KR102614905B1 - System of style commerce platform - Google Patents

Abstract

We receive, store and manage platform entry information from brands, match influencers and brands, provide a styling coaching subscription service that allows users to receive styling coaching from influencers, and charge fees for the styling coaching subscription service. Discloses a style commerce platform system that includes a platform server that processes.

Description

Style Commerce Platform System{SYSTEM OF STYLE COMMERCE PLATFORM}

The present invention relates to a platform system that provides not only clothing but also a styling coaching subscription service through matching new domestic designer brands and micro-influencers.

Fashion is explained and understood below as including clothing, shoes, bags, hats, scarves, gloves, socks, wallets, belts, glasses, watches, jewelry, accessories, underwear, etc., and clothing and clothing have the same meaning. It is written selectively so that the context flows relatively smoothly and is appropriate for explanation and easy to understand.

The clothing (apparel, clothing) industry, which is the most basic and important part of fashion, forms a large market, ranking second in sales in the global consumer goods industry.

Recently, with the development of multimedia and IT technology using smartphones, user interest in clothing coordination styles (styling) using new technologies is increasing significantly.

Due to the development of the Internet, TV, SNS, computers, and communication technology, it is possible to quickly and easily access the trends of celebrities and influencers, including celebrities, sports figures, and politicians, and communicate directly or indirectly (doctors, etc.) As this has become possible, interest in the fashion of celebrities or influencers is increasing, and the popularity of imitating the styling fashion of celebrities or influencers is increasing significantly.

In general, whenever you go out, a lot of time and effort is spent on styling yourself with a popular but slightly unique fashion, and even when purchasing clothes (fashion) on a regular basis, if you do not consider the styling associated with the provided clothes, you may end up making impulsive purchases. This can result in financial waste and unused clothing that is thrown away because it is difficult to style.

Many websites or companies (sites) that provide coordination services and products related to clothing styling or sell or provide clothing-related products, goods, and services are being introduced online and offline, but the preferred fashion styling, especially celebrity styling, is popular. There is a problem that there is no site that provides reliable, accurate, and detailed information about each fashion in a non-contact manner.

A prior art that partially solves these problems is 'Clothing coordination system and method' issued by Republic of Korea Patent Registration No. 10-1725960 (April 5, 2017).

1 is a functional block diagram illustrating a platform system that provides a fashion styling service according to an embodiment of the prior art.

Hereinafter, the prior art will be described in detail with reference to the attached drawings. The input unit 11 inputs information on the type of clothing that is the standard for fashion styling, and the camera 17 acquires an image of the clothing that is the standard for fashion styling. , the color matching unit 13 extracts color information from the image data of the costume acquired by the camera 17, then searches the color database 19 to check color information that matches the extracted color information, and creates a costume proposal unit ( 15) Delivered to. The costume suggestion unit 15 searches the costume database 21, selects a costume corresponding to the searched color among the costumes owned by the user, and proposes it to the user as a coordination award.

The prior art has the advantage of analyzing colors based on the preferred outfit selected by the user, searching for outfits of matching colors from the outfits (fashion) owned by the user, and suggesting them as coordinated outfits (fashion).

However, the prior art simply searches for and suggests or provides only color-matched clothing, so the provided styling fashion may not be a popular styling, and even in the case of a trendy styling, it may not be the user's preferred styling fashion. still remains.

One aspect of the present invention discloses a system that provides a styling coaching subscription platform through matching new domestic designer brands and influencers.

Another aspect of the present invention discloses a system that provides a user-customized styling coaching recommendation service based on an artificial neural network.

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

The system of the present invention receives, stores and manages platform entry information from brands, matches influencers and brands, provides a styling coaching subscription service that allows users to receive styling coaching from influencers, and provides the styling coaching. Includes a platform server that processes costs for subscription services.

