KR20200119870A - Fragrance-related product recommendation system - Google Patents

Abstract

The present invention relates to a fragrance product recommendation system, comprising: a content storage unit in which information on a fragrance product is stored; An input unit for receiving color information selected by a user; A matching unit matching the color information input by the user with the fragrance information of the fragrance product included in the content storage unit; And an output unit that provides fragrance product information according to the matching result.

Description

Fragrance-related product recommendation system

The present invention relates to a system for recommending a fragrance-related product, and more particularly, to a system for recommending a fragrance-related product reminiscent of an image similar to the color when a consumer expresses an image of a fragrance he or she desires in color.

As people's overall quality of life improves, interest in appearance is on the rise. Modern consumers use scented products (hereinafter referred to as fragrance products) as a means to pursue individuality and express images. These fragrance products include perfumes, fragrances, diffusers, scented candles, creams, and powder.

When using scented products, as in choosing clothes, use them according to mood, place, and situation. For example, lighter and more refreshing fragrances are better used in summer, they feel enveloping, and warm, spreading fragrances are preferred in winter. Also, when they are depressed, they often use bright perfumes, and when they go to job interviews, they prefer serious perfumes.

When consumers choose fragrance products, they are guided by the sales clerk who sells fragrance products, but it is difficult for consumers who do not have a wealth of knowledge about fragrance products to express their desired fragrance to the clerk in a language. In particular, it is even more difficult to express the scent in words in the case of a complex scent with multiple scents. And according to the customer's inaccurate expression, the clerk guides the fragrance product, and the consumer tastes and selects the fragrances of some of the guided fragrance products. In particular, in the case of perfume, it is common to choose a perfume only with Top Note (the most volatile component among the combined perfumes, which lasts about 10 to 20 minutes after the perfume starts in contact with the air). Because consumers want to purchase perfumes immediately after they are in store, they do not consider the middle notes (scent lasts 1-2 hours) and base notes (scent lasts more than 3 hours) with longer scent durations. Eventually, they rely on the guidance of the clerk and often choose a perfume that does not suit their taste.

Fragrance stores, including Sephora.com, provide services that help consumers find the product they want according to their preferences. These services match the fragrance products being sold using the description of the fragrance entered by the consumer.

However, since the conventional fragrance product recommendation system selects a fragrance product based on the fragrance expressed by the consumer in a language, there is a limit to finding a fragrance product close to the fragrance that the consumer truly wants.

In addition, a program for recommending cosmetics by acquiring user information has been developed as in Korean Patent Application Publication No. 10-2018-0064326 (published on 14 June 2018), but at the level of recommending cosmetics based on the user's skin information. However, the composition for recommending the fragrance products desired by consumers is not disclosed.

The present invention is a method for solving the problem of searching for and selecting a fragrance product by expressing the fragrance that the consumer wants in a language. When the consumer expresses an image of the fragrance they want in a color, the image most similar to this color is displayed. It provides a system that recommends fragrance products with reminiscent scents.

In addition, the object of the present invention is not limited to those mentioned in the problem to be solved, and other problems to be solved that are not mentioned will be clearly understood by those skilled in the art from the following description.

In order to achieve the object of the present invention, the fragrance product recommendation system according to the present invention comprises: a content storage unit in which information on fragrance products is stored; An input unit for inputting color information desired by the user; A matching unit matching the color input by the user with the fragrance information of the fragrance product included in the storage unit; And an output unit that provides flavor product information according to the matching result of the matching unit.

The content storage unit includes general information such as the name, manufacturer, and release date of the fragrance product as related information (hereinafter referred to as “scent product information”) and fragrance related information such as notes and accords (hereinafter referred to as “scent information”). It includes).

Among fragrance products, perfume, in particular, volatilizes fragrance by mixing alcohol with various kinds of fragrances, and the feeling of fragrance changes over time after spraying the fragrance depending on which fragrances are prepared by combining them. Fragrances are classified into top note, middle note, and base note according to the scent stage. In other words, it can be said that the body of the perfume is determined by the base note, but the first impression of the perfume is determined by the top note. Therefore, the information on the fragrance raw materials is included in each of the top note, middle note, and base note as fragrance information of perfume.

