Server for providing treatment compatibility according to gel combination based on artificial intelligence model and method operation thereof

Abstract

According to various embodiments, a server for providing procedural compatibility based on a gel combination based on an artificial intelligence model comprises: a communication interface; and a processor; wherein the processor receives at least one procedural request data and at least one gel data from an external electronic device through the communication interface, inputs the at least one procedural request data and the at least one gel data into an artificial intelligence model to determine at least one gel combination compatibility data, and is configured to transmit the at least one gel combination compatibility data to the external electronic device through the communication interface; and the artificial intelligence model is learned based on a plurality of procedural request data and a plurality of gel data, a plurality of gel combination compatibility data, a plurality of gel feature data, a plurality of label data, and a plurality of experiment-based data, a first procedural compatibility result data in which the plurality of gel combination compatibility data does not exceed a preset first compatibility threshold and is determined to be in a highest grade state, and a second procedural compatibility result data in which the plurality of gel combination compatibility data exceeds the first compatibility threshold and is determined to be the next step after the first procedural compatibility result data.

Description

Technology Field

[0001] The present invention relates to a server and a method for operating the same for providing procedural compatibility according to gel combinations based on an artificial intelligence model. Background Technology

[0002] Conventionally, there was no system capable of accurately predicting the chemical and physical compatibility between gel nail products in advance. Since conventional systems lacked a database capable of systematically integrating and analyzing various factor data—such as brand-specific product ingredient data, viscosity data, curing time data, peel-off rate data, durability data, and discoloration potential data—there were limitations in practitioners' ability to predict product interactions.

[0003] Conventionally, user feedback data collected from nail salons and consumers was not systematically reflected, and there was a lack of functionality to calculate actual compatibility information for product combinations by integrating experimental and user experience data. Consequently, it was difficult to prevent problems such as peeling, reduced durability, and discoloration caused by product inconsistencies in advance.

[0004] Conventionally, the absence of AI or big data-based analysis engines capable of providing compatibility analysis and optimal combination recommendations inevitably led to repetitive trial and error at every product launch. Furthermore, since conventional systems lacked a structure to improve compatibility predictions by updating data in real time or training models, they were unable to respond to the continuously changing gel nail market and new product launches. Prior art literature

[0005] Korean Published Patent Application No. 10-2022-0150499 (2022.11.11) The problem to be solved

[0006] The present invention aims to solve the above-mentioned problem by providing a server and a method for operating the same, which inputs procedure request data obtained from a user's external electronic device into an artificial intelligence model to check determined gel combination data step by step, and matches the combinations calculated according to each step to provide them to the user. means of solving the problem

[0007] According to various embodiments, a server for providing procedural compatibility based on a gel combination based on an artificial intelligence model comprises: a communication interface; and a processor; wherein the processor receives at least one procedural request data and at least one gel data from an external electronic device through the communication interface, inputs the at least one procedural request data and the at least one gel data into an artificial intelligence model to determine at least one gel combination compatibility data, and is configured to transmit the at least one gel combination compatibility data to the external electronic device through the communication interface; and the artificial intelligence model is learned based on a plurality of procedural request data and a plurality of gel data, a plurality of gel combination compatibility data, a plurality of gel feature data, a plurality of label data, and a plurality of experiment-based data, a first procedural compatibility result data in which the plurality of gel combination compatibility data does not exceed a preset first compatibility threshold and is determined to be in a highest grade state, and a second procedural compatibility result data in which the plurality of gel combination compatibility data exceeds the first compatibility threshold and is determined to be the next step after the first procedural compatibility result data.

[0008] According to other various embodiments, a method for operating a server to provide procedure compatibility based on a gel combination based on an artificial intelligence model comprises: receiving at least one procedure request data and at least one gel data from an external electronic device through a communication interface; inputting the at least one procedure request data and the at least one gel data into an artificial intelligence model through a processor to determine at least one gel combination compatibility data; and setting the at least one gel combination compatibility data to be transmitted to the external electronic device through the communication interface, wherein the artificial intelligence model is learned based on a plurality of procedure request data and a plurality of gel data, a plurality of gel combination compatibility data, a plurality of gel feature data, a plurality of label data, and a plurality of experiment-based data, a first procedure compatibility result data in which the plurality of gel combination compatibility data does not exceed a preset first compatibility threshold and the plurality of gel combinations are determined to be in a highest grade state, and a second procedure compatibility result data in which the plurality of gel combination compatibility data exceeds the first compatibility threshold and the plurality of gel combinations are determined to be in the next stage after the first procedure compatibility result data. Effects of the invention

[0009] The server according to the present embodiment can check gel compatibility step by step based on gel compatibility data determined by inputting at least one received procedure request data into an artificial intelligence model, and separately performs an indication of incompatibility according to values ​​determined to be incompatible, and by providing this to an external electronic device of the user, it can perform a review of optimal gel compatibility and incompatibility for at least one user in advance, thereby providing the advantage of being able to purchase customized skin gel treatment and cosmetics accordingly for the user. Brief explanation of the drawing

[0010] A brief description of each drawing is provided to help to better understand the drawings cited in the detailed description of the invention. FIG. 1 is a block diagram of a server and network according to an embodiment of the present invention; FIG. 2 is a specific block diagram of a server according to an embodiment of the present invention; FIG. 3 is a detailed block diagram of a sensing module installed in an external electronic device according to an embodiment of the present invention; FIG. 4 is a structural diagram of an artificial intelligence model according to an embodiment of the present invention; FIG. 5 is a first flowchart for a method of server operation according to an embodiment of the present invention; FIG. 6 is a second flowchart for a method of server operation according to an embodiment of the present invention. Specific details for implementing the invention

[0011] Hereinafter, various embodiments of the present invention are described with reference to the accompanying drawings. The present invention is not limited to specific embodiments and should be understood to include various modifications, equivalents, and / or alternatives of the embodiments of the present invention. In connection with the description of the drawings, similar reference numerals may be used for similar components.

[0012] In this document, expressions such as "have," "can have," "include," or "can include" refer to the existence of the relevant feature (e.g., numerical values, functions, actions, or components, etc.) and do not exclude the existence of additional features.

[0013] In this document, expressions such as “A or B,” “at least one of A or / and B,” or “one or more of A or / and B” may include all possible combinations of items listed together. For example, “A or B,” “at least one of A and B,” or “at least one of A or B” may refer to cases including (1) at least one A, (2) at least one B, or (3) both at least one A and at least one B.

[0014] Expressions such as "first," "second," "first," or "second" used in this document may modify various components regardless of order and / or importance, and are used merely to distinguish one component from another without limiting such components. For example, without departing from the scope of rights set forth in this document, the first component may be named the second component, and similarly, the second component may be renamed the first component.

[0015] FIG. 1 is a block diagram of a server and network according to one embodiment of the present invention.

[0016] Referring to FIG. 1, a server (108) can operate an application composed of multiple execution screens or a website composed of multiple web pages, communicates with an electronic device (e.g., the electronic device (101, 102, 104) of FIG. 1) (e.g., smartphone, laptop, etc.) via a network (161), processes requests received from the electronic device (101) regarding the application or web page, and transmits requested information to the electronic device (101). The server (108) can transmit source code to the electronic device (101) that enables each execution screen of the dedicated application or website to be displayed on the electronic device (101), and the electronic device (101) receives the source code and can display an execution screen requested by at least one user of the electronic device (101) through the dedicated application or web browser. According to one embodiment, the components referred to as electronic devices (101) in the present disclosure may mean at least one user account that accesses a platform provided by a server (108) through said electronic device.

[0017] Additionally, the network (161) can communicate with at least one detection module (210) installed externally and can transmit data obtained from at least one precision detection module (210) to the server (108).

[0018] FIG. 2 is a specific block diagram of a server according to one embodiment of the present invention.

[0019] Referring to FIG. 2, a server (108) within a network environment (100) in various embodiments is described. The server (108) may include a bus (110), a processor (120), memory (130), an input / output interface (140), a display (150), a communication interface (160), and a database (170). In some embodiments, the server (108) may omit at least one of the components or additionally include other components. The bus (110) may include a circuit that connects the components (110-170) to each other and transmits communication (e.g., control messages or data) between the components. The processor (120) may include one or more of a central processing unit, an application processor, or a communication processor (CP). The processor (120) may, for example, perform operations or data processing regarding the control and / or communication of at least one other component of the server (108).

[0020] The memory (130) may include volatile and / or non-volatile memory. The memory (130) may store commands or data related to at least one other component of the server (108), for example.

[0021] The input / output interface (140) can, for example, transmit commands or data input from a user or other external device to other component(s) of the server (108), or output commands or data received from other component(s) of the server (108) to the user or other external device.

[0022] The display (150) may include, for example, a liquid crystal display (LCD), a light-emitting diode (LED) display, an organic light-emitting diode (OLED) display, a microelectromagnetic system (MEMS) display, or an electronic paper display. The display (150) may display various content (e.g., text, images, videos, icons, and / or symbols, etc.) to a user. The display (150) may include a touch screen and may receive touch, gesture, proximity, or hovering input using, for example, an electronic pen or a part of the user's body. The communication interface (160) may establish communication between, for example, a server (108) and an external device (e.g., a first external electronic device (102), a second external electronic device (104), or the server (108)). For example, the communication interface (160) can be connected to a network (161) via wireless or wired communication to communicate with an external device (e.g., a second external electronic device (104) or a server (108)).

