Personalized Fragrance Recommendation System and Method

Abstract

The present invention is a system for recommending customized fragrances through the collection of personal information via images or questionnaires, characterized by comprising: a fragrance information storage unit capable of storing and providing information on fragrances by various categories; a fragrance recommendation unit that receives information from the fragrance information storage unit, analyzes personal information using images or questionnaires, and generates a customized fragrance list; a fragrance note classification unit that receives the fragrance list from the fragrance recommendation unit and classifies fragrances by note; and a fragrance combination unit that receives notes from the fragrance note classification unit and provides an optimal blending ratio according to the fragrance list.

Description

Technology Field

[0001] The present invention relates to a personalized fragrance recommendation system and method that extracts a fragrance list through images and surveys. Background Technology

[0002] Due to recent rapid environmental changes, health is being threatened by a lack of pleasant living environments and a decline in natural purification rates, leading to the widespread use of fragrance-emitting products such as diffusers and air fresheners to make indoor air pleasant.

[0003] In addition, fragrance plays an important role in aromatherapy, which involves inhaling the scent of various natural fragrances beneficial to the human body such as herbs, aromatherapy that helps treat diseases, and cosmetics used for skin care.

[0004] The fragrance market, including cosmetics and perfumes, is largely divided into offline and online sectors.

[0005] However, in the online sale of fragrance products, only product images, descriptions, and video information are provided to consumers; considering the nature of fragrance products where scent is important, there are difficulties in product selection due to the limitation that consumers cannot directly smell the fragrance.

[0006] Meanwhile, consumers experience specific sensibilities that are difficult to express in words due to the scent emanating from fragrance products. For example, they may feel freshness, freshness, calmness, melancholy, vitality, sexiness, and others may also be assimilated by the scent or feel that person's unique sensibility.

[0007] As such, the specific sensation evoked by the scent of a fragrance product is an important factor in selecting a perfume; however, particularly in the case of online purchases, users face difficulties in making a purchase because they cannot determine whether the perfume they intend to buy emits a scent they prefer.

[0008] Meanwhile, perfume is regarded by people as a part of fashion and a means of self-expression. However, unless users try the scents in person at a store, it is not easy to find the fragrance they desire.

[0009] Meanwhile, due to technological advancements, various online shopping malls selling perfumes have emerged, allowing users to purchase products without visiting physical stores; these online malls are actively trading a wider variety of perfume products than traditional offline stores.

[0010] However, since it is impossible to directly sample or check the actual size of perfume products purchased from online shopping malls, buyers often make purchases based solely on the information provided online. Consequently, cases frequently occur where the scent differs from what the buyer expected upon receiving the product, resulting in low user satisfaction.

[0011] In such cases, users take actions such as returning, canceling, or exchanging the perfume product, which causes problems in terms of time and money for shopping mall operators, product manufacturers, and buyers.

[0012] Although conventional technologies are disclosed to address these problems, these conventional technologies have the disadvantage that user satisfaction can vary significantly depending on artificial intelligence algorithms, matching algorithms, etc., and it takes a long time for the algorithms to be optimized, as they output recommendation data without additional correction using only information input by the user.

[0013] Therefore, there is a need for research on a big data-based user-customized perfume recommendation system and method that can ensure high satisfaction with the recommendation system and rapidly optimize a user-customized recommendation algorithm by generating primary recommendation data using information input by the user and providing it to the user, and generating final recommendation data based on feedback signals regarding the primary recommendation data received from the user. Prior art literature

[0014] Republic of Korea Published Patent No. 10-2024-0060120 (May 8, 2024) Republic of Korea Registered Patent No. 10-2534852 (May 26, 2023) The problem to be solved

[0015] Accordingly, the present invention has been devised to solve the aforementioned problems, and the objective of the present invention is to provide a personalized fragrance recommendation system and method that generates a list, provides a blending ratio suitable for the fragrance, and tags the fragrance after matching keywords suitable for the fragrance, which can be utilized when performing fragrance recommendations in the future.

