KR102251612B1 - Method of managing categorized contents and system thereof - Google Patents

Abstract

According to an embodiment of the present invention, a content management system comprises: a content extraction unit for extracting content tagged with interest information from a plurality of different servers; a content classification unit that classifies the content extracted by an artificial intelligence engine by category; and a storage unit for storing the content by tagging classification information. Therefore, a user may arrange content of interest included in various platforms by category and receive the same.

Description

Content classification management method and system {METHOD OF MANAGING CATEGORIZED CONTENTS AND SYSTEM THEREOF}

Content classification management method and system {METHOD OF MANAGING CATEGORIZED CONTENTS AND SYSTEM THEREOF}

Recently, various platforms that provide information to users have been formed, and users are accustomed to searching for desired information through content uploaded by individuals as well as official information providers. In addition, individuals share not only content related to personal daily life such as product reviews, travel destinations, and restaurant reviews, but also professional knowledge and opinions with the majority through personal SNS (Social Network Service). Accordingly, users obtain necessary information or share opinions through contents uploaded to various platforms.

In addition, each platform provides functions that allow users to express their opinions such as'like' and'dislike', collecting opinions such as user's comments, and storing or sharing contents with others.

However, since the user's activities on the platform can only be checked on individual platforms, the user cannot check the information that has been checked and collected on multiple platforms at once. In addition, the information that the user has checked does not correspond to one field and may include information in various fields such as finance, shopping, entertainment, society, and culture. Remember the location.

That is, platforms provide information and provide some functions that allow users to utilize it, but users using multiple platforms have the inconvenience of not being able to check a large amount of information at once.

Unexamined Patent Publication No. 10-2016-0105019, published on September 6, 2016

Publication Patent Publication No. 10-2016-0105019, published on September 6, 2016 The problem to be solved by the present invention is to extract content that the user was interested in from among a large amount of information provided by a plurality of platforms, and categorize it by category and provide it. There is one.

In addition, it is to generate data by classifying contents that are of interest to users by category and to use it for advertisements and the like.

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

A content classification management method according to an aspect of the present invention for solving the above-described problem includes the steps of extracting a content tagged with interest information input by a user from among a plurality of contents stored in a plurality of different servers, the extracted content And classifying at least one of a plurality of preset categories using at least one of text, image, and video data included in the content, and tagging and storing at least one classification information in the content.

According to an embodiment, the step of classifying text into at least one of a plurality of preset categories using text and image data included in the extracted content includes classifying text included in the text through a natural language processing function. Analyzing the content using at least one of a text mining technique learned to classify an image and a machine learning technique learned to classify an image.

According to an embodiment, the step of classifying into at least one of a plurality of preset categories using text and image data included in the extracted content includes receiving platform information and reference category information for providing content from a consumer. The step of, generating a learning data set using the content included in the platform information, and generating an artificial intelligence classification engine learned through the learning data set may be included.

According to an embodiment, the step of extracting content tagged with interest information input by a user from among a plurality of contents stored in a plurality of different servers, when a URL address is stored in a specific server, is a content corresponding to the URL address. It may include the step of extracting.

According to an embodiment, the interest information corresponds to data stored in the server by the user, and the interest information is data for evaluation of the content, data for transmission to the other server, and input in association with the content. It may correspond to at least one of text data.

According to an embodiment, the extracted content may include data stored in a storage device by a user.

According to an embodiment, the content classification management method may further include generating a user's behavior pattern based on the classification information tagged to the collected content.

According to an embodiment, the step of matching the collected advertisement data to the behavior pattern and providing the collected content together with the collected content may be further included.

According to an embodiment, the step of tagging and storing at least one classification information in the content includes receiving a content output mode, and an open server in a form that other users can browse when the received mode is an open mode. And storing the content in a private mode, storing the content in a private server.

According to an embodiment, the content tagged with the classification information may be converted into at least one of an image, text, and PDF electronic file and stored.

According to an embodiment, the step of providing related content related to the classification information may be further included, and the related content may be collected from the plurality of servers.