[0023] Wireless communication may include cellular communication using at least one of, for example, LTE, LTE-A (LTE Advance), CDMA (code division multiple access), WCDMA (wideband CDMA), UMTS (universal mobile telecommunications system), WiBro (Wireless Broadband), or GSM (Global System for Mobile Communications). According to one embodiment, wireless communication may include at least one of, for example, WiFi (wireless fidelity), Bluetooth, Bluetooth Low Energy (BLE), Zigbee, NFC (near field communication), Magnetic Secure Transmission, Radio Frequency (RF), or Body Area Network (BAN). According to one embodiment, wireless communication may include GNSS. GNSS may be, for example, GPS (Global Positioning System), Glonass (Global Navigation Satellite System), Beidou Navigation Satellite System (hereinafter “”) or Galileo, the European global satellite-based navigation system. Hereinafter, in this document, “”) may be used interchangeably with “”). Wired communication may include at least one of, for example, USB (universal serial bus), HDMI (high definition multimedia interface), RS-232 (recommended standard 232), power line communication, or POTS (plain old telephone service).The network (161) may include at least one of a telecommunications network, for example, a computer network (e.g., LAN or WAN), the Internet, or a telephone network.

[0024] The database (170) may be implemented in memory (130) or on a separate storage medium. The database (170) may store all contents, details, etc. of data transmitted and received with user terminals (101, 102, 104) or a server (108). Data stored in the database (170) may be updated regularly according to a predetermined period, or may be updated frequently when new data is input through user terminals (101, 102, 104) or a server (108). According to an embodiment of the present disclosure, various information received from user terminals (101, 102, 104) or received from a server (108) may be stored in the database (170).

[0025] FIG. 3 is a specific block diagram of a sensing module installed in at least one external electronic device according to one embodiment of the present invention.

[0026] Referring to FIG. 3, at least one sensing module (200) connected to at least one external electronic device (101) includes a camera sensor (210), a temperature sensor (220), a biosensor (230), a speed sensor (240), and a position sensor (250). Additionally, at least one sensing module (200) may be configured to detect the user's skin condition and bio information to determine the type, mixing ratio, and application method of the gel combination to be applied to the user.

[0027] The camera detector (210) may be configured to capture the surface condition of the user's skin to acquire image data. Additionally, the camera detector (210) may include a high-resolution image sensor or a multispectral sensor to acquire image data including skin color, moisture distribution, pore size, wrinkles, erythema, pigmentation, and skin surface texture data. Furthermore, the camera detector (210) may acquire additional data regarding moisture distribution or sebum distribution within the skin by utilizing the near-infrared region or polarization imaging as well as the visible light region. The acquired image data may be used to analyze skin characteristics such as the user's skin type, skin sensitivity, oil level, and dryness, and may be used as basic data to determine a gel combination or the mixing ratio of gel ingredients suitable for the user based on this.

[0028] A temperature sensor (220) may be configured to measure temperature data of the user's skin surface. Additionally, the temperature sensor (220) may include an infrared temperature sensor or a contact temperature sensor to detect the skin surface temperature in real time. The measured skin temperature data may be used to estimate the blood flow status of the skin, the potential for an inflammatory response, or the skin irritation status. Additionally, based on the data, the server (108) may be configured to apply a gel combination containing irritation-relieving ingredients to a specific area if the skin temperature of that area is higher than a reference value, and may decide to apply a gel combination with a high proportion of moisturizing or active ingredients if the skin temperature is low or circulation is determined to be reduced.

[0029] The biosensor (230) may include a sensor for measuring the physiological characteristics of the user's skin. Additionally, the biosensor (230) may include a skin moisture sensor, a sebum sensor, an electrical impedance sensor, a heart rate sensor, or a skin conductivity sensor. The skin moisture sensor may be used to determine the degree of skin dryness by measuring the moisture content of the stratum corneum, and the sebum sensor may be used to analyze the oiliness status by measuring the amount of sebum secreted on the skin surface. Additionally, the electrical impedance sensor may estimate skin elasticity or moisture status by measuring the electrical characteristics of the skin tissue. Furthermore, the server (108) may determine the skin stress state or sensitivity by measuring skin conductivity or micro-biosignals based on the electrical impedance sensor.

[0031] FIG. 4 is a structural diagram of an artificial intelligence model according to one embodiment of the present invention.

[0032] An artificial intelligence model according to one embodiment can be driven by an AI neural network model trained through unsupervised learning on basic information, as illustrated in FIG. 4. The artificial intelligence model can be configured to increase the ease of information collection and to provide various information output values. As a structure that outputs image information from text information, the artificial intelligence model may utilize at least one of BigScience’s bloom and T0pp, EleutherAI’s GPT series, Tsinghua UNIV’s GLM series, GOOGLE’s UL and T5 series, and META AI’s OPT series. According to one embodiment, the artificial intelligence model may be implemented using a plurality of Cloud Foundation models, utilizing the structure of Microsoft’s Chat GPT, Google’s BARD series, and NVIDIA’s translation service-based Transformer model. For example, the artificial intelligence model can be trained as a multimodal-based model based on at least one of text information, image information, and audio information to implement various image renderings. In one embodiment, compared to conventional deep learning methods, the amount of labeled training information per task can be reduced, and once established, various training can be performed with a small amount of training information, making information collection and labeling easier and improving accuracy. Additionally, the server (108) can be used as a training process for an artificial intelligence model to output state prediction information by obtaining a result value (output information) using an artificial intelligence model to which arbitrary weights are assigned, comparing the obtained result value with the labeling information of the training information, and performing backpropagation according to the error to optimize the weights. Specifically, training of the artificial intelligence model refers to a process of training the artificial intelligence model based on training information and labeling information or unlabeled information so that the artificial intelligence model can determine output information for input information.That is, the artificial intelligence model forms rules regarding the above information and makes a judgment. According to one embodiment, the server (108) may use multiple learning algorithms among multiple learning algorithms that calculate predicted values. For example, an ensemble method may be used in the artificial intelligence model, and better prediction performance can be obtained compared to using learning algorithms separately. The meaning of training the artificial intelligence model may mean adjusting the weights of the model. According to one embodiment, as a learning method, various methods such as supervised learning, unsupervised learning, reinforcement learning, imitation learning, and federated learning may be used.

[0033] Although not described, the server (108) may include an evaluation step for evaluating the performance of the artificial intelligence model during the learning process of the artificial intelligence model. In the evaluation step, the artificial intelligence model may be evaluated using an evaluation information set. The evaluation of the artificial intelligence model may be a step of evaluating the artificial intelligence model learned by the learning step and making predictions about new information using the artificial intelligence model. Specifically, the evaluation step may be a step of measuring whether the learned artificial intelligence model is capable of generalization about new information.

[0034] Furthermore, the artificial intelligence model is a type of artificial neural network specialized in learning patterns from time-series or sequential information, utilizing a Long Short-Term Memory (LSTM) structure. It is primarily an improved version of the Recurrent Neural Network (RNN). While RNNs predict the future based on past information, they suffer from the Gradient Vanishing problem, which makes learning difficult in long sequences and hinders the processing of long-term dependencies. However, the artificial intelligence model (LSTM) can learn long-term dependencies by introducing a special gate structure to control the flow of information and solve this problem. The artificial intelligence model can operate by selectively remembering and forgetting information using three gates: an Input Gate, a Forget Gate, and an Output Gate. These gates can perform the following actions at each stage. First, the Input Gate determines how much newly input information to accept; the Forget Gate determines how much previously stored information to forget; and the Output Gate determines the amount of information to be passed from the current state to the next. Based on the three gates at the top, the artificial intelligence model learns and adjusts on its own whether past information is needed for current predictions, and learns through learning whether information at the beginning of a sentence is needed at the end of a sentence.Furthermore, the Artificial Intelligence Model (LSTM) is a natural language processing technology utilized in sentence generation, translation, and sentiment analysis. It possesses strengths particularly in machine translation, such as the ability to grasp the context of an entire sentence. It can recognize specific words or phrases by processing speech information in a time series, and it can be used to predict future stock prices by learning past fluctuation patterns. It can also be applied to behavior prediction or scene classification by learning changes between frames over time in videos, and it can be used for long-term predictions, such as the probability of disease onset, by analyzing a user's past medical history and treatment records. Additionally, the LSTM has the advantage of effectively remembering and utilizing long periods of historical information. However, the LSTM is computationally expensive, and training times can become prolonged as the amount of information increases. Consequently, other sequential models, such as the Gated Recurrent Unit (GRU) and Transformer models, have emerged and can be selectively used in various situations to overcome these limitations.

[0036] FIG. 5 is a first flowchart for a method of server operation according to an embodiment of the present invention.

[0038] In operation 501, the server (108) (e.g., processor (120) of FIG. 2) can receive at least one procedure request data from an external electronic device (101, 102, 104) through a communication interface (e.g., communication interface (160) of FIG. 2).

[0039] According to one embodiment, at least one procedure request data may include recommendation data for a recommendation regarding a gel ingredient product requested by at least one user, and personal input data for a customized recommendation for at least one user.