[0016] However, the technical problems to be solved by the present invention are not limited to those mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art to which the present invention belongs from the description below. means of solving the problem

[0017] The present invention was created to improve upon the problems of the prior art described above and is a system for recommending customized fragrances through the collection of personal information via images or questionnaires. It may include: a fragrance information storage unit capable of storing and providing information on fragrances by various categories; a fragrance recommendation unit that receives information from the fragrance information storage unit, analyzes personal information using images or questionnaires, and generates a customized fragrance list; a fragrance note classification unit that receives the fragrance list from the fragrance recommendation unit and classifies fragrances by note; and a fragrance combination unit that receives notes from the fragrance note classification unit and provides an optimal blending ratio according to the fragrance list.

[0018] In addition, in one embodiment, the fragrance information storage unit may include: a category selection unit that selects various categories of season, weather, emotion, place, and image; a keyword generation unit that generates recommended keywords corresponding to the categories; a matching unit that matches the keywords corresponding to the categories with fragrances; and a database unit that stores and databases the information as tags for each of the categories.

[0019] In addition, in one embodiment, the fragrance recommendation unit may include: a tag selection unit for selecting keywords suitable for oneself to select a personalized fragrance; a duplicate cleanup unit for removing duplicate fragrances from the keywords selected by the individual through the tag selection unit; and a final extraction unit for selecting a personalized fragrance list from the fragrance list cleaned through the duplicate cleanup unit.

[0020] Additionally, in one embodiment, the duplicate sorting unit may include: a text sorting unit that sorts text by analyzing the text data form obtained through analysis by the tag selection unit; a fragrance sorting unit that sorts specific or repeated fragrances among the matched tags; and a frequency ranking display unit that displays the frequency ranking of fragrances with a high frequency of appearance by topic.

[0021] In addition, in one embodiment, the fragrance note classification unit may include: a top note unit that first selects the scent smelled when the perfume is sprayed; a middle note unit selected from the fragrance list that connects the scent while maintaining the top note unit; and a base note unit selected from the fragrance list that increases the depth set in the scent.

[0022] In addition, in one embodiment, the fragrance note classification unit receives fragrance information listed by the fragrance recommendation unit, classifies which note is used among the top note unit, the middle note unit, and the base note unit, and can generate a fragrance list for each note.

[0023] In addition, in one embodiment, the fragrance combination unit may include: a receiving unit that receives the fragrance list classified by note in the fragrance note classification unit and receives the most preferred fragrance among the notes; a selection unit that removes and re-surveys fragrances that do not go well with each other or incompatible fragrances for each note; a selection unit that selects a main fragrance among a plurality of preferred fragrances and, after selecting the main fragrance, selects a kick fragrance among fragrances other than the main fragrance; and a blending ratio providing unit that provides a blending ratio according to a desired set afterglow time.

[0024] A method for recommending customized fragrances through the collection of personal information via images or questionnaires according to another embodiment of the present invention may comprise: a fragrance information storage step for storing and providing information on fragrances by various categories; a fragrance recommendation step for receiving information after the fragrance information storage step and generating a customized fragrance list by analyzing personal information using images or questionnaires; a fragrance note classification step for receiving the fragrance list after the fragrance recommendation step and classifying fragrances by note; and a fragrance combination step for receiving notes after the fragrance note classification step and providing an optimal blending ratio according to the fragrance list.

[0025] Additionally, in one embodiment, the fragrance recommendation step comprises: an information collection step for collecting information through images or questionnaires regarding seasons, weather, emotions, and places; an image and survey analysis step for analyzing images and surveys after the information collection step; a first fragrance list extraction step for extracting a first fragrance list after the image and survey analysis step; a duplicate fragrance determination step for determining whether duplicate fragrances exist for each list after the first fragrance list extraction step; a duplicate fragrance sorting step for sorting duplicate fragrances if they are determined to be duplicates after the duplicate fragrance determination step; a second fragrance list extraction step for extracting a second fragrance list after the duplicate fragrance sorting step; a fragrance addition determination step for determining whether more diverse fragrances are desired after the second fragrance list extraction step; and a non-preferred fragrance existence determination step for determining whether non-preferred fragrances exist in the list if fragrances are not added after the fragrance addition determination step. and a final fragrance list extraction step for extracting a final fragrance list if no undesirable fragrance exists after going through the above step of determining whether an undesirable fragrance exists. Effects of the invention

[0026] According to one embodiment of the present invention, a list is generated and a blending ratio suitable for the fragrance is provided, and keywords suitable for the fragrance are matched and tagged so that they can be utilized when recommending fragrances in the future.

