KR101899843B1 - System and method for analysing trend of cosmetic customer - Google Patents

Abstract

The present invention relates to a cosmetics customer trend analysis system and method. The cosmetics customer trend analysis system of the present invention comprises: a data collection unit connected to the SNS (Social Network Service) and the web and configured to collect cosmetics-related data according to cosmetics type keywords according to the Cosmetics Act Enforcement Regulations; A public data collection unit connected to a public institution server and configured to collect cosmetic-related data (including data collected through standard data and a public API) on public data and provide standard data to the data collection unit; A big data storage unit configured to store the cosmetic related data and the standard data collected by the data collecting unit and the data collected through the public API in the public data collecting unit in a plurality of categories; The data stored in the big data storage unit is analyzed by natural language data based on the Korean alphabet morpheme analyzer to analyze trends of customers for cosmetics and the analysis result is verified using cosmetic related data on public data, Analyzer; A formatting database configured to convert the data analyzed by the big data analyzer into formatted data and store the formatted data; A web visualization unit configured to read the formatting data stored in the formatting database and convert the formatting data into a chart format; A web server configured to convert data of a chart form obtained from the web visualization unit into a web form; A statistical information visualization unit configured to convert the data analyzed by the big data analyzer into a local form; And a final analysis information output unit configured to display web-type data and local-type data from the web server and the statistical information visualization unit, respectively, as final analysis information.

Description

TECHNICAL FIELD [0001] The present invention relates to a system and method for analyzing customer trends in cosmetics,

The present invention relates to a system and method for analyzing customer trends of cosmetics, and more particularly, to a system and method for analyzing cosmetics customer trends by collecting cosmetics data such as customer opinions related to cosmetics on SNS (Social Network Service) A cosmetics customer trend analysis system and method that can collect public data, analyze the collected cosmetics data to analyze customer trends, and verify and integrate the analysis results using public data to improve the reliability of analysis service .

With the recent development of mobile networks and the spread of smartphones, users can access the Internet anytime and anywhere. In addition, since it is possible to locate the current user through GPS, wireless Internet, and mobile communication network, studies on SNS combining location-based services are actively conducted. With the development of mobile network environment, importance of social search considering users' tendency is becoming more important. Unlike the conventional web search, the social search is a method of providing the search result desired by the user by analyzing the tendency of the individual from the various SNSs frequently used by the user and reflecting it on the search result. In mobile environments, social search is a very important issue in terms of how to keep up-to-date data state for places and how to rank the results. However, unlike a general computing environment, a mobile terminal has a strong personal tendency and the amount of information that can be output on one screen is limited. Therefore, efficient arrangement of search results can make users feel convenient. Generally, the most popular social search method collects user behavior information from SNS or e-mail, and searches various information provided through common interest or SNS. That is, a keyword, an internet link, and the like are collected from the body of an email or a post on the SNS, and the user's tendency is analyzed and reflected in the search result to rank. Most social searches use implicit information gathering methods to gather information for propensity analysis without user involvement. In other words, the user does not input his / her own tendency or profile in the search process but collects the activity information of the SNS and extracts the tendency or interests of the recent users. However, implicit information gathering methods must collect information for a certain period of time in order to analyze the user's propensity. If sufficient information is not gathered, the accuracy of the search may deteriorate because the implicit information gathering may not clarify the users' propensity.

The conventional social search system and technique, for example, as disclosed in Korean Patent Registration No. 1523192 (hereinafter referred to as prior art), selects a candidate group using the keyword and position information included in the query, The candidates not operating through the time information are excluded, the popularity score is calculated through the visit frequency of each place included in the candidate group, the candidates are weighted with respect to the places satisfying the user tendency through the skyline, And the score of the user and the score of the user tendency to which the weight is assigned.

Since the preceding document constructed as above selects only candidates suitable for a time zone to be searched through the use of time information, there is an advantage in that the calculation amount can be reduced because all the places within the radius are not evaluated.

However, since the prior art is a method of searching and analyzing based on the data of the SNS, there is a problem in the reliability of the analysis result, and accordingly, a system capable of enhancing the reliability of the analysis result is needed.

SUMMARY OF THE INVENTION The present invention has been made in view of the above problems, and it is an object of the present invention to provide a cosmetic customer trend analysis system and method which can enhance the reliability of a trend analysis result of a cosmetic customer.