[0040] Specifically, recommendation data can be generated based on skin image data obtained through a camera detector (210), skin temperature data obtained through a temperature detector (220), and skin bio-specificity data obtained through a bio-detector (230). Additionally, recommendation data can be analyzed by a server (108) based on a plurality of skin condition data including skin color data, skin texture data, pore condition data, wrinkle degree data, erythema data, pigmentation data, skin temperature data, skin moisture content data, sebum secretion data, skin conductivity data, and skin impedance data.

[0041] The server (108) can analyze multiple skin condition data to produce user skin type data, skin sensitivity data, skin oil level data, skin dryness data and skin irritation potential data, and can generate recommendation data for at least one gel ingredient product or a combination of multiple gel ingredients based on the produced results.

[0042] In addition, recommendation data may include product data containing specific ingredients, ingredient formulation ratio data, application priority data, application data by skin area, or application frequency data.

[0043] Specifically, personal input data may consist of user-related data received through an input device, which is used by the server (108) to perform user-customized recommendations.

[0044] In addition, personal input data may include user age data, gender data, data related to skin sensitivity, allergy data, data related to existing skin diseases, data related to preferred ingredients, data related to ingredients to avoid, data on the purpose of treatment, skin care goal data, usage frequency data, living environment data, and user preference data.

[0045] In addition, personal input data can be combined with skin condition data obtained through the detection module (200) and analyzed, and can be used as data to more precisely recommend a gel ingredient product or gel combination suitable for the user.

[0046] According to another embodiment, at least one gel data may include product physical property data for at least one gel nail, product ingredient data for at least one gel nail, experimental data for at least one user, user feedback data written directly by at least one user, and worker feedback data written by a worker who performed the procedure on at least one user.

[0047] Additionally, at least one gel data may be obtained from a database (e.g., the database (170) of FIG. 2) and / or memory (e.g., the memory (130) of FIG. 2) or an external server.

[0048] Specifically, product physical property data may include data regarding the physical characteristics of gel nail products.

[0049] In addition, product physical property data may include viscosity data, curing time data, hardness data after curing, elasticity data, adhesion data, durability data, gloss data, color stability data, heat resistance data, moisture resistance data, thickness retention data, and surface smoothness data.

[0050] The server (108) can analyze product physical property data to identify gel nail product data suitable for specific skin condition data or nail condition data, or generate multiple product combination data.

[0051] Specifically, product ingredient data may include data regarding chemical components included in gel nail products.

[0052] In addition, product ingredient data may include base resin data, photoinitiator data, plasticizer data, colorant data, stabilizer data, viscosity modifier data, moisturizing ingredient data, protective ingredient data, and additive data.

[0053] The server (108) can analyze product ingredient data to evaluate compatibility with specific skin sensitivity data or allergy-related data, and can derive suitable gel ingredient combination data through correlation analysis with user skin condition data.

[0054] Specifically, experimental data may include result data obtained after applying a specific gel nail product or gel combination to at least one user.

[0055] In addition, experimental data may include data on skin condition before application, data on changes in skin condition after application, data on maintenance period after application, data on discoloration occurrence, data on peeling occurrence, data on skin irritation response, and data related to user satisfaction.

[0056] Experimental data can be stored in a server (108) in conjunction with skin image data, skin temperature data, and skin biological characteristic data obtained through a sensing module (200), and the server (108) can perform analysis on gel product performance data or gel combination effect data using the data.

[0057] Specifically, user feedback data is evaluation data created directly by the user through an input device, and may include usage experience data regarding gel nail products or gel combinations.

[0058] In addition, user feedback data may include data on ease of use, color satisfaction, durability satisfaction, gloss satisfaction, ease of removal, perceived skin irritation, intention to reuse, and overall satisfaction.

[0059] The server (108) can analyze user feedback data to produce user satisfaction data for specific gel product data or gel combination data, and can use it as weight data in the future recommendation data generation process.

[0060] Specifically, worker feedback data may include evaluation data created by the worker who performed the procedure through an input device.

[0061] In addition, worker feedback data may include data on procedure difficulty, work time, gel application stability, curing process stability, problems that occurred during the work, product compatibility data, and worker satisfaction data.

[0062] The server (108) can analyze worker feedback data to evaluate the applicability data of gel nail products or gel combinations in an actual treatment environment, and can derive more suitable gel product recommendation data or gel combination generation data by combining with user skin condition data.

[0063] In operation 503, the server (108) (e.g., the processor (120) of FIG. 2) can perform preprocessing on at least one procedure request data and at least one gel data received.

[0064] According to one embodiment, the server (108) can generate at least one text vector by performing text preprocessing on at least one user feedback data, at least one worker feedback data, product ingredient data, and experiment data.

[0065] Specifically, the server (108) can collect and store experimental data and feedback data associated with user skin condition data obtained through the detection module (200), and can perform normalization data generation, stop word removal data generation, token separation data generation, and morphological analysis data generation on sentence data or word data included in the data.

[0066] Additionally, the server (108) can produce word frequency data, context relationship data, or semantic similarity data for the token data, and can generate word embedding data or sentence embedding data based on this.

[0067] Additionally, the server (108) can generate multiple-dimensional text vector data corresponding to each data using the generated embedding data.

[0068] Additionally, the server (108) may use text vector data generated as analysis data that is utilized in the process of analyzing the relationship between user skin condition data, gel ingredient data and experiment result data or generating recommendation data.

[0069] According to another embodiment, the server (108) can generate at least one numerical vector by performing numerical preprocessing on gel product physical property data and product ingredient data.

[0070] Specifically, the server (108) can collect physical property data such as viscosity data, curing time data, hardness data after curing, adhesion data, durability data, elasticity data, glossiness data, color stability data, and thickness retention data related to the gel product.

[0071] Additionally, the server (108) can collect component data such as base resin data, photoinitiator data, plasticizer data, pigment data, stabilizer data, and additive data included in the gel product.

[0072] The server (108) can convert physical property data and component data into numeric data through the processes of generating normalized data, generating categorical transformation data, generating scaling data, and generating missing value correction data.

[0073] The server (108) can generate multi-dimensional numerical vector data by organizing value data corresponding to each data item into an array structure.

[0074] Additionally, the server (108) can use the generated numerical vector data to generate correlation analysis data with user skin condition data obtained through the detection module (200), calculate gel combination suitability data, or generate gel product recommendation data.

[0075] According to another embodiment, the server (108) can generate at least one image vector by performing image preprocessing on at least one product physical property data, recommendation data, and personal input data.

[0076] Specifically, the server (108) can generate image representation data based on recommendation data and personal input data associated with user state data, including skin image data, skin temperature data, and skin bio-specificity data obtained through the detection module (200).

[0077] Additionally, the server (108) can convert color data, texture data, gloss data, and surface condition data included in product physical property data or recommendation data into visual representation data, and can map skin type data, preference characteristic data, or purpose of use data included in personal input data into visual feature data.

[0078] Additionally, the server (108) can perform the processes of generating size normalized data, generating noise removal data, generating feature extraction data, and generating channel normalized data for visual representation data.

[0079] Additionally, the server (108) can generate convolution-based feature extraction data or pattern analysis data to produce feature map data corresponding to each image representation data.

[0080] The server (108) can generate multi-dimensional image vector data based on feature map data, and can use the image vector data generated during the process of generating similarity analysis data between user skin condition data and gel product characteristic data, generating gel combination suitability evaluation data, or generating user-customized recommendation data.

[0081] In operation 505, the server (108) (e.g., the processor (120) of FIG. 2) can input at least one procedure request data and at least one gel data that has been preprocessed into an artificial intelligence model.

[0082] According to one embodiment, the server (108) can determine at least one gel combination compatibility data by inputting at least one text data, at least one numerical vector, and at least one image vector into an artificial intelligence model.

[0083] Specifically, the server (108) can convert text representation data, numeric representation data, and image representation data into multidimensional data structures, respectively, and reconstruct them into a form that allows for integrated analysis.

[0084] Additionally, the server (108) can generate multiple-dimensional semantic representation data based on word semantic relationship data and contextual relationship data included in text representation data, and can organize physical property value data and component ratio data included in numeric representation data into array-type numerical structure data.

[0085] Additionally, the server (108) can generate feature map data or pattern feature data based on skin condition data and visual feature data for image representation data.

[0086] Specifically, the server (108) can generate dimension expansion process data for each data representation result. Additionally, the server (108) can expand the data representation space by additionally generating combined data between semantic feature data included in text representation data, interrelationship data between physical property values ​​included in numeric representation data, and combined data between visual feature data included in image representation data.

[0087] Additionally, the server (108) can produce interrelationship data between different data representation results to form an integrated feature data set.

[0088] Additionally, the server (108) can generate relationship data between skin moisture data and gel component data, relationship data between skin temperature data and physical property data, or relationship data between user feedback data and experimental result data, and integrated feature data with expanded dimensions of the data representation space can be generated.

[0089] Specifically, the server (108) can generate dimension reduction process data for dimension-expanded integrated feature data.

[0090] Additionally, the server (108) can extract a set of key feature data based on correlation data between data, variance value data, or importance data.

[0091] The server (108) can generate feature selection data, generate feature combination data, or generate importance-based filtering data, and through this process, can generate a low-dimensional feature data structure in which unnecessary feature data or duplicate data is removed.

[0092] Specifically, the server (108) can perform analysis by inputting the integrated feature data generated through the dimension expansion and dimension reduction processes into the artificial intelligence analysis structure.