[0027] In addition, according to one embodiment of the present invention, by conducting an analysis through images or surveys, customized fragrances can be selected for each individual and a fragrance list can be extracted.

[0028] However, the effects obtainable from the present invention are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art from the description below. Brief explanation of the drawing

[0029] The following drawings attached to this specification illustrate preferred embodiments of the present invention and serve to further enhance understanding of the technical concept of the present invention together with the detailed description of the invention provided below; therefore, the present invention should not be interpreted as being limited only to the matters described in such drawings. FIG. 1 is a block diagram of the overall components of a personalized fragrance recommendation system according to one embodiment of the present invention. Figure 2 is a block diagram of the components of the flavor information storage unit. Figure 3 is a block diagram of the components of the fragrance recommendation section. Figure 4 is a block diagram of the components of the fragrance note classification section. Figure 5 is a block diagram of the components of the fragrance combination unit. FIG. 6 is a flowchart illustrating a personalized fragrance recommendation method according to an embodiment of the present invention. Figure 7 is a detailed flowchart of the fragrance recommendation step. Figure 8 is a detailed flowchart of the redundant fragrance sorting step. Figure 9 is a detailed flowchart of the flavor combination step. Specific details for implementing the invention

[0030] Below, with reference to the attached drawings, embodiments of the present invention are described in detail so that those skilled in the art can easily implement the invention. However, since the description of the present invention is merely an example for structural or functional explanation, the scope of the present invention should not be interpreted as being limited by the embodiments described in the text. That is, since the embodiments are subject to various modifications and may take various forms, the scope of the present invention should be understood to include equivalents capable of realizing the technical concept. Furthermore, the objectives or effects presented in the present invention do not imply that a specific embodiment must include all of them or only such effects; therefore, the scope of the present invention should not be understood as being limited by them.

[0031] The meaning of the terms described in this invention should be understood as follows.

[0032] Terms such as "first" and "second" are intended to distinguish one component from another, and the scope of rights shall not be limited by these terms. For example, the first component may be named the second component, and similarly, the second component may be named the first component. When a component is referred to as being "connected" to another component, it should be understood that it may be directly connected to that other component, or that there may be other components in between. Conversely, when a component is referred to as being "directly connected" to another component, it should be understood that there are no other components in between. Meanwhile, other expressions describing the relationship between components, such as "between" and "exactly between," or "adjacent to" and "directly adjacent to," shall be interpreted in the same manner.

[0033] A singular expression should be understood to include a plural expression unless the context clearly indicates otherwise, and terms such as "include" or "have" are intended to specify the existence of the set-up features, numbers, steps, actions, components, parts, or combinations thereof, and should be understood not to preclude the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0034] Unless otherwise defined, all terms used herein have the same meaning as generally understood by those skilled in the art to which this invention pertains. Terms defined in commonly used dictionaries should be interpreted as having meanings consistent with the context of the relevant technology and should not be interpreted as having an ideal or overly formal meaning unless explicitly defined in this invention.

[0035] FIG. 1 is a block diagram of the overall components of a personalized fragrance recommendation system according to an embodiment of the present invention, FIG. 2 is a block diagram of the components of a fragrance information storage unit, FIG. 3 is a block diagram of the components of a fragrance recommendation unit, FIG. 4 is a block diagram of the components of a fragrance note classification unit, and FIG. 5 is a block diagram of the components of a fragrance combination unit.

[0036] As illustrated in FIGS. 1 to 5, the present invention is a system for recommending customized fragrances through the collection of personal information via images or questionnaires, and may include a fragrance information storage unit (100), a fragrance recommendation unit (200), a fragrance note classification unit (300), and a fragrance combination unit (400).

[0037] The fragrance information storage unit (100) can store and provide information on fragrances by various categories. Specifically, the fragrance information storage unit (100) can generate keywords by category, such as weather, emotion, situation, and place, and store and database fragrances that match each keyword.

