KR20200063299A - Method for providing skin care cosmetics recommendation serivce using bigdata based ai machine learning - Google Patents

Abstract

The present invention relates to a method for providing skincare recommendation service using big data-based artificial intelligence machine learning. The method includes: a step of performing skin type diagnosis by transmitting a Baumann skin type questionnaire (BSTQ) to a user terminal and receiving survey result data regarding the BSTQ from the user terminal; a step of collecting from the user terminal product data including at least one or at least one combination among basic care, sun care, cleansing, and heavy makeup products used by a user; a step of collecting from the user terminal environment data including gender, age, weight, lifecycle, diet, and job; a step of parsing the diagnosed skin type, the product data, and the environment data and deriving and classifying skin type, product, and environment identifiers as input values; and a step of extracting reference data having a preset similarity from established big data based on the classified identifier, extracting a product containing a recommendation component pre-mapped in the reference data and stored, and recommending the product to the user terminal.

Description

METHOD FOR PROVIDING SKIN CARE COSMETICS RECOMMENDATION SERIVCE USING BIGDATA BASED AI MACHINE LEARNING}

The present invention relates to a method for providing a skin care recommendation service using big data-based artificial intelligence machine learning, to learn patterns inherent in skin condition, products used, and environmental information through unsupervised learning and recommend products based on big data Provide a method.

Cosmetics is a consumer product that is used every day in everyday life of ordinary consumers, and is a product that immediately responds to users. Due to the spread of mobile devices and the development of the Internet environment, such contents can be found on social networks and can be analyzed as big data through the collection of the data, but human skin has different states for each individual. According to the condition of the skin of the people, skin problems are also different. Accordingly, in 2016, as the Ministry of Health and Welfare allows the general public to conduct genetic tests through private institutions, users with various skin concerns are activating the genetic tests to use cosmetics that are more suitable for them, and skin diagnosis with big data And cosmetics recommendation platform.

At this time, the method of recommending cosmetics using big data is made as a method of analyzing trends. In connection with this, in Korean Patent Publication No. 2018-0074323 (published on July 03, 2018), access to SNS (Social Network Service) and the web, and collect cosmetics-related data by keywords for each cosmetic type according to the Enforcement Rules of the Cosmetic Act. To access the public institution server, collect standard data related to cosmetics on public data, store the big data by organizing cosmetics-related data, standard data, and data collected through public API into multiple categories. , It analyzes the trend of customers about cosmetics by analyzing big data in natural language, and verifies and fuses the analysis results using cosmetic-related data on public data.

However, even if the big data described above is used, the skin of a person has different states for each individual, and the skin suffers differently depending on the individual's skin condition, and the preferences for the use of cosmetics by ordinary consumers are my own and my skin Since preferences appear in the order of the right cosmetics and detailed counseling, the probability that the status of the group clustered into the same group is not very high unless accurate analysis is performed, so the recommendation service using only big data is less accurate. At this time, the genetic analysis of the skin is also enabled as a result of genetic testing in private institutions, and personalized skin type and genetic information are considered and personalized recommendations through big data analysis by collecting data from social networks Development of services is required.

In one embodiment of the present invention, the components contained in the cosmetics are collected and stored, and the individual's skin condition is diagnosed through a Baumann skin type questionnaire (BSTQ), and the skin condition is not taught as an input value. Proceed with (Unsupervised Learning) to learn the patterns, characteristics and structures inherent in the skin condition, and generate queries with reference data based on the learned results using the pre-built big data to output the recommended cosmetic products and management methods By providing a method for providing skin care recommendation services using artificial intelligence machine learning based on big data, which can accurately diagnose the user's skin condition through machine learning and search for big data by querying the learning results. Can provide. However, the technical problem to be achieved by the present embodiment is not limited to the technical problem as described above, and other technical problems may exist.

As a technical means for achieving the above-described technical problem, an embodiment of the present invention transmits a Baumann skin type questionnaire (BSTQ) to a user terminal, and surveys the Bauman skin type questionnaire from the user terminal. Diagnosing the skin type by receiving the result data, collecting product data including at least one or a combination of at least one of basic care products, sun care products, cleansing products, and makeup products used by the user from the user terminal, the user Collecting environmental data including gender, age, weight, life cycle, diet, and occupation from the terminal; parsing the diagnosed skin type, product data, and environmental data, and paring (Parsing) the skin type, product, and Deriving and classifying the identifier of the environment, and extracting reference data having a predetermined similarity from the pre-built big data based on the classified identifier, and extracting a product including recommended components that are pre-mapped and stored in the reference data And recommending to the user terminal.

According to any one of the above-described problem solving means of the present invention, the components contained in cosmetics are collected and stored, and the individual's skin condition is diagnosed through a Baumann skin type questionnaire (BSTQ), and the skin condition is diagnosed. Unsupervised learning is performed as an input value to learn patterns, characteristics, and structures inherent in the skin condition, and a query is generated with reference data based on the learned results using pre-built big data to recommend the results By outputting cosmetics and management methods, it is possible to accurately diagnose the user's skin condition by machine learning, and to search for big data by querying the learning results to generate more accurate recommendation results, and when there is negative feedback. , Reinforcement Learning can be conducted to minimize analysis errors.