[0093] Additionally, the server (108) can comprehensively analyze the suitability data between user skin condition data and gel ingredient data, the stability data between physical property data and user condition data, and satisfaction data based on feedback data, based on integrated feature data.

[0094] Specifically, the server (108) can generate gel combination compatibility data for at least one gel combination based on the analysis results.

[0095] Additionally, the server (108) can calculate compatibility data with user skin condition data, irritation potential data, maintenance period data, and satisfaction gel combination compatibility data for each of the multiple gel component combination data, and can combine the calculated results into a single gel combination compatibility data form.

[0096] Gel combination compatibility data can be generated as result data representing the compatibility level data or suitability level data of a gel combination corresponding to specific user data, and the server (108) can determine the gel combination data or procedure control data to be applied to the user based on the result data.

[0097] In operation 507, the server (108) (e.g., the processor (120) of FIG. 2) can determine at least one gel compatibility data through an artificial intelligence model.

[0098] According to one embodiment, an artificial intelligence model can be trained based on a plurality of procedure request data and a plurality of gel data, a plurality of gel combination compatibility data, a plurality of gel feature data, a plurality of label data, and a plurality of experiment-based data.

[0099] In addition, the artificial intelligence model can be trained based on recommendation data regarding recommendations for gel ingredient products requested by multiple users, and personal input data for personalized recommendations for multiple users.

[0100] In addition, the artificial intelligence model can be trained based on additional product physical property data for multiple gel nails, product ingredient data for multiple gel nails, experimental data for multiple users, user feedback data directly written by multiple users, and worker feedback data written by the worker who performed the procedures on multiple users.

[0101] In addition, since the artificial intelligence model for determining at least one gel combination compatibility data is the same as the artificial intelligence model described in the contents of Fig. 4, a specific explanation thereof may be omitted.

[0102] In operation 509, the server (108) (e.g., the processor (120) of FIG. 2) can transmit at least one gel combination compatibility data to an external electronic device (101, 102, 104) through a communication interface (e.g., the communication interface (160) of FIG. 2).

[0103] According to one embodiment, the server (108) can transmit the generated gel combination compatibility data to an external electronic device (101, 102, 104).

[0104] Additionally, the server (108) can transmit result data including user-customized gel combination recommendation data to an external electronic device (101) corresponding to a user terminal device, control data including gel ingredient mixing ratio data, application order data, and procedure control data to an external electronic device (102) corresponding to a procedure device, and management data including analysis result data, recommendation ranking data, and statistical analysis data to an external electronic device (104) corresponding to a management terminal device.

[0105] Additionally, the server (108) can transmit gel combination compatibility data generated based on user status data and gel-related data obtained through the detection module (200) to external electronic devices (101, 102, 104) through a communication interface (e.g., communication interface (160) of FIG. 2), and the external electronic devices (101, 102, 104) can perform user-customized gel combination recommendations, procedure execution, or management analysis operations based on the received data.

[0107] FIG. 6 is a second flowchart for a method of server operation according to an embodiment of the present invention.

[0109] In operation 601, the server (108) (e.g., processor (120) of FIG. 2) can receive at least one procedure request data and at least one gel data from an external electronic device (101, 102, 104) through a communication interface (e.g., communication interface (160) of FIG. 2).

[0110] According to one embodiment, at least one procedure request data may include recommendation data for a recommendation regarding a gel ingredient product requested by at least one user, and personal input data for a customized recommendation for at least one user.

[0111] Specifically, personal input data may include at least one user's nail shape and health status data, at least one user's skin tone data, at least one user's preferred color / style data, and at least one user's past product usage history data.

[0112] According to another embodiment, at least one gel data may include product physical property data for at least one gel nail, product ingredient data for at least one gel nail, experimental data for at least one user, user feedback data written directly by at least one user, and worker feedback data written by a worker who performed the procedure on at least one user.

[0113] Additionally, at least one gel data may be obtained from a database (e.g., the database (170) of FIG. 2) and / or memory (e.g., the memory (130) of FIG. 2) or an external server.

[0114] Specifically, product physical property data and product component data may include the chemical composition ratio of the gel component, viscosity, curing time, durability, peel-off rate, discoloration potential, technical data provided by the manufacturer, and product-specific layering (base-color-top) combination data.

[0115] Specifically, experimental data may include whether peel-off occurs and the time of occurrence, durability test results, discoloration test results, reaction data according to UV / LED curing conditions, and surface hardness change data.

[0116] Specifically, user feedback data and worker feedback data may include user reviews (text → vectorized after NLP preprocessing), data on duration after treatment, data on whether lifting occurred, satisfaction score data by product combination, nail condition data (dryness / damage / oiliness, etc.), and skin tone data.

[0117] In operation 603, the server (108) (e.g., the processor (120) of FIG. 2) can determine at least one gel combination compatibility data by inputting at least one procedure request data and at least one gel data into an artificial intelligence model.

[0118] According to one embodiment, the server (108) may include a plurality of processing configurations for generating gel combination compatibility data in conjunction with a user terminal.

[0119] Additionally, the server (108) may include a component data storage structure, a name normalization processing structure, a feature generation processing structure, a learning processing structure, an inference processing structure, a rule processing structure, a recommendation generation structure, a result description structure, an experiment record storage structure, and a notification management structure.

[0120] The server (108) performs preprocessing and analysis based on user status data and gel-related data obtained through the detection module, and can determine gel combination compatibility data through this.

[0121] Specifically, the server (108) can receive product name data, ingredient list data, experiment result data and environment variable data from the user terminal.

[0122] Additionally, the server (108) can produce environmental variable data including water contact frequency data, job-related data, curing device data, and curing time data. Additionally, the server (108) can collect user status data including skin image data, skin temperature data, and skin bio-specificity data obtained through the sensing module (200).

[0123] Specifically, the server (108) can generate name normalization processing data for the collected data.

[0124] Additionally, the server (108) can apply standardization rule data to brand data, product name data, and ingredient name data to convert data of different expression methods into the same standard data structure.

[0125] Additionally, the server (108) can generate ingredient identification data, brand identification data, and product identification data to form matching relationship data between ingredient data.

[0126] Specifically, the server (108) can perform feature generation processing for component data.

[0127] Additionally, the server (108) can generate data on the presence of components by layer by correlating the component data included in the base gel data, clear gel data, color gel data, and top gel data with the common component axis data.

[0128] Additionally, the server (108) can generate layer-by-layer component representation data by forming a binary data structure that includes an existence value for each component item.

[0129] Additionally, the server (108) can combine environment variable data and user state data with component representation data to generate integrated feature data.

[0130] Specifically, the server (108) can construct training data using experimental result data stored in an experimental record data storage structure.

[0131] Additionally, the server (108) can collect experimental result data including data at the observation point after the procedure, peel-off rate data, discoloration occurrence data, pinhole occurrence data and crack occurrence data.

[0132] Additionally, the server (108) can generate final compatibility status data based on experimental result data.

[0133] Additionally, the server (108) can generate compatibility status data by combining peel-off ratio data, discoloration data, and damage occurrence data.

[0134] Specifically, the server (108) can generate a training data set based on component representation data, environment variable data, user state data and experiment result data.

[0135] In addition, the server (108) can train a classification analysis structure using a training data set.

[0136] Additionally, the server (108) can improve the analysis accuracy data by performing cross-validation data processing or verification data separation processing.

[0137] Specifically, the server (108) can generate gel combination compatibility data using a learned analysis structure when gel combination data is input.

[0138] Additionally, the server (108) can generate component representation data of base gel data, clear gel data, color gel data, and top gel data included in the input gel combination data, and can form analysis input data by combining the data with user status data and environment variable data.

[0139] Specifically, the server (108) can calculate compatibility probability data for gel combinations using analysis input data. Additionally, the server (108) can generate final gel combination compatibility data by applying probability correction data to the probability data.

[0140] Additionally, the server (108) can classify gel combination compatibility data into one of a plurality of grade data according to the set threshold standard data.

[0141] Specifically, the server (108) can apply rule data such as ingredient prohibition condition data, curing condition data, and allergy-related data using a rule processing structure.

[0142] Additionally, the server (108) can generate warning level data when specific component combination data corresponds to dangerous condition data and can adjust the prediction result data.

[0143] Specifically, the server (108) can generate alternative combination data based on the analysis results.

[0144] Additionally, the server (108) can generate combination data that replaces some of the base gel data, clear gel data, or top gel data while maintaining color data or texture data similar to the input gel combination data.

[0145] Additionally, the server (108) can generate expected compatibility probability data for each alternative combination data.

[0146] The server (108) can organize the generated gel combination compatibility data, alternative combination data, and analysis basis data into result data. The result data can be transmitted to a user terminal or a management terminal, and can display compatibility level data, risk factor data, and component contribution data through visual representation data.

[0147] Additionally, the server (108) may be determined by including data to calculate component-based numerical values, peel-off rates according to auxiliary indicators, discoloration scores, and environmental feature-based numerical values ​​in at least one gel combination compatibility data.

[0148] According to another embodiment, an artificial intelligence model may be learned based on a plurality of procedure request data and a plurality of gel data, a plurality of gel combination compatibility data, a plurality of gel feature data, a plurality of label data, and a plurality of experiment-based data, a first procedure compatibility result data in which a plurality of gel combinations are determined to be in a highest grade state because the plurality of gel combination compatibility data does not exceed a preset first compatibility threshold, and a second procedure compatibility result data in which a plurality of gel combinations are determined to be the next step after the first procedure compatibility result data in which the plurality of gel combination compatibility data exceeds the first compatibility threshold but does not exceed the second compatibility threshold.

