WO2024014625A1

WO2024014625A1 - Personalized fragrance recommendation service system and method therefor

Info

Publication number: WO2024014625A1
Application number: PCT/KR2022/019020
Authority: WO
Inventors: 박소현
Original assignee: 박소현
Priority date: 2022-07-13
Filing date: 2022-11-29
Publication date: 2024-01-18
Also published as: KR20240009191A

Abstract

The present invention provides a personalized fragrance recommendation service providing system and method therefor. The personalized fragrance recommendation service providing method, performed by a server, may comprise the steps of: receiving, from a user, recommendation request information including user information; if music is played for a pre-set reference playback time on the basis of playback data generated according to a selection by the user by using the recommendation request information, generating customized fragrance information by using emotional state information generated by comparing and analyzing the playback data on the basis of the user data; and providing a fragrance recommendation service to the user in response to the customized fragrance information, wherein the generating of the customized fragrance information may comprise the steps of: generating first emotional state information by determining a previous emotional state before the music is played by analyzing subjective information included in the user information; generating second emotional state information by determining the present emotional state of the user while the music is being played by analyzing the playback data; generating third emotional state information corresponding to an emotional state change of the user by analyzing the first emotional state information and the second emotional state information; and generating the customized fragrance information on the basis of the third emotional state information.

Description

Personalized scent recommendation service system and method

The present invention relates to a personalized scent recommendation service system and method. In particular, the present invention relates to a personalized scent recommendation service system and method. In particular, the user's patterns and keywords are extracted using the user's playback data, and the emotional state before and during music playback is identified to identify positive The present invention relates to a personalized scent recommendation service system and method that can individually recommend a corresponding scent to maintain or induce an emotional state.

In general, perfume is regarded by people as a part of fashion and a means of self-expression.

However, in the case of perfume, it is not easy for users (consumers) to find the scent they want unless they try the perfume in person at a store.

Accordingly, in recent years, a variety of solutions have been introduced to recommend scents that are necessary and suitable for people.

In offline stores, which can be considered a traditional sales channel, it was common for store clerks or experts with extensive knowledge of perfumes and scented candles to consult with users to understand their tastes and preferences and recommend scents suitable for them based on that. .

Recently, technology has been introduced to recommend a scent suitable for a user based on the user's tastes or preferences obtained from information obtained through Q&A with the user in an online store.

However, according to the above prior art, the seller or service provider has to go through the cumbersome process of asking the user questions and receiving answers to determine the user's tastes, and the user also experiences the inconvenience of having to answer many questions one by one. problems may arise, and due to these problems, there was a limitation that it was difficult to sufficiently collect the information necessary to determine the user's tastes (see Korean Patent Publication No. 10-2017-0018778).

The matters described as background technology above are only for the purpose of improving understanding of the background of the present invention, and should not be taken as an acknowledgment that they correspond to prior art already known to those skilled in the art.

The problem to be solved by the present invention is to provide a personalized scent recommendation service system and method.

The problems to be solved by the present invention are not limited to the problems mentioned above, and other problems not mentioned can be clearly understood by those skilled in the art from the description below.

The personalized scent recommendation service system method according to an embodiment of the present invention to solve the above-described problem is a method of providing a personalized scent recommendation service performed by a server, where recommendation request information including user information is received from the user. receiving; When music is played for a preset standard playback time based on playback data generated according to the user's selection using the recommendation request information, emotional state information generated by comparing and analyzing the playback data based on the user information Generating customized scent information using; And providing a scent recommendation service to the user in response to the customized scent information, wherein the step of generating the customized scent information includes analyzing subjective information included in the user information to determine the previous emotional state before music playback. Identifying and generating first emotional state information; Analyzing the playback data to identify the user's current emotional state while playing music and generating second emotional state information; Analyzing the first emotional state information and the second emotional state information to generate third emotional state information corresponding to a change in the user's emotional state; And it may include generating the customized scent information based on the third emotional state information.

In one embodiment of the present invention, generating the second emotional state information may include extracting user patterns and keywords from the playback data.

In one embodiment of the present invention, the step of generating the third emotional state information includes, when the second emotional state information is lower than the preset reference emotional state information, the first emotional state information and the second emotional state information are The third emotional state information is generated by determining that they are not similar, and when the second emotional state information is higher than the preset standard emotional information, it is determined that the first emotional state information and the second emotional state information are similar, and the second emotional state information is determined to be similar. 3 It may include the step of generating emotional state information.