[0038] The flavor information storage unit (100) may include a category selection unit (110), a keyword generation unit (120), a matching unit (130), and a database unit (140).

[0039] The category selection unit (110) can select various categories of season, weather, emotion, place and image.

[0040] The keyword generation unit (120) can generate recommended keywords suitable for the category. Specifically, the keyword generation unit (120) includes, for example, things related to weather such as four seasons, clear, gloomy, sunny, cool, and warm, and things related to emotions such as happiness, liveliness, freshness, warmth, and excitement.

[0041] The matching unit (130) can match keywords and fragrances that fit the category. Specifically, the matching unit (130) can generate multiple tags through matching for each fragrance, for example, lime can be summer, clear, spring day, etc. regarding weather, liveliness, freshness, excitement, etc. regarding emotion, and cafe, sunshine, park, beach, etc. regarding place.

[0042] Likewise, bergamot can be clear, sunny, spring, autumn, etc. in terms of weather; happy, stable, refreshing, etc. in terms of emotion; and a study, garden, cafe, etc. in terms of place.

[0043] The database section (140) can be stored as tags for each category and converted into a database.

[0044] The fragrance recommendation unit (200) can receive information from the fragrance information storage unit (100) and generate a customized fragrance list by analyzing personal information using images or surveys. Specifically, the fragrance recommendation unit (200) can extract keywords such as season, weather, emotion, and location using images or surveys, analyze them, and recommend personalized fragrances through additional surveys in stages.

[0045] The fragrance recommendation unit (200) may include a tag selection unit (210), a duplicate sorting unit (220), and a final extraction unit (230).

[0046] The tag selection unit (210) can select keywords that suit the individual for personalized fragrance selection. Specifically, the tag selection unit (210) can collect individual information through image and survey analysis and select tags by extracting keywords from images or surveys by category. For example, if the preferred weather is spring, the keywords may be bitter lemon, bergamot, yuzu, lime, etc., and if the preferred time of day is morning, the keywords may be bitter lemon, citron fruit, bergamot, yuzu, etc. Therefore, fragrances that match the tags by category can be extracted, listed, and compared.

[0047] The duplicate cleanup unit (220) can remove duplicate scents from among the keywords selected by an individual through the tag selection unit (210).

[0048] The duplicate organization section (220) may include a text organization section (222), a flavor organization section (224), and a frequency ranking display section (226).

[0049] The text organization unit (222) can organize text by analyzing the text data form obtained through analysis from the tag selection unit (210).

[0050] The fragrance sorting unit (224) can sort specific or repeated fragrances among the matched tags.

[0051] Specifically, the fragrance sorting unit (224) can analyze the form of text data obtained through image and survey analysis. For example, it can be analyzed as sunny weather, sunny, spring weather, sunshine, and clear weather.

[0052] In addition, each text data can be extracted and organized into text. For example, sunny, spring weather, sunshine, clarity, and clearness can be organized into sunny, spring, sunshine, and clarity.

[0053] In addition, by matching tags for each text, it is possible to organize specific or repeated duplicate fragrances. For example, if it is spring with an image of sunshine on sunny days, it can be organized into bergamot, yuzu, lime, green tea, lily, etc.; if it is clear, into bitter lemon, citron fruit, bergamot, yuzu, lime, tangerine, lilac, etc.; and regarding sunshine, into citron fruit, grey fruit, bergamot, yuzu, lime, lilac, etc. A duplicate word cleanup algorithm can be implemented so that the aforementioned duplicate fragrances are set as a single fragrance.

[0054] In addition, through each integrated keyword, display colors and rankings based on frequency order can be shown for fragrances with high occurrence frequency by topic. It is possible to determine rankings for each fragrance in the order of most frequently mentioned.

[0055] For example, regarding the image of sunshine on a sunny day, the first priority could be bergamot, yuzu, lime, etc., the second priority could be lilac, and the third priority could be others. And, a customized fragrance list can be generated based on the priority.

[0056] The frequency ranking display section (226) can display the frequency ranking of flavors that appear frequently by topic.