[0149] Additionally, the artificial intelligence model may be further trained based on: third procedure compatibility result data in which multiple gel combinations are determined to be the next stage after the second procedure compatibility result data, where multiple gel combinations exceed a second compatibility threshold but do not exceed a third compatibility threshold; fourth procedure compatibility result data in which multiple gel combinations are determined to be in the lowest grade state, where multiple gel combinations do not exceed the second compatibility threshold and the third compatibility threshold; multiple first incompatible gel combination data output as image data for combinations that do not match compatibility with the multiple first procedure compatibility result data; multiple second incompatible gel combination data output as image data for combinations that do not match compatibility with the multiple second procedure compatibility result data; and multiple third incompatible gel combination data output as image data for combinations that do not match compatibility with the multiple third procedure compatibility result data.

[0150] In addition, the artificial intelligence model can be further trained based on multiple first procedure compatibility result data to multiple fourth procedure compatibility result data and multiple first incompatible gel combination data to multiple third incompatible gel combination data.

[0151] In operation 605, the server (108) (e.g., the processor (120) of FIG. 2) can determine whether at least one gel combination compatibility data exceeds a preset first compatibility threshold.

[0152] According to one embodiment, the server (108) can calculate the component-based numerical value included in at least one gel combination compatibility data, the peel-off rate according to an auxiliary indicator, the discoloration score, and the environmental feature-based numerical value data as numerical values, respectively.

[0153] Additionally, the server (108) can calculate a component-based numerical value from 0 to 100, such that the closer it is to 0, the lower the combinatoriality, and the closer it is to 100, the higher the combinatoriality, and can calculate a score based on the following [Equation 1].

[0154] [Mathematical Formula 1]

[0155] SCORE=0.6×(1-|RB|)+0.4×(1 / (1+n))

[0156] Here, SCORE is a component-based value, R represents a value accepted by experts, B represents a value not accepted by experts, and n is a numerical value input for the weights.

[0157] In addition, the server (108) can calculate the peel-off rate according to the auxiliary indicator based on the [Mathematical Formula 2] below, such that the closer it is to 0, the lower the combinability, and the closer it is to 100, the higher the combinability.

[0158] [Mathematical Formula 2]

[0159] P=Bo / Fo*100

[0160] Here, P is the peel-off rate, Bo is the boundary line value, and Fo is the total coating width value.

[0161] Additionally, the server (108) can calculate a discoloration score value from 0 to 100, such that the closer the value is to 0, the lower the color difference value and the lower the compatibility, and the closer the value is to 100, the higher the color difference value and the better the compatibility.

[0162] Additionally, the server (108) can calculate the water contact frequency value, the occupational risk applied to the gel combination, and the curing condition suitability from the environmental feature-based numerical values, respectively, and calculate them as final values.

[0163] Additionally, the server (108) can calculate the water contact frequency value as 0 to 3, such that the closer it is to 0, the higher the contact frequency, and the closer it is to 3, the lower the contact frequency. In terms of occupational risk, the closer it is to 0, the more likely it is an occupational group where damage or wear of the gel occurs frequently, such as cooking or beauty, and the closer it is to 3, the less likely it is an occupational group where damage or wear of the gel occurs, such as office work. In terms of curing condition suitability, the closer it is to 0, the lower the degree of agreement with the recommended condition, and the closer it is to 4, the higher the degree of agreement with the recommended condition.

[0164] Additionally, the server (108) can finally calculate an environment feature-based numeric value from 0 to 10.

[0165] The server (108) can calculate a first compatibility threshold value based on the data of the calculated component-based numerical value, the peel-off rate according to the auxiliary indicator, the discoloration score, and the environment feature-based numerical value.

[0166] In addition, the first compatibility threshold is calculated as a component-based numerical value of 92.2 to 93.4, a peel-off rate value of 87.75 to 91.23, a discoloration score value of 90.11 to 94.1, and an environmental feature-based numerical value of 8 to 9, and can be calculated as a reference value when at least one value is exceeded.

[0167] The server (108) can compare whether at least one gel combination compatibility data is exceeded based on a set first compatibility threshold.

[0168] In operation 607, the server (108) (e.g., the processor (120) of FIG. 2) can determine that at least one gel combination compatibility data does not exceed a first compatibility threshold, and that the gel combination is determined to be in a top-grade state, and that the first procedure compatibility result data.

[0169] According to one embodiment, when the server (108) outputs a component-based numerical value of 93.52 to 94.63, a peel-off rate value of 91.34 to 92.86, a discoloration score value of 94.21 to 95.74, and an environmental feature-based numerical value of 9.08 to 9.86, it can determine that at least one gel combination compatibility prediction data has not exceeded the first compatibility threshold (e.g., component-based numerical value_92.2 to 93.4, peel-off rate value_87.75 to 91.23, discoloration score value_90.11 to 94.1, environmental feature-based numerical value_8.00 to 9.00, at least one exceeding), since the total value has not exceeded the first compatibility threshold, it can determine that at least one gel combination compatibility prediction data has not exceeded the first compatibility threshold and can determine the first procedure compatibility result data in which the gel combination is determined to be in the highest grade state.

[0170] Meanwhile, in operation 605, if the server (108) (e.g., the processor (120) of FIG. 2) determines that at least one gel combination compatibility data exceeds a first compatibility threshold, in operation 609, the server (108) (e.g., the processor (120) of FIG. 2) can determine whether at least one gel combination compatibility data exceeds a second compatibility threshold set to be smaller than the first compatibility threshold.

[0171] According to one embodiment, when the server (108) outputs a component-based numeric value of 93.52 to 94.63, a peel-off rate value of 84.84 to 89.37, a discoloration score value of 94.21 to 95.74, and an environmental feature-based numeric value of 9.08 to 9.86, it can determine that at least one gel combination compatibility prediction data has exceeded the first compatibility threshold (e.g., component-based numeric value_92.2 to 93.4, peel-off rate value_87.75 to 91.23, discoloration score value_90.11 to 94.1, environmental feature-based numeric value_8.00 to 9.00, at least one exceeding) because the peel-off rate value has exceeded the first compatibility threshold, even though the remaining values ​​have not exceeded it.

[0172] The server (108) can calculate a second compatibility threshold that is set smaller than the first compatibility threshold based on the data of the calculated component-based numerical value, the peel-off rate according to the auxiliary indicator, the discoloration score, and the environment feature-based numerical value.

[0173] In addition, the second compatibility threshold is calculated as a component-based numerical value of 78.92 to 81.4, a peel-off rate value of 74.58 to 78.98, a discoloration score value of 77.11 to 83.2, and an environmental feature-based numerical value of 6 to 7, and can be calculated as a reference value when at least one value is exceeded.

[0174] The server (108) can compare whether at least one gel combination compatibility data is exceeded based on a set second compatibility threshold.

[0175] In operation 611, the server (108) (e.g., the processor (120) of FIG. 2) can determine that if at least one gel combination compatibility data exceeds a first compatibility threshold but does not exceed a second compatibility threshold, the gel combination for at least one user is determined to be a second procedure compatibility result data that is the next step after the first procedure compatibility result data.

[0176] According to one embodiment, when the server (108) outputs a component-based numerical value of 84.12–87.84, a peel-off rate value of 80.02–83.73, a discoloration score value of 85.35–88.48, and an environmental feature-based numerical value of 7.87–8.86, the total value exceeds the first compatibility threshold (e.g., component-based numerical value_92.2–93.4, peel-off rate value_87.75–91.23, discoloration score value_90.11–94.1, environmental feature-based numerical value_8–9, exceeding at least one), the total value exceeds the first compatibility threshold, but the total value does not exceed the second compatibility threshold (e.g., component-based numerical value_78.92–81.4, peel-off rate value_74.58–78.98, discoloration score value_77.11–83.2, environmental feature-based numerical value_6–7, exceeding at least one). Since it has not been done, it can be determined that at least one gel combination compatibility prediction data has exceeded the first compatibility threshold but has not exceeded the second compatibility threshold, and the second procedure compatibility result data can be determined that the gel combination for at least one user is the next step after the first procedure compatibility result data.

[0177] In operation 613, the server (108) (e.g., the processor (120) of FIG. 2) may output first incompatible gel combination data as image data for combinations that do not match compatibility based on second procedure compatibility result data.

[0178] According to one embodiment, the server (108) can identify gel combination data that does not meet the set compatibility standard data among the second procedure compatibility result data.

[0179] Specifically, the server (108) can classify the gel combination data as incompatible combination data if the compatibility probability data is lower than a set reference value, or if at least one of the peel-off rate data, discoloration score data, crack occurrence data, or surface defect occurrence data exceeds a reference range.

[0180] Additionally, the server (108) can generate first incompatible gel combination data by identifying base gel data, clear gel data, color gel data, and top gel data included in the incompatible combination data. Additionally, the server (108) can generate visualization data using product identification data, ingredient data, and visual representation data corresponding to each gel product.

[0181] Specifically, the server (108) can generate image representation data based on visualization data. Additionally, the server (108) can diagram the composition relationship data of the gel combination to represent the combination structure of base gel data, clear gel data, color gel data, and top gel data in the form of an image.