In one embodiment of the present invention, the step of generating the customized scent information includes: when the second emotional state information is lower than the preset reference emotional state information, the second emotional state information is guided to the first emotional state information. The customized scent information may be generated, and if the second emotional state information is higher than preset standard emotional information, the customized scent information may be generated so that the second emotional state information is maintained.

In addition, a personalized scent recommendation service system according to another embodiment of the present invention for solving the above-described problem includes a management server that provides a personalized scent recommendation service to a user terminal, and the management server includes the User information including subjective information and objective information is received from the user terminal, and when music is played for a preset standard playback time based on playback data generated according to the user's selection, the playback data is generated based on the user information. Generate customized scent information by comparing and analyzing, and provide a scent recommendation service to the user in response to the customized scent information. The management server analyzes the subjective information based on the user information and provides information prior to music playback. Generate first emotional state information by identifying the emotional state, analyze the playback data to determine the current emotional state of the user while playing music, and generate second emotional state information, and generate the first emotional state information and the second emotional state information. By analyzing emotional state information, third emotional state information corresponding to changes in the user's emotional state can be generated, and the customized scent information can be generated based on the third emotional state information.

The program according to one embodiment of the present invention is combined with a computer as hardware and stored in a computer-readable recording medium to perform the method of providing a personalized scent recommendation service.

Other specific details of the invention are included in the detailed description and drawings.

According to the present invention, by providing a personalized scent recommendation service in response to the user's emotional state that changes in real time, scent information optimized for the user's current state of emotions can be provided.

According to the present invention, by recognizing the user's previous and current emotional state in real time, a personalized scent can be recommended to induce or maintain the user's current emotional state in a positive direction.

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

1 is a conceptual diagram illustrating a personalized scent recommendation service system according to an embodiment of the present invention.

FIG. 2 is a diagram for explaining the detailed configuration of the personalized scent recommendation service system shown in FIG. 1.

Figure 3 is a diagram for explaining a personalized scent recommendation service method according to an embodiment of the present invention.

FIG. 4 is a diagram for explaining the step of generating customized scent information shown in FIG. 3.

FIG. 5 is a diagram for explaining the step of generating emotional state information shown in FIG. 4.

The advantages and features of the present invention and methods for achieving them will become clear by referring to the embodiments described in detail below along with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below and may be implemented in various different forms. The present embodiments are merely provided to ensure that the disclosure of the present invention is complete and to provide a general understanding of the technical field to which the present invention pertains. It is provided to fully inform the skilled person of the scope of the present invention, and the present invention is only defined by the scope of the claims.

The terminology used herein is for describing embodiments and is not intended to limit the invention. As used herein, singular forms also include plural forms, unless specifically stated otherwise in the context. As used in the specification, “comprises” and/or “comprising” does not exclude the presence or addition of one or more other elements in addition to the mentioned elements. Like reference numerals refer to like elements throughout the specification, and “and/or” includes each and every combination of one or more of the referenced elements. Although “first”, “second”, etc. are used to describe various components, these components are of course not limited by these terms. These terms are merely used to distinguish one component from another. Therefore, it goes without saying that the first component mentioned below may also be a second component within the technical spirit of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used with meanings commonly understood by those skilled in the art to which the present invention pertains. Additionally, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless clearly specifically defined.

Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings.

Figure 1 is a conceptual diagram for explaining a personalized scent recommendation service system according to an embodiment of the present invention, and Figure 2 is a diagram for explaining the detailed configuration of the personalized scent recommendation service system shown in Figure 1.

As shown in Figures 1 and 2, the personalized scent recommendation service system 1, which is an embodiment of the present invention, may include a user terminal 10, a management server 20, and an administrator terminal 30. At this time, depending on the embodiment, the manager terminal 30 may be omitted.