Meanwhile, the platform server receives and stores platform entry information from the brand, calculates a brand score using influencers' evaluation scores for the store entry information, and provides product sales, settlement, and statistics management pages for the platform brand. A store management department that provides new designer brands; Viral content information including a plurality of domestic and foreign promotional means is provided to brands located on the platform, and promotional means are extracted and provided according to the brand score among the plurality of promotional means included in the viral content information, and influencers and the platform are provided. Influencer viral content management department that matches stores with brands; A styling coaching subscription management department that provides a styling coaching subscription service that allows people to receive styling coaching from influencers; and a sales management unit that calculates the cost of the styling coaching subscription service and allows the cost of the styling coaching subscription service to be paid through a subscriber terminal.

Meanwhile, the new designer brand store entry management department receives and stores store entry information including sales product information, payment information, brand information, and target customer information, and receives brand entry information from a plurality of influencers through the influencer terminal. A score of 1 to 10 is input for each item, and the sales product information score (P _p ) is calculated according to the average of the evaluation scores of multiple influencers on the sales product information among the store entry information. , Calculate the payment information score (P _c ) according to the average of the evaluation scores of a plurality of influencers on the payment information among the store entry information, and calculate the payment information score (P c ) according to the average of the evaluation scores of a plurality of influencers on the brand information among the store entry information. Calculate the brand information score (P _b ), calculate the target customer information score (P _g ) according to the average of the evaluation scores of multiple influencers on the target customer information among the store entry information, and calculate the sales information in Equation 1 below. Calculating a brand score (P brand) by applying the product information score (P _p ), the payment information score (P _c ), the brand information score (P _b ), and _the target customer information score (P _g ),

The styling coaching subscription management unit receives subscription application information including the influencer name, SNS type, brand name, and Seongho style hashtag through the subscriber terminal, generates the subscription application information as input data, and provides styling coaching. The input data may be input into an artificial neural network trained to recommend an influencer to provide, output data may be obtained from the artificial neural network, and the output data may be calculated as an influencer to provide styling coaching.

[Equation 1]

According to one aspect of the present invention described above, marketing effectiveness can be increased by matching new designer brands with influencers, and further, by providing a subscription service for styling coaching by influencers, the brand promotion effect can be increased, and new profits can be achieved. A model can be created.

1 is a functional block diagram illustrating a platform system that provides a fashion styling service according to an embodiment of the prior art.
Figure 2 is a conceptual diagram of a style commerce platform system according to an embodiment of the present invention.
FIG. 3 is a conceptual diagram of the platform server shown in FIG. 1.

The advantages and features of the present invention and methods for achieving them will become clear by referring to the embodiments described in detail below along with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below and will be implemented in various different forms. The present embodiments only serve to ensure that the disclosure of the present invention is complete and that common knowledge in the technical field to which the present invention pertains is not limited. It is provided to fully inform those who have the scope of the invention, and the present invention is only defined by the scope of the claims. Like reference numerals refer to like elements throughout the specification.

The terminology used herein is for describing embodiments and is not intended to limit the invention. As used herein, singular forms also include plural forms, unless specifically stated otherwise in the context. As used in the specification, “comprises” and/or “comprising” does not exclude the presence or addition of one or more other components, steps and operations.

Figure 2 is a conceptual diagram of a style commerce platform system according to an embodiment of the present invention.

Referring to FIG. 2, the style commerce platform system 1 according to an embodiment of the present invention may include a platform server 100, an influencer terminal 200, and a subscriber terminal 300.

The platform server 100 may be its own server, a cloud server, or a p2p (peer-to-peer) set of distributed nodes for providing the style commerce platform service according to the present invention.

The platform server 100 may perform one or more of the calculation, storage, reference, input/output, and control functions of a general computer, and may include an artificial neural network to be described later based on input data.

Platform server 100 may include a processor and memory. The processor may provide the style commerce platform service according to the present invention, and may include devices capable of providing the style commerce platform service. The processor may execute a program or control the platform server 100. Program code executed by the processor may be stored in memory. The memory may store related information for performing the style commerce platform according to the present invention or a program for implementing a method. The memory may be volatile memory or non-volatile memory.