[0182] Additionally, the server (108) can be configured to display incompatibility cause data together, and can also include specific component conflict data, curing condition mismatch data, environmental condition influence data, or experimental result-based problem data as visual display data.

[0183] Specifically, the server (108) may apply color data or display symbol data to visually represent incompatible level data.

[0184] Additionally, the server (108) can generate image data including warning data, danger data, or highlighting data for gel combinations with low compatibility.

[0185] Additionally, the server (108) can generate visualization data that highlights the location of the nail area or gel layer based on the problem occurrence location data.

[0186] The server (108) can configure the generated first incompatible gel combination data in the form of image data and can transmit it to an external electronic device (101, 102, 104) in the operation 625 described below. Additionally, the server (108) can transmit the image data to a user terminal device (101, 102, 104) to visually provide the user with incompatible gel combination information, and can transmit the data to a management terminal device (101, 102, 104) to provide the practitioner or manager with the problematic combination data for verification.

[0187] Meanwhile, in operation 609, if the server (108) (e.g., the processor (120) of FIG. 2) determines that at least one gel combination compatibility data exceeds a first compatibility threshold and exceeds a second compatibility threshold, in operation 615, the server (108) (e.g., the processor (120) of FIG. 2) can determine whether at least one gel combination compatibility data exceeds a third compatibility threshold set to be smaller than the second compatibility threshold.

[0188] According to one embodiment, when the server (108) outputs a component-based numeric value of 78.12–81.84, a peel-off rate value of 80.02–83.73, a discoloration score value of 85.35–88.48, and an environmental feature-based numeric value of 6.87–7.44, the total value exceeds the first compatibility threshold (e.g., component-based numeric value_92.2–93.4, peel-off rate value_87.75–91.23, discoloration score value_90.11–94.1, environmental feature-based numeric value_8–9, exceeding at least one) and the total value exceeds the first compatibility threshold, and the component-based numeric value and at the second compatibility threshold (e.g., component-based numeric value_78.92–81.4, peel-off rate value_74.58–78.98, discoloration score value_77.11–83.2, environmental feature-based numeric value_6–7, exceeding at least one) Even though the remaining values ​​were not exceeded because the discoloration score value was exceeded, it can be determined that at least one gel combination compatibility prediction data exceeded the first compatibility threshold and the second compatibility threshold.

[0189] The server (108) can calculate a third compatibility threshold that is set smaller than the second compatibility threshold based on the data of the calculated component-based numerical value, the peel-off rate according to the auxiliary indicator, the discoloration score, and the environment feature-based numerical value.

[0190] In addition, the third compatibility threshold is calculated as a component-based numerical value of 49.92 to 57.4, a peel-off rate value of 46.18 to 50.13, a discoloration score value of 53.11 to 59.2, and an environmental feature-based numerical value of 4 to 5, and can be calculated as a reference value when at least two values ​​are exceeded.

[0191] The server (108) can compare whether at least one gel combination compatibility data is exceeded based on a set third compatibility threshold.

[0192] In operation 617, the server (108) (e.g., the processor (120) of FIG. 2) can determine that if at least one gel combination compatibility data exceeds a second compatibility threshold but does not exceed a third compatibility threshold, the gel combination for at least one user is determined to be a third procedure compatibility result data that is the next step after the second procedure compatibility result data.

[0193] According to one embodiment, when the server (108) calculates that the component-based numerical value is 62.4–66.8, the peel-off rate value is 60.2–64.5, the discoloration score value is 63.7–68.1, and the environmental feature-based numerical value is 5.3–5.8, the total value exceeds the second compatibility threshold (e.g., component-based numerical value_78.92–81.4, peel-off rate value_74.58–78.98, discoloration score value_77.11–83.2, environmental feature-based numerical value_6–7, exceeding at least one), the total value exceeds the second compatibility threshold, but the total value does not exceed the third compatibility threshold (e.g., component-based numerical value_49.92–57.4, peel-off rate value_46.18–50.13, discoloration score value_53.11–59.2, environmental feature-based numerical value_4–5, exceeding at least two), so the third compatibility threshold It can be determined that the value has not been exceeded, and the third procedure compatibility result data can be determined that the gel combination for at least one user is the next step after the second procedure compatibility result data.

[0194] In operation 619, the server (108) (e.g., the processor (120) of FIG. 2) may output second incompatible gel combination data as image data for combinations that do not match compatibility based on third procedure compatibility result data.

[0195] According to one embodiment, the server (108) can derive a combination that includes more incompatible cases than the problem shown in the first incompatible gel combination data. Additionally, unlike the first incompatible gel combination which has only a single component conflict, the second incompatible gel combination may simultaneously include complex problems such as multiple component conflicts, mismatch in curing conditions, potential for discoloration, increased peel-off rate, and potential for cracking.

[0196] Specifically, when the server (108) generates the second incompatible combination data, it may utilize product identification data, ingredient data, and visual representation data corresponding to each gel product (base, clear, color, top).

[0197] Additionally, the server (108) can visually display the causes of incompatibility and can include component conflicts, curing time discrepancies, environmental condition influences, experimental result-based problems, etc., as highlighted data.

[0198] Specifically, the server (108) can generate image data by applying visual indicators such as color codes, warning signs, and risk level icons to the second incompatible gel combination data so that the severity of the problem can be checked at a glance. Additionally, the server (108) can highlight combinations with high severity in red, combinations with medium severity in orange, and so on, and can also visualize the location of the problem by diagramming it by nail position and layer.

[0199] Specifically, the server (108) can configure the second incompatible gel combination data in the form of image data and transmit it to an external electronic device (101, 102, 104) in the operation 625 described below. Additionally, the server (108) can check the incompatible combination in advance before the procedure at the user terminal (101, 102, 104), and can provide the gel combination data with complex problems to the practitioner or administrator at the management terminal device.

[0200] Accordingly, the server (108) can generate and visualize and output second incompatible gel combination data containing more problems than the first incompatible combination based on the third procedure compatibility result data.

[0201] Meanwhile, in operation 615, if the server (108) (e.g., the processor (120) of FIG. 2) determines that at least one gel combination compatibility data exceeds a second compatibility threshold and a third compatibility threshold, in operation 621, the server (108) (e.g., the processor (120) of FIG. 2) may determine a fourth procedure compatibility result data in which the gel combination for at least one user is determined to be at the lowest level.

[0202] According to one embodiment, when the server (108) calculates that the component-based numerical value is 62.4–66.8, the peel-off rate value is 46.2–52.5, the discoloration score value is 52.7–58.1, and the environmental feature-based numerical value is 5.3–5.8, the total value exceeds the second compatibility threshold (e.g., component-based numerical value_78.92–81.4, peel-off rate value_74.58–78.98, discoloration score value_77.11–83.2, environmental feature-based numerical value_6–7, exceeding at least one) and the peel-off rate value and discoloration score value exceed the third compatibility threshold (e.g., component-based numerical value_49.92–57.4, peel-off rate value_46.18–50.13, discoloration score value_53.11–59.2, environmental feature-based numerical value_4–5, exceeding at least two) Since it exceeds, it can be determined that the third compatibility threshold has been exceeded even though the remaining values ​​have not been exceeded, and the fourth procedure compatibility result data can be determined in which the gel combination for at least one user is determined to be the lowest level.

[0203] In operation 623, the server (108) (e.g., the processor (120) of FIG. 2) may output third incompatible gel combination data as image data for combinations that do not match compatibility based on fourth procedure compatibility result data.

[0204] According to one embodiment, the server (108) can derive a combination that includes the most incompatible cases.

[0205] Additionally, the server (108) may include all of the following: a third incompatible gel combination, multi-component conflict, mismatch in curing time and ramp conditions, increased peel-off rate due to environmental influence, discoloration, cracking, reduced adhesion, color change, inter-layer interaction problems, user feedback-based problems, and operator feedback reflection problems, and may be configured as a complex worst combination in which multiple problems occur simultaneously in a single procedure.

[0206] Specifically, when the server (108) generates third incompatible combination data, it may utilize product identification data, ingredient data, and visual representation data corresponding to each gel product (base, clear, color, top).

[0207] Additionally, the server (108) can visually highlight the cause of the problem and can graphically display the location of the conflict of various components, the area of ​​mismatch in curing conditions, the location of discoloration / cracks, the area of ​​weakened adhesion, the area of ​​expected color change, etc., within the image data.

[0208] Specifically, the server (108) can apply visual emphasis, such as color codes, warning signs, and danger level icons, to the third incompatible gel combination data.

[0209] Additionally, the server (108) can display the area with the most problems in red, the area with medium problems in orange, and the area with minor problems in yellow, and can also visualize the problem area by nail position and layer in detail.

[0210] Specifically, the server (108) can transmit the third incompatible gel combination data in the form of image data to an external electronic device (101, 102, 104) in the operation 625 described later, and the worst incompatible combination can be checked in advance at the user terminal before the procedure, and can be provided to the operator or manager to check the complex problem combination data at the management terminal device (101, 102, 104).

[0211] Additionally, the server (108) can generate and visualize and output data for a third incompatible gel combination with the most incompatible form, which includes more problems than the first incompatible combination and the second incompatible combination, based on the fourth procedure compatibility result data.

