measures in terms of actual pregnant women's eating habits or health management.

As there are no nutritional guidelines for healthy foods or foods consumed by pregnant women, a system is needed to simultaneously support the health of the fetus and the health of the pregnant woman.

There are also online knowledge data recommended by special professionals such as nutritionists and diet recommendation algorithms based on the diets of dietitians of the same group, but there is a problem in that they only suggest recommended diets based on region, age, and special environment.

In this embodiment, based on personal questionnaires (individual questions and answers), the recommended diet is divided into multiple groups and organized into categories, and the recommended diet is again recommended using personal information (gender, age, preference, etc.) based on the multiple groups. We provide a customized diet recommendation method and device using personal questionnaire information that can be used as basic data in an engine to generate recommended diets tailored to individual tendencies.

According to one aspect of the present embodiment, a questionnaire unit that transmits pre-generated personal questionnaire data to a plurality of user terminals; A type classification unit that classifies user types based on questionnaire result data including answers corresponding to the questionnaire data received from the user terminal; a grouping unit that creates a group by grouping the user types by the same type; a diet recommendation unit that generates diet recommendation information including necessary nutrient information for each group; A feedback unit that transmits the dietary recommendation information to the user terminal corresponding to the group and receives re-examination result data including preference diet feedback for the dietary recommendation information from the user terminal. Characterized in comprising a. Provides a diet recommendation device.

As described above, according to this embodiment, based on the personal questionnaire (individual questions and answers), the individual is divided into a plurality of groups and organized into categories, and personal information (gender, age, preferences, etc.) is collected based on the plurality of groups. This has the effect of providing recommended diets tailored to each individual's personality by using it as basic data in an engine that recommends recommended diets.

According to this embodiment, the preference for the recommended personal diet can be increased by analyzing personal tendencies and preferences based on the items of the personal questionnaire, which has the effect of securing the sustainability of the diet.

According to this embodiment, there is an effect in that an individual can secure a preference and interest in the diet and link it with other industries for predictable results such as additional services (obesity control, anemia, etc.) by securing the preferred diet.

Figure 1 is a diagram showing a customized diet recommendation system using personal questionnaire information according to this embodiment.
Figure 2 is a block diagram schematically showing a diet recommendation device according to this embodiment.
Figure 3 is a diagram for explaining the method of extracting necessary nutrients based on a questionnaire according to this embodiment.
Figure 4 is a diagram showing group modeling according to input values for each required nutrient according to this embodiment.
Figure 5 is a diagram showing a recommendation algorithm based on grouping and dietary nutrients according to this embodiment.
Figure 6 is a diagram showing diet recommendations according to priority according to this embodiment.

Hereinafter, this embodiment will be described in detail with reference to the attached drawings.

Figure 1 is a diagram showing a customized diet recommendation system using personal questionnaire information according to this embodiment.

The customized diet recommendation system according to this embodiment includes a user terminal 110, a network 120, and a diet recommendation device 130. The components included in the customized diet recommendation system are not necessarily limited to this.

The user terminal 110 refers to an electronic device that can receive various web page data via the network 120 according to the user's key operations. The user terminal 110 includes a tablet PC, a laptop, a personal computer (PC), a smart phone, a personal digital assistant (PDA), and a mobile communication terminal. (Mobile Communication Terminal), etc.

The user terminal 110 refers to a terminal equipped with a memory for storing an application for accessing the diet recommendation device 130 in conjunction with the network 120 and a microprocessor for calculating and controlling the program by executing it. .

The user terminal 110 is generally a personal PC, but includes any terminal connected to the network 120 and capable of server-client communication with the diet recommendation device 130.

The user terminal 110 according to this embodiment receives medical examination data from the diet recommendation device 130 via the network 120. The user terminal 110 generates questionnaire result data including answers corresponding to the questionnaire data by a user's command or operation. The user terminal 110 transmits the questionnaire result data to the diet recommendation device 130 via the network 120.

The user terminal 110 receives diet recommendation information from the diet recommendation device 130 via the network 120. The user terminal 110 generates feedback information reflecting preferences for dietary recommendation information through the user's command or manipulation. The user terminal 110 transmits feedback information to the diet recommendation device 130 via the network 120.

The user terminal 110 receives re-examination data from the diet recommendation device 130 via the network 120. The user terminal 110 generates re-questionnaire result data including answers corresponding to the re-questionnaire data by a user's command or operation. The user terminal 110 transmits the re-interrogation result data to the diet recommendation device 130 via the network 120.