The platform server 100 can send data to or receive data from an external device using a network.

The platform server 100 can train an artificial neural network, and can also use a trained artificial neural network. The processor can train or execute an artificial neural network stored in memory, and the memory can store a trained artificial neural network. The electronic device that trains the artificial neural network and the electronic device that uses it may be the same, but may also be separate.

The platform server 100 may provide a service for matching an influencer who will perform styling coaching when receiving styling coaching request information from the subscriber terminal 300 so that the styling coaching subscription service according to the present invention can be provided.

Artificial intelligence is a computer system that implements some of the functions of the human brain and can learn, guess, and make decisions on its own. As learning progresses, the probability of extracting an answer may increase. Artificial intelligence can be composed of learning and elemental technologies using it. Artificial intelligence learning is an algorithmic technology that classifies and learns features based on input data, and elemental technologies may be technologies that implement some of the functions of the human brain using learning algorithms.

Artificial intelligence is a technology that makes it easy to approach problems that can have multiple answers probabilistically, and can logically and probabilistically infer the optimal cycle, method, and plan according to any input data. Artificial intelligence's inference technology can include judging input data, optimization predictions, knowledge and probability-based reasoning, and preference-based planning.

Artificial neural network is one of the learning algorithms in the machine learning field and is a program that implements the connection between neurons and synapses in the brain. Artificial neural networks can be created through a program to create a neural network structure and then learn it to have the desired function. Although there may be errors, it is possible to learn based on huge data and output appropriate output data with input data. It has the advantage of being able to obtain output data with statistically good results and being similar to human reasoning.

The platform server 100 can output influencers based on artificial intelligence, and may include a number of artificial neural networks trained in advance for this purpose.

The influencer terminal 200 and the subscriber terminal 300 may include any terminal capable of exchanging data over a network, such as a desktop computer, laptop, tablet, or smartphone.

The influencer terminal 200 and the subscriber terminal 300 may include any one or more of the calculation function, storage function, reference function, input/output function, and control function of a computer in order to perform the style commerce platform according to the present invention. there is.

The influencer terminal 200 and the subscriber terminal 300 can access a website or install an application to receive the style commerce platform according to the present invention. The influencer terminal 200 and the subscriber terminal 300 can exchange data through a website or application.

Network refers to a network that transmits data by TCP/IP.

FIG. 3 is a conceptual diagram of the platform server shown in FIG. 1.

Referring to Figure 3, the platform server 100 according to an embodiment of the present invention includes a new designer brand store management unit 110, an influencer viral content management unit 120, a styling coaching subscription management unit 130, and a sales management unit ( 140) may be included.

The new designer brand store entry management unit 110 may receive and store store entry information from the brand to enter the platform according to the present invention.

For example, store entry information includes sold product information including images of sold products, product categories, prices, etc., payment information including payment methods, brand history, brand ideology, brand designer, etc. It may contain target customer information, including information, target customer age, target customer description, target customer style keywords, etc.

The new designer brand store entry management unit 110 can receive an evaluation score from the influencer terminal 200 regarding store entry information, and can use the evaluation score to calculate a brand score.

For example, the new designer brand store entry management unit 110 receives a score of 1 to 10 for each item of brand store entry information from a plurality of influencers through the influencer terminal 200. You can.

The new designer brand store management department 110 can calculate the sales product information score (P _p ) by averaging the evaluation scores of a plurality of influencers on the sales product information among the store entry information, and the sales product information score (P _p ). If is 5 points or more, P p = 1, and if the sales product information score (P _p ) is less than 5 points, P _p can be set to 0.

The new designer brand store management department 110 can calculate the payment information score (P _c ) by averaging the evaluation scores of a plurality of influencers on payment information among the store entry information, and the payment information score (P _c ) is 5 points. If the score is above 5, P _c = 1, and if the payment information score (P _c ) is less than 5, it can be set to P _c = 0.