1 is a view for explaining a skin care recommendation service providing system using big data-based artificial intelligence machine learning according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating a skin care recommendation service providing server included in the system of FIG. 1.
3 is a view for explaining an embodiment in which a skin care recommendation service using a big data-based artificial intelligence machine learning according to an embodiment of the present invention is implemented.
4 is a diagram illustrating a process in which data is transmitted and received between each of the components included in the skin care recommendation service providing system using big data-based AI machine learning of FIG. 1 according to an embodiment of the present invention.
5 is an operation flowchart for explaining a method for providing a skin care recommendation service using big data-based artificial intelligence machine learning according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art to which the present invention pertains may easily practice. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. In addition, in order to clearly describe the present invention in the drawings, parts irrelevant to the description are omitted, and like reference numerals are assigned to similar parts throughout the specification.

Throughout the specification, when a part is "connected" to another part, this includes not only "directly connected" but also "electrically connected" with another element in between. . Also, when a part is said to "include" a certain component, it means that the component may further include other components, not exclude other components, unless specifically stated otherwise. However, it should be understood that the existence or addition possibilities of numbers, steps, actions, components, parts or combinations thereof are not excluded in advance.

The terms "about", "substantially", and the like used throughout the specification are used in or at a value close to the value when manufacturing and substance tolerances unique to the stated meaning are given, and the understanding of the present invention. To aid, accurate or absolute figures are used to prevent unscrupulous use of the disclosed disclosure by unscrupulous infringers. The term "~(step)" or "step of" as used in the entire specification of the present invention does not mean "step for".

In the present specification, the term “unit” includes a unit realized by hardware, a unit realized by software, and a unit realized by using both. Further, one unit may be realized using two or more hardware, and two or more units may be realized by one hardware.

In the present specification, some of the operations or functions described as performed by the terminal, the device, or the device may be performed instead on a server connected to the corresponding terminal, device, or device. Similarly, some of the operations or functions described as being performed by the server may be performed in a terminal, apparatus, or device connected to the corresponding server.

In this specification, some of the operations or functions described as mapping or matching with the terminal means that the unique number of the terminal or identification information of the individual, which is identification data of the terminal, is mapped or matched. Can be interpreted as

Hereinafter, the present invention will be described in detail with reference to the accompanying drawings.

1 is a view for explaining a skin care recommendation service providing system using big data-based artificial intelligence machine learning according to an embodiment of the present invention. Referring to FIG. 1, the system 1 for providing skin care recommendation services using big data-based artificial intelligence machine learning includes at least one user terminal 100, a skin care recommendation service providing server 300, and at least one information Server 400 may be included. However, the system 1 for providing skin care recommendation services using artificial intelligence machine learning based on big data in FIG. 1 is only an embodiment of the present invention, and thus the present invention is not limitedly interpreted through FIG. 1.

At this time, each component of FIG. 1 is generally connected through a network (network, 200). For example, as illustrated in FIG. 1, at least one user terminal 100 may be connected to the skin care recommendation service providing server 300 through the network 200. In addition, the skin care recommendation service providing server 300 may be connected to at least one user terminal 100 and at least one information providing server 400 through the network 200. Also, the at least one information providing server 400 may be connected to the skin care recommendation service providing server 300 through the network 200.

Here, the network means a connection structure capable of exchanging information between each node such as a plurality of terminals and servers, and examples of such a network include RF, 3GPP (3rd Generation Partnership Project) network, and LTE (Long Term) Evolution network, 5GPP (5rd Generation Partnership Project) network, WIMAX (World Interoperability for Microwave Access) network, Internet (Internet), Local Area Network (LAN), Wireless Local Area Network (LAN), Wide Area Network (WAN) , PAN (Personal Area Network), Bluetooth (Bluetooth) network, NFC network, satellite broadcasting network, analog broadcasting network, DMB (Digital Multimedia Broadcasting) network, and the like.

In the following, the term at least one is defined as a term including singular and plural, and even if the term at least one does not exist, each component may exist in singular or plural, and may mean singular or plural. It will be self-evident. In addition, it may be said that each component is provided in a singular or plural form, depending on the embodiment.

At least one user terminal 100 is a terminal receiving skin diagnosis and cosmetics or skin care suitable for the user by using a web page, app page, program or application related to skin care recommendation service using big data-based artificial intelligence machine learning. Can be At this time, the at least one user terminal 100 may be a terminal that receives a Baumann skin type questionnaire (BSTQ) from the skin care recommendation service providing server 300 and transmits a response thereto. Here, at least one user terminal 100 may be a terminal that transmits it to the skin care recommendation service providing server 300 when a genetic test result exists. In addition, the at least one user terminal 100 may be a terminal that inputs cosmetics used for each purpose and transmits environmental data including body data and occupation data to the skin care recommendation service providing server 300. Accordingly, the at least one user terminal 100 may be a terminal capable of receiving accurate diagnosis and product or management suitable for their skin type based on big data from the skin management recommendation service providing server 300.