Here, the user terminal 10, management server 20, and administrator terminal 30 can transmit and receive data in real time in synchronization using a wireless communication network. The wireless communication network may support various long-distance communication methods, such as Wireless LAN (WLAN), DLNA (Digital Living Network Alliance), Wibro (Wireless Broadband: Wibro), and Wimax (World Interoperability for Microwave Access: Wimax). ), GSM (Global System for Mobile communication), CDMA (Code Division Multi Access), CDMA2000 (Code Division Multi Access 2000), EV-DO (Enhanced Voice-Data Optimized or Enhanced Voice-Data Only), WCDMA (Wideband CDMA) , HSDPA (High Speed Downlink Packet Access), HSUPA (High Speed Uplink Packet Access), IEEE 802.16, Long Term Evolution (LTE), LTEA (Long Term Evolution-Advanced), broadband wireless mobile communication service (Wireless Mobile) Broadband Service: Various communication methods such as WMBS (WMBS), BLE (Bluetooth Low Energy), Zigbee, RF (Radio Frequency), LoRa (Long Range), etc. may be applied, but are not limited to these and include various widely known wireless or mobile communications. method may be applied.

First, in this embodiment, a personalized scent is provided to the user terminal 10 located in a space or place where music can be played using playback data transmitted from the management server 20 using the personalized scent recommendation service system 1. Although it started out as providing a recommendation service, it is not limited to this.

For example, a personalized scent recommendation service can be provided individually or simultaneously to a plurality of user terminals 10 located in spaces such as transportation means such as vehicles equipped with sound equipment, theaters, movie theaters, and concert halls.

The user terminal 10 can receive a personalized scent recommendation service through communication with the management server 20 or the administrator terminal 30.

Specifically, the user terminal 10 transmits recommendation request information to the management server 20 through a personalized scent recommendation service, and receives playback data corresponding to the recommendation request information from the management server 20 based on the playback data. You can receive generated customized scent information.

Here, the recommendation request information may include user information consisting of objective information and subjective information, and request data for scent recommendation requesting a personalized scent recommendation service, but is not limited to this.

Objective information includes basic information such as age, gender, name, contact information, address, and occupation, and priority information such as desired scent, scent preference, time, location, date, payment method, hobby, and inclination when providing a personalized scent recommendation service. Additional information may be included, but is not limited to this. For example, tendencies may include, but are not limited to, rational, sensitive, emotional, conservative, progressive, passive, negative, and positive tendencies.

Depending on the embodiment, the user information may include location information of the user terminal 10. The location information may include, but is not limited to, the current location information of the user terminal 10 or location information provided with a personalized scent recommendation service. At this time, the emotional state information may change depending on the presence or absence of music playback by playback data of the user terminal 10 according to the location information, and thus the customized scent information provided to the user terminal 10 may change.

Additionally, subjective information may include emotional state information such as Happiness, Neutral, Anger, Disgust, Fear, Sadness, and Surprise. At this time, the emotional state information may be current emotional state information, but is not limited to this and may include information about previous emotional states or average emotional states.

In addition, customized scent information is data that matches playback data generated using recommendation request information based on standard data, and information on personalized scent recommendation services is provided in various formats such as text, video, image, URL address, and voice. It may be included, but is not limited to this.

In addition, the playback data may be data generated by the user's selection based on recommendation request information based on standard data, but is not limited to this and may also be generated using standard data.

In addition, standard data is data generated through repeated learning using deep learning techniques or machine learning techniques based on big data. In this embodiment, it is disclosed as including reference playback time, reference emotion information, etc., but is limited to this. I never do that.

The user terminal 10 can output playback data and customized scent information visually and audibly separately or simultaneously.

For example, the user terminal 10 may include a display window that can output symbols, letters, numbers, etc. on the screen depending on the operating state, a lamp that outputs color changes or blinks, or a speaker that outputs audio. there is.

The user terminal 10 may first register as a member using user information in order to perform a personalized scent recommendation service with the management server 20, but is not limited to this and can use the personalized scent recommendation service using a one-time ID. It may be possible.

Depending on the embodiment, when the user terminal 10 is provided with a personalized scent recommendation service through the management server 20, the user terminal 10 makes payment through a separate payment server (not shown) or a payment service provided by the management server 20. It is desirable that the procedure be carried out. The payment procedure is omitted as it is a known technology.

Depending on the embodiment, the user terminal 10 may generate a feedback signal for the personalized scent recommendation service and transmit it to the management server 20 after or while using the personalized scent recommendation service. In contrast, the user terminal 10 may transmit the personalized scent recommendation service before use or in real time.

Depending on the embodiment, the user terminal 10 may receive a feedback control signal corresponding to the feedback signal before, during, or after using the personalized scent recommendation service.