The new designer brand store management department 110 can calculate the brand information score (P _b ) by averaging the evaluation scores of a plurality of influencers on the brand information among the store entry information, and the brand information score (P _b ) is 5 points. If the brand information score (P _{b )} is less than 5 points, P b = 1, and if the brand information score (P _b ) is less than 5 points, it can be set to P _b = 0.

The new designer brand store management department 110 can calculate the target customer information score (Pg) by averaging the evaluation scores of a plurality of influencers on target customer information among the store entry information, and the target customer information score (P _g ) is If it is 5 points or more, P _g = 1, and if the target customer information score (P _g ) is less than 5 points, it can be set to P _g = 0.

[Equation 1]

According to Equation 1, a brand score can be calculated by reflecting each element of store entry information but increasing the proportion of sales product information among store entry information. The brand score can be calculated from 0 to 3 points, and the brand score can be calculated from 0 to 3 points. The higher the score, the higher the influencer can be considered to have evaluated the value of the brand. At this time, the brand score places more emphasis on sales products among the various elements of a new designer brand, so that even if the awareness of the new designer brand is low, it can obtain a high score based on marketability alone.

The new designer brand store entry management department 110 can provide services such as product sales, settlement, and statistics management by providing a product sales, settlement, and statistics management page to the brand based on store entry information.

The influencer viral content management unit 120 can provide viral content information to brands located on the platform according to the present invention. For example, viral content information may include multiple domestic and international promotional means such as K-Fashion Audition, Korea Fashion Competition, and overseas collections.

The influencer viral content management unit 120 may recommend the type of viral content information according to the brand score. In other words, the influencer viral content management unit 120 can recommend a promotional method that can maximize the promotional effect of the brand according to the brand score among a plurality of domestic and foreign promotional methods included in the viral content information. To this end, the influencer viral content management unit 120 can monitor changes in the brand score of a given brand and the domestic and foreign promotional means used, and extract domestic and foreign promotional means with high promotional effectiveness for each brand score.

For example, the influencer viral content management unit 120 can output viral content information according to the brand score using an artificial neural network.

The influencer viral content management unit 120 generates a brand score of 0 to 3 points and a promotional means matched to each brand score as input data, and inputs the input data into an artificial neural network learned to recommend viral content information. You can.

The influencer viral content management unit 120 may obtain output data from an artificial neural network and calculate the output data as customized viral content information.

In this embodiment, the influencer viral content management unit 120 may include a plurality of artificial neural networks that have been trained in advance to perform a machine learning algorithm. With machine learning, you can output output data based on input data and use the results to learn on your own, which can improve your own data processing ability. Artificial neural networks can extract features based on input data, infer regularities, and output result data. As this process accumulates, the reliability of the result data increases.

In this embodiment, the artificial neural network may be an algorithm that selects customized domestic and overseas promotional means according to the brand score. Artificial neural networks can infer the best output data by using the brand score as input data as is or after going through a processing process to clean up unnecessary data.

Depending on the type of learning, artificial intelligence machine learning models include Super Viser Learning, UnSuper Viser Learning, Semisupervised Learning, and Reinforcement Learning. And machine learning algorithms include Decision Tree, K-Nearest Nearest Bor, Artificial Neural Network, Support Vector Machine, Ensemble Learning, Gradient Descent, Na*?*ve Bayes Classifier, Hidden Markov Model, K-Means Clustering, etc. can be used.

Artificial neural networks can stack and connect numerous artificial neurons in several layers. The input data of the artificial neural network may include design budget, site specifications, numerical values representing each site environmental element, number of family members, and number of rooms. The artificial neural network may be pre-trained on various input values that may be included in the input data. The artificial neural network can output output data by inferring the plane type according to the design requirement information input by the user.

An artificial neural network may be an artificial neural network that is learned according to reinforcement learning, one of the learning methods. Reinforcement learning is a method of gradually increasing the probability of obtaining the correct result by setting rewards and limits. For example, compared to conventional design data by the automatic design system according to this embodiment, maintenance can be made if an appropriate plan type is output, and restrictions can be assigned if the plan type is not appropriate, thereby allowing gradual optimization.