The input unit receives one or more color information selected by the user as input. Color information is inputted by selecting a color through an input window such as a color palette, or after a video image is captured in real time using a video device such as a camera, the color information is extracted or stored in a storage medium such as a hard disk. There is a method in which color information is extracted after a pre-stored video image is selected.

In addition, the matching unit, (a) converting the color information input through the input unit to a value; (B) converting the fragrance information of the fragrance product stored in the storage unit into a value; And (c) comparing the converted two values with respect to a plurality of flavor products, and performing a similar degree to each other. Through a verification method including, a consumer can find a flavor product desired by the consumer.

At this time, the verification method, in the step (b), when the fragrance of the fragrance product is a complex fragrance, the weight occupied by the notes of the fragrance product may be reflected.

According to the scent product recommendation system according to the present invention, the consumer can more easily and accurately find a product having the desired scent by expressing the image he or she thinks in color.

In addition, the effects of the present invention are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

1 is a diagram showing the configuration of a fragrance product recommendation system according to the present invention.
2 is a diagram showing a color mode usable in the present invention.
3 is a diagram showing an input unit of the first embodiment of the fragrance product recommendation system according to the present invention.
4 is a view showing the output unit of the first embodiment of the fragrance product recommendation system according to the present invention.
5 is a view showing the input unit of the second embodiment of the fragrance product recommendation system according to the present invention.

Prior to the detailed description of the present invention, the present invention can be made various modifications and various embodiments, and the examples described below and shown in the drawings are intended to limit the present invention to specific embodiments. It should be understood as including all changes, equivalents, and substitutes included in the spirit and scope of the present invention.

When a component is referred to as being "connected" or "connected" to another component, it is understood that it may be directly connected or connected to the other component, but other components may exist in the middle. Should be. On the other hand, when a component is referred to as being "directly connected" or "directly connected" to another component, it should be understood that there is no other component in the middle.

The terms used in the present specification are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this specification, terms such as "comprise" or "have" are intended to designate the presence of features, numbers, steps, actions, components, parts, or a combination thereof described in the specification, but one or more other features. It is to be understood that the presence or addition of elements or numbers, steps, actions, components, parts, or combinations thereof, does not preclude in advance.

In addition, terms such as "... unit", "... unit", and "... module" described in the specification mean a unit that processes at least one function or operation, which is hardware, software, or hardware and It can be implemented as a combination of software.

In addition, in the description with reference to the accompanying drawings, the same reference numerals are assigned to the same components regardless of the reference numerals, and redundant descriptions thereof will be omitted. In describing the present invention, when it is determined that a detailed description of related known technologies may unnecessarily obscure the subject matter of the present invention, a detailed description thereof will be omitted.

As individuality is important in modern times, individuals use fragrance products to express their image as much as possible, and the fragrance product industry is developing more than ever. Fragrance products use a variety of scents to widen consumers' choices, and this phenomenon is giving consumers difficulties in choosing at the same time. Therefore, the technology that recommends fragrance products with the scent desired by consumers is attracting attention.

When consumers choose fragrance products, it is not easy to express their desired fragrance in language, so an easier and more accurate means of expression is required.

Humans also identify the smell of objects through visual information recognized by their eyes. This is because the perceived color information brings up the image of a specific object, so that the smell can be guessed based on the experience of the associated image.

The present invention relates to a method for finding a fragrance product having a fragrance most similar to an image associated with a color selected by a consumer.

Hereinafter, the configuration and operation of the first embodiment to which the fragrance product recommendation system according to the present invention is applied will be described in detail with reference to FIGS. 1 to 5.

As shown in Fig. 1, the first embodiment to which the fragrance product recommendation system according to the present invention is applied includes a content storage unit 100, a user input unit 200, a matching unit 300, and an output unit 400. It is composed by

At this time, the content storage unit 100, the user input unit 200, the matching unit 300, and the output unit 400 may be independently implemented in various media such as smartphones, computers, and TVs. It can also be implemented through communication.

In other words, it is natural that how and what to implement each of the above-described configurations does not limit the scope of the present invention. However, for more detailed description, it will be described by way of example that all other embodiments including the first embodiment are implemented through one portable terminal 10 as in the first embodiment.

To describe in more detail each of the configurations that can be implemented in various ways as described above, first, the content storage unit 100 stores various information of the flavor product as content.