Another object of the present invention is to provide a cosmetics customer trend analysis system and method that enables small-scale grouped or personalized micro-targeting.

In order to achieve the above object, a cosmetics customer trend analysis system according to an embodiment of the present invention includes a data collection unit connected to the SNS and the web and configured to collect cosmetics-related data according to cosmetics type keywords according to the Cosmetics Act Enforcement Regulations; A public data collection unit connected to a public institution server and configured to collect cosmetic-related data (including data collected through standard data and a public API) on public data and provide standard data to the data collection unit; A big data storage unit configured to store the cosmetic related data and the standard data collected by the data collecting unit and the data collected through the public API in the public data collecting unit in a plurality of categories; The data stored in the big data storage unit is analyzed by natural language data based on the Korean alphabet morpheme analyzer to analyze trends of customers for cosmetics and the analysis result is verified using cosmetic related data on public data, Analyzer; A formatting database configured to convert the data analyzed by the big data analyzer into formatted data and store the formatted data; A web visualization unit configured to read the formatting data stored in the formatting database and convert the formatting data into a chart format; A web server configured to convert data of a chart form obtained from the web visualization unit into a web form; A statistical information visualization unit configured to convert the data analyzed by the big data analyzer into a local form; And a final analysis information output unit configured to display, as final analysis information, web type data and local type data from the web server and the statistical information visualization unit, respectively.

In the cosmetics customer trend analysis system according to the above embodiment, the public institution server may include a server of the Korea Health Industry Development Institute and a server of the food and drug safety center.

In the cosmetics customer trend analysis system according to the above embodiment, the data related to the cosmetics from the Korea Health Industry Development Institute server include the size and trend of the cosmetics market, the sales trend by the company, the production status / trend by the cosmetics type, Cosmetics sales by mobile / online shopping, and production status by age group.

In the cosmetics customer trend analysis system according to the above embodiment, the cosmetics-related data from the food and drug safety target server may include cosmetic safety information (allergen-inducing component), compound inhibition component, and compounding limit component.

In the cosmetic customer trend analysis system according to the above embodiment, the standard data may have a file format such as CSV, JSON, RDF, XLS, and XML.

In order to achieve the above object, according to another aspect of the present invention, there is provided a method of analyzing customer trends in cosmetics, comprising the steps of: a first step of collecting cosmetics-related data according to a cosmetics type keyword according to a Cosmetics Act enforcement rule, ; A second step of the public data collection unit accessing the public agency server to collect cosmetic-related data (including data collected through standard data and public API) on public data and provide standard data to the data collection unit; The data collecting unit provides the cosmetic related data collected in the first step and the standard data provided in the second step to the big data storing unit and the public data collecting unit stores the collected data through the public API A third step of providing the part; A fourth step of constructing a first category for each of the data source channels (sources) provided by the third data storage unit and then storing and organizing the detailed categories into data for each product type, brand / enterprise, color, and function; The Big Data Analyzer analyzes the data stored in the fourth step in the natural language Big data based on the Korean alphabet morpheme analyzer to analyze the customer's trends in the cosmetics and verifies and fuses the analysis results using the cosmetic related data on the public data Step 5; A sixth step of the formatting database changing the data obtained in the fifth step into formatted data and storing the formatted data; A seventh step of the web visualization unit reading the formatting data stored in the sixth step and converting the formatted data into data in the form of a chart; An eighth step of the web server converting the data of the chart form obtained in the step 7 into data of web form; A statistical information visualization step of converting the data obtained in the fifth step into a local form; And a final analysis information output unit displaying the web type data and the local type data obtained in the eighth and ninth steps as final analysis information.

According to the cosmetics customer trend analysis system and method according to the embodiment of the present invention, the data collection unit accesses the SNS and the web, collects cosmetics-related data according to the cosmetics type keyword according to the Cosmetics Act enforcement rule, (Including data collected through standard data and public API) on the public data to provide standard data to the data collection unit, and the large data storage unit is connected to the server to collect cosmetics related data The data and standard data and the public data collection unit are constructed by storing the data collected through the open API in a plurality of categories and the big data analyzer analyzes the data stored in the big data storage unit by the natural language data analysis based on the national English morpheme analyzer, To analyze customer trends for The analysis result is verified and merged using public data, the formatting database converts the data analyzed by the big data analyzer into the formatted data and stores it, and the web visualization unit reads the formatted data stored in the formatting database and converts the formatted data into a chart , The web server converts the data of the chart form obtained from the web visualization unit into the web form, the statistical information visualization unit converts the data analyzed by the big data analyzer into the local form, and the final analysis information output unit displays the web server and statistical information visualization And the data of the web form and the data of the local form are displayed as the final analysis information, respectively, so that the reliability of the trend analysis result of the cosmetics customer can be enhanced.