The network 120 refers to a network that can transmit and receive data using the Internet protocol using various wired and wireless communication technologies such as the Internet network, intranet network, mobile communication network, and satellite communication network.

The diet recommendation device 130 includes the same hardware module as a typical web server or network server. The diet recommendation device 130 may be implemented in the form of a web server or network server. The diet recommendation device 130 generally communicates with an unspecified number of clients or other servers via an open computer network such as the Internet.

The diet recommendation device 130 refers to a computer system and computer software (web server program) that derives and provides task results corresponding to task performance requests from a client or other web server. In addition to the above-described web server program, the diet recommendation device 130 includes a series of application programs running on a web server or various databases built inside the device.

The diet recommendation device 130 according to this embodiment classifies user types (type a, type b, type c, type d, etc.) based on questionnaire information (height, weight, age, blood type, etc.). The diet recommendation device 130 generates and recommends diet recommendation information for each user type. The diet recommendation device 130 recommends diet recommendation information and then performs a follow-up interview after a certain period of time has elapsed.

The diet recommendation device 130 classifies user types based on questionnaire information. The diet recommendation device 130 receives the repeat questionnaire information and classifies the user type again.

The diet recommendation device 130 transmits pre-generated personal questionnaire data to a plurality of user terminals 110. The diet recommendation device 130 classifies the user type based on questionnaire result data including answers corresponding to the questionnaire data received from the user terminal 110. The diet recommendation device 130 creates a group that groups user types by the same type. The diet recommendation device 130 generates diet recommendation information including necessary nutrient information for each group. The diet recommendation device 130 transmits diet recommendation information to the user terminal 110 corresponding to the group. The diet recommendation device 130 receives re-examination result data including preference diet feedback for diet recommendation information from the user terminal 110.

Figure 2 is a block diagram schematically showing a diet recommendation device according to this embodiment.

The diet recommendation device 130 according to this embodiment includes a questionnaire unit 210, a type classification unit 220, a grouping unit 230, a diet recommendation unit 240, and a feedback unit 250. Components included in the diet recommendation device 130 are not necessarily limited thereto.

Each component included in the diet recommendation device 130 is connected to a communication path connecting software modules or hardware modules within the device and can operate organically with each other. These components communicate using one or more communication buses or signal lines.

Each component of the diet recommendation device 130 shown in FIG. 2 refers to a unit that processes at least one function or operation, and may be implemented as a software module, a hardware module, or a combination of software and hardware.

The medical examination unit 210 transmits previously generated personal medical examination data to a plurality of user terminals 110. The questionnaire unit 210 generates questionnaire data including inquiries about intake and deficiency of each nutrient.

The type classification unit 220 receives questionnaire result data including answers corresponding to the questionnaire data from the user terminal 110. The type classification unit 220 classifies user types based on the questionnaire result data.

The type classification unit 220 classifies user types based on the re-interview result data. The type classification unit 220 distinguishes user types using one or more of gender information, age information, and preference information included in the questionnaire result data.

The type classification unit 220 sets the threshold value for each required nutrient depending on whether the questions included in the questionnaire result data are answered. The type classification unit 220 distinguishes between users exceeding the required nutrient threshold and users below the required nutrient threshold based on the answers included in the questionnaire result data.

The type classification unit 220 determines the individual required nutrients to reduce the nutrients exceeding the required nutrient threshold based on the answers for users exceeding the required nutrient threshold and classifies user types. The type classification unit 220 classifies user types by determining individual nutritional requirements that increase the nutrients below the required nutrient threshold based on the answers of users below the required nutrient threshold.

The type classification unit 220 generates a deficiency classification inference result as a result of performing a prediction by applying an ML (Machine Learning) model to a query about intake or deficiency of each nutrient. The type classification unit 220 generates a necessary nutrient deficiency result classifying the necessary nutrient deficiency based on the questionnaire result data. The type classification unit 220 classifies user types based on the deficiency classification inference result and the required nutrient deficiency result.

The type classification unit 220 compares the deficiency classification inference results and the required nutrient deficiency results and selects only the nutrients that match each other. The type classification unit 220 distinguishes user types by additionally applying one or more information among gender information, age information, and preference information based on matching nutrients.

The grouping unit 230 creates a group by grouping user types by the same type. The grouping unit 230 creates a group that groups user types into the same type based on preference diet information included in the re-interview result data.

The diet recommendation unit 240 generates diet recommendation information including necessary nutrient information for each group. The diet recommendation unit 240 generates diet recommendation information for one or more of group-specific nutrient information, obesity control including priority of preferred diets, and anemia.

The diet recommendation unit 240 checks the correlation between required nutrient information for each group and food. When the correlation between required nutrient information for each group and food satisfies preset conditions, the diet recommendation unit 240 generates diet recommendation information including the corresponding food.

The diet recommendation unit 240 confirms the correlation by simply matching the required nutrient information for each group with the nutritional ingredients of the diet components.

The diet recommendation unit 240 extracts the user's preferences and preferences included in the questionnaire data when the nutrients required for each group are the same as the nutritional ingredients of the diet components. The diet recommendation unit 240 generates diet recommendation information by reflecting weights on foods containing nutrients corresponding to user tastes and preferences to increase their priority.

The diet recommendation unit 240 simply matches the required nutrient information for each group with the nutritional ingredients of the diet components and then extracts user preferences and preferences included in the questionnaire data. The diet recommendation unit 240 generates a multiclass SVM (Multiclass SVM) model for each user taste and preference. The diet recommendation unit 240 generates diet recommendation information to include the first ranked food among diets including a plurality of diets generated from a multiclass SVM model.

The diet recommendation unit 240 checks the correlation between required nutrient information for each group and food. If the correlation between the necessary nutrient information for each group and the food does not satisfy preset conditions, the diet recommendation unit 240 extracts highly recommended nutrients, recommended nutrients, and non-recommended nutrients for each food from the food DB and diet DB. The diet recommendation unit 240 generates diet recommendation information by combining foods according to the contents of highly recommended nutrients, recommended nutrients, and non-recommended nutrients.

The feedback unit 250 transmits diet recommendation information to the user terminal 110 corresponding to the group. The feedback unit 250 receives re-examination result data including feedback including a preferred diet for the diet recommendation information from the user terminal 110.

The feedback unit 250 receives re-interview result data from the user terminal 110, including feedback that categorizes preferences for diet recommendation information into highly preferred, preferred, and neutral.

Figure 3 is a diagram for explaining the method of extracting necessary nutrients based on a questionnaire according to this embodiment.

The diet recommendation device 130 specifies required nutrient thresholds for various required nutrients depending on whether or not the questions included in the personal questionnaire are answered. The diet recommendation device 130 distinguishes between users exceeding the required nutrient threshold and users below the required nutrient threshold based on the questionnaire information.

The diet recommendation device 130 determines individual nutrient requirements by adding or subtracting weights based on additional information included in the questionnaire information for users whose nutrient requirements exceed the threshold. The diet recommendation device 130 determines individual nutrient requirements by adding or subtracting weights based on additional information included in the questionnaire information for users whose nutrient requirements are below the threshold.

Figure 4 is a diagram showing group modeling according to input values for each required nutrient according to this embodiment.

The diet recommendation device 130 generates test data by referring to the nutrient-specific questionnaire and deficiency classification (410). The diet recommendation device 130 generates questionnaire data in which the contents of the questionnaire for each nutrient are changed based on the test data (S420).

The diet recommendation device 130 performs prediction by applying an ML model to the questionnaire data whose query content has been changed (S430). The diet recommendation device 130 generates a deficiency classification inference result as a result of performing predictions by applying an ML model to the questionnaire data with changed query contents (S440).

The diet recommendation device 130 receives questionnaire result data from the user terminal 110 for the test data generated in step S410. The diet recommendation device 130 classifies necessary nutrient deficiencies based on the questionnaire result data (S450).

The diet recommendation device 130 generates result data by comparing the deficiency classification inference result generated in step S440 with the required nutrient deficiency generated in step S450 (S460).

In step S460, the diet recommendation device 130 performs group modeling according to input values for each required nutrient. The diet recommendation device 130 classifies the grouping results based on data (input values for each required nutrient). The diet recommendation device 130 compares the classified grouping results with the results of various intelligent engines and constructs the same grouping results for large-scale questionnaire results and large-scale results.

In Figure 4, steps S410 to S460 are described as being sequentially executed, but the process is not limited to this. In other words, the steps shown in FIG. 4 may be applied by modifying them or executing one or more steps in parallel, so FIG. 4 is not limited to a time-series order.

As described above, the group modeling method according to the input values for each required nutrient according to the present embodiment shown in FIG. 4 may be implemented as a program and recorded on a computer-readable recording medium. The computer-readable recording medium on which the program for implementing the group modeling method according to the input values for each required nutrient according to this embodiment is recorded includes all types of recording devices that store data that can be read by a computer system. .

Figure 5 is a diagram showing a recommendation algorithm based on grouping and dietary nutrients according to this embodiment.

The diet recommendation device 130 receives questionnaire result data from the user terminal 110 corresponding to the recommendation target (user) (S510). In step S510, the diet recommendation device 130 determines the nutritional composition and correlation of each food by measuring the correlation between the questionnaire result data.

The diet recommendation device 130 checks whether a diet that satisfies the search conditions based on the nutritional composition and correlation of each food exists (S520). In step S520, the diet recommendation device 130 simply matches the correlation between the results of the questionnaire and the nutrients and components of the diet components.

As a result of step S520, if there is a diet that satisfies the search conditions according to the nutritional composition and correlation of each food, the diet recommendation device 130 searches according to the nutritional composition and correlation of each food and provides a diet that satisfies the conditions. is created as dietary recommendation information and then transmitted to the corresponding user terminal 110 (S522). In step S522, the diet recommendation device 130 applies weights according to preferences and preferences in the case of the same ingredients to prioritize the selection so that selection can be made through simple matching. When simple matching diets are grouped, the diet recommendation device 130 generates a multiclass SVM (Multiclass SVM) model for each preference again for the grouping. The diet recommendation device 130 selects the first food from the created group.

As a result of step S520, if there is a diet that satisfies the search conditions based on the nutritional composition and correlation of each food, the diet recommendation device 130 executes the rule to select highly recommended nutrients and recommended nutrients from the food DB and diet DB. , extract non-recommended nutrients (S530).

The diet recommendation device 130 executes the rule to generate diet recommendation information according to the contents of highly recommended nutrients, recommended nutrients, and non-recommended nutrients extracted from the food DB and diet DB, and then transmits it to the corresponding user terminal 110 (S540). .

The diet recommendation device 130 receives feedback information reflecting each user's preference for the diet recommendation information from the user terminal 110 that transmitted the diet recommendation information (S550). In step S550, the diet recommendation device 130 re-performs steps S510 to S540 based on the received feedback information.

In Figure 5, steps S510 to S550 are described as being sequentially executed, but this is not necessarily limited. In other words, the steps shown in FIG. 5 may be applied by modifying them or executing one or more steps in parallel, so FIG. 5 is not limited to a time-series order.

As described above, the grouping and dietary nutrient-based recommendation algorithm according to this embodiment shown in FIG. 5 may be implemented as a program and recorded on a computer-readable recording medium. A computer-readable recording medium on which a program for implementing the grouping and dietary nutrient-based recommendation algorithm according to this embodiment is recorded includes all types of recording devices that store data that can be read by a computer system.

Figure 6 is a diagram showing diet recommendations according to priority according to this embodiment.

The diet recommendation device 130 categorizes and configures individuals by type based on questionnaire information. The diet recommendation device 130 groups individuals by type.

The diet recommendation device 130 uses an engine to match groups of groups and preferred foods based on nutrients and components of the diet. The diet recommendation device 130 receives feedback information about the diet recommendation information from the user terminal 110 with priorities set to 1: very preferred, 2: preferred, and 3: average.

The diet recommendation device 130 provides diet recommendation information for each user type and then performs a new questionnaire after the user consumes food corresponding to the diet recommendation information. The diet recommendation device 130 generates new diet recommendation information reconstructed into the same diet and additional diet based on the new questionnaire information.

The above description is merely an illustrative explanation of the technical idea of the present embodiment, and those skilled in the art will be able to make various modifications and variations without departing from the essential characteristics of the present embodiment. Accordingly, the present embodiments are not intended to limit the technical idea of the present embodiment, but rather to explain it, and the scope of the technical idea of the present embodiment is not limited by these examples. The scope of protection of this embodiment should be interpreted in accordance with the claims below, and all technical ideas within the equivalent scope should be interpreted as being included in the scope of rights of this embodiment.