At this time, the content includes aroma information such as a note corresponding to the raw material of the fragrance product to be compared with the color information input by the user and an accord indicating the combination of fragrance, as well as general information such as the name and manufacturer of the fragrance product to be additionally displayed in the output unit. It includes more.

The input unit 200 may receive color information directly input by a user through an input window of a user terminal. In addition, a video image captured by a camera connected to a user terminal may be input in real time, or a video image file stored in a user terminal or another terminal connected through a communication network may be input and color information may be extracted therefrom. These input units use one or more color information.

When a fragrance product is searched according to a user's input, the matching unit 300 is configured to check whether the color information input by the user and the fragrance of the fragrance product included in the content storage unit are similar.

At this time, there may be various methods of checking whether the color desired by the user and the scent of the fragrance product are similar through the matching unit 300, and thus, it is natural that the scope of the right is not limited.

However, for a more detailed description, if an example of the verification method is described, it may consist of three steps, such as steps (a) to (c), as follows, but these three steps are not necessarily limited to the order of course. .

Specifically, an example of the verification method includes the step (a) of converting color information input through an input unit into a value; (B) converting the fragrance information of the fragrance product stored in the content storage unit into a value; And (c) step of comparing the converted two values for a plurality of flavor products to find similar flavor products.

At this time, the process in each step will be described in more detail. In step (a), the user designates a color he or she wants through the user input unit 200 (FIG. 3). At this time, any color mode such as HSB, RGB, CMYK, etc. may be used (Fig. 2). The color mode in this embodiment uses HSB and the input unit 200 uses the color wheel 210. The color wheel systematically arranges changes in color in a ring shape. The user selects one color on the color wheel (220), and the selected color is selected from [1 to 360].

Meanwhile, in step (b), the fragrance of the fragrance product stored in the storage unit is stored as a value. For example, the perfume "Aquadigio Profumo" is composed of five notes (Geranium, Rosemary, Sage, Patchouli, Incense) as fragrance information. Each note is mapped to the scent group (olfactory group) as shown in [Table 1]. As the fragrance group, a fragrance group designed by Michael Edwards can also be used. These include [Floral, Soft Floral, Floral Oriental, Soft Oriental, Oriental, Woody Oriental, Woods, Mossy Woods, Dry Woods, Aromatic, Citrus, Fruity, Green, Water]. And these scent groups are related to “The Fragrance Wheel.” Fragrance Wheel is a scent classification system used in the perfume industry, by arranging olfactory groups in a ring shape and the correlation between their scent groups. The neighboring scent groups on the scent wheel share relatively more scent characteristics compared to the other scent groups, which is similar to the color arrangement principle of the color wheel. The scent group in Table 1 is converted first, and this scent group is converted secondarily to the representative value on the scent wheel in [Table 2].

At this time, the conversion value corresponding to each fragrance group in Table 2 is determined according to the mapping between the fragrance group on the fragrance wheel and the color on the color wheel. This mapping is a value corresponding to the color reminiscent of when smelling the scent of the scent group, which is built on the basis of the results of many studies on the mutual conversion of fragrance and color. An example is the smell of caramel or honey and orange. Such research is possible through questionnaires or big data processing, and can be constructed in various ways according to gender, age, region, and occupation. If the value corresponding to Floral Oriental in Table 2 is "30", the color associated with scent group Floral Oriental notes (eg Caramel, Honey) is Orange, and Orange is the color-representative value in Table 3. This is because it has a value of "30" in the table. The color-representative value table in Table 3 may be an existing color mode as shown in FIG. 2 or may be separately defined and used.

The perfume "Aquadigio Profumo" in the examples is converted into values as follows. In the embodiment, the arithmetic mean is used in the cubic transformation. This is the same weight of each note, and various modifications are possible, such as increasing the weight of the base note.

Notes: Bergamot + Sea Water + Geranium + Rosemary + Sage + Patchouli + Incense

1st transformation: Citrus + Water + Floral + Aromatic + Aromatic + Woody Oriental + Soft Oriental

Quadratic Transformation: 180 + 120 + 60 + 2Х210 + 300 + 15

3rd transformation: (2nd transformation) / 7 = 156

In addition to notes, as fragrance information, accord, which is a combination of individual fragrances, is used. Common accords include [Amber, Aquatic, Aromatic, Balsam, Citrus, Floral, Fresh, Fruit, Gourmand, Green, Herbal, Oriental, Spice, Woods].

