KR20190113110A - Method for wine recommendation using preference analysis algoritm - Google Patents

Abstract

An embodiment of the present invention is to provide a method for recommending wine through an algorithm for analyzing taste information of a user. According to the present invention, in the method, the taste of the user is analyzed based on profile of a user for wine and posts on social network services, preferences of the user, and preferences for wine of the user, each characteristic of the wine is individually scored, and the taste of the user is scored based on the individual scores, thereby recommending wines that match the taste of the user.

Description

Wine recommendation method using taste analysis algorithm {METHOD FOR WINE RECOMMENDATION USING PREFERENCE ANALYSIS ALGORITM}

The present invention relates to a wine recommendation method using a taste analysis algorithm. More particularly, the present invention relates to a method of recommending a wine in consideration of a user's taste by analyzing a user's preference for each attribute of wine's attribute information.

Conventionally, the recommendation system uses a content-based recommendation system that performs a recommendation by using information that is already purchased or serviced by a user or content of a product, and a history of the purchased or serviced information or product of the user. A collaborative filtering recommendation system does not make customized recommendations before the actual purchase or service.

As a result, the user's perception of the recommendation system is negative, and in some cases, the user is often re-recommended for goods or services that the user is not satisfied with, thus reducing the reliability of the recommendation system.

The present invention is to solve the above-described problems of the prior art, it is possible to extract the user's taste information based on the user's social network activity and based on it can recommend wine that the user prefers.

In recommending a wine to a user, through a user's taste analysis algorithm, scores may be calculated for various elements that define the characteristics of the wine, such as the taste and aroma of the wine, to recommend wines having higher satisfaction.

However, the technical problem to be achieved by the embodiment of the present invention is not limited to the technical problem as described above, and other technical problems may exist.

As a technical means for achieving the above-described technical problem, according to an embodiment of the present invention, the wine recommendation method using the taste analysis algorithm performed by the server, (a) to the profile of the user corresponding to the wine information service terminal Accordingly, collecting the initial taste analysis data of the user; (b) collecting wine taste analysis data of the user based on data on application activity history of the user performed through the wine information service terminal from the user; (c) updating the initial taste analysis data with the wine taste data of the user based on the wine taste analysis data; And (d) recommending wine based on the updated wine taste data of the user; wherein each profile item is defined as a plurality of attributes, and the initial taste analysis data is each attribute of each profile item. The score of the user may be defined every time.

The server performing the wine recommendation method using the taste analysis algorithm collects initial taste analysis data of the user according to a profile of the user corresponding to the wine information service terminal, and performs the wine information service terminal from the user. Collecting the wine taste analysis data of the user based on the data on the application activity history of the user, updating the initial taste analysis data with the wine taste data of the user based on the wine taste analysis data, and updating the update The wine is recommended based on the user's wine taste data, wherein each profile item may be defined as a plurality of attributes, and the initial taste analysis data may be defined such that a user score is set for each attribute of each profile item. .

One embodiment of the present invention is to provide a method for recommending wine through an algorithm for analyzing the user's taste information.

Analyzes the user's taste based on the user's profile of wine and posts on social network services, the user's preferences for the user's posts, and the user's preferences for the wine, and individually for each characteristic of the wine. By assigning a score and scoring the score according to the user's taste, it is possible to make a recommendation for a customized wine that matches the user's taste.

1 is a block diagram of a system for performing a wine recommendation method using a taste analysis algorithm according to an embodiment of the present invention.
2 is a flowchart illustrating a wine recommendation method using a taste analysis algorithm according to an embodiment of the present invention.
3 is a flowchart illustrating a wine recommendation step of a wine recommendation method using a taste analysis algorithm according to an embodiment of the present invention.
4 is a diagram illustrating an index score for wine recommendation among wine recommendation methods using a taste analysis algorithm according to an embodiment of the present invention.

DETAILED DESCRIPTION Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art may easily implement the present invention. As those skilled in the art would realize, the described embodiments may be modified in various different ways, all without departing from the spirit or scope of the present invention. In the drawings, parts irrelevant to the description are omitted in order to clearly describe the present invention, and like reference numerals designate like parts throughout the specification.

Throughout the specification, when a part is "connected" to another part, this includes not only "directly connected" but also "electrically connected" with another element in between. . In addition, when a part is said to "include" a certain component, which means that it may further include other components, except to exclude other components unless otherwise stated.

In the present specification, the term 'unit' includes a unit realized by hardware, a unit realized by software, and a unit realized by both. In addition, one unit may be realized using two or more pieces of hardware, and two or more units may be realized by one piece of hardware. Meanwhile, '~' is not limited to software or hardware, and '~' may be configured to be in an addressable storage medium or may be configured to reproduce one or more processors. Thus, as an example, '~' means components such as software components, object-oriented software components, class components, and task components, and processes, functions, properties, procedures, and the like. Subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functionality provided within the components and the 'parts' may be combined into a smaller number of components and the 'parts' or further separated into additional components and the 'parts'. In addition, the components and '~' may be implemented to play one or more CPUs in the device or secure multimedia card.

The term "terminal" described below may be implemented as a computer or a portable terminal that can access a server or another terminal through a network. Here, the computer is, for example, a laptop equipped with a web browser (desktop), desktop (desktop), laptop (laptop), VR HMD (for example, HTC VIVE, Oculus Rift, GearVR, DayDream, PSVR, etc.) It may include. Here, VR HMD can be used for PC (e.g. HTC VIVE, Oculus Rift, FOVE, Deepon, etc.) and mobile (e.g. GearVR, DayDream, Stormscape, Google Cardboard, etc.) and console (PSVR) This includes all stand-alone models (eg Deepon, PICO, etc.) that are implemented independently. The portable terminal is, for example, a wireless communication device that ensures portability and mobility, and is not only a smart phone, a tablet PC, a wearable device, but also Bluetooth (BLE, Bluetooth Low Energy), NFC, RFID, and Ultrasonic (Ultrasonic). It may include a variety of devices equipped with a communication module, such as infrared, Wi-Fi (WiFi), LiFi (LiFi). In addition, "network" refers to a connection structure capable of exchanging information between respective nodes such as terminals and servers, and includes a local area network (LAN), a wide area network (WAN), and the Internet. (WWW: World Wide Web), wired and wireless data communication networks, telephone networks, wired and wireless television networks, and the like. Examples of wireless data networks include 3G, 4G, 5G, 3rd Generation Partnership Project (3GPP), Long Term Evolution (LTE), World Interoperability for Microwave Access (WIMAX), Wi-Fi, Bluetooth communication, Infrared communication, Ultrasound Communication, visible light communication (VLC), liFi (LiFi), and the like, but are not limited thereto.

Hereinafter, a system for performing a wine recommendation method using a taste analysis algorithm according to an embodiment of the present invention will be described in detail with reference to FIG. 1.

As shown in FIG. 1, the system 10 for performing a wine recommendation method using a taste analysis algorithm may include a server 100 and a wine information service terminal 200, and the server 100 and a wine information service. The terminal 200 may be connected through a network.

The server 100 collects initial taste analysis data of the user according to the profile of the user corresponding to the wine information service terminal 200, and records the user's application activity performed by the user through the wine information service terminal 200. The wine taste analysis data of the user may be collected based on the data.

The initial taste analysis data may be updated with the user's wine taste data based on the collected wine taste analysis data, and the wine may be recommended based on the updated user's wine taste data.

In this case, the profile item may be defined as a plurality of attributes, and the initial taste analysis data may be defined such that a score of the user is set for each attribute of each profile item. The plurality of attributes constituting the profile item include one or more of wine attribute information (specifically, dry attribute information, Acidity attribute information, Tannin attribute information, Body attribute information), country information, fruit information, cooking information, and aroma information. Can be.

In addition, the wine attribute information items are defined as 1 to 5 grades for each attribute information, and the index score of the user may be set for each grade.

The wine information service terminal 200 may be a device possessed by a user or a computing device installed at a specific place and may be capable of providing wine and food pairing and recommendation. A social network service (SNS) capable of exchanging wine-related posts between a plurality of users provided from the server 100 may be provided to the user.

In addition, the wine information service terminal 200 may collect the user's activity history for the social network service application that can exchange wine-related posts used by the user and provide the user's taste analysis data to the server 100.

Hereinafter, an index score for recommending wine in a wine recommendation method using a taste analysis algorithm will be described in detail according to an embodiment of the present invention.

The server 100 may define a group of wines by classifying them into red wine, white wine, and sparkling wine, and collect taste analysis data for each group.

In this case, taste analysis data including at least one of wine attribute information, country information, fruit information, cooking information, and aroma information may be collected for each group, and the wine attribute information items may be classified into 1 to 5 grades for each attribute information. The index score of the user may be set for each class.

Wine attribute information may be defined as dry, Acidity, Tannin, Body, but is not limited thereto.

The initial taste score of the user may be collected by the information to be entered when the first login information in the wine information service terminal 200, the user profile creation page inputs a preference for attributes such as wine attributes or wine producing countries It can be configured to do so. In this case, a value corresponding to each attribute may be input through a circular image.