[0057] Additionally, more tags can be recommended by category through additional surveys. After extracting the fragrance list, if more fragrances are desired, the process can be repeated after gathering information; furthermore, since the list may contain undesirable scents, these can be removed through the survey.

[0058] The final extraction unit (230) can select a customized fragrance list from the fragrance list organized through the duplicate sorting unit (220).

[0059] The fragrance note classification unit (300) can receive a fragrance list from the fragrance recommendation unit (200) and classify fragrances by note.

[0060] The fragrance note classification section (300) may include a top note section (310), a middle note section (320), and a base note section (330).

[0061] The top note section (310) can be selected as the first scent to be smelled when the perfume is sprayed. Specifically, the top note section (330) may be lemon, orange, bergamot, rose, lavender scent, etc.

[0062] The middle note (320) can be selected from a list of fragrances that connect the scent while maintaining the top note (310). Specifically, the middle note (320) may be jasmine, cinnamon, pepper scent, etc.

[0063] The base note section (330) can be selected from a list of fragrances that increase the depth set in the fragrance. Specifically, the base note section (330) may be vanilla, musk, amber, etc.

[0064] The fragrance note classification unit (300) receives fragrance information listed in the fragrance recommendation unit (200), classifies which note is used among the top note unit (310), middle note unit (320), and base note unit (330), and can generate a fragrance list for each note.

[0065] The fragrance combination unit (400) can receive notes from the fragrance note classification unit (300) and provide an optimal blending ratio according to the fragrance list.

[0066] The fragrance combination unit (400) may include a receiving unit (410), a selection unit (420), a selection unit (430), and a mixing ratio providing unit (440).

[0067] The receiving unit (410) receives a list of fragrances classified by note from the fragrance note classification unit (300) and can receive the most preferred fragrance among the notes.

[0068] The selection unit (420) can remove fragrances that do not match each other or incompatible fragrances and conduct a re-survey for each note. Specifically, the selection unit (420) may, for example, list bergamot (first priority), yuzu, lime, lilac, woody, etc., and lime may be removed as it is a similar citrus scent, and woody may be removed because it does not match well with fresh scents. When removing, a survey can be conducted regarding the selection of the most desired scent among the notes and / or the selection of the next priority for each note.

[0069] The selection unit (430) can select a main scent from among multiple preferred scents, and after selecting the main scent, can select a kick scent from among scents other than the main scent. Specifically, the selection unit (430) can select the most preferred scent as the main scent by the user's choice.

[0070] The main accord is a combination of key scents that forms the most central theme and is a core component of the fragrance or scent note that plays a role in determining the overall atmosphere and identity. However, while the main accord is the scent you want to smell the longest or the scent that determines the overall theme, it may not be the scent you smell the longest because the scent may fade or change over time.

[0071] Additionally, the selection unit (430) can select a kick scent from among the scents other than the one selected as the main scent from among the multiple preferred scents. Additionally, the selection unit (430) can select the scent with the lowest frequency of appearance as the kick scent after checking the scent list.

[0072] Here, the kick scent refers to a scent that can be combined into a desired scent by modifying the main scent, and means a scent combined with a modifier. A modifier is a flavoring agent that gives originality and individuality by changing the main scent.

[0073] The blending ratio providing unit (440) can provide a blending ratio according to the desired set afterglow time. Specifically, the blending ratio providing unit (440) can provide a blending ratio by selecting both the afterglow time of the main scent and the afterglow time of the kick scent. Additionally, the blending ratio providing unit (440) can provide a blending ratio by selecting either the afterglow time of the main scent or the afterglow time of the kick scent.

[0074] The details regarding specific components are described below in the invention of the personalized fragrance recommendation method.

[0075] FIG. 6 is a flowchart illustrating a personalized fragrance recommendation method according to an embodiment of the present invention, FIG. 7 is a detailed flowchart of the fragrance recommendation step, FIG. 8 is a detailed flowchart of the duplicate fragrance sorting step, and FIG. 9 is a detailed flowchart of the fragrance combination step.