110: user terminal
120: network
130: Diet recommendation device
210: Paper weight department
220: Type classification unit
230: Grouping department
240: Diet recommendation section
250: Feedback unit

Claims (14)

A questionnaire unit that transmits previously generated personal questionnaire data to a plurality of user terminals;
A type classification unit that classifies user types based on questionnaire result data including answers corresponding to the questionnaire data received from the user terminal;
a grouping unit that creates a group by grouping the user types by the same type;
a diet recommendation unit that generates diet recommendation information including necessary nutrient information for each group;
a feedback unit that transmits the diet recommendation information to the user terminal corresponding to the group and receives re-examination result data including preference diet feedback for the diet recommendation information from the user terminal;
A diet recommendation device comprising: According to paragraph 1,
The type classification unit distinguishes the user type based on the re-interview result data,
The grouping unit creates a group in which the user type is grouped by the same type based on preference diet information included in the re-interview result data,
A diet recommendation device characterized in that the diet recommendation unit generates the diet recommendation information for one or more of the necessary nutrient information for each group, obesity control including priority of the preferred diet, and anemia. According to paragraph 1,
The type classification section is
A diet recommendation device that distinguishes the user type using one or more of gender information, age information, and preference information included in the questionnaire result data. According to paragraph 1,
The type classification unit is,
Thresholds for each required nutrient are set depending on whether or not there is an answer to the question included in the questionnaire result data, and users exceeding the required nutrient threshold and users below the required nutrient threshold based on the answer included in the questionnaire result data. A diet recommendation device characterized in that it distinguishes between. According to paragraph 3,
The type classification unit is,
For users exceeding the required nutrient threshold, the user type is classified by determining individual nutritional requirements that reduce the nutrients exceeding the required nutrient threshold based on the answers, and for users below the required nutrient threshold. A diet recommendation device that classifies the user type by determining individual nutritional requirements that increase nutrients below the required nutrient threshold based on the answers. According to paragraph 1,
The questionnaire section said,
A diet recommendation device that generates the questionnaire data including inquiries about intake and deficiency of each nutrient. According to clause 5,
The type classification unit is,
A deficiency classification inference result is generated as a result of performing predictions by applying an ML (Machine Learning) model to queries regarding intake of each nutrient and deficiency, and classification of necessary nutrient deficiencies based on the questionnaire result data. A diet recommendation device that generates a necessary nutrient deficiency result and classifies the user type based on the deficiency classification inference result and the required nutrient deficiency result. According to clause 6,
The type classification unit is,
By comparing the deficiency classification inference results with the required nutrient deficiency results, only the nutrients that match each other are selected, and based on the matching nutrients, one or more information among gender information, age information, and preference information is additionally applied to determine the user type. A diet recommendation device characterized by classification. According to paragraph 1,
In the dietary recommendation section,
Check the correlation between the necessary nutrient information for each group and the food, and if the correlation between the necessary nutrient information for each group and the food satisfies preset conditions, generate the diet recommendation information including the food. Featured diet recommendation device. According to clause 8,
In the dietary recommendation section,
A diet recommendation device characterized in that the correlation is confirmed by simply matching the required nutrient information for each group with the nutritional ingredients of the diet components. According to clause 9,
In the dietary recommendation section,
If the nutrient information for each group is the same as the nutritional components of the diet components, user preferences and preferences included in the questionnaire data are extracted, and weights are given to foods containing nutrients corresponding to the user preferences and preferences. A diet recommendation device that generates the diet recommendation information by reflecting the priority to increase the priority. According to clause 10,
In the dietary recommendation section,
After simply matching the required nutrient information for each group with the nutritional ingredients of the diet components, user preferences and preferences included in the questionnaire data are extracted, and a multiclass SVM (Multiclass SVM) model is created for each user preference and preference. and generating the diet recommendation information to include the first ranked food among the diets including a plurality of diets generated from the multiclass SVM model. According to paragraph 1,
In the dietary recommendation section,
Check the correlation between the required nutrient information for each group and the food, and if the correlation between the required nutrient information for each group and the food does not meet the preset conditions, strongly recommended nutrients for each food from the food DB and diet DB, A diet recommendation device that extracts recommended nutrients and non-recommended nutrients, and generates the diet recommendation information by combining the foods according to the contents of the highly recommended nutrients, the recommended nutrients, and the non-recommended nutrients. According to paragraph 1,
The feedback unit,
A diet recommendation device, characterized in that it receives the re-questionnaire result data from the user terminal, including feedback classifying the preference for the diet recommendation information as highly preferred, preferred, and average.