A content management system according to another embodiment of the present invention includes a content extraction unit for extracting content tagged with interest information input by a user from among contents stored in a plurality of different servers, text, images, and texts included in the extracted content. A content classification unit for classifying at least one of a plurality of preset categories using at least one of image data, and a storage unit for tagging and storing at least one classification information on the content, and providing the content for each category. do.

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

According to an embodiment of the present invention, only contents of interest are extracted from contents provided by various platforms, and are provided in a state classified by category, so that users can collect and manage information without losing interest or necessary information. .

In addition, since the classified information can be shared with others or stored privately, the information collected and classified according to the needs of the user can be utilized.

In addition, since the user's behavior pattern can be derived through the analysis of the extracted content, it is possible to provide accurate user information to the advertiser, so that the advertiser can market to a more accurate customer.

In addition, since the information that the user is interested in or needs can be categorized and provided by category, the user can receive recommended information without searching for additional information.

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

1A is a configuration diagram of a content management system.
1B is a conceptual diagram of a content management system according to the present invention.
2 is a flowchart of a content management method according to an embodiment of the present invention.
3A is a flowchart illustrating a method of classifying content by category by a content classifying unit.
3B is a conceptual diagram for providing customized classification result data for a demand company.
4 is a flowchart illustrating a method of storing and providing classified content.
5 is a flowchart illustrating a method of providing advertisement data through a user behavior pattern.
6 is a flowchart illustrating a method of providing related content based on category information.

Advantages and features of the present invention, and a method of achieving them will become apparent with reference to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in a variety of different forms. It is provided to fully inform the skilled person of the scope of the present invention, and the present invention is only defined by the scope of the claims.

The terms used in the present specification are for describing exemplary embodiments and are not intended to limit the present invention. In this specification, the singular form also includes the plural form unless specifically stated in the phrase. As used herein, “comprises” and/or “comprising” do not exclude the presence or addition of one or more other elements other than the mentioned elements. Throughout the specification, the same reference numerals refer to the same elements, and "and/or" includes each and all combinations of one or more of the mentioned elements. Although "first", "second", and the like are used to describe various elements, it goes without saying that these elements are not limited by these terms. These terms are only used to distinguish one component from another component. Therefore, it goes without saying that the first component mentioned below may be the second component within the technical idea of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used in the present specification may be used with meanings that can be commonly understood by those of ordinary skill in the art to which the present invention belongs. In addition, terms defined in a commonly used dictionary are not interpreted ideally or excessively unless explicitly defined specifically.

The term "unit" or "module" used in the specification refers to a hardware component such as software, FPGA or ASIC, and the "unit" or "module" performs certain roles. However, "unit" or "module" is not meant to be limited to software or hardware. The “unit” or “module” may be configured to be in an addressable storage medium, or may be configured to reproduce one or more processors. Thus, as an example, "sub" or "module" refers to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, Includes procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays and variables. Components and functions provided within "sub" or "modules" may be combined into a smaller number of components and "sub" or "modules" or into additional components and "sub" or "modules". Can be further separated.

Spatially relative terms "below", "beneath", "lower", "above", "upper", etc. It can be used to easily describe the correlation between a component and other components. Spatially relative terms should be understood as terms including different directions of components during use or operation in addition to the directions shown in the drawings. For example, if a component shown in a drawing is turned over, a component described as "below" or "beneath" of another component will be placed "above" the other component. I can. Accordingly, the exemplary term “below” may include both directions below and above. Components may be oriented in other directions, and thus spatially relative terms may be interpreted according to the orientation.

In the present specification, a computer means all kinds of hardware devices including at least one processor, and may be understood as encompassing a software configuration operating in the corresponding hardware device according to embodiments. For example, the computer may be understood as including all of a smartphone, a tablet PC, a desktop, a laptop, and a user client and application running on each device, and is not limited thereto.

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

Each of the steps described herein is described as being performed by a computer, but the subject of each step is not limited thereto, and at least some of the steps may be performed by different devices according to embodiments.

1A is a configuration diagram of a content management system, