KR102599608B1 - Wine recommendation system and method thereof based on professional evaluatoin - Google Patents

Abstract

The present invention relates to a wine recommendation system and a wine recommendation method. The wine recommendation system includes a wine information provision service server that provides information about wine through a user interface, and the wine information provision service server includes a wine type. The user's input information and the user's profile information are collected, number of wine ratings provided, number of types of wine purchased, number of posts registered, number of wine-related professional qualifications, experience in the wine industry, morphological analysis score, and expertise in wine. Using at least one of the measurement information as a variable, the expertise score of each user is calculated based on this, and based on this, the final score of each wine type is calculated, and recommended information about N types of wine is provided in the order of the wine type with the highest final score. Provided through the user interface.

Description

Professional evaluation-based wine recommendation system and method {WINE RECOMMENDATION SYSTEM AND METHOD THEREOF BASED ON PROFESSIONAL EVALUATOIN}

The present invention relates to a wine recommendation system and a wine recommendation method. More specifically, the present invention relates to a system and method for providing highly reliable wine recommendation information by analyzing the user's wine experience and expertise and reflecting this in the rating of the wine type. It's about.

Recently, wine is not only a luxury alcoholic beverage enjoyed by a few enthusiasts or the upper class, but is also recognized as a wellness beverage or lifestyle product that enriches the quality of life for the general public. As the number of wine lovers increases, they are enjoying the aesthetics of wine and the lifestyle of wine culture rather than drinking alcohol called wine. Popular wine culture is gradually expanding not only in the West but also in Eastern countries, including Korea and Japan.

However, in the East, the general public, except for some enthusiasts, still faces many difficulties in choosing wine. In particular, unlike other alcoholic beverages, wine is divided into very diverse and complex types according to numerous standards, so it is very difficult for ordinary people without expert knowledge about wine to select a wine that satisfies the various conditions they want. .

For example, wine can be classified into numerous types depending on the country of production, production area, producer, grape harvest year (Vintage), and grape variety, etc. Each of the items listed above is often written in a relatively unfamiliar native language, The scale of classification also varies depending on the type of wine and country, so expert knowledge is required to select wine. For example, in the case of grape varieties, Cabernet Sauvignon, Merlot, Pinot Noir, Sangiovese, Zinfandel, Chardonnay, Sauvignon Blanc, and Gewürz. There are Gewurztraminer, Riesling, etc., but the names of these grape varieties themselves are very unfamiliar and difficult terms for general consumers, so it is inevitable that they will have difficulty making a choice.

In addition, when a consumer selects a wine, he or she must consider not only the items listed above, but also the wine's color, aroma (grape varietal scent), bouquet (wine ripening scent), and whether the sugar content is dry or sweet. , to select a wine that will satisfy you, you must consider a wide variety of items such as weight (body), tannin (astringency), production company, and whether it goes well with any food.

On the other hand, consumers who lack knowledge about wine only consider whether it is red wine or white wine, what food it goes well with, and the price when purchasing wine. In addition, the wine selection criteria are so broad that it may be difficult for sellers to recommend appropriate wines to consumers, making it difficult for consumers to select wines that suit their tastes.

Even though general consumers without specialized knowledge about wine have a desire to drink wine, most do not actively participate in purchasing wine for the above reasons, and this situation is pointed out as a major obstacle to the spread of wine culture.

Accordingly, the development of a wine recommendation method that allows general consumers to easily and conveniently search for the style of wine they want based on information and evaluations provided by those with expert knowledge about wine is emerging.

In general, product recommendation systems include a content-based recommendation system that normalizes product attributes to random values or characters to recommend products with the highest similarity to the user's information, and other users with similar tendencies to the user. A collaborative filtering recommendation system that recommends products based on opinions, performs content-based recommendation and collaborative filtering-based recommendation separately and combines the predicted ratings, or combines some of the characteristics of content-based recommendation with collaborative filtering. There is a hybrid recommendation system that recommends products.

However, as mentioned above, the selection criteria for wine are very broad and various specialized knowledge may be required to select a wine that matches one's taste, so it is difficult to guarantee the reliability of the recommendation if the above recommendation system is applied to wine products. There are limits. Accordingly, in order to improve the accuracy, reliability, and user satisfaction of wine recommendations, there is a need to build a system that recommends wine by reflecting more heavily the evaluation information provided by those with expertise, such as various experiences in wine.

The present invention is intended to solve the problems of the prior art described above. The present invention quantifies the user's expertise based on the user's input information and profile information and reflects this in the rating for each wine type, so that N types of wine are ranked in the order of the highest rating. Provides a system and wine recommendation method for recommending wines.

However, the technical challenge that this embodiment aims to achieve is not limited to the technical challenges described above, and other technical challenges may exist.

The wine recommendation system according to the present invention includes a wine information providing service server that provides information about wine through a user interface, and the wine information providing service server collects the user's input information about wine and the user's profile information. And, it is based on at least one of the following variables: the number of wine ratings provided, the number of types of wine purchased, the number of posts registered, the number of wine-related professional qualifications, the experience in the wine industry, the morphological analysis score, and the information on measuring expertise in wine. Calculate the expertise score of each user according to Equation 1,

Equation 1:

Here, x=1,...,x=n are individual variables, n is the total number of users, i is an individual user,' ' is the score for each variable for each individual user, ' 'is the highest score among all users' scores for individual variables,' ' means the total number of variables,

The wine information provision service server calculates the final rating for each type of wine according to Equation 2 below based on the expertise score of each user calculated as above,

Equation 2:

Here, i is an individual user, m is the total number of users who gave ratings to individual wine types, ' ' is the individual user's expertise score value calculated according to Equation 1 above, ' ' refers to the rating given by individual users to individual wine types,

The wine information provision service server compares the final scores of individual wine types calculated as above and provides information about N wines in the order of wines with the highest final scores through a user interface.

The present invention calculates the final rating of each individual wine type by reflecting the user's expertise score in the rating given to each individual wine type and recommends the wine type based on this, so even those who lack expert knowledge about wine can receive more reliable information. There is an advantage in that you can select wine using .

Figure 1 is a block diagram of the entire wine recommendation system.
FIG. 2 is a block diagram of the user terminal of FIG. 1.
Figure 3 is a block diagram of the wine information providing service server of Figure 1.
Figures 4a and 4b are exemplary diagrams of the process of calculating the user's expertise score and the final rating of the wine.
Figure 5 is an example diagram of a wine recommendation page.
Figure 6 is an example diagram of the process of calculating a morphological analysis score.
Figure 7 is an example diagram of morpheme information.
Figure 8 is a flow chart of the wine recommendation method according to the present invention.

Below, with reference to the attached drawings, embodiments of the present invention will be described in detail so that those skilled in the art can easily implement the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein.

In describing the present invention, if it is determined that a detailed description of related known technology or configuration may unnecessarily obscure the gist of the present invention, the detailed description will be omitted. In addition, the terms described below are terms defined in consideration of functions in the present invention, and may vary depending on the intention or custom of the client, operator, or user. Therefore, the definition of terms should be judged based on the content throughout this specification.

In terms used herein, singular expressions should be understood to include plural expressions unless clearly interpreted differently from the context, and when a part is said to be “connected” to another part, it is “directly connected.” It should be understood to include not only cases in which they are connected, but also cases in which they are "electrically connected" with other elements in between, and when a part is said to "include" a certain component, this means unless there is a special statement to the contrary. It should be understood that it does not exclude one other component, but may further include other components.

Now, with reference to Figure 1, we will look at the wine recommendation system according to the present invention in more detail.

As shown in FIG. 1, the wine recommendation system according to the present invention may include a communication network 100, a user terminal 200, and a wine information providing service server 300.

The communication network 100 includes, for example, Long Term Evolution (LTE), LTE-Advanced (LTE-A), WI-FI, Local Area Network (LAN), Wide Area Network (WAN), Code Division Multiple Access (CDMA), It can be implemented through Time Division Multiple Access (TDMA), Wireless Broadband (WiBro), and Global System for Mobile Communications (GSM), and can also be implemented using other communication methods developed in the past, present, or that will be available in the future. .

The user terminal 200 includes, for example, a smart phone, a portable terminal, a mobile terminal, a personal digital assistant (PDA), a portable multimedia player (PMP) terminal, and telematics. (Telematics) terminal, navigation terminal, personal computer, laptop computer, Slate PC, Tablet PC, ultrabook, wearable device, WiBro ( Wibro) terminals, IPTV (Internet Protocol Television) terminals, smart TVs, digital broadcasting terminals, AVN (Audio Video Navigation) terminals, A/V (Audio/Video) systems, flexible terminals, etc., perform communication It can be implemented as an electronic device or similar device that can receive user input and output a screen.

The user terminal 200 is a terminal used by the user to access the wine information provision service server 300 and receive a wine recommendation service. The user terminal 200 and the wine information providing service server 300 are connected through the communication network 100 as shown in FIG. 1 and can communicate with each other through the communication network 100. The user terminal 200 will be described in detail later with reference to FIG. 2.

The wine information provision service server 300 may be implemented as, for example, a workstation, wine information service server, general-purpose computer, other electronic device capable of performing communication, or a similar device, and includes a web server or application server. can do.

In addition, the wine information providing service server 300 provides a user interface that the user terminal 200 can access through the communication network 100, and the user terminal 200 provides a wine information providing service through the user interface. Specific information may be requested or provided to the server 300, and the wine information providing service server 300 may display specific information on the user interface. The wine information providing service server 300 may transmit and receive information by voice or other methods instead of transmitting and receiving information visually. Hereinafter, for convenience, it will be described as if the user terminal 200 or other external device and the wine information providing service server 300 communicate directly.

Additionally, the wine information provision service server 300 may provide a social network service that allows wine-related posts to be exchanged between a plurality of users. The social network service is a service that allows users to register posts or comments on other users' posts, and may be an independent service or a service linked to another social network service, but is not limited thereto. Additionally, the social network service may include a page where users can register posts or comments. The wine information providing service server 300 will be described in detail later with reference to FIG. 3.

Now, let's look at the user terminal 200 in detail with reference to FIG. 2.

As shown in FIG. 2, the user terminal 200 may include an input unit 210, a display unit 220, a communication unit 230, a storage unit 240, and a control unit 250.

The input unit 210 converts information entered by the user into the user terminal 200 or the user's input action into an input signal and transmits it to the control unit 250. The input unit 210 may be implemented, for example, with a keyboard, a mouse, a touch sensor on a touch screen, a touchpad, a keypad, a voice input, and other input processing devices that are currently available in the past or will be available in the future.

The display unit 220 outputs a user interface screen of the wine information providing service server 300 under the control of the control unit 250. At this time, the user interface can be accessed through an application stored in the user terminal 200, but is not limited to this.

The display unit 220 may be implemented as, for example, a liquid crystal display (LCD), a light emitting diode (LED), an organic light emitting diode (OLED), a projector, or other display devices that are currently available in the past or will be available in the future. Depending on the embodiment, a component that uses other methods to transmit information to the user terminal 200, such as voice output or vibration, instead of screen output, may be used instead of the display unit 220.

The communication unit 230 can exchange information with the wine information provision service server 300. At this time, the communication unit 230 transmits the information received from the wine information provision service server 300 to the control unit 250, and provides wine information according to the control of the control unit 250 with the information entered by the user in the input unit 210. Delivered to the service server 300. The communication technology used by the communication unit 230 may vary depending on the type of communication network 100 or other circumstances.

The storage unit 240 stores information in the user terminal 200 under the control of the control unit 250 and transmits information requested from the control unit 250 to the control unit 250. The storage unit 240 may be implemented as a total of physically separated storage devices.

The control unit 250 controls the overall operation and each component of the user terminal 200. The control unit 250 may cause the information input to the input unit 210 to be transmitted to the wine information provision service server 300 through the communication unit 230, and the communication unit 230 may receive the information from the wine information provision service server 300. Information is displayed through the display unit 220. The role performed by the control unit 250 can be distributed and processed by several physically separated computing devices, and in this case, the control unit 250 can be implemented as the sum of the physically separated computing devices.

If the control unit 250 or the storage unit 240 is implemented as the sum of several physically separated devices, communication between multiple devices may be necessary. In this specification, for simplicity of explanation, description will be made on the assumption that the storage unit 240 or the control unit 250 is implemented as a single object.

When the user terminal 200 transmits and receives information, depending on the viewpoint, it may be expressed that the communication unit 230 transmits and receives information under the control of the control unit 250, or the control unit 250 controls the communication unit 230 to transmit and receive information. It can also be expressed that it does.

Now, with reference to FIG. 3, we will look at the wine information providing service server 300 in detail.

As shown in FIG. 3, the wine information providing service server 300 according to the present invention may include a communication unit 310, a control unit 320, and a storage unit 330.

The communication unit 310 exchanges information with the user terminal 200 or other external devices connected to the wine information provision service server 300, or other portals, websites, applications, or servers. For example, the communication unit 310 transfers the request or information received from the user terminal 200 connected to the wine information providing service server 300 to the control unit 320, and transfers the information stored in the storage unit 330 to the control unit 320. It can be transmitted to the user terminal 200 under the control of 320. The communication technology used by the communication unit 310 may vary depending on the type of communication network 100 or other circumstances.

The storage unit 330 stores information under the control of the control unit 320 and transmits information requested from the control unit 320 to the control unit 320. The storage unit 330 may be implemented as a total of physically separated storage devices. The storage unit 330 refers to a non-volatile storage device that continues to maintain stored information even when power is not supplied, and a volatile storage device that requires power to maintain the stored information.

A wine recommendation program is stored in the storage unit 330. This wine recommendation program is designed to calculate wine recommendation information based on information stored in the storage unit 330 and is executed through the control unit 320.

Additionally, the storage unit 330 stores information about a plurality of wines. At this time, the information about the wine may include meta information about the wine. Meta-information about wine is defined for each wine and may include information such as name, image, type, production area, price, raw materials, production year, taste, user posting, and rating. Meta information about wine may be registered by the user terminal 200 or other external device, or may be received and stored from another portal, website, application, or server.

Additionally, the storage unit 330 stores user profile information. At this time, the user's profile information may be provided from the user terminal 200 to the wine information provision service server 300, or may be information disclosed on other portals, websites, applications, or servers. For example, the rating of a wine or the profile information of the relevant evaluator that is not registered in the wine information provision service server 300 and is disclosed in other portals, websites, applications or servers is received through the communication unit 310 and stored in the storage unit. It can be stored at (330).

The user's profile information stored in the storage unit 330 includes the content of ratings or posts provided by the user in the past, the number of types of wine purchased in the past, the number of wine-related professional qualifications, or experience in the wine industry. It can be done, but it is not limited to this. At this time, the post may include a comment written by the user on a post primarily registered by another user.

The control unit 320 controls the overall operation and each component of the wine information providing service server 300. For example, the control unit 320 may retrieve necessary information from the storage unit 330 and transmit the information to the user terminal 200 or other external device through the communication unit 310. When information is received from the user terminal 200 or other external device, the information can be stored in the storage unit 330.

Additionally, the control unit 320 may execute the wine recommendation program stored in the storage unit 330 to calculate wine recommendation information and provide the information to the user terminal 200 through the user interface. Specifically, the control unit 320 extracts information about the wine type and the user's profile information from the storage unit 330, calculates the final rating for the corresponding wine type by reflecting the weight on the rating given to each wine by each user, and N types of wine are recommended to the user in the order of the wine type with the highest final rating.

Now, we will look at the process by which the control unit 320 calculates the final score of the wine type in which the weight is reflected. In order to calculate the final score reflecting the weight for each type of wine whose information is stored in the wine information provision service server 300, the control unit 320 first collects the user's profile information and calculates the expertise score of each user based on this. . At this time, the variables used to calculate each user's expertise score include the number of past ratings provided, the number of types of wine purchased, the number of posts registered, the number of wine-related professional qualifications, experience in the wine industry, and morphological analysis. The score may be included, but is not limited to this, and the expertise score can be calculated by adding other information that serves as a standard for measuring the user's expertise as a variable.

The equation used to calculate the expertise score of individual user i is as follows:

Here, x=1,...,x=n are individual variables, 'n' is the total number of users, 'i' is individual users,' ' is the score for each variable for each individual user, ' 'is the highest score among all users' scores for individual variables,' ' means the total number of variables. The expertise score of an individual user represents the relative expertise level among all users and is calculated as a percentage. The higher the expertise score, the higher the wine expertise among all users.

The expertise score of the individual user calculated in this way is multiplied by the rating given by the user to the individual wine type to calculate the weighted score, and the value added by the user's weighted rating is divided by the value added by the user's expertise score. The final score for the corresponding wine type is calculated. The method for calculating the final rating of an individual wine type can be expressed mathematically as follows:

Here, 'i' is an individual user, 'm' is the total number of users who gave ratings to individual wine types, ' ' is the expertise score value of each user calculated according to the above equation, ' ' refers to the rating given by individual users to individual wine types. Accordingly, a higher weight may be applied to the rating given by a user with a high expertise score.

Figure 4a is an example diagram of the process of calculating the user's expertise score, and Figure 4b is an example diagram of the process of calculating the final rating of wine.

Figure 4a is based on the assumption that there are a total of 4 users ('A', 'B', 'C', and 'D') who gave ratings to a specific wine, and the variable is the number of users who gave ratings to the wine in the past (' 'Number of evaluations'), number of types of wine purchased in the past ('Number of wines purchased'), number of posts about wine in the past ('Number of posts'), and number of professional qualifications related to wine ('Number of certificates'). set.

Figure 4b shows the process of calculating the final score of a wine type based on the expertise score of each user calculated in Figure 4a. The table on the left shows each user's 'Wine 1', 'Wine 2', and 'Wine'. It shows the ratings given to 'Wine 3', 'Wine 4', and 'Wine 5'. At this time, each user's rating is multiplied by the user's expertise score shown in the table in the middle to calculate the users' 'Wine Rating' for each type of wine. Then, dividing this sum by the sum of the expert scores of the relevant users yields the final rating for each type of wine.

The control unit 320 compares the final scores of each wine type calculated as above and provides recommended information about N wines in the order of the wine type with the highest final score through the user interface. This wine recommendation information may include detailed information about the wine, such as the final rating of the wine type, wine name, grape variety, price, sugar content, and image.

Figure 5 is an example diagram of a wine recommendation page according to the present invention.

Meanwhile, among the variables that can be applied to calculate the expertise score of an individual user, the 'morphological analysis score' is a quantification of the user's expertise in wine based on the content of the post written by the individual user. Hereinafter, the calculation method is described. Let's take a look at this.

The control unit 320 may perform morpheme analysis on the user's post to extract valid morphemes corresponding to the evaluation opinion about the wine. At this time, technical terms presented through credible institutions, organizations, wine-related web pages, books, etc. can be set to be extracted as valid morphemes, but the method is not limited to this. For example, among the valid morphemes that can be extracted, morphemes according to the '101 Michelin Wine Terms' listed on the Michelin Guide's web page may be included.

For example, if the post written by the user is “I can feel the depth of the wine in the light oak scent,” the control unit 320 can extract “light,” “oak scent,” and “heaviness” as valid morphemes. In the case of “It has a citrus scent and a fresh aftertaste,” “citrus” and “fresh” can be extracted as effective morphemes.

In addition, the control unit 320 can set each valid morpheme to be weighted according to the degree to which it represents expertise in wine, and calculate the morphological analysis score for the user by adding up the weight values of the valid morphemes extracted from the user's posts. You can. At this time, even if the same user uses the same valid morpheme multiple times, the weight value for the valid morpheme is not added repeatedly.

For example, morphemes such as “vanilla” and “bouquet” that are uncommon and can be seen as indicating the user’s high level of experience and expertise in wine can be set to be given higher weight than common morphemes such as “bitter” and “sweet.” there is. Accordingly, users with high morphological analysis scores can be interpreted as having relatively higher expertise in wine compared to users with low morphological analysis scores.

Figure 6 is an example diagram of the process of calculating a morphological analysis score. The table at the top of Figure 6 displays the number of morphemes included in the previously set set of valid morphemes (see first row) among the morphemes of the user's posting through document-term matrix analysis, and shows the number of morphemes included in the set of valid morphemes (see the first row) of the user's posting. The table displays the weight given to each valid morpheme previously set, and the table at the bottom displays the morpheme analysis score ('score') calculated by adding up the weight values of all valid morphemes included in the user's post.