Here, the at least one user terminal 100 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, navigation, a laptop equipped with a web browser (WEB Browser), a desktop, a laptop, and the like. At this time, the at least one user terminal 100 may be implemented as a terminal capable of accessing a remote server or terminal through a network. The at least one user terminal 100 is, for example, a wireless communication device in which portability and mobility are guaranteed, navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), Personal Handyphone System (PHS), Personal Digital Assistant (PDA), International Mobile Telecommunication (IMT)-2000, Code Division Multiple Access (CDMA)-2000, W-Code Division Multiple Access (W-CDMA), Wireless Broadband Internet ) It may include all kinds of handheld-based wireless communication devices such as a terminal, a smartphone, a smartpad, and a tablet PC.

The skin care recommendation service providing server 300 may be a server that provides a skin care recommendation service web page, app page, program, or application using big data-based artificial intelligence machine learning. Then, the skin care recommendation service providing server 300 collects raw data including raw data, weather data, ingredient data, cosmetic data, and social media data from at least one information providing server 400 and , It may be a server that builds big data based on the collected data. In addition, the skin care recommendation service providing server 300 may be a server for learning by associating a skin type, a product, an ingredient, and the like, as a result of skin diagnosis. In addition, the skin care recommendation service providing server 300 transmits a Bauman skin type questionnaire to at least one user terminal 100, receives a response from at least one user terminal 100, and at least one user terminal 100 In case of performing genetic test in ), based on skin type and genetic test, machine learning of patterns, characteristics and structures inherent in the user's data by non-supervised learning, and extracting reference data for this to generate queries and generate It may be a server that transmits the query to the user terminal 100 by extracting recommendation data, which is a result value by inputting the query to the big data. To this end, skin type, genetic testing, product information, etc. must be mapped and stored, and this data can be updated and re-learned continuously to update big data. In addition, the skin care recommendation service providing server 300 receives feedback from at least one user terminal 100 and evolves in the direction of correcting errors by performing reinforcement learning when the feedback is negative. It can be a server. To this end, the skin care recommendation service providing server 300 builds big data using at least one information providing server 500 and pre-stored history log data, and classifies big data through collection, preprocessing, and analysis. And a server for learning after clustering. In addition, the skin care recommendation service providing server 300 performs data learning using a deep learning artificial neural network algorithm for tagging identifiers from image data and image data in order to extract identifiers from image data or image data that is unstructured data. It can be an ongoing server. In addition, the skin care recommendation service providing server 300 may be a server that tags or extracts an identifier from an image, image, etc. that is subsequently input according to the learning result.

Here, the skin care recommendation service providing server 300 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, navigation, a laptop equipped with a web browser (WEB Browser), a desktop, a laptop, and the like.

The at least one information providing server 400 provides information to the skin care recommendation service providing server 300 using a web page, app page, program, or application related to skin care recommendation service using big data-based AI machine learning. Server. At this time, the at least one information providing server 400 may be a server of a public institution or a server of a private company. In addition, the server of a private company may also be a server of a cosmetics company, a social media related company, a portal service company, etc., the type is not limited to the above, and the list increases or decreases according to embodiments or as data collected is changed. It is obvious that it can be transformed. Here, the skin care recommendation service providing server 300 may collect information through web crawling when it is difficult to directly receive feedback from the at least one information providing server 400, and in this case, provide at least one information The server 400 may be deleted.

Here, the at least one information providing server 400 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, navigation, a laptop equipped with a web browser (WEB Browser), a desktop, a laptop, and the like. At this time, the at least one information providing server 400 may be implemented as a terminal that can access a remote server or terminal through a network.

2 is a block diagram for explaining a server for providing a skin care recommendation service included in the system of FIG. 1, and FIG. 3 is a skin care recommendation service using big data-based artificial intelligence machine learning according to an embodiment of the present invention. It is a diagram for explaining one embodiment implemented.

2, the skin care recommendation service providing server 300 includes a diagnosis unit 310, a product collection unit 320, an environment collection unit 330, a classification unit 340, a recommendation unit 350, and a management unit 360, a big data unit 370, a learning unit 380, and a verification unit 390.

Skin care recommendation service providing server 300 according to an embodiment of the present invention or another server (not shown) operating in conjunction with at least one user terminal 100 and at least one information providing server 400 as big data Skin care recommendation service based on artificial intelligence machine learning When transmitting an application, program, app page, web page, etc., at least one user terminal 100 and at least one information providing server 400 are big data-based artificial Skin care recommendation service application, program, app page, web page, etc. using intelligent machine learning can be installed or opened. In addition, the service program may be driven in at least one user terminal 100 and at least one information providing server 400 using a script executed in a web browser. Here, the web browser is a program that enables the use of the world wide web (WWW) service, and refers to a program that receives and displays hypertext described in a hypertext mark-up language (HTML), for example, Netscape. , Explorer, Chrome, and the like. Further, the application means an application on the terminal, and includes, for example, an app that is executed on a mobile terminal (smartphone).

Referring to FIG. 2, the diagnosis unit 310 transmits a Baumann skin type questionnaire (BSTQ) to the user terminal 100, and results of a survey on the Bauman skin type questionnaire from the user terminal 100 Skin type can be diagnosed by receiving data. Here, the Baumann skin type questionnaire is Oily or Dry, Sensitive or Resistant, Pigmented or Non-Pigmented, Wrinkled or Tight. The purpose of this study is to classify skin types by the Bauman skin type index so that they can identify their own skin type among 16 types of skin types by evaluating. The four uppercase letters displayed from ,3) represent the above-described characteristics in two letters. For example, OSPW is Oily, Sensitive, Pigmented, Wrinkled, that is, a skin type having oily, sensitive, pigmented, and wrinkled characteristics. In addition, here, since the Bauman skin type questionnaire is the same as the public technology, detailed description will be omitted in the specification of the present invention.

OILY DRY PIGMENTED NONPIGMENTED PIGMENTED NONPIGMENTED Wrinkled OSPW OSNW DSPW DSNW Sensitive Tight OSPT OSNT DSPT DSNT Sensitive Wrinkled ORPW ORNW DRPW DRNW Resistant Tight ORPT ORNT DRPT DRNT Resistant

At this time, in addition to the Bowman questionnaire, further genetic test results may be added, and DNA, hair mineral, etc. test results may be added. This can be used later to analyze a user's skin pattern by calculating a user's skin type analysis result and genetic information. Here, the genetic information can be converted into a perfect score based on the results of a genetic analysis specialized institution, and classified into good/careful/managed by scores. Genetic testing is the basis for judging the current skin condition. Based on the can check the current skin care status and suggest direction, examples of this are shown in Table 2 below.

division Skin condition Judgment criteria Good gene index
(No variation) Good Excellent skin care Problem Lack of skin care Genetic index variation
(Including some variations) Good Excellent skin care before mutation gene expression Problem Insufficient management of mutation gene expression

The product collection unit 320 may collect product data including at least one or a combination of at least one of basic care products, sun care products, cleansing products, and makeup products used by the user from the user terminal 100. At this time, basic care may include skin, toner, lotion, essence, cream, face oil, no care, neck care, mist, mask, pack, and sun care, sun cream, sun spray, sun stick, after sun care, tanning May include, cleansing may include eye remover, lip remover, cleansing oil, cleansing oil, lotion, cleansing foam, cleansing gel, cleansing water, cleansing tissue, soap, scrub, peeling, makeup, face It can be divided into parts and classified. At this time, the components contained by product can be classified and analyzed by component name. Here, it will be apparent that the product data collected is not limited to the listed ones. The environment collection unit 330, the environment data including gender, age, weight, life cycle, diet, and occupation from the user terminal 100 Can be collected. At this time, the environment data may collect body data including gender, age, weight, height, etc., and data such as occupation, lifestyle, and diet for grasping the environment such as external environment and electromagnetic wave exposure. It is obvious that the environmental data collected is not limited to those listed.

The classification unit 340 may parse the diagnosed skin type, product data, and environmental data to derive and classify the identifiers of the skin type, product, and environment as input values. For example, assuming that the skin type is classified as the type A, the product data is the B product, and the environmental data is the C data, the pre-stored identifiers X, Y, and Z corresponding to A, B, and C are extracted, and the user XYZ, which is an identifier for the skin, used product, and environment, can be assigned. This can be used as an input value (reference value, reference data) to find a group closest to the user in the big data. Here, in one embodiment of the present invention, unsupervised learning can be conducted to find a pattern inherent in the data using the user's skin type, product data, and environmental data as input values. Here, machine learning may be defined as a methodology that empowers a computer to self-learn even if it is not explicitly programmed, and this is a method of allowing a program to learn patterns of data by itself based on data. Machine learning is obtained by supervised learning and unsupervised learning depending on whether or not the correct answer is specified in the data required for learning, and classification, which divides data into finite categories according to the purpose of use, continuous It is divided into regression that maps to values, clustering that bundles similar data, and dimension reduction methodology that maps multidimensional data to a representative low dimension.

Deep learning is one of the machine learning techniques that dramatically improves the performance of machine learning, which has been stagnant for a while.Deep learning is a methodology based on the Artificial Neural Network (ANN) algorithm that mimics the overlap of synapses in the human brain structure. In the deep learning structure, a deep neural network (DNN) in which a plurality of hidden layers exist between an input layer and an output layer, a filter necessary for factor extraction in front of the hidden layer It may include a convolutional neural network (CNN) that learns filters together, and a recurrent neural network (RNN) capable of processing time series data by stacking artificial neural networks of each time. Here, the high performance of the deep learning model is explained in two ways. First, the neural network is a superposition of weighted sum of functions in each layer, and if enough general data is given as a universal approximator that can approximate all kinds of functions. Data can be simulated with high accuracy. Second, it is important to properly extract the factors representing the data in order to classify the data well, and it is possible to extract the optimal factors through filter learning using a spiral neural network. In addition, deep learning is a form in which a model of the artificial intelligence field called a neural network is developed, and the inner layer of the artificial neural network composed of hierarchical structures is composed of several stages. In recent deep learning models, the number of weights (meaning the connection strength) connecting the nodes may be up to several billions due to the large number of internal layers.

At this time, the convolutional neural network (CNN) is a model that has the advantage of being able to recognize even if the size or position of a pattern changes by imitating the visual processing process of an organism, and has three characteristics. receptive field), weight sharing, and subsampling. First, the local receptive field means that the existing model is connected with weights (filters) to only some of the nodes in the upper layer, unlike each node in the lower layer is connected to all upper layer nodes. When a filter is applied to all areas of an input pattern and a weight is multiplied by a corresponding area to sum, the transfer to a node of a panel of an upper node is called convolution. Second, weight sharing means that weights are shared, which means that the filters applied to nodes and input patterns (or lower layers) in one panel are the same. Since one filter can recognize one feature (or a small pattern), one panel can find the feature present at a specific location of the input pattern. Third, subsampling is a process that takes place in the second and third layers, compressing the panels present in the second layer, and is also called pooling. At this time, the average pooling (Average Pooling) that multiplies the weight by averaging is often used, but in one embodiment of the present invention, the maximum pooling using the largest value among the four values in the 2X2 region will be used. . The sub-sampling function reduces the size of the input pattern and makes it less sensitive to variations in the position of the discovered feature. The convolution and sub-sampling process may be repeated multiple times according to an embodiment, and after the sub-sampling is completed, the neural network is connected.

At this time, when learning the weights of the convolutional neural network, the convolutional neural network has a large number of internal layers, so the number of nodes increases and the weights connecting the nodes increase. In general, when the number of weights in the model increases, when the error back-propagation algorithm is applied, the problem that the size of the linear one-way function iteratively becomes very large or conversely becomes zero. However, in the case of a convolutional neural network, since it has a feature of weight sharing, the number of weights is not large enough to cause such a problem, so an error back propagation algorithm can be applied without difficulty. However, the algorithm may be modified because the characteristics of weight sharing and the process of subsampling are different from the general neural network model. For example, for the shared weight, the process of adding the values of the linear one-way functions to all the same weights after calculating the linear one-way function in the same way as when the weights are different may be applied. When the pattern is compressed through sub-sampling, an operation in the opposite direction must be performed when back-propagating the error, so a process of extending through up-sampling may be further added. However, it will be apparent that various methods may be used without being limited to the above-described method.

On the other hand, the recurrent neural network (RNN) model is suitable for processing sequential information such as speech recognition or language recognition. RNN receives and processes elements constituting sequential data one at a time, and stores the processed information in the internal node. It is necessary to generate the internal node corresponding to the input time and store the processed information up to that point. If it is, it is a method of printing through the output node. In addition, in the case of the circulatory neural network model, in some cases, non-sequential data may be input/output, and various applications are possible depending on the type of input/output data. When the input/output data is sequential, it may be applied to machine translation or annotation on a video. In the case where the output is non-sequential, it can be applied to emotional analysis, and when the input is non-sequential, it can be applied to comments on pictures, but is not limited thereto. Lastly, the deep belief network is an unsupervised learning model, and it is characterized by humans and animals learning themselves through observation. At this time, it will be apparent that various machine learning methods are not limited to those listed, and may be changed according to embodiments.

The recommendation unit 350 extracts reference data having a predetermined degree of similarity from pre-built big data based on the classified identifier, and extracts a product including a recommendation component that is pre-mapped to the reference data and extracts the user terminal 100 ). The recommendation unit 350 extracts reference data having a predetermined degree of similarity from pre-built big data based on the classified identifier, and extracts a product including a recommendation component that is pre-mapped to the reference data and extracts the user terminal 100 When recommending with ), a query for retrieving reference data having a predetermined similarity based on the classified identifier is automatically derived, and using the derived query, retrieving reference data having a predetermined similarity, As a result of the search, reference data having a predetermined similarity may be extracted.

At this time, when using big data for recommendation, collaborative filtering may be used. Here, Collaborative Filtering creates a profile based on information about the user's skin condition, environmental data, and product data, and based on this, other users who have similar purchase preferences, skin condition, and environmental data to the target customer It is a way to recommend items that you want to purchase or prefer. For example, after creating a single profile or multiple profiles based on purchase preference, skin condition and environmental data similar to the target customer, ensemble data mining techniques such as artificial neural networks and decision trees and collaborative filtering techniques to improve recommendation performance. Can improve. Alternatively, a fusion technique that generates a single profile using the skin condition and combines the prediction results of the k-NN model between users and the product may be used, and purchase data and review data of online stores can be used. It is also possible to create a user-product matrix-based profile by using and construct ensemble by constructing logistic regression analysis, decision tree, artificial neural network model. However, the method is not limited to the above-described method, and it may be apparent that a method of recommending based on a user profile in various ways may be used.

The management unit 360 parses the skin type, product data, and environment data diagnosed by the classification unit 340 to derive and classify the skin type, product, and environment identifiers as input values, and then classifies them by day. Weather data including any one or at least one of temperature, humidity, ultraviolet light, fine dust, ultrafine dust, and yellow dust may be collected using a web crawler. Then, the management unit 360 extracts reference data having a predetermined similarity level from the pre-built big data based on the classified identifier, and extracts the skin management method pre-mapped to the reference data to the user terminal 100 Can recommend For example, in the autumn when the dry weather continues, as the moisture in the skin decreases, tickling and skin pulling appear, and many women try to keep the skin moisturized by applying moisturizing products. However, people who have many skin problems and show oily skin even in the autumn are worried about choosing a moisturizing product, because if they choose wrongly, they can cause greasy and trouble. Accordingly, if the user is oily skin, it may be recommended to use a moisture cream or moisturizing product without oil, or a product that helps to prevent wetting and trouble such as glycerin and tea tree ingredients. In addition, after cleansing, applying a moisturizing cream or essence that has less oil but can increase water supply and holding power can prevent the skin from drying out, and provide recommended products extracted according to the skin condition identified by the diagnostic unit (310). Can be.