That is, by accessing the SNS and the web, cosmetics-related data such as the product use and after-use period, product and company thinking, evaluation and purchase place are collected and analyzed, and the analysis result is verified by the public data provided by the public institution server So that the reliability of the trend analysis result of the cosmetics customer can be improved.

Also, according to the cosmetic customer trend analysis system and method according to the embodiment of the present invention, after analysis using SNS data, it is possible to provide the analysis result to a small group or individual, There is an excellent effect that personalized micro targeting is possible.

1 is a block diagram showing the entire configuration of a cosmetics customer trend analysis system according to an embodiment of the present invention.
FIG. 2A and FIG. 2B are flow charts illustrating a method of analyzing customer trends in cosmetics using a cosmetics customer trend analysis system according to an embodiment of the present invention.

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

1 is a block diagram showing the entire configuration of a cosmetics customer trend analysis system according to an embodiment of the present invention.

1, the cosmetics customer trend analysis system according to an embodiment of the present invention includes a data collecting unit 100, a public data collecting unit 200, a big data storing unit 300, a big data analyzing unit 500 A shaping database 500, a web visualization unit 600, and a final division information output unit 900.

The data collecting unit 100 is connected to the SNS (e.g., Twitter, Facebook) and the web (e.g., Naver Blog, Naver Cafe, Naver News, Naver Knowledge, Next Cafe, It collects cosmetic related data by keyword. The data collection unit 100 collects text and document file types.

The public data collection unit 200 accesses the public institution server (for example, a server of the Korea Health Industry Development Institute and a server of the food and drug safety center) and stores the cosmetic related data (including the standard data and the data collected through the public API) Provides the standard data to the data collecting unit 100, and provides the collected data to the big data storing unit 300 through the open API.

The data related to cosmetics collected from the Korea Health Industry Development Institute (KHIDI) server are as follows: cosmetics market size and trends, sales trends by company, production trends by cosmetics type, cosmetics trade by FTA, turnover by mobile / online shopping, Includes production status.

Cosmetic related data collected from the Food and Drug Administration's server include cosmetic safety information (allergen-inducing components), inhibition components, and compounding components.

Standard data has a common file format such as CSV, JSON, RDF, XLS, and XML.

The public API form of public data is a form of retrieving data collected directly from public data servers according to Government 3.0 policy.

The big data storage unit 300 stores cosmetic related data and standard data (provided by the public data collection unit 200) collected by the data collection unit 100 and data collected through the public API in the public data collection unit 200 In a plurality of categories.

More specifically, the big data storage unit 300 stores the data collected in the form of NoSQL as the unstructured data in a primary category for each data source channel (source), and then stores the data in the form of product type, brand / enterprise, Configure and store detailed categories.

The big data analyzer 400 analyzes the data stored in the big data storage unit 300 by analyzing natural language data based on the Korean alphabet morpheme analyzer to analyze the trend of the customer for the cosmetics and verifies the analysis result using public data It plays a role of fusion.

The Big Data Analyzer 400 follows Mapidurus, a Hadoop Big Data Analysis structure.

That is, the stored data is fetched and natural language analysis is performed to count the number of times of mentioning about the type of the cosmetics, the keyword of the brand / company, the color, and the function (map step)

We analyze the structure of the language in morphological form and divide the positive and negative sentences of the counted keywords into positive and negative, and analyze the preferences and complaints about ingredients, purchase motive, makeup object, and cosmetics advertisement through related keyword analysis (Reduce step) .

At this time, analyzing the channel where the most talk about cosmetics comes and going based on the source of collected data, and positively / negatively data about brand / company analyzes the positioning against all data for a specific company / brand (Reduce step ).