[0212] In operation 625, the server (108) (e.g., processor (120) of FIG. 2) can transmit at least one gel combination compatibility data to an external electronic device (101, 102, 104) through a communication interface (e.g., communication interface (160) of FIG. 2) based on at least one determined data among the first procedure compatibility result data to the fourth procedure compatibility result data.

[0213] According to one embodiment, the server (108) may be configured to include first procedure compatibility result data, including component-based numerical values, peel-off rate, discoloration score, environmental feature-based numerical values, compatibility probability, and grade information for each gel combination. Additionally, when transmitting the data to an external electronic device (101), the server (108) may package and transmit the data in JSON or XML form, along with a combination ID, user ID, and layer-specific component identifier that can identify each gel combination. Furthermore, the server (108) may utilize this for procedure planning and initial compatibility verification at an external terminal, confirm that it is an optimal customized product for at least one user, and receive and utilize product recommendations based on gel combination compatibility.

[0214] According to another embodiment, the server (108) can identify combinations with some limited compatibility based on second procedure compatibility result data and generate first incompatible gel combination data for said combination in the form of image data.

[0215] Additionally, the server (108) can visually display the generated image data, such as potential problem areas, component conflict locations, and curing time discrepancies, and can transmit it to external electronic devices (101, 102, 104). At least one user can identify some deficiencies based on their external electronic devices (101, 102, 104) and provide this to the practitioner, who can immediately identify incompatible combinations and select alternative combinations.

[0217] According to another embodiment, the server (108) can utilize the third procedure compatibility result data to identify combinations containing multiple compatibility issues and generate second incompatible gel combination data based thereon. Additionally, the server (108) can include the second incompatible gel combination data along with images, text-based problem summaries, risk grades, and the likelihood of peel-off / discoloration / cracking by layer, and can combine the third procedure compatibility result data into one.

[0218] Additionally, the server (108) can transmit to an external electronic device (101, 102, 104), and at least one user can confirm the complex problem combination to a practitioner or manager of a second incompatible gel combination that is more incompatible than the first incompatible gel combination data through their external electronic device (101, 102, 104), confirm that modification is required, and provide it to be reflected in the treatment plan accordingly.

[0219] According to another embodiment, the server (108) can identify the combination containing the most incompatible cases based on the fourth procedure compatibility result data and generate the third incompatible gel combination data in the form of images and visual highlights.

[0220] Additionally, the server (108) can combine the third incompatible gel combination data with the fourth procedure compatibility result data, with all of the multi-component conflict, curing non-uniformity, discoloration, increased peel-off rate, reduced adhesion, color change, and inter-layer interaction problems being displayed.

[0221] Additionally, the server (108) can transmit the data above and at least one gel combination compatibility data to an external electronic device (101, 102, 104), and at least one user can be configured to provide a warning and visual guide to the practitioner and / or expert about the worst combination before the procedure through their external electronic device (101, 102, 104).

[0222] Additionally, the server (108) can input at least one determined gel combination compatibility data, the first procedure compatibility result data to the fourth procedure compatibility result data, and the first incompatible gel combination data to the third incompatible gel combination data into the artificial intelligence model to further reinforce the artificial intelligence model in real time.

[0224] According to another embodiment, the server (108) can perform the function of analyzing compatibility between gel nail products and recommending an optimal product combination as a central processing unit. Additionally, the server (108) can utilize big data and AI technology to independently build and manage a database containing various physical and chemical characteristics of gel nail products by brand, such as ingredient data, viscosity data, curing time data, peel-off occurrence rate data, durability data, and discoloration potential data. Furthermore, the server (108) can integrate user feedback data collected from nail salons and consumers to evaluate and normalize the reliability of the data.

[0225] According to another embodiment, the server (108) can analyze product compatibility data by applying machine learning and deep learning algorithms based on a constructed database (e.g., the database (170) of FIG. 2).

[0226] Additionally, the server (108) can calculate indicators such as component-based numerical data, peel-off rate data, discoloration score data, and environmental feature-based numerical data, and can produce compatibility score data and grade data for each product combination. The server (108) can automatically perform these analysis processes internally and can also produce prediction data for key elements such as peel-off probability data, durability data, and discoloration probability data.

[0227] According to another embodiment, the server (108) can utilize compatibility analysis result data to recommend optimal product combination data and generate visualized image data for combination data where compatibility is limited or incompatible is expected.

[0228] Additionally, the server (108) can automatically integrate and package each compatible and incompatible data, including compatibility result data from the first procedure data to the fourth procedure data, and can transmit it to external electronic devices (101, 102, 104) in various data forms such as image data, numeric data, and text data.

[0229] Additionally, the server (108) can highlight and display problem area data by combination, location data where component conflicts are possible, curing time discrepancy data, area data where discoloration may occur, etc.

[0230] According to another embodiment, the server (108) can update the database in real time even when new product data is released, and can automatically improve the analysis model data through learning user feedback data. In addition, the server (108) can perform all processes including learning an AI-based recommendation algorithm, generating compatibility analysis data, generating incompatibility warning data, recommending and visualizing optimal combination data, and preparing data for external transmission.

[0231] In addition, since all modules and functions can be integrated and operated based on data within the server (108), the entire analysis and recommendation process can be performed in a single server environment.

[0233] The server (108) according to the present embodiment can check gel compatibility step by step based on gel compatibility data determined by inputting at least one treatment request data received into an artificial intelligence model, and separately performs an indication of non-compatibility according to the value determined as non-compatibility, and provides this to the user's external electronic device (101, 102, 104), thereby enabling prior review of optimal gel compatibility and non-compatibility for at least one user, and thus has the advantage of being able to purchase customized skin gel treatment and cosmetics accordingly.

[0235] According to various embodiments, a server for providing procedural compatibility based on a gel combination based on an artificial intelligence model comprises: a communication interface; and a processor; wherein the processor receives at least one procedural request data and at least one gel data from an external electronic device through the communication interface, inputs the at least one procedural request data and the at least one gel data into an artificial intelligence model to determine at least one gel combination compatibility data, and is configured to transmit the at least one gel combination compatibility data to the external electronic device through the communication interface; and the artificial intelligence model is learned based on a plurality of procedural request data and a plurality of gel data, a plurality of gel combination compatibility data, a plurality of gel feature data, a plurality of label data, and a plurality of experiment-based data, a first procedural compatibility result data in which the plurality of gel combination compatibility data does not exceed a preset first compatibility threshold and is determined to be in a highest grade state, and a second procedural compatibility result data in which the plurality of gel combination compatibility data exceeds the first compatibility threshold and is determined to be the next step after the first procedural compatibility result data.

[0236] According to various embodiments, the system further comprises a database and a memory, wherein the at least one treatment request data includes recommendation data for a recommendation regarding a gel ingredient product requested by at least one user and personal input data for a customized recommendation for at least one user, and the at least one gel data includes product physical property data for at least one gel nail, product ingredient data for at least one gel nail, experimental data for at least one user, user feedback data written directly by at least one user, and worker feedback data written by a worker who performed the treatment on at least one user, and is obtained from the database and / or the memory or an external server.

[0237] According to various embodiments, the processor is configured to generate at least one text vector by performing text preprocessing on at least one user feedback data, at least one worker feedback data, the product ingredient data, and the experiment data; generate at least one numerical vector by performing numerical preprocessing on the gel product physical property data and the product ingredient data; generate at least one image vector by performing image preprocessing on at least one product physical property data, the recommendation data, and the personal input data; and input the at least one text data, the at least one numerical vector, and the at least one image vector into the artificial intelligence model to determine at least one gel combination compatibility data.

[0238] According to various embodiments, the processor determines that if it determines that the at least one gel combination compatibility data does not exceed the first compatibility threshold, it determines the first procedure compatibility result data in which the gel combination is determined to be in a highest grade state, and transmits the at least one gel combination compatibility data and the first procedure compatibility result data to the external electronic device through the communication interface, only for the one determined to be the first procedure compatibility result data; if it determines that the at least one gel combination compatibility data exceeds the first compatibility threshold, it determines the second procedure compatibility result data in which the gel combination for the at least one user is determined to be the next step after the first procedure compatibility result data, and outputs the first incompatible gel combination data output as image data for combinations where compatibility is not matched based on the second procedure compatibility result data; and further transmits the at least one gel combination compatibility data, the second procedure compatibility result data, and the first incompatible gel combination data through the communication interface, only for the at least one user determined to be the second procedure compatibility result data.

[0239] According to other various embodiments, a method for operating a server to provide procedure compatibility based on a gel combination based on an artificial intelligence model comprises: receiving at least one procedure request data and at least one gel data from an external electronic device through a communication interface; inputting the at least one procedure request data and the at least one gel data into an artificial intelligence model through a processor to determine at least one gel combination compatibility data; and setting the at least one gel combination compatibility data to be transmitted to the external electronic device through the communication interface, wherein the artificial intelligence model is learned based on a plurality of procedure request data and a plurality of gel data, a plurality of gel combination compatibility data, a plurality of gel feature data, a plurality of label data, and a plurality of experiment-based data, a first procedure compatibility result data in which the plurality of gel combination compatibility data does not exceed a preset first compatibility threshold and the plurality of gel combinations are determined to be in a highest grade state, and a second procedure compatibility result data in which the plurality of gel combination compatibility data exceeds the first compatibility threshold and the plurality of gel combinations are determined to be in the next stage after the first procedure compatibility result data.