Meanwhile, the wine information provision service server 300 extracts morphemes corresponding to valid morphemes from users' posts registered for individual wine types, and provides a set of extracted morphemes to the user interface as one of the information about individual wine types. can do. Here, the area occupied by each valid morpheme can be set differently depending on the frequency of the valid morpheme, and the color of each valid morpheme can be set differently depending on whether its meaning is positive or negative.

Figure 7 is an example diagram of morpheme information provided through a user interface.

Now, with reference to FIG. 8, a wine recommendation method performed by the wine information providing service server 300, which constitutes the wine recommendation system according to the present invention, will be described.

Figure 8 is a flow chart of the wine recommendation method according to the present invention.

First, the wine information provision service server 300 collects and stores user input information and user profile information for individual wine types. This information may be registered on the wine information provision service server 300 by the user terminal 200 or other external device, or may be received and stored from other portals, websites, applications, or servers. At this time, information about the wine may include the name, image, type, production area, price, raw materials, production year, taste, user posting, rating, etc. of the wine. Additionally, the user's profile information may include ratings or posts about wine that the user has provided in the past, the number of types of wine purchased in the past, the number of wine-related professional qualifications, or experience in the wine industry. . At this time, the user's posting may include not only posts directly registered by the user, but also comments written by the user on posts primarily registered by other users.

In the next step, the wine information provision service server 300 calculates the user's expertise score using the user's profile information. The equation used to calculate the expertise score of individual user i is as follows:

The expertise score of the individual user is calculated as a percentage, where x=1,...,x=n are individual variables, 'n' is the total number of users, 'i' is the individual user,' ' is the score for each variable for each individual user, ' 'is the highest score among all users' scores for individual variables,' ' means the total number of variables. Here, the variable is information that serves as a standard for measuring the user's expertise score, such as the number of times the user provided ratings for wine products in the past, the number of types of wine purchased in the past, and the number of posts about wine in the past. , the number of wine-related professional qualifications, number of days of experience working in the wine industry, morphological analysis score, etc. can be variables.

The morpheme analysis score, which can be used as a variable in calculating the expertise score, is calculated by performing morpheme analysis on the posts registered by the user. To this end, the wine information provision service server 300 extracts effective morphemes corresponding to evaluation opinions about wine from the content of the posting registered by the user, and assigns weight to each effective morpheme according to the degree of expertise in wine. The sum of all the weight values of the extracted individual morphemes is taken as the user's morpheme analysis score. At this time, even if the same user uses the same valid morpheme multiple times, the weight value for the valid morpheme is not added repeatedly. Meanwhile, valid morphemes that can be extracted as described above may be technical terms presented through credible institutions/organizations or wine-related web pages, books, etc., but are not limited thereto.

In the next step, based on the individual user's expertise score, the final rating for each wine type is calculated according to the following equation:

Here, 'i' is an individual user, 'm' is the total number of users who gave ratings to individual wine types, ' ' is the expertise score value of each user calculated according to the expertise score equation above, ' ' refers to the rating given by individual users to individual wine types.

In the next step, the wine information provision service server 300 compares the final scores of individual wine types calculated as above and displays recommended information about N types of wine through the user interface in the order of the wine type with the highest final score. do. This wine recommendation information may include detailed information about the wine, such as wine name, grape variety, price, sugar content, and image.

The description of the present invention described above is for illustrative purposes, and those skilled in the art will understand that the present invention can be easily modified into other specific forms without changing the technical idea or essential features of the present invention. will be. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive. For example, each component described as unitary may be implemented in a distributed manner, and similarly, components described as distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the claims rather than the detailed description above, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be construed as being included in the scope of the present invention.

100: communication network
200: user terminal
210: input unit
220: display unit
230: Department of Communications
240: storage unit
250: control unit
300: Wine information provision service server
310: Department of Communications
320: control unit
330: storage unit

Claims (8)

In the wine recommendation system,
The wine recommendation system includes a wine information provision service server that provides wine recommendation information through a user interface,
The wine information provision service server collects the user's input information about the type of wine and the user's profile information, and collects the number of wine ratings provided, the number of types of wine purchased, the number of posts registered, the number of wine-related professional qualifications, and the experience in the wine industry. , at least one of the morphological analysis score and the expertise measurement information about wine is used as a variable, and based on this, the expertise score of each user is calculated according to Equation 1 below,
Equation 1:

Here, x=1,...,x=n are individual variables, 'n' is the total number of users, 'i' is individual users,' ' is the score for each variable for each individual user, ' 'is the highest score among all users' scores for individual variables,' ' means the total number of variables,
The wine information provision service server calculates the final score for each type of wine according to Equation 2 below based on the expertise score of each user calculated as above,
Equation 2:

Here, 'i' is an individual user, 'm' is the total number of users who gave ratings to individual wine types, ' ' is the individual user's expertise score value calculated according to Equation 1 above, ' ' refers to the rating given by individual users to individual wine types,
The wine information provision service server compares the final scores of individual wine types calculated as above and provides information about N types of wine through a user interface in the order of the wine type with the highest final score. In claim 1,
A wine recommendation system, wherein information about the type of wine provided through the user interface includes at least one of the wine name, grape variety, price, sugar content, and image. In claim 1,
The wine information provision service server stores terms representing evaluation opinions about wine as effective morphemes, and assigns weight to each effective morpheme according to the degree to which it represents expertise in wine.
Extracting morphemes corresponding to valid morphemes from the contents of posts registered by the user, adding up the weight values of all extracted individual morphemes as the user's morpheme analysis score, and applying this as a variable in the individual user's expertise score, Wine recommendation system. In claim 3,
Extract morphemes corresponding to valid morphemes from the content of posts by users registered for individual wine types, and provide the extracted morphemes to the user interface as information about individual wine types,
Here, the area occupied by each valid morpheme is set differently depending on the frequency of the valid morpheme, and the color of each valid morpheme is set differently depending on whether its meaning is positive or negative. This is a wine recommendation system. In the wine recommendation method performed by the wine recommendation system,
A wine information providing service server included in the wine recommendation system collects the user's input information about the type of wine and the user's profile information;
The wine information provision service server collects at least one of the following information: the number of times a user's wine rating is provided, the number of types of wine purchased, the number of posts registered, the number of wine-related professional qualifications, experience in the wine industry, morphological analysis score, and wine expertise measurement information. This is a step of calculating the expertise score of each user according to Equation 1 below, based on this as a variable,
Equation 1:

Here, x=1,...,x=n are individual variables, 'n' is the total number of users, 'i' is individual users,' ' is the score for each variable for each individual user, ' 'is the highest score among all users' scores for individual variables,' ' refers to the total number of variables;
A step in which the wine information provision service server calculates a final rating for each type of wine according to Equation 2 below based on the expertise score of the individual user calculated as above,
Equation 2:

Here, 'i' is an individual user, 'm' is the total number of users who gave ratings to individual wine types, ' ' is the individual user's expertise score value calculated according to Equation 1 above, ' ' refers to the rating given by an individual user to an individual wine type; and,
Comprising the step of the wine information providing service server comparing the final scores of individual wine types calculated as above and providing information about N types of wine through a user interface in the order of the wine type with the highest final score. Recommended method. In claim 5,
A wine recommendation method comprising including at least one of a wine name, grape variety, price, sugar content, and image in information about a wine type provided through a user interface. In claim 5,
The wine information provision service server stores terms representing evaluation opinions about wine as effective morphemes, and assigns weight to each effective morpheme according to the degree to which it represents expertise in wine.
Includes the step of extracting morphemes corresponding to valid morphemes from the contents of posts registered by the user, adding up the weight values of all extracted individual morphemes as the user's morpheme analysis score, and applying this as a variable in the individual user's expertise score. How to recommend wine. In claim 7,
A step of extracting morphemes corresponding to valid morphemes from the content of a user's post registered for an individual wine type and providing the extracted morphemes to the user interface as information about the individual wine type,
Here, the area occupied by each effective morpheme is set differently according to the frequency of the effective morpheme, and the color of each effective morpheme is set differently depending on whether its meaning is positive or negative.

Images