Artificial neural networks can also be modeled based on Convelutional Neural Network (CNN) or Recurrent Neural Network (RNN).

The influencer viral content management unit 120 can match influencers and new designer brands.

For example, the influencer viral content management unit 120 can calculate the influencer score using Equation 2 below.

[Equation 2]

In Equation 2, view _normal means the average number of views on the influencer's SNS during a certain period when viral content was not launched, and view _contents refers to the number of views on the influencer's SNS during the period when viral content containing a certain keyword was launched. means average.

According to Equation 2, if the average number of SNS views during the period of launching viral content exceeds twice the average number of views on SNS when viral content was not launched, P _i = 1 is calculated, and vice versa, P _i = It can be calculated as 0.

The influencer viral content management unit 120 can receive at least one keyword of viral content from the brand to be opened, and can calculate the influencer score by applying the keyword input from the brand to each influencer.

In other words, the influencer viral content management unit 120 uses Equation 2 to determine if the average number of SNS views when launching a keyword of viral content designated by a brand among a plurality of influencers exceeds twice the average number of SNS views in normal times. Influencers can be detected and brands can be matched with the influencer. For example, the influencer viral content management unit 120 applies keywords input from a certain brand to Equation 2, and matches the influencer whose influencer score is calculated as 1 through Equation 2 with the corresponding brand. can do.

In this way, the influencer viral content management unit 120 improves the promotional effect by matching influencers with good responses to keywords to be promoted for each brand.

The styling coaching subscription management unit 130 may provide a styling coaching subscription service that allows users to receive styling coaching from influencers.

The styling coaching subscription management unit 130 may receive subscription application information from the subscriber terminal 300. Subscription application information may include influencer name, SNS type, brand name, preferred style hashtag, etc.

The styling coaching subscription management unit 130 may use an artificial neural network to output influencers who will provide styling coaching according to subscription application information.

The styling coaching subscription management unit 130 may generate subscription application information as input data and input the input data into an artificial neural network trained to recommend influencers to provide styling coaching.

The styling coaching subscription management unit 130 may obtain output data from an artificial neural network and calculate the output data as an influencer to provide styling coaching.

In this embodiment, the styling coaching subscription management unit 130 may include a plurality of artificial neural networks that have been trained in advance to perform a machine learning algorithm. With machine learning, you can output output data based on input data and use the results to learn on your own, which can improve your own data processing ability. Artificial neural networks can extract features based on input data, infer regularities, and output result data. As this process accumulates, the reliability of the result data increases.

In this embodiment, the artificial neural network may be an algorithm that selects a customized influencer according to subscription application information. Artificial neural networks can infer the best output data by using subscription application information as input data as is, or by using it as input data after going through a processing process to organize unnecessary data.

ve Bayes Classifier, Hidden Markov Model, K-Means Clustering 등이 사용될 수 있다.Depending on the type of learning, artificial intelligence machine learning models include Super Viser Learning, UnSuper Viser Learning, Semisupervised Learning, and Reinforcement Learning. And machine learning algorithms include Decision Tree, K-Nearest Nearest Bor, Artificial Neural Network, Support Vector Machine, Ensemble Learning, Gradient Descent, Na

ve Bayes Classifier, Hidden Markov Model, K-Means Clustering, etc. can be used.

Artificial neural networks can stack and connect numerous artificial neurons in several layers. The input data of the artificial neural network may include design budget, site specifications, numerical values representing each site environmental element, number of family members, and number of rooms. The artificial neural network may be pre-trained on various input values that may be included in the input data. The artificial neural network can output output data by inferring the plane type according to the design requirement information input by the user.

An artificial neural network may be an artificial neural network that is learned according to reinforcement learning, one of the learning methods. Reinforcement learning is a method of gradually increasing the probability of obtaining the correct result by setting rewards and limits. For example, compared to conventional design data by the automatic design system according to this embodiment, maintenance can be made if an appropriate plan type is output, and restrictions can be assigned if the plan type is not appropriate, thereby allowing gradual optimization.