[0076] As illustrated in FIG. 6, in a method for recommending customized fragrances through the collection of personal information via images or questionnaires, the present invention may comprise a fragrance information storage step (S100), a fragrance recommendation step (S200), a fragrance note classification step (S300), and a fragrance combination step (S400).

[0077] The fragrance information storage step (S100) is a step of storing and providing information on fragrances by various categories.

[0078] The fragrance recommendation step (S200) is a step that generates a customized fragrance list by receiving information after the fragrance information storage step (S100), analyzing personal information using images or surveys, and generating information after receiving the information.

[0079] The fragrance recommendation step (S200) may include an information collection step (S210), an image and survey analysis step (S220), a first fragrance list extraction step (S230), a duplicate fragrance determination step (S240), a duplicate fragrance sorting step (S250), a second fragrance list extraction step (S260), a fragrance addition determination step (S270), a non-preferred fragrance existence determination step (S280), and a final fragrance list extraction step (S290).

[0080] The information collection stage (S210) is a stage of collecting information through images or questionnaires regarding seasons, weather, emotions, and places.

[0081] The image and survey analysis step (S220) is a step of analyzing images and surveys after going through the information collection step (S210).

[0082] The first fragrance list extraction step (S230) is a step of extracting the first fragrance list after going through the image and survey analysis step (S220).

[0083] The duplicate fragrance determination step (S240) is a step for determining whether there are duplicate fragrances for each list after the first fragrance list extraction step (S230).

[0084] Specifically, after going through the duplicate fragrance determination step (S240), if it is not determined to be a duplicate fragrance, it can be returned to the information collection step (S210).

[0085] The duplicate fragrance sorting step (S250) is a step for sorting duplicate fragrances when they are determined to be duplicates after going through the duplicate fragrance determination step (S240).

[0086] Specifically, the duplicate fragrance sorting step (S250) may include a data form analysis step (S251), a text data extraction step (S252), a text data sorting step (S253), a tag matching step (S254), a sorting algorithm implementation step (S255), a fragrance priority display step (S256), and a fragrance listing step (S257).

[0087] The data form analysis step (S251) is a step for analyzing the form of text data by image and survey.

[0088] The text data extraction step (S252) is a step of extracting text data after the data form analysis step (S251).

[0089] The text data cleaning step (S253) is a step for cleaning text data after the text data extraction step (S252).

[0090] The tag matching step (S254) is a step of matching tags for each extracted text after the text data cleaning step (S253).

[0091] The cleanup algorithm implementation step (S255) is a step of implementing a duplicate word cleanup algorithm after going through the tag matching step (S254).

[0092] The fragrance priority display step (S256) is a step of displaying the fragrance priority based on the frequency of occurrence after going through the sorting algorithm implementation step (S255).

[0093] The fragrance listing step (S257) is a step of listing fragrances after going through the fragrance priority display step (S256).

[0094] The second fragrance list extraction step (S260) is a step of extracting the second fragrance list after going through the duplicate fragrance sorting step (S250).

[0095] The fragrance addition determination step (S270) is a step for determining whether more diverse fragrances are desired after going through the secondary fragrance list extraction step (S260). Specifically, if fragrances are added after going through the fragrance addition determination step (S270), it is sent back to the information collection step (S210).

[0096] The step for determining whether there is an undesirable scent (S280) is a step for determining whether there is an undesirable scent among the list when no scent is added after going through the step for determining whether to add a scent (S270).

[0097] The final fragrance list extraction step (S290) is a step of extracting the final fragrance list if no undesirable scent exists after going through the step of determining whether undesirable scent exists (S280).

[0098] Specifically, after going through the step of determining whether a non-preferred scent exists (S280), if a non-preferred scent exists, the non-preferred scent is selected and removed, and then sent back to the final scent list extraction step (S290).

[0099] The fragrance note classification step (S300) is a step of receiving a fragrance list after passing through the fragrance recommendation step (S200) and classifying fragrances by note.

[0100] The fragrance combination step (S400) is a step that receives notes after passing through the fragrance note classification step (S300) and provides an optimal blending ratio according to the fragrance list.