The formatting database 500 converts the data analyzed by the big data analyzer 400 into formatted data and stores the formatted data. The data output from the data collecting unit 100, the public data collecting unit 200, the big data storing unit 300, and the big data analyzing unit 400 are free-form data and analysis information type data that are not in operation, In order to use the service through the web browser, it is necessary to change the data into the standardized data. In the formalization database 500, the non-standardized data is converted into regularized data according to a service function (menu) so that the web service can be performed, and the modified data is stored in a general RDBMS type MySQL or MS-SQL.

The web visualization unit 600 reads the formatting data stored in the formatting database and converts the formatting data into a chart format. The data stored in the formalization database () need to be visualized for service in the form of charts on the web as character and numerical data. Web Visualization () is a tool that converts / applies these character and numeric data into various charts.

The web server 700 serves to convert data of a chart form obtained from the web visualization unit 600 into a web form.

The statistical information visualization unit 800 converts the data analyzed by the big data analyzer 400 into a local form. The statistical information visualization unit 800 is a tool for visualization such as the web visualization unit 600, but it confirms the analysis result in the system server itself (local) rather than the web form. That is, the statistical information visualization unit 800 allows more detailed and detailed statistical information to be viewed together than the web visualization unit 600.

The final analysis information output unit 900 displays the web type data and the local type data as the final analysis information from the web server 700 and the statistical information visualization unit 800 and displays the final analysis information to the user (small group or individual) It is a role to play.

Hereinafter, a cosmetic customer trend analysis method using the cosmetic customer trend analysis system according to an embodiment of the present invention configured as described above will be described.

2A and 2B are flow charts illustrating a cosmetic customer trend analysis method using a cosmetics customer trend analysis system according to an embodiment of the present invention, wherein S represents a step.

First, the data collecting unit 100 accesses the SNS and the web and collects cosmetics-related data according to the cosmetics type keyword according to the Cosmetics Act enforcement rule (S10).

Then, the public data collection unit 200 accesses the public institution server and collects the cosmetic-related data (including the data collected through the standard data and the public API) on the public data (S20) (S30).

In step S40, the data collection unit 100 provides the cosmetic-related data collected in step S10 and the standard data provided in step S30 to the big data storage unit 300, (200) provides the collected data through the open API to the big data storage unit (300).

In step S50, the big data storage unit 300 forms the primary category for each of the data source channels (sources) provided in the step S40, and then the detailed category And stores it.

In step S60, the big data analyzer 400 analyzes the data stored in the step S50 by analyzing the natural language data based on the national English morpheme analyzer to analyze the trend of the customer for the cosmetics, And verifies and fuses them.

In step S70, the formatting database 500 changes the data obtained in step S60 into formatted data and stores the formatted data.

In step S80, the web visualization unit 600 reads the formatting data stored in step S70 and converts the formatting data into a chart format.

In step S90, the web server 700 converts the data of the chart form obtained in the step S80 into a web form in order to display on the web.

In step S100, the statistical information visualization unit 800 converts the data obtained in step S60 into a local form so that detailed and detailed statistical information can be viewed.

In step S110, the final analysis information output unit 900 displays the web type data and the local type data obtained in the above steps S90 and S100 as the final analysis information, so that the user (small group or individual) .

According to the cosmetics customer trend analysis system and method according to the embodiment of the present invention, the data collector connects to the SNS and the web, collects cosmetics-related data according to the cosmetics type keyword according to the Cosmetics Act enforcement rule, (Including data collected through standard data and public API) on the public data to provide standard data to the data collection unit, and the large data storage unit is connected to the server to collect cosmetics related data The data and standard data and the public data collection unit are constructed by storing the data collected through the open API in a plurality of categories and the big data analyzer analyzes the data stored in the big data storage unit by the natural language data analysis based on the national English morpheme analyzer, To analyze the customer's trends and The result of the query is verified and merged using public data, the formatting database converts the data analyzed by the big data analyzer into the formatted data, stores the formatted data, and the web visualization unit reads the formatted data stored in the formatting database and converts the formatted data into a chart , The web server converts the data of the chart form obtained from the web visualization unit into the web form, the statistical information visualization unit converts the data analyzed by the big data analyzer into the local form, and the final analysis information output unit displays the web server and statistical information visualization And the data of the web form and the data of the local form are displayed as the final analysis information, respectively, so that the reliability of the trend analysis result of the cosmetics customer can be enhanced. That is, by accessing the SNS and the web, cosmetics-related data such as the product use and after-use period, product and company thinking, evaluation and purchase place are collected and analyzed, and the analysis result is verified by the public data provided by the public institution server So that the reliability of the trend analysis result of the cosmetics customer can be improved.