At this time, the feedback signal may include information such as satisfaction, accuracy, and reliability for the personalized scent recommendation service, and the feedback control signal may include improved or updated information on the personalized scent recommendation service corresponding to the feedback signal. Here, the feedback control signal may include event information. Event information may include, but is not limited to, advertisements or information about discounts or events for personalized scent recommendation services.

Depending on the embodiment, when the user terminal 10 does not receive customized scent information corresponding to the recommendation request information, additional data is transmitted at the request of the management server 20 and received customized scent information reflecting the additional data. can do.

Depending on the embodiment, the user terminal 10 may receive customized scent information that reflects only additional data, or may receive only customized scent information that does not reflect additional data.

As such, the user terminal 10 may include a management server 20 or various portable electronic communication devices that support communication with the user terminal 30. For example, the user terminal 10 is a separate smart device, such as a smart phone, a personal digital assistant (PDA), a tablet, a wearable device, a smartwatch, It may include various portable terminals such as glass-type terminals (including Smart Glass, HMD (Head Mounted Display), etc.) and various IoT (Internet of Things) terminals, but in contrast, non-portable desktop computers and It may include electronic communication devices such as workstation computers.

In addition, the user terminal 10 can operate using an application program (application program or application) in the present disclosure, and such application program can be downloaded from an external server or management server 20 through wireless communication. there is.

As discussed above, the user terminal 10 can receive a personalized scent recommendation service by transmitting and receiving playback data with the management server 20 in real time. In other words, when the user terminal 10 plays music during the standard playback time using playback data, customized scent information corresponding to the user's emotional state information that changes in real time during music playback can be received based on the standard data. . Accordingly, when the user terminal 10 is provided with a personalized scent recommendation service, a positive emotional state can be maintained or induced, and at the same time, the user can be provided with customized scent information optimized for the user's current state of emotion.

In other words, the personalized scent recommendation service system (1), which is an embodiment of the present invention, is a personalized scent with high objectivity, accuracy, and quantification of the user who requests a personalized scent recommendation service using the user's real-time changing emotional state information. By providing a recommendation service, convenience and reliability can be improved while respecting the diversity of users who receive a personalized scent recommendation service.

The management server 20 may include a data transmission/reception unit 22, a database unit 24, a display unit 26, and a management control unit 28.

The data transmitting and receiving unit 22 can transmit and receive data for a personalized scent recommendation service with the user terminal 10 in real time.

For example, the data transmitting and receiving unit 22 may receive user information from the user terminal 10 and transmit playback data and customized scent information to the user terminal 10.

Depending on the embodiment, the data transmitting and receiving unit 22 may transmit and receive data for performing a personalized scent recommendation service with the user terminal 10 and the manager terminal 30 in real time.

Depending on the embodiment, the data transmitting and receiving unit 22 may receive a feedback signal from the user terminal 10 and transmit a feedback control signal corresponding to the feedback signal to the user terminal 10.

Depending on the embodiment, the data transmitting and receiving unit 22 may receive additional data from the user terminal 10.

The database unit 24 can store data transmitted and received from the user terminal 10 through a wireless communication network.

The database unit 24 can store data supporting various functions of the management server 20. The database unit 24 may store a number of application programs (application programs or applications) running on the management server 20, data for operation of the management server 20, and commands. At least some of these applications may be downloaded from an external server through wireless communication.

The display unit 26 displays the operating state of the user terminal 10 by user manipulation, the operating state of the management server 20, and data transmitted and received between the user terminal 10 and the management server 20 through the screen. It can be monitored. In other words, by checking the usage status of the user terminal 10 in real time, it is possible to conveniently use the user and provide the user with greater confidence.

The management control unit 28 generates playback data using the recommendation request information received from the user terminal 10 based on standard data, and determines the emotional state of the user terminal 10 in consideration of the playback time of the generated playback data. Customized scent information corresponding to the change can be generated and transmitted to the user terminal 10.

Specifically, the management control unit 28 may analyze recommendation request information input from the user terminal 10 and generate playback data corresponding to the user's selection based on standard data.

For example, the management control unit 28 may generate playback data containing music desired by the user by analyzing user information included in the recommendation request information based on the request data included in the recommendation request information.

Depending on the embodiment, the management control unit 28 uses the user information of the user terminal 10 to provide objective information such as people in their 20s, single, female, doctors, pets, sunny weather, travel, likes swimming, and peppermint scent. Playback data can be generated using preferred subjective information.

Depending on the embodiment, the management control unit 28 may generate general playback data using standard data based on user information.