[0101] Specifically, the fragrance combination step (S400) may include an information reception step (S410), a step for determining whether incompatible fragrances exist (S420), a step for selecting multiple preferred fragrances (S430), a step for selecting a main fragrance (S440), a step for selecting a kick fragrance (S445), a step for selecting a lingering fragrance time (S450), and a step for providing a blending ratio (S460).

[0102] The information reception step (S410) is a step of receiving information from the fragrance note classification step (S410).

[0103] The step for determining the presence of incompatible fragrances (S420) is a step for determining whether incompatible fragrances exist for each note if no incompatible fragrances exist after passing through the information reception step (S410). Specifically, if incompatible fragrances exist after passing through the step for determining the presence of incompatible fragrances (S420), a re-survey is conducted, the next priority for each note is selected, and the result is sent to the information reception step (S410).

[0104] The multiple preferred scent selection step (S430) is a step of selecting multiple preferred scents when there are no incompatible scents after going through the incompatible scent determination step (S420).

[0105] The main scent selection step (S440) is a step in which the most preferred scent is selected as the main scent by the user's choice after going through multiple preference scent selection steps (S430).

[0106] The kick scent selection step (S445) is a step for selecting a kick scent after going through the main scent selection step (S440). Specifically, the kick scent selection step (S445) may select a kick scent from among the scents other than the one selected as the main scent in the multiple preferred scent selection steps (S430). Additionally, the kick scent selection step (S445) may select the scent with the lowest frequency of appearance as the kick scent after checking the scent list.

[0107] The afterglow time selection step (S450) is a step for selecting the afterglow time of the main scent or the kick scent after passing through the kick scent selection step (S445). Specifically, the afterglow time selection step (S450) can select both the afterglow time of the main scent and the afterglow time of the kick scent. Additionally, the afterglow time selection step (S450) can select either the afterglow time of the main scent or the afterglow time of the kick scent.

[0108] The mixing ratio providing step (S460) is a step of providing a mixing ratio that matches the fragrance ratio after going through the afterglow time selection step (S450).

[0109] The details regarding the specific components below are as described above in the invention of the personalized fragrance recommendation system.

[0110] As described above, the detailed description of the preferred embodiments of the present invention disclosed is provided to enable those skilled in the art to implement and practice the present invention. Although the present invention has been described with reference to preferred embodiments, those skilled in the art will understand that various modifications and changes can be made to the present invention without departing from the scope of the invention. For example, those skilled in the art may utilize each configuration described in the embodiments described above in combination with one another. Accordingly, the present invention is not intended to be limited to the embodiments shown herein, but to be given the broadest scope consistent with the principles and novel features disclosed herein.

[0111] The present invention may be embodied in other specific forms without departing from the spirit and essential features of the invention. Accordingly, the above detailed description should not be interpreted restrictively in all respects but should be considered exemplary. The scope of the invention shall be determined by a reasonable interpretation of the appended claims, and all modifications within the equivalent scope of the invention are included within the scope of the invention. The invention is not intended to be limited to the embodiments shown herein, but to be given the broadest possible scope consistent with the principles and novel features disclosed herein. Furthermore, embodiments may be constructed by combining claims that are not explicitly related in the claims, or by including them as new claims through amendments made after filing. Explanation of the symbols

[0112] 10: Flavor Recommendation System 100 : Flavor information storage 110 : Category Selection Department 120 : Keyword generation section 130 : Matching part 140 : Database section 200 : Flavor Recommendation Section 210 : Tag selection section 220 : Duplicate Cleanup Section 222 : Text Organization Section 224 : Fragrance Organizer 226 : Frequency ranking display section 230 : Final extraction section 300 : Fragrance Note Classification Section 310 : Top Note 320 : Middle Note 330 : Bass note section 400 : Flavoring Combination Unit 410 : Receiver 420 : Selection 430 : Selection Department 440 : Mixing ratio provision section