[0241] As used in this document, the expression "configured to" may be replaced, depending on the context, with, for example, "suitable for," "having the capacity to," "designed to," "adapted to," "made to," or "capable of." The term "configured to" does not necessarily mean "specifically designed to."

[0242] In this document, terms transmitted or received between the first electronic device(s) and the second electronic device(s), such as “command,” “instruction,” “control information,” “message,” “information,” “data,” “packet,” “data packet,” “intent,” and / or “signal,” may include or refer to humanly perceptible ideas or specific electrical representations (e.g., digital codes / analog physical quantities) without being limited by their expression. It will be obvious to a person skilled in the art to which the invention disclosed in this document pertains that the exemplary expressions listed above may be interpreted in various ways depending on the context in which they are used. In this document, “a is greater than B” means not only that “a is greater than B” but also includes the meaning that “a is equal to or greater than B”.

[0243] The terms used in this document are used merely to describe specific embodiments and are not intended to limit the scope of other embodiments. Singular expressions may include plural expressions unless the context clearly indicates otherwise. Terms used herein, including technical or scientific terms, may have the same meaning as generally understood by those skilled in the art described in this document. Terms used in this document that are defined in general dictionaries may be interpreted as having the same or similar meaning as they have in the context of the relevant technology, and are not to be interpreted in an ideal or overly formal sense unless explicitly defined in this document. In some cases, even terms defined in this document may not be interpreted to exclude the embodiments of this document.

[0244] Although all components constituting an embodiment of the present invention have been described above as being combined or operating in combination, the present invention is not necessarily limited to such embodiments. That is, within the scope of the purpose of the present invention, all components may be selectively combined in one or more ways to operate.

[0245] Meanwhile, the various embodiments described herein may be implemented by hardware, middleware, microcode, software and / or combinations thereof. For example, the various embodiments may be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, other electronic units designed to perform the functions presented herein, or combinations thereof.

[0246] Additionally, for example, various embodiments may be stored or encoded on a computer-readable medium containing instructions. Instructions stored or encoded on a computer-readable medium may enable a programmable processor or other processor to perform a method, for example, when the instructions are executed. A computer-readable medium includes a computer storage medium, and the computer storage medium may be any available medium accessible by a computer. For example, such a computer-readable medium may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage media, magnetic disk storage media or other magnetic storage devices.

[0247] Such hardware, software, firmware, etc., may be implemented within the same device or in individual devices to support the various operations and functions described in this specification. Additionally, components, units, modules, components, etc., described as "parts" in this invention may be implemented together or individually as separate but interoperable logic devices. Descriptions of different features of modules, units, etc., are intended to highlight different functional embodiments and do not necessarily imply that they must be realized by individual hardware or software components. Rather, functions associated with one or more modules or units may be performed by individual hardware or software components or integrated within common or individual hardware or software components.

[0248] Although operations are depicted in a specific order in the drawings, it should not be understood that these operations must be performed in the specific order depicted or in a sequential order to achieve the desired result, or that all depicted operations must be performed. In any environment, multitasking and parallel processing may be advantageous. Furthermore, the distinction of various components in the above-described embodiments should not be understood as requiring such distinction in all embodiments, and it should be understood that the described components may generally be integrated together into a single software product or packaged into multiple software products.

[0249] The electronic device, server, or external device according to the various embodiments of the present document described above may include, for example, at least one of a smartphone, tablet PC, mobile phone, video phone, desktop PC, laptop PC, PDA (personal digital assistant), PMP (portable multimedia player), MP3 player, mobile medical device, camera, or wearable device.

[0250] According to various embodiments, the wearable device may include at least one of an accessory type (e.g., a watch, ring, bracelet, anklet, necklace, glasses, contact lens, or head-mounted device (HMD)), a fabric or clothing integrated type (e.g., electronic clothing), a body-attached type (e.g., a skin pad or tattoo), or a bio-implantable type (e.g., an implantable circuit).

[0251] In some embodiments, the electronic device or external device may be a home appliance. The home appliance may include, for example, at least one of a television, a DVD player (Digital Video Disk player), audio, a refrigerator, an air conditioner, a vacuum cleaner, an oven, a microwave oven, a washing machine, an air purifier, a set-top box, a home automation control panel, a security control panel, a TV box, a game console, an electronic dictionary, an electronic key, a camcorder, or a digital photo frame.

[0252] In another embodiment, the electronic device, external device, and wearable device may include at least one of various medical devices (e.g., various portable medical measuring devices (blood glucose meter, heart rate monitor, blood pressure monitor, or body temperature monitor, etc.), MRA (magnetic resonance angiography), MRI (magnetic resonance imaging), CT (computed tomography), imaging device, or ultrasound device, etc.), navigation device, satellite navigation system (GNSS (Global Navigation Satellite System)), EDR (event data recorder), FDR (flight data recorder), automotive infotainment device, home robot, or Internet of Things device (e.g., light bulb, various sensor, electric or gas meter, sprinkler device, fire alarm, thermostat, street light, exercise equipment, hot water tank, heater, boiler, etc.).

[0254] As described above, the best embodiments have been disclosed in the drawings and specification. Specific terms have been used herein, but they are used only for the purpose of describing the invention and are not intended to limit the meaning or the scope of the invention as described in the claims. Therefore, those skilled in the art will understand that various modifications and equivalent alternative embodiments are possible therefrom. Accordingly, the true technical scope of protection of the invention should be determined by the technical spirit of the appended claims.

Claims

Claim 1 A server for providing procedural compatibility according to a gel combination based on an artificial intelligence model, comprising: a communication interface; and a processor; wherein the processor receives at least one procedure request data and at least one gel data from an external electronic device through the communication interface, inputs the at least one procedure request data and the at least one gel data into an artificial intelligence model to determine at least one gel combination compatibility data, and is configured to transmit the at least one gel combination compatibility data to the external electronic device through the communication interface; and wherein the artificial intelligence model is learned based on a plurality of procedure request data and a plurality of gel data, a plurality of gel combination compatibility data, a plurality of gel feature data, a plurality of label data, and a plurality of experiment-based data, a first procedure compatibility result data in which the plurality of gel combination compatibility data does not exceed a preset first compatibility threshold and is determined to be in a highest grade state, and a second procedure compatibility result data in which the plurality of gel combination compatibility data exceeds the first compatibility threshold and is determined to be the next stage after the first procedure compatibility result data. Claim 2 A server for providing treatment compatibility according to a gel combination based on an artificial intelligence model, wherein, in claim 1, the database and / or memory are further included; wherein the at least one treatment request data includes recommendation data for a recommendation regarding a gel ingredient product requested by at least one user, and personal input data for a customized recommendation of the at least one user, and the at least one gel data includes product physical property data for at least one gel nail, product ingredient data for at least one gel nail, experimental data for the at least one user, user feedback data written directly by the at least one user, and worker feedback data written by a worker who performed the treatment of the at least one user, and is obtained from the database and / or memory, or an external server. Claim 3 A server for providing procedure compatibility according to a gel combination based on an artificial intelligence model, wherein the processor performs text preprocessing on the at least one user feedback data, the at least one worker feedback data, the product ingredient data, and the experimental data to generate at least one text vector; performs numerical preprocessing on the product physical property data and the product ingredient data to generate at least one numerical vector; performs image preprocessing on the at least one product physical property data, the recommendation data, and the personal input data to generate at least one image vector; and inputs the at least one text data, the at least one numerical vector, and the at least one image vector into the artificial intelligence model to determine the at least one gel combination compatibility data. Claim 4 In claim 1, the processor determines the first procedure compatibility result data in which the gel combination is determined to be in a highest grade state when it is determined that the at least one gel combination compatibility data does not exceed the first compatibility threshold; transmits the at least one gel combination compatibility data and the first procedure compatibility result data to the external electronic device through the communication interface, limited to the one determined to be the first procedure compatibility result data; determines the second procedure compatibility result data in which the gel combination for the at least one user is determined to be the next step after the first procedure compatibility result data when it is determined that the at least one gel combination compatibility data exceeds the first compatibility threshold; outputs the first incompatible gel combination data output as image data for combinations where compatibility is not matched based on the second procedure compatibility result data; and is configured to additionally transmit the at least one gel combination compatibility data, the second procedure compatibility result data, and the first incompatible gel combination data through the communication interface, limited to the at least one user determined to be the second procedure compatibility result data. Server for. Claim 5 A method for operating a server to provide procedural compatibility based on a gel combination based on an artificial intelligence model, the method comprises: receiving at least one procedural request data and at least one gel data from an external electronic device through a communication interface; inputting the at least one procedural request data and the at least one gel data into an artificial intelligence model through a processor to determine at least one gel combination compatibility data; and setting the at least one gel combination compatibility data to be transmitted to the external electronic device through the communication interface, wherein the artificial intelligence model is learned based on a plurality of procedural request data and a plurality of gel data, a plurality of gel combination compatibility data, a plurality of gel feature data, a plurality of label data, and a plurality of experimental-based data, a first procedural compatibility result data in which the plurality of gel combination compatibility data does not exceed a preset first compatibility threshold and the plurality of gel combinations are determined to be in a highest grade state, and a second procedural compatibility result data in which the plurality of gel combination compatibility data exceeds the first compatibility threshold and the plurality of gel combinations are determined to be in the next stage after the first procedural compatibility result data.

Images