In addition, when the generated playback data is transmitted to the user terminal 10, the management control unit 28 determines changes in the emotion of the user terminal 10 during music playback in consideration of the playback time of the playback data and provides emotional state information. can be created.

Specifically, when music is played for a preset standard playback time based on playback data generated according to the user's selection using recommendation request information, the management control unit 28 compares and analyzes the playback data based on standard data. Thus, emotional state information can be generated.

For example, when the standard playback time is set to 1 minute, the management control unit 28 determines that music has been played when the actual playback time of the playback data is 1 minute or more and generates emotional state information reflecting the current emotional state. You can.

In contrast, when the standard playback time is set to 1 minute, the management control unit 28 determines that the music is not played when the actual playback time of the playback data is 1 minute or less and provides emotional state information that does not reflect the current emotional state. can be created.

More specifically, when the standard playback time is set to 1 minute and the actual playback time of the playback data is more than 1 minute and it is determined that music has been played, the management control unit 28 analyzes the subjective information included in the user information and First emotional state information is generated by identifying the previous emotional state before music playback. Second emotional state information is generated by analyzing playback data to determine the user's current emotional state during music playback. The first emotional state information and By analyzing the second emotional state information, third emotional state information corresponding to changes in the user's emotional state can be generated.

For example, if the second emotional state information is lower than the preset standard emotional information, the management control unit 28 may determine that the first emotional state information and the second emotional state information are not similar and generate the third emotional state information. there is.

Additionally, when the second emotional state information is higher than preset standard emotional information, the management control unit 28 may determine that the first emotional state information and the second emotional state information are similar and generate third emotional state information.

Here, the management control unit 28 can generate second emotional state information by extracting the user's patterns and keywords from the playback data.

Specifically, the management control unit 28 may determine whether the user's patterns and keywords extracted from the playback data are text or voice and preprocess the extracted data so that it is clearly recognized.

For example, if the extracted data is text, the management control unit 28 may preprocess it by sequentially performing tokenization, cleaning, and normalization. That is, the management control unit 28 performs a tokenization operation to filter data consisting of text, a refinement operation to remove noise data included in the tokenized data, and then the refinement operation is performed. The finished data can be normalized and preprocessed.

In other words, the management control unit 28 performs tokenization using a space removal filter and a special character removal filter so that the words included in the text are divided into the minimum unit of meaningful words, and then After performing a refinement operation to highlight the meaning of the remaining words by removing noise data for words that appear less frequently or those words that are repeated a lot, the refined data can be normalized and preprocessed.

At this time, the management control unit 28 can quantify the noise data and determine whether to delete it in response to the user information of the user terminal 10.

Depending on the embodiment, the management control unit 28 may automatically check and convert typos included in the text or automatically remove duplicate data.

On the other hand, when the extracted data is voice, the management control unit 28 can extract each word from voice over 10 seconds and convert the extracted words into text. Here, the converted text may be preprocessed.

Depending on the embodiment, when the extracted data is conversation data, the management control unit 28 may preprocess the conversation data and convert it into text. Converted text can be preprocessed.

Depending on the embodiment, second emotional state information may be generated by extracting user patterns and keywords included in playback data generated using objective information and subjective information.

For example, the management control unit 28 uses the user information of the user terminal 10 to provide objective information such as people in their 20s, single, female, doctors, pets, likes clear weather, travel, swimming, and prefers peppermint flavor. By analyzing playback data generated using subjective information, user patterns and keywords such as 'travel', 'swimming', 'skin scuba', and 'dog companion' can be extracted.

In addition, the management control unit 28 uses the emotional state information generated by identifying changes in the emotional state of the user terminal 10 to provide customized scent information corresponding to the change in the emotional state so that the user's positive emotional state is maintained or induced. can be created.

Specifically, when the second emotional state information is lower than the preset standard emotional information, the management control unit 28 may generate customized scent information so that the second emotional state information is guided to the first emotional state information.

For example, if the standard emotional state information is normal, the first emotional state information is a positive emotional state such as happiness or normal, and the second emotional state information is a negative emotional state such as angry or sad, the management control unit 28 Can generate customized scent information such that the second emotional state information of a negative emotional state is guided to the first emotional state information of a positive emotional state.

In contrast, when the second emotional state information is higher than the preset standard emotional information, the management control unit 28 may generate customized scent information so that the second emotional state information is maintained.