For example, it may be configured to set attribute values such as "light", "sour", "heavy and dark", "bubble", and "sweet" for the wine attribute. In addition, the image corresponding to each attribute value may be configured in a circle.

In this case, the circular image corresponding to each attribute value may be generated in a form in which the thickness of the edge of the circle is gradually increased. For example, an image corresponding to each attribute value may have a thin border, and may be changed to have a thicker thickness from one border of the circular image by user interaction.

The user interaction may change an image of a corresponding attribute value based on the duration or intensity of the interaction when the user inputs a long click or touch input of a specific attribute or a force touch interaction that makes a hard click or touch.

In addition, there may exist an initialization interaction for initializing the set property value and initializing the image of the property value. In this case, the initialization interaction may be a double click and may be to maintain a click for a predetermined time or more. In addition, the initialization interaction may be shaking input through an acceleration sensor (not shown), but is not limited thereto.

The user's initial taste score collected based on the user's profile may then be updated with wine taste information by the user's application activity history, and the wine taste information may be continuously updated corresponding to subsequent activities.

For example, among the user's initial taste scores, the dry grade of the dry attribute information is defined as a grade 1 to 5 grade, and the initial taste scores (ie, index scores) for all wines of grades 1 to 5 are 3 Assume that After that, if a user evaluates one point for a wine with a dry grade of 1 that is provided through the application (for example, through a post uploaded by another user within the application), a score equal to 1 grade ( That is, 3 points) can be updated.

At this time, the update on the wine taste information is performed based on one or more information of the evaluation information, preference information, search information. Here, rating information refers to a score that a user has rated for a wine, and preference information includes 'like' information about a post uploaded by another user and 'wine' information about wine included in the post. The search information refers to values searched by a user by inputting text based on a search box in the application.

In addition, the updated index score may be updated based on a value obtained by multiplying an existing index score by an evaluation coefficient (a preset value) and a sum of the user's evaluation scores. In the above example, the index score is updated based on the sum of the existing index score (3 points) multiplied by the evaluation coefficient and the user's evaluation score (1 point).

The index score is a score given to each of the plurality of grades included in the wine attribute information as described above, and may be a score that is a standard for recommending wine to the user.

More specifically, the method of updating the index score may be performed based on the score to be evaluated, the current index score, and the evaluation coefficient for the current index score, wherein the current index score is multiplied by the evaluation coefficient, and the value is multiplied by the user. The score can be updated by adding up the scores and dividing the evaluation factor with 1 for the total score. In this case, the evaluation coefficient may be set differently according to whether the application activity history of the user is one of input of preference information, input of evaluation score, and wine search.

For example, assuming that the evaluation coefficient is set to 10 and the user evaluates 2 points for the wine corresponding to the stage where dry is 3 points, the index score to be updated may be 2.90909091.

In this case, when a user directly inputs an evaluation score for wine, the corresponding score may be an evaluation score. However, when inputting preference information or inputting search information, since the preference information does not have an evaluation score for the input wine or the searched wine, it may be defined as a predetermined score in the first place.

The score of the step for the corresponding information may be stored by collecting scores for the evaluation information on the wine, the preference information for the post, the preference information for the wine included in the post, and the search information for searching for a specific wine in the application. .

In addition, as a further embodiment of the present invention, in addition to the red wine, white wine and sparkling wine group, the same taste analysis may be performed to collect taste analysis data as described above for Madeira wine, fortified wine and rose wine. Can be.

Hereinafter, a wine recommendation method using a taste analysis algorithm according to an embodiment of the present invention will be described in detail with reference to FIG. 2.

In the wine recommendation method using the taste analysis algorithm, the server 100 may collect initial taste analysis data of the user according to the profile of the user corresponding to the wine information service terminal 100 (S310).

All profile items are defined by a plurality of attributes, and the initial taste analysis data may be defined such that a score of a user is set for each attribute of each profile item.

That is, the initial taste score may be set to a preset score for the profile item, and a score (which may be a negative or positive numeric value) according to the degree input by the user through the interaction may be added or subtracted to the preset score.

At this time, the maximum value of the additional score that can be input through the interaction may be limited.

After collecting the initial taste analysis data, the user can collect the wine taste data of the user based on the data on the application activity history of the user performed through the wine information service terminal 200 (S320).

In this case, the application activity history may include at least one of evaluation information on the wine, preference information on the post, preference information on the wine included in the post, and search information searching for a specific wine in the application.

Thereafter, the server 100 may update the initial taste analysis data with the wine taste data of the user based on the wine taste data (S330).

In this case, the profile item may include one or more of wine attribute information, country information, fruit information, cooking information, aroma information, and items of 1 to 5 grades are defined in detail in the wine attribute information, and for each grade. The user's index score can be set.

In updating the wine taste data of the user, the index score is updated based on the sum of the index score multiplied by the evaluation score and the user's evaluation score, wherein the evaluation coefficient is inputted by the user's application activity information. It may be set differently depending on whether one of the evaluation score input and the wine search.

That is, when performing based on the evaluation information on the wine of the user, receiving the wine attribute information described in the evaluation information entered by the user and the evaluation score entered by the user, the evaluation score and the index score entered by the user is added to the current The index score for the wine attribute information can be updated.

In addition, when performing based on the preference information of the wine of the user, receiving the wine attribute information described in the preference information entered by the user and the preference information input by the user, the predetermined score corresponding to the preference information and the index score of the wine By summating the index score for the current wine attribute information can be updated.

In addition, when the search is performed based on the search information on the wine of the user, the wine attribute information described in the search information input by the user and the search information input by the user receive a preset score corresponding to the search information and the index score of the wine By summating the index score for the current wine attribute information can be updated.

After the server 100 updates the wine taste data of the user, the server 100 may recommend wine based on the updated wine taste data of the user (S340).

Hereinafter, the wine recommendation step of the wine recommendation method using the taste analysis algorithm according to an embodiment of the present invention will be described in detail with reference to FIG. 3.

In recommending the wine, it is possible to determine the maximum value of the score of each profile item included in the wine taste data (S341). In detail, various grades may be defined for each profile item, and which grades are most preferred by the user may be determined based on a maximum value among scores prescribed for each grade. For example, when dry attribute information is defined as 1 to 5 grades, if the user's score for the 1st grade is 5 points and the user's score for the 2-4 grade is 1-3 points, the maximum value is obtained. The first grade corresponding to 5 points may be regarded as the most preferred grade by the user. Accordingly, the user may determine that the user likes the wine corresponding to the first grade for the dry property.

The server 100 may determine whether the maximum number of scores is plural (S342).

At this time, if the index scores of two or more grades are the same, and the index score is the maximum value, first, an average value is calculated based on a statistical table having a column of grades and index scores for which a deviation is obtained based on a predetermined grade (S343). ). This average value may be referred to as a grade average value.

After calculating the average value, it is possible to determine the grade closest to the average value of the two or more grades ties with each other (S344).

Based on the determined grade, the user may grasp the most preferred grade for each profile item, and may search for and recommend wines having a value within the predetermined range and the determined grades (S345).

For example, assume that grade 3 is the average and assign it as a preset grade. Subsequently, the average value can be calculated in the form of calculating the deviation around three.

In other words, class 1 is -2 points, class 2 is -1 point, class 3 is 0 point, class 4 is 1 point, class 5 is 2 points, and {(-2) * ( Score) + (-1) * (user's score for 2 ratings) + (0) * (user's score for 3 ratings) + (1) * (user's score for 4 ratings) + (2) * (The user's score for 5 grades)} / {sum of the user's scores +3 (that is, a predetermined grade)}.

For example, assuming that scores corresponding to each grade are 5, 1, 2, 4, and 5 sequentially, as shown in FIG. 4, grade 1 and grade 5 have the same maximum score. Therefore, it is necessary to determine which grade the user prefers among the first and fifth grades. The average value calculated in this way is 3.4.

At this time, since the average value is 3.4, the fifth grade nearest to the 3.4 grade may be selected as the most preferred grade by the user.

The maximum value for each profile item can be determined and a personalized wine can be recommended to the user based on this.

An embodiment of the present invention may also be implemented in the form of a recording medium including instructions executable by a computer, such as a program module executed by the computer. Computer readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. In addition, computer readable media may include all computer storage media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.

Although the methods and systems of the present invention have been described in connection with specific embodiments, some or all of their components or operations may be implemented using a computer system having a general purpose hardware architecture.

The foregoing description of the present invention is intended for illustration, and it will be understood by those skilled in the art that the present invention may be easily modified in other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are exemplary in all respects and not restrictive. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined form.

The scope of the present invention is shown by the following claims rather than the above description, and all changes or modifications derived from the meaning and scope of the claims and their equivalents should be construed as being included in the scope of the present invention. do.

10: system
100: server 200: terminal

Claims (12)

In the wine recommendation method using a taste analysis algorithm performed by the server,
(a) collecting initial taste analysis data of the user according to a profile of the user corresponding to the wine information service terminal;
(b) collecting wine taste data of the user based on data of application activity history of the user performed through the wine information service terminal from the user;
(c) updating the initial taste analysis data with the wine taste data of the user based on the wine taste data; And
(d) recommending wine based on the updated wine taste data of the user;
Including,
Each profile item is defined by a plurality of attributes, and the initial taste analysis data is defined such that a score of a user is set for each attribute of each profile item.
Wine recommendation method using taste analysis algorithm.
The method of claim 1,
The profile item,
One or more of wine attribute information, country information, fruit information, cooking information, aroma information,
The wine attribute information is defined by each of the attribute information, the grade of 1 to 5 grades, the index score of the user is set for each grade,
The highest rating score is regarded as the user's most preferred rating for the wine attribute information,
Wine recommendation method using taste analysis algorithm.
The method of claim 1,
In step (a),
Setting the initial taste score as a preset score with respect to the profile item, and adding or subtracting a score corresponding to a degree input by the user through an interaction with the preset score;
Including,
The maximum value of the score that can be input through the interaction is limited,
Wine recommendation method using taste analysis algorithm.
The method of claim 1,
In step (b),
The application activity history,
It includes at least one of the evaluation information for the wine, preference information for the post, preference information for the wine contained in the post and search information for searching for a specific wine in the application,
Wine recommendation method using taste analysis algorithm.
The method of claim 2,
In step (c),
The index score is updated based on the product of the index score multiplied by the evaluation coefficient and the sum of the user's evaluation scores.
The evaluation coefficient is,
The application activity history of the user is set differently according to one of the preference information input, evaluation score input and wine search,
Wine recommendation method using taste analysis algorithm.
The method of claim 5,
The update,
Based on the evaluation information on the wine of the user,
Receiving the attribution information of the wine described in the evaluation information input by the user and the evaluation score input by the user; And
The grade of each attribute of the wine is determined from the attribute information of the wine, the grades matching the attribute-specific grade of the wine among the grades of profile items in the existing wine taste data are recognized, and the index corresponding to the recognized grade Updating the scores;
Including,
Wine recommendation method using taste analysis algorithm.
The method of claim 5,
The update,
Based on the user's wine preference information,
Receiving wine attribute information and preference information input by the user for a post in which the preference information input by the user is recorded; And
The grade of each attribute of the wine is determined from the attribute information of the wine, the grades matching the attribute-specific grade of the wine among the grades of profile items in the existing wine taste data are recognized, and the index corresponding to the recognized grade Updating a score, adding the predetermined score corresponding to the preference information and the index score to update the index score;
Including,
Wine recommendation method using taste analysis algorithm.
The method of claim 5,
The update,
Based on the search information for the wine of the user,
Receiving attribute information of wine represented by text included in the search information input by the user and search information input by the user; And
The grade of each attribute of the wine is determined from the attribute information of the wine, the grades matching the attribute-specific grade of the wine among the grades of profile items in the existing wine taste data are recognized, and the index corresponding to the recognized grade Updating a score, adding the predetermined score corresponding to the search information and the index score to update the index score;
Including,
Wine recommendation method using taste analysis algorithm.
The method of claim 1,
In step (d),
(d-1) determining a grade having a maximum index score among a plurality of grades defined in each profile item, in order to grasp the most preferred grade for each profile item included in the external taste data; ; And
(d-2) searching for and recommending wines having a grade value within a predetermined range and the determined grade for each profile item;
Including,
Wine recommendation method using taste analysis algorithm.
The method of claim 9,
Step (d-1),
If the maximum index score is two or more in one profile item,
Calculating a grade mean value based on statistics defining the grade and the index score as columns; And
Determining a rating closest to the rating mean value among two or more ratings having the maximum index score, and considering the determined rating as the rating most preferred by the user;
Including,
Wine recommendation method using taste analysis algorithm.
In the server performing the wine recommendation method using the taste analysis algorithm,
Collecting initial taste analysis data of the user according to the profile of the user corresponding to the wine information service terminal;
Collecting wine taste data of the user based on data on application activity history of the user performed through the wine information service terminal from the user,
Update the initial taste analysis data with the wine taste data of the user based on the wine taste data,
Recommend wine based on the updated wine taste data of the user,
Each profile item is defined by a plurality of attributes, and the initial taste analysis data is defined such that a score of a user is set for each attribute of each profile item.
Server that performs wine recommendation method using taste analysis algorithm.
A computer-readable recording medium having recorded thereon a computer program for performing a wine recommendation method using a taste analysis algorithm according to claim 1.

Images