The big data unit 370 transmits a Baumann skin type questionnaire (BSTQ) from the diagnosis unit 310 to the user terminal 100, and surveys the Bauman skin type questionnaire from the user terminal 100 Before receiving the result data and diagnosing the skin type, it collects cosmetic ingredient information from at least one cosmetic manufacturer server, collects review data and ingredient data for at least one cosmetic type by web crawling, and at least one It collects harmful ingredient data from public servers, stores raw and collected raw ingredient data, review data, ingredient data, and raw ingredient data in parallel and distributed. Purification of unstructed data, structured data and semi-structured data, pre-processing including classification by meta data, extraction of pre-processed data, and analysis including data mining You can build big data by performing and visualizing and outputting the analyzed data. At this time, it can be stored to be classified according to components, items, categories, keywords, and the like, and can also perform classification analysis by component, user cluster analysis, trouble-related analysis, and product prediction analysis.

Here, data mining is a classification that predicts a class of new data by learning a training data set in which a class is known by exploring an implicit relationship between preprocessed data, or clustering data based on similarity without class information ( Clustering) may be included. Of course, in addition, various mining methods may exist, and may be mined differently depending on the type of big data collected and stored or the type of query to be requested later. The big data constructed in this way may be verified through artificial neural network deep learning or machine learning. At this time, a convolutional neural network (CNN) structure may be used for the artificial neural network. CNN is a network structure using a convolutional layer and is suitable for image processing, and classifies an image based on characteristics in the image by inputting image data. Because it can. In addition, text mining is a technology aimed at extracting and processing useful information based on natural language processing technology from non/semi-structured text data. Through text mining technology, it is possible to extract meaningful information from a large bunch of text, grasp the linkage with other information, find categories of text, or get more than just searching for information. Using this, in the free travel integrated reservation service according to an embodiment of the present invention, a large-scale language resource, statistical and regular algorithms may be used to analyze an identifier or natural language inputted into a query and discover hidden information therein. have. In addition, cluster analysis can be used to finally discover a group of similar characteristics while merging sieves having similar characteristics, and by identifying the characteristics of a user cluster, and subsequently requesting the recommendation advisory object, Can be sorted.

The learning unit 380 extracts reference data having a predetermined similarity level from pre-built big data based on the identifier classified by the recommendation unit 350, and extracts a product including recommended components that are pre-mapped and stored in the reference data. After extraction and recommendation to the user terminal 100, feedback data on whether the recommended product is appropriate or not is received from the user terminal 100, and reinforcement learning may be performed using the received feedback data. . At this time, reinforcement learning is a field of artificial intelligence that learns through rewards for behavior, and various algorithms to implement it have been developed and applied in various fields such as robot control, communication networks, and board games. At this time, in the machine learning problem, reinforcement learning assumes that an agent (or robot) placed in an arbitrary environment recognizes and acts on its current state. Then, the agent gets a positive reward or a negative reward from the environment, and the reinforcement learning algorithm finds a policy that maximizes the accumulated reward value in the agent during problem solving. In the reinforcement learning method, the environment is formalized by finite state Markov decision processes (MDPs). And the reinforcement learning algorithm is directly related to the dynamic programming technique, where dynamic programming refers to the execution of a given problem by dividing it into several problems, recording the results of previous executions, and reusing them later. In addition, it can be said that it is important to find a balance between exploration of an area that has not yet been investigated and exploration of knowledge already known.

The verification unit 390 extracts reference data having a predetermined similarity level from pre-built big data based on the identifier classified by the recommendation unit 350, and extracts a product including recommended components that are pre-mapped and stored in the reference data. After extracting and recommending it to the user terminal 100, when receiving negative feedback data on the adequacy of the recommended product from the user terminal 100, an error is performed by authenticating for error verification of the product containing the recommended component. Deep learning using artificial neural networks and deep learning are performed to identify parts and causes of errors, update the identified errors parts and causes of errors to big data, discover patterns of errors and predict error rates through classification. The data derived from can be reflected in big data. At this time, deep learning, artificial neural networks, and reinforcement learning are the same as the above-described methods, so the description thereof will be omitted.

Hereinafter, an operation process according to the configuration of the skin care recommendation service providing server of FIG. 2 will be described in detail with reference to FIG. 3 as an example. However, the embodiment is only one of various embodiments of the present invention, it will be apparent that it is not limited thereto.