The accords included as fragrance information in fragrance products are sometimes included in pairs with each accord, which is a relative percentage value indicating how distinctive each accord is compared to other accords, and the response of fragrance experts or general consumers (comments or votes, etc.) ) Is determined by convergence.

For example, in the case of the fragrance Christian Dior's sobaju, it is composed of three accords (Bergamot, Amber, Woods) as fragrance information. When the relative sharpness of these is expressed on a scale from 1 to 10, in the case of 7, 2, and 1, respectively, they are converted as follows.

Accord: Bergamot x 7 + Amber x 2 + Woods x 1

1st order transformation: Citrus x 7 + Soft Oriental x 2 + Woods x 1

Quadratic transformation: 180 x 7 + 15 x 2 + 240 x 1

Cubic transformation: (quaternary transformation) / 10 = 153

And the matching unit 300 in step (c) compares the converted value of the color information for the color selected by the user input through the input unit and the converted value for the fragrance information of the fragrance product stored in the content storage unit, Flavor products having values are preferentially displayed through the output unit 400. At this time, a plurality of flavor products may be selected.

In the case of the first embodiment, the perfume "Aquadigio Profumo" has a converted value of fragrance information of "156", so if the color information selected by the user is an index between Green and (converted value 120) and Cyan (converted value 180), similar Recommended for perfume.

5 shows the input unit of the second embodiment to which the fragrance product recommendation system according to the present invention is applied, and its operation will be described in detail as follows.

A video image is input through a video device such as a camera of a user terminal, and a fragrance product having a scent similar to the color included in the video image is searched for, and the information is displayed. When a user takes a picture of his or her clothes to find the perfume of the image that matches the clothes he wears, when the captured image of the top and bottom of the clothes is input, that is, when two or more color information is input, the matching unit is used for each color. Fragrance products with fragrance information belonging to the fragrance group corresponding to the information are matched.

On the other hand, the output unit 400 displays the matching result of the matching unit, the information as color and flavor information input by the consumer, including a manufacturer and a note (Fig. 4).

As described above, in the specification and drawings, various embodiments of the present invention have been disclosed, and although specific terms are used, these are merely used in a general meaning to easily explain the technical content of the present invention and to aid understanding of the present invention. It is not intended to limit the scope of the invention. In addition to the embodiments disclosed herein, it is apparent to those of ordinary skill in the art that other modified examples based on the technical idea of the present invention may be implemented.

The present invention is a method for solving the problem of searching for and selecting a fragrance product by expressing the fragrance that the consumer wants in a language. When the consumer expresses an image of the fragrance they want in a color, the image most similar to this color is displayed. It provides a system that recommends fragrance products with reminiscent scents. In addition, the object of the present invention is not limited to those mentioned in the problem to be solved, and other problems to be solved that are not mentioned will be clearly understood by those skilled in the art from the following description.

Claims (6)

A content storage unit for storing flavor product information;
An input unit for receiving color information from a user;
A matching unit for matching color information input by the user through the input unit and scent information among scent product information included in the content storage unit; And
Containing; an output unit that provides the matching result of the matching unit,
Flavor product recommendation system. The method of claim 1,
The content storage unit,
Comprising at least one of notes and accords as fragrance information of a fragrance product to be compared with the color information input by the user,
Flavor product recommendation system. The method of claim 1,
The input unit,
Using at least one of color information input through the color input window, color information extracted from a video image captured in real time by a video device, and color information extracted from a pre-stored video image,
Flavor product recommendation system. The method of claim 1,
The matching unit,
(A) converting color information input by a user through the input unit into a value;
(B) converting the fragrance information of the fragrance product stored in the content storage unit into a value; And
Through a verification method comprising a; step (c) of comparing the converted two values for a plurality of flavor products to find similar flavor products,
Recommends fragrance products that have a similar scent with the color information entered by the user and the image,
Flavor product recommendation system. The method of claim 4,
The matching unit,
When two or more color information is input through the input unit, a fragrance product having fragrance information belonging to two or more fragrance groups corresponding to each color information is found and recommended,
Flavor product recommendation system. The method of claim 1,
The output unit,
Preferentially displaying information on the most similar fragrance products for one or more fragrance products found as a result of matching by the matching unit,
Flavor product recommendation system.

Images