Artificial neural networks can also be modeled based on Convelutional Neural Network (CNN) or Recurrent Neural Network (RNN).

The sales management department 120 calculates the cost of the styling coaching subscription service, allows the cost of the styling coaching subscription service to be paid through the subscriber terminal 300, and allows the cost to be paid to the influencer. .

For example, the sales management department 120 can calculate the score for the styling coaching subscription service using Equation 3 below.

[Equation 3]

In Equation 3, i is the period of receiving the subscription service, f _average is the average number of SNS followers of the subscriber, and f _m of the subscriber is the number of followers m days ago.

The sales management department 120 can predict significant changes in the number of SNS followers of subscribers receiving the subscription service through Equation 3. If the score calculated through Equation 3 is above the standard value, the styling change due to the subscription service is positive. It can be considered as having worked. This is because the number of followers can be seen to have increased as subscribers write SNS posts after receiving styling services.

The sales management unit 120 may preset and store the styling coaching subscription service cost for each subscription service score (P_sub) section and calculate the subscription service cost according to the subscription service score.

In this way, the sales management unit 120 can increase service quality and subscriber satisfaction by setting service costs differently according to positive changes in styling according to the styling subscription service.

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

1: Style Commerce Platform System
100: platform server
200: Influencer terminal
300: Subscriber terminal

Claims (3)

We receive, store and manage platform entry information from brands, match influencers and brands, provide a styling coaching subscription service that allows users to receive styling coaching from influencers, and charge fees for the styling coaching subscription service. Includes a platform server that processes
The platform server is,
A new designer brand that receives and stores platform entry information from the brand, calculates the brand score using influencers' evaluation scores for the store entry information, and provides product sales, settlement, and statistics management pages for brands entering the platform. Store management department;
Viral content information including a plurality of domestic and foreign promotional means is provided to brands located on the platform, and promotional means are extracted and provided according to the brand score among the plurality of promotional means included in the viral content information, and influencers and the platform are provided. Influencer viral content management department that matches stores with brands;
A styling coaching subscription management department that provides a styling coaching subscription service that allows people to receive styling coaching from influencers; and
It includes a sales management unit that calculates the cost of the styling coaching subscription service and allows the cost of the styling coaching subscription service to be paid through a subscriber terminal,
The management department of the new designer brand,
Store entry information including sales product information, payment information, brand information, and target customer information is transmitted and stored, and 1 to 10 points are awarded for each item of brand entry information from multiple influencers through the influencer terminal. One of the scores is input, a sales product information score (P _p ) is calculated according to the average of the evaluation scores of a plurality of influencers on the sales product information among the store entry information, and a plurality of payment information among the store entry information are calculated. The payment information score (P _c ) is calculated according to the average of the influencers' evaluation scores, and the brand information score (P _b ) is calculated according to the average of the evaluation scores of a plurality of influencers on the brand information among the store entry information. , The target customer information score (P _g ) is calculated according to the average of the evaluation scores of a plurality of influencers on the target customer information among the store entry information, and the sales product information score (P _p ) and the payment are calculated in Equation 1 below. Calculating a brand score (P brand) by applying the information score (P _c ), the brand information score (P _b ), and _the target customer information score (P _g ),
[Equation 1]

The styling coaching subscription management department,
Subscription application information including influencer name, SNS type, brand name, and Seongho style hashtag is input through the subscriber terminal, the subscription application information is generated as input data, and influencer recommendations to provide styling coaching are made. Entering the input data into an artificial neural network learned to obtain output data from the artificial neural network, calculating the output data as an influencer to provide styling coaching,
The influencer viral content management department,
An influencer who receives at least one keyword for viral content from the brand to enter the store, and whose average number of SNS views when launching a keyword for viral content designated by the brand among multiple influencers exceeds twice the average number of views on SNS during normal times A styling commerce platform system that detects influencers and matches brands with the influencers.
delete delete