In addition, according to the cosmetic customer trend analysis system and method according to the embodiment of the present invention, after analysis using the data of the SNS, the analysis result can be provided to a small group or individuals, Personalized micro-targeting is possible.

Although the best mode has been shown and described in the drawings and specification, certain terminology has been used for the purpose of describing the embodiments of the invention and is not intended to be limiting or to limit the scope of the invention described in the claims. It is not. Therefore, those skilled in the art will appreciate that various modifications and equivalent embodiments may be made without departing from the scope of the present invention. Accordingly, the true scope of the present invention should be determined by the technical idea of the appended claims.

100: Data collection unit
200: public data collection unit
300: Big data storage unit
400: Big Data Analyzer
500: Formulation database
600: Web visualization unit
700: Web server
800: statistical information visualization unit
900: Final analysis information output section

Claims (6)

A data collection unit connected to the SNS and the web and configured to collect cosmetics-related data in the form of text and documents by the cosmetics type keyword according to the Cosmetics Act enforcement rule;
A public data collection unit connected to a public institution server and collecting cosmetic-related data (including data collected through standard data and a public API) on public data, and collecting and providing standard data to the data collection unit;
A big data storage unit configured to store the cosmetic related data and the standard data collected by the data collecting unit and the data collected through the public API in the public data collecting unit in a plurality of categories;
The data stored in the big data storage unit is analyzed by natural language data based on the Korean alphabet morpheme analyzer to analyze trends of customers for cosmetics and the analysis result is verified using cosmetic related data on public data, Analyzer;
A formatting database configured to convert the data analyzed by the big data analyzer into formatted data and store the formatted data;
A web visualization unit configured to read the formatting data stored in the formatting database and convert the formatting data into a chart format;
A web server configured to convert data of a chart form obtained from the web visualization unit into a web form;
A statistical information visualization unit configured to convert the data analyzed by the big data analyzer into a local form; And
A final analysis information output unit configured to display, as final analysis information, web type data and local type data from the web server and the statistical information visualization unit, respectively;
The data related to cosmetics from the above public agency servers are as follows: cosmetics market size and trend, sales trend by company, production status / trend by cosmetics type, cosmetics trade by FTA, turnover by cosmetics type by mobile / online shopping, ;
The cosmetic-related data from the public entity server includes cosmetic safety information (allergen-inducing component), compound inhibiting component, and compounding limit component;
Wherein the standard data has a file format such as CSV, JSON, RDF, XLS, and XML.
delete delete delete delete A cosmetic customer trend analysis method using the cosmetic customer trend analysis system according to claim 1, comprising:
A first step of connecting the data collecting unit to the SNS and the web and collecting cosmetics related data according to the cosmetics type keyword according to the Cosmetics Act enforcement rule;
A second step of the public data collection unit accessing the public agency server to collect cosmetic-related data (including data collected through standard data and public API) on public data and provide standard data to the data collection unit;
The data collecting unit provides the cosmetic related data collected in the first step and the standard data provided in the second step to the big data storing unit and the public data collecting unit stores the collected data through the public API A third step of providing the part;
A fourth step of constructing a first category for each of the data source channels (sources) provided by the third data storage unit and then storing and organizing the detailed categories into data for each product type, brand / enterprise, color, and function;
The Big Data Analyzer analyzes the data stored in the fourth step in the natural language Big data based on the Korean alphabet morpheme analyzer to analyze the customer's trends in the cosmetics and verifies and fuses the analysis results using the cosmetic related data on the public data Step 5;
A sixth step of the formatting database changing the data obtained in the fifth step into formatted data and storing the formatted data;
A seventh step of the web visualization unit reading the formatting data stored in the sixth step and converting the formatted data into data in the form of a chart;
An eighth step of the web server converting the data of the chart form obtained in the step 7 into data of web form;
A statistical information visualization step of converting the data obtained in the fifth step into a local form; And
And the final analysis information output unit displays the web type data and the local type data obtained in the eighth and ninth steps as final analysis information.

Images