For example, if the standard emotional state information is normal, the first emotional state information is a positive emotional state such as happiness or normal, and the second emotional state information is a negative emotional state such as angry or sad, the management control unit 28 Can generate customized scent information so that the first emotional state information of a positive emotional state continues to be maintained.

Additionally, the management control unit 28 can generate standard data by repeatedly learning using deep learning techniques or machine learning techniques based on big data.

At this time, the management control unit 28 can generate standard data with high accuracy by testing the generated standard data.

In addition, the management control unit 28 may generate a feedback control signal that can improve the personalized scent recommendation service in response to the feedback signal received from the user terminal 10.

Depending on the embodiment, the management control unit 28 may generate a feedback control signal containing event information to increase the use of the personalized scent recommendation service of the user terminal 10.

Depending on the embodiment, the management control unit 28 receives recommendation request information from the user terminal 10 and, if it is unable to generate playback data or customized scent information corresponding to the recommendation request information, before transmitting the personalized scent information. After receiving additional data through the user terminal 10, playback data or customized scent information can be generated by considering the additional data.

For example, the management control unit 28 can generate playback data or customized scent information reflecting additional data.

Depending on the embodiment, the management control unit 28 may generate playback data or customized scent information that reflects only additional request information without reflecting additional data, or may generate playback data or customized scent information that does not reflect additional data.

In addition, when the user terminal 10 requests a personalized scent recommendation service, the management server 20 can process the corresponding payment service automatically or according to the user's priority information.

Alternatively, the payment procedure of the user terminal 10 may be processed through a separate payment server.

Such management server 20 may be implemented by hardware circuits (eg, CMOS-based logic circuits), firmware, software, or a combination thereof. For example, it can be implemented using transistors, logic gates, and electronic circuits in the form of various electrical structures.

The administrator terminal 30 is a terminal owned by a separate administrator, and can transmit and receive data in real-time synchronization with the user terminal 10 and the management server 20 using a wireless communication network. At this time, the administrator terminal 30 can transmit and receive data using an application program (application program).

The administrator terminal 30 can learn the standard data received from the management server 20, analyze the request data received from the user terminal 10, and generate result data using the result information corresponding to the request data. .

This manager terminal 30 may include various portable electronic communication devices that support communication with the user terminal 10 and the management server 20. For example, as separate smart devices, smart phones, PDAs (Personal Digital Assistants), tablets, wearable devices (e.g., smartwatches, glass-type terminals) It may include, but is not limited to, various terminals such as (including Smart Glass, HMD (Head Mounted Display), etc.) and various IoT (Internet of Things) terminals.

The operation of the personalized scent recommendation service system according to an embodiment of the present invention having this structure is as follows. FIG. 3 is a diagram for explaining a personalized scent recommendation service method according to an embodiment of the present invention, FIG. 4 is a diagram for explaining the step of generating customized scent information shown in FIG. 3, and FIG. 5 is a diagram for explaining a personalized scent recommendation service method according to an embodiment of the present invention. This diagram is intended to explain the steps for generating the depicted emotional state information.

First, as shown in FIG. 3, the management server 20 can generate standard data (S10).

Specifically, the management server 20 can generate standard data by repeatedly learning using deep learning techniques or machine learning techniques based on big data.

For example, the management server 20 may preprocess the collected big data and convert it into classifiable data, then classify the converted data and repeatedly learn the classified data to generate standard data.

For example, the management server 20 may convert data into classifiable data through RPA (Robot Process Automation) preprocessing, but is not limited to this.

Next, the management server 20 may receive recommendation request information from the user terminal 10 (S12).

Specifically, the user terminal 20 may generate recommendation request information by a user requesting a personalized scent recommendation service.

At this time, the user information may be entered by the user through prior membership registration in order to perform a personalized scent recommendation service, but is not limited to this and may be entered on a one-time basis without membership registration.

According to the embodiment, the management server 20 provides recommendation information using user information consisting of objective information and subjective information received from the user terminal 10 and request data for scent recommendation requesting a personalized scent recommendation service. can be created.

Next, the management server 20 can generate playback data corresponding to the user's selection using recommendation request information based on standard data (S14).

For example, the management server 20 may generate playback data containing music desired by the user by analyzing user information included in the recommendation request information based on the request data included in the recommendation request information.

According to the embodiment, the management server 20 uses the user information of the user terminal 10 to provide objective information such as people in their 20s, single, female, doctors, pets, sunny weather, travel, likes swimming, and peppermint scent. Playback data can be generated using preferred subjective information.

Depending on the embodiment, the management server 20 may generate general playback data using standard data based on user information.

Next, the management server 20 may transmit the generated playback data to the user terminal 10 and provide a personalized scent recommendation service to the user terminal 10 (S16).

Specifically, the user terminal 10 can receive a personalized scent recommendation service through communication with the management server 20.

For example, the user terminal 10 may output playback data visually and audibly separately or simultaneously.

Next, when music is played by the user terminal 10 during a preset standard playback time based on the playback data, the management server 20 can generate customized scent information by analyzing the playback data based on the standard data. There is (S18).

Specifically, referring to FIG. 4, the management server 20 compares and analyzes the playback data based on standard data (S100), and when the actual playback time of the playback data is played during the preset standard playback time ( S110), emotional state information can be generated (S120).

For example, when the standard playback time is set to 1 minute, the management server 20 may determine that music has been played and generate emotional state information when the actual playback time of the playback data is more than 1 minute.

In contrast, when the standard playback time is set to 1 minute, the management server 20 may determine that music is not played when the actual playback time of the playback data is 1 minute or less.

Next, the management server 20 can analyze the emotional state information and determine changes in the user's current emotional state (S130).

Specifically, referring to FIG. 5, when the standard playback time is set to 1 minute and the actual playback time of the playback data is more than 1 minute, if it is determined that music has been played, the management server 20 stores the information included in the user information. By analyzing subjective information, the previous emotional state before music playback can be identified and first emotional state information can be generated (S200).

Next, the management server 20 may analyze the playback data to identify the user's current emotional state while playing music and generate second emotional state information (S210).

Specifically, the management server 20 may generate second emotional state information by extracting the user's patterns and keywords from the playback data.

For example, if the extracted data is text, the management server 30 may preprocess it by sequentially performing tokenization, cleaning, and normalization. That is, the management control unit 28 performs a tokenization operation to filter data consisting of text, a refinement operation to remove noise data included in the tokenized data, and then the refinement operation is performed. The finished data can be normalized and preprocessed.

Additionally, when the extracted data is voice, the management control unit 28 can extract each word from voice over 10 seconds and convert the extracted words into text. Here, the converted text may be preprocessed.

Depending on the embodiment, the second emotional state information may be generated by extracting the user's patterns and keywords included in playback data generated using objective information and subjective information.

Next, the management server 20 may generate third emotional state information by comparing the generated first and second emotional state information with reference emotional state information.

Specifically, when the second emotional state information is lower than the preset standard emotional information (S220), the management server 20 determines that the first emotional state information and the second emotional state information are not similar (S230). Corresponding third emotional state information can be generated (S240).

For example, if the standard emotional state information is normal, the first emotional state information is a positive emotional state such as happiness or normal, and the second emotional state information is a negative emotional state such as angry or sad, the management server 20 Can generate third emotional state information that can lead the second emotional state information of a negative emotional state to the first emotional state information of a positive emotional state.

On the other hand, when the second emotional state information is higher than the preset standard emotional information (S220), the management server 20 determines that the first emotional state information and the second emotional state information are similar (S250) and responds accordingly. Third emotional state information can be generated (S260).

For example, if the standard emotional state information is normal, the first emotional state information is a positive emotional state such as happiness or normal, and the second emotional state information is a negative emotional state such as angry or sad, the management control unit 28 Can generate third emotional state information so that the first emotional state information of a positive emotional state continues to be maintained.

Next, the management server 20 can generate customized scent information reflecting the current emotional state using the third emotional state information (S140).

Specifically, the management server 20 uses the third emotional state information generated to guide the second emotional state information to the first emotional state information when the second emotional state information is lower than the preset standard emotional information. To generate reflected customized scent information, and to generate customized scent information reflecting the emotional state using the generated third emotional state information so that the second emotional state information is maintained when the second emotional state information is higher than the preset standard emotional information. You can.

On the other hand, if the music is not played during the actual playback time of the playback data for the preset reference playback time (S110), it is determined that the music has not been played and there is no change in the emotional state, so the current emotional state is not reflected. Customized scent information can be created (S150).

Next, the management server 20 may receive a feedback signal for the personalized scent recommendation service from the user terminal 10 (S20).

Specifically, the user terminal 10 may receive a personalized scent recommendation service corresponding to the request data and then generate a feedback signal for the personalized scent recommendation service.

At this time, the feedback signal may include information such as satisfaction, accuracy, and reliability for the personalized scent recommendation service.

Next, the management server 20 may generate a feedback control signal that can improve the personalized scent recommendation service in response to the feedback signal received from the user terminal 10 (S22).

Depending on the embodiment, the user terminal 10 may receive a feedback control signal containing improved or updated information of the personalized scent recommendation service in response to the feedback signal before, during, or after using the personalized scent recommendation service. You can. At this time, the feedback control signal may include event information. Event information may include, but is not limited to, advertisements or information about discounts or events for personalized scent recommendation services.

Depending on the embodiment, the manager terminal 30 may generate a feedback control signal that can improve a personalized scent recommendation service in response to the feedback signal.

Next, the management server 20 can update the standard data in real time using the customized scent information (S24).

Depending on the embodiment, the management server 20 may update standard data in real time in response to the feedback signal and the feedback control signal.

Finally, the manager terminal 30 can monitor the personalized scent recommendation service in real time (S26).

The steps of the method or algorithm described in connection with embodiments of the present invention may be implemented directly in hardware, implemented as a software module executed by hardware, or a combination thereof. Software modules can be RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), Flash Memory, hard disk, removable disk, CD-ROM, or It may reside on any type of computer-readable recording medium well known in the art to which the invention pertains.

Above, embodiments of the present invention have been described with reference to the attached drawings, but those skilled in the art will understand that the present invention can be implemented in other specific forms without changing its technical idea or essential features. You will be able to understand it. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive.

Claims

In a method of providing a personalized scent recommendation service performed by a server,

Receiving recommendation request information including user information from a user;

When music is played for a preset standard playback time based on playback data generated according to the user's selection using the recommendation request information, emotional state information generated by comparing and analyzing the playback data based on the user information Generating customized scent information using; and

Including providing a scent recommendation service to the user in response to the customized scent information,

The step of generating the customized scent information is,

Generating first emotional state information by analyzing subjective information included in the user information to identify a previous emotional state before music playback;

Analyzing the playback data to identify the user's current emotional state while playing music and generating second emotional state information;

Analyzing the first emotional state information and the second emotional state information to generate third emotional state information corresponding to a change in the user's emotional state; and

A method of providing a personalized scent recommendation service, comprising generating the customized scent information based on the third emotional state information.
According to paragraph 1,

The step of generating the second emotional state information is,

A method of providing a personalized scent recommendation service, comprising extracting user patterns and keywords from the playback data.
According to paragraph 2,

The step of generating the third emotional state information is,

When the second emotional state information is lower than the preset standard emotional information, it is determined that the first emotional state information and the second emotional state information are not similar, and the third emotional state information is generated, and the second emotional state information is determined to be not similar to the second emotional state information. A method of providing a personalized scent recommendation service comprising the step of determining that the first emotional state information and the second emotional state information are similar when the emotional state information is higher than the preset standard emotional information and generating the third emotional state information.
According to paragraph 3,

The step of generating the customized scent information is,

When the second emotional state information is lower than the preset standard emotional information, the customized scent information is generated so that the second emotional state information is guided to the first emotional state information, and the second emotional state information is the preset standard emotional state. A method of providing a personalized scent recommendation service, generating the customized scent information so that the second emotional state information is maintained when it is higher than the information.
It includes a management server that provides a personalized scent recommendation service to the user terminal,

The management server is,

User information including subjective information and objective information is received from the user terminal, and when music is played for a preset reference playback time based on playback data generated according to the user's selection, the playback is performed based on the user information. Generate customized scent information by comparing and analyzing data, and provide scent recommendation services to users in response to the customized scent information.

The management server is,

Based on the user information, the subjective information is analyzed to determine the previous emotional state before music playback to generate first emotional state information, and the playback data is analyzed to determine the user's current emotional state during music playback to generate second emotional state information. Generating emotional state information, analyzing the first emotional state information and the second emotional state information to generate third emotional state information corresponding to a change in the user's emotional state, and generating the third emotional state information based on the third emotional state information. A system that provides a personalized scent recommendation service that generates customized scent information.
A computer program combined with a computer as hardware and stored in a computer-readable recording medium so as to perform the method of claim 1.