Referring to FIG. 3A, (a) skin care recommendation service providing server 300 extracts review data and cosmetic ingredient data online, and identifies harmful ingredients, extracts ingredient information, and provides natural environment information through public data collection. It is extracted and it is possible to collect cosmetic information of the manufacturer through the cosmetic manufacturer. In addition, the skin care recommendation service providing server 300 constructs big data and not recommends products to the user only based on the big data, but performs the user's skin type including genetic testing, and (b) the user's By using the unsupervised learning method and the convolutional (convolutional) network, sharing the weights, and zooming out to the maximum pooling, only the user's information is input to discover patterns, characteristics, and structures inherent in the data through learning, It consists of only the input properties of the object for the learning data to be calculated. In addition, (c) personal information can be collected in three levels (3rd), and reinforced learning can be conducted through feedback to provide a recommendation service in consideration of the scope of observation of consumer behavior and state transition rules.

Referring to Figure 3b, the method of collecting data and the type of data include web documents, content, OPNE API, real-time collection data, data collection log, and the collection destination is open such as the Ministry of Food and Drug Safety public data, ICID, WIKI It may include a database, a web database, social media, a keyword database of Google search, but is not limited to the above. And, the data pre-processing can go through the process of filtration, conversion, purification, integration, and reduction, and data can be stored according to various factors including item, component, classification, keyword effectiveness, classification analysis by component, and user cluster Analysis, trouble-related analysis, and product prediction analysis can be performed to visualize the results on the platform.

The methods for providing skin care recommendation service using the artificial intelligence machine learning based on big data in FIGS. 2 and 3 are not explained. The method for providing skin care recommendation service using the artificial intelligence machine learning based on big data through FIG. Since it is possible to easily infer from the contents described or described, the following description will be omitted.

4 is a diagram illustrating a process in which data is transmitted and received between each of the components included in the skin care recommendation service providing system using big data-based AI machine learning of FIG. 1 according to an embodiment of the present invention. Hereinafter, an example of a process in which data is transmitted and received between each of the components will be described with reference to FIG. 4, but the present application is not limited to such an embodiment, and is illustrated in FIG. 4 according to various embodiments described above. It is apparent to those skilled in the art that the process of transmitting and receiving data can be changed.

Referring to FIG. 4, the skin care recommendation service providing server 300 collects data from at least one information providing server 400 (S4100), analyzes data through data preprocessing (S4200), and visualizes the result. How to build big data (S4300).

Meanwhile, when the skin care recommendation service providing server 300 receives a diagnostic request from the user terminal 100 (S4400), the Bauman questionnaire is transmitted to the user terminal 100 to receive an answer (S4500, S4600), and the skin The type is diagnosed (S4700), and the product and environment data input from the user terminal 100 are integrated (S4800) to learn patterns and characteristics of user data through unsupervised learning (S4810). Then, the skin care recommendation service providing server 300 parses the data to extract the identifier (S4820), generates a query with the identifier (S4830), and extracts a recommended product that answers the query (S4840), the user terminal It is recommended as a method of transmitting to (100) (S4850).

At this time, when the skin care recommendation service providing server 300 has feedback from the user terminal 100 (S4860), if it is negative feedback, reinforcement learning is performed (S4900, S4910), more preferably, artificial neural network deep learning. To verify the error (S4920), extract the error pattern (S4930) and re-learn and update the big data based on this.

The order between the above-described steps (S4100 to S4930) is only an example, and is not limited thereto. That is, the order between the above-described steps (S4100 to S4930) may be mutually variable, some of which may be executed or deleted simultaneously.

How to provide a skin care recommendation service using the big data-based artificial intelligence machine learning of FIG. 4 is not described above. A method for providing a skin care recommendation service using the big data-based artificial intelligence machine learning through FIG. Since it is possible to easily infer from the contents described or described, the following description will be omitted.

5 is an operation flowchart for explaining a method for providing a skin care recommendation service using big data-based artificial intelligence machine learning according to an embodiment of the present invention. Referring to FIG. 5, the skin care recommendation service providing server transmits a Baumann skin type questionnaire (BSTQ) to a user terminal, and receives survey result data for a Bauman skin type questionnaire from the user terminal to derive skin Diagnose the type (S5100).

Then, the skin care recommendation service providing server collects product data including at least one or at least one combination of basic care products, sun care products, cleansing products, and makeup products used by the user from the user terminal (S5200), Environmental data including gender, age, weight, life cycle, diet, and occupation is collected from the terminal (S5300).

In addition, the skin care recommendation service providing server parses the diagnosed skin type, product data, and environmental data to derive and classify the identifiers of the skin type, product, and environment as input values (S5400). Based on the identifier, reference data having a predetermined similarity is extracted from the pre-built big data, and a product including a recommendation component pre-mapped and stored in the reference data is extracted and recommended to the user terminal (S5500).

How to provide a skin care recommendation service using the big data-based artificial intelligence machine learning of FIG. 5 is not described above. A method for providing a skin care recommendation service using the big data-based artificial intelligence machine learning through FIG. Since it is possible to easily infer from the contents described or described, the following description will be omitted.

A method for providing skin care recommendation service using big data-based artificial intelligence machine learning according to an embodiment described with reference to FIG. 5 is a recording medium including instructions executable by a computer, such as an application or program module executed by a computer It can also be implemented in the form of. Computer readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. Also, the computer-readable medium may include any computer storage medium. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.