Claims

Claim 1 A personalized fragrance recommendation system for collecting personal information through images or questionnaires, characterized by comprising: a fragrance information storage unit capable of storing and providing information on fragrances by various categories; a fragrance recommendation unit that receives information from the fragrance information storage unit and generates a personalized fragrance list by analyzing personal information using images or questionnaires; a fragrance note classification unit that receives the fragrance list from the fragrance recommendation unit and classifies fragrances by note; and a fragrance combination unit that receives notes from the fragrance note classification unit and provides an optimal blending ratio according to the fragrance list. Claim 2 A personalized fragrance recommendation system according to claim 1, wherein the fragrance information storage unit comprises: a category selection unit that selects various categories of season, weather, emotion, place, and image; a keyword generation unit that generates recommended keywords corresponding to the categories; a matching unit that matches the keywords corresponding to the categories with fragrances; and a database unit that stores tags for each of the categories and forms a database. Claim 3 A personalized fragrance recommendation system according to claim 1, wherein the fragrance recommendation unit comprises: a tag selection unit for selecting keywords suitable for oneself to select personalized fragrances; a duplicate cleanup unit for removing duplicate fragrances among the keywords selected by the individual through the tag selection unit; and a final extraction unit for selecting a personalized fragrance list from the fragrance list cleaned through the duplicate cleanup unit. Claim 4 A personalized fragrance recommendation system according to claim 3, wherein the duplicate sorting unit comprises: a text sorting unit that sorts text by analyzing the text data form obtained through analysis from the tag selection unit; a fragrance sorting unit that sorts fragrances that are specified or repeated among the matched tags; and a frequency ranking display unit that displays the frequency ranking of fragrances with a high frequency of appearance by topic. Claim 5 A personalized fragrance recommendation system according to claim 1, further comprising: a fragrance note classification unit comprising: a top note unit that prioritizes selecting the scent that is first smelled when perfume is sprayed; a middle note unit selected from the fragrance list that connects the scent while maintaining the top note unit; and a base note unit selected from the fragrance list that increases the depth set in the scent. Claim 6 A personalized fragrance recommendation system according to claim 5, wherein the fragrance note classification unit receives fragrance information listed in the fragrance recommendation unit, classifies which note is used among the top note unit, the middle note unit, and the base note unit, and generates a fragrance list for each note. Claim 7 A personalized fragrance recommendation system according to claim 1, wherein the fragrance combining unit comprises: a receiving unit that receives the fragrance list classified by note in the fragrance note classification unit and receives the most preferred fragrance among the notes; a selection unit that removes and re-surveys fragrances that do not go well with each other or incompatible fragrances for each note; a selection unit that selects a main fragrance among a plurality of preferred fragrances and, after selecting the main fragrance, selects a kick fragrance among fragrances other than the main fragrance; and a blending ratio providing unit that provides a blending ratio according to a desired set afterglow time. Claim 8 A method for recommending personalized fragrances by collecting personal information through images or questionnaires, comprising: a fragrance information storage step for storing and providing information on fragrances by various categories; a fragrance recommendation step for generating a personalized fragrance list by receiving information after the fragrance information storage step and analyzing personal information using images or questionnaires; a fragrance note classification step for classifying fragrances by note after receiving the fragrance list after the fragrance recommendation step; and a fragrance combination step for providing an optimal blending ratio according to the fragrance list after receiving the notes after the fragrance note classification step. Claim 9 In claim 1, the fragrance recommendation step comprises: an information collection step for collecting information through images or questionnaires regarding seasons, weather, emotions, and places; an image and survey analysis step for analyzing images and surveys after the information collection step; a first fragrance list extraction step for extracting a first fragrance list after the image and survey analysis step; a duplicate fragrance determination step for determining whether duplicate fragrances exist for each list after the first fragrance list extraction step; a duplicate fragrance sorting step for sorting duplicate fragrances if they are determined to be duplicates after the duplicate fragrance determination step; a second fragrance list extraction step for extracting a second fragrance list after the duplicate fragrance sorting step; a fragrance addition determination step for determining whether more diverse fragrances are desired after the second fragrance list extraction step; and a non-preferred fragrance existence determination step for determining whether non-preferred fragrances exist among the list if fragrances are not added after the fragrance addition determination step. A personalized fragrance recommendation method characterized by comprising: a final fragrance list extraction step for extracting a final fragrance list when no undesirable scent exists after undergoing the above-mentioned step of determining whether an undesirable scent exists.

Images