The method for providing skin care recommendation service using big data-based artificial intelligence machine learning according to an embodiment of the present invention described above includes an application installed in the terminal (this includes a program included in a platform or an operating system basically installed in the terminal) It can be executed by the user, or an application (i.e., program) installed directly on the master terminal through an application providing server such as a web server related to an application store server, an application, or a corresponding service. In this sense, the method for providing skin care recommendation service using big data-based artificial intelligence machine learning according to an embodiment of the present invention described above is implemented as an application (that is, a program) basically installed in a terminal or directly installed by a user. It may be recorded on a computer-readable recording medium such as a terminal.

The above description of the present invention is for illustration only, and a person having ordinary knowledge in the technical field to which the present invention pertains can understand that it can be easily modified to other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined form.

The scope of the present invention is indicated by the following claims rather than the above detailed description, and it should be interpreted that all changes or modified forms derived from the meaning and scope of the claims and equivalent concepts thereof are included in the scope of the present invention. do.

Claims (7)

In the method for providing a skin care recommendation service provided by the skin care recommendation service providing server,
Diagnosing a skin type by transmitting a Baumann skin type questionnaire (BSTQ) to a user terminal and receiving survey result data for the Bauman skin type questionnaire from the user terminal;
Collecting product data including at least one or a combination of at least one of basic care products, sun care products, cleansing products, and makeup products used by the user from the user terminal;
Collecting environmental data including gender, age, weight, life cycle, diet, and occupation from the user terminal;
Parsing the diagnosed skin type, product data, and environmental data to derive and classify the identifiers of the skin type, product, and environment as input values; And
Extracting reference data having predetermined similarity from pre-built big data based on the classified identifier, and extracting a product including a recommendation component pre-mapped to the reference data and recommending it to the user terminal;
Including, a method for providing skin care recommendation service using big data-based artificial intelligence machine learning.
According to claim 1,
After parsing the diagnosed skin type, product data, and environmental data, deriving and classifying the identifiers of the skin type, product, and environment as input values.
Collecting weather data including any one or at least one of temperature, humidity, ultraviolet light, fine dust, ultrafine dust, and yellow dust on a daily basis using a web crawler;
Extracting reference data having a predetermined similarity from the pre-built big data based on the classified identifier, extracting a skin management method pre-mapped to the reference data and recommending it to the user terminal;
The method further comprising, Big data-based artificial intelligence machine learning using skin care recommendation service providing method.
According to claim 1,
Before the step of diagnosing a skin type by transmitting a Baumann skin type questionnaire (BSTQ) to the user terminal and receiving survey result data for the Bauman skin type questionnaire from the user terminal,
Collecting cosmetic ingredient information from at least one cosmetic manufacturer server;
Collecting review data and ingredient data for at least one kind of cosmetics by web crawling;
Collecting harmful ingredient data from at least one public server;
Storing, in parallel and distributed, raw data including the collected cosmetic ingredient information, review data, ingredient data, and harmful ingredient data;
Purifying unstructured data, structured data, and semi-structured data included in the stored raw data, and performing pre-processing including classification as metadata;
Performing an analysis including data mining on the preprocessed data;
Visualizing and outputting the analyzed data;
The method further comprising, Big data-based artificial intelligence machine learning using skin care recommendation service providing method.
The method of claim 3,
The data mining is a classification (Classification) that predicts a class of new data by learning a training data set in which a class is known by searching for an implicit relationship between the pre-processed data, or clustering data based on similarity without class information ( Clustering), a method for providing skin care recommendation services using big data-based artificial intelligence machine learning.
According to claim 1,
After the step of extracting the reference data having the predetermined similarity from the pre-built big data based on the classified identifier, and extracting the product containing the recommended component that is pre-mapped to the reference data and recommending it to the user terminal ,
Receiving feedback data on whether the recommended product is appropriate from the user terminal;
Performing reinforcement learning using the received feedback data;
The method further comprising, Big data-based artificial intelligence machine learning using skin care recommendation service providing method.
According to claim 1,
After the step of extracting the reference data having the predetermined similarity from the pre-built big data based on the classified identifier, and extracting the product containing the recommended component that is pre-mapped to the reference data and recommending it to the user terminal ,
When receiving negative feedback data on whether the recommended product is appropriate from the user terminal, performing authentication for error verification of the product containing the recommended component to identify the error part and the cause of the error;
Performing the deep learning using an artificial neural network in order to discover the pattern of the error and predict the error rate through classification after updating the identified error part and the cause of the error in the big data;
Allowing data derived from the deep learning to be reflected in the big data;
The method further comprising, Big data-based artificial intelligence machine learning using skin care recommendation service providing method.
According to claim 1,
The step of extracting the reference data having a predetermined similarity from the pre-built big data based on the classified identifier, and extracting a product including a recommendation component that is pre-mapped to the reference data and recommending it to the user terminal,
Deriving a query for automatically retrieving reference data having the predetermined similarity based on the classified identifier;
Searching for reference data having the preset similarity using the derived query;
Extracting reference data having the predetermined similarity as a result of the search;
Method for providing skin care recommendation service using big data-based artificial intelligence machine learning, which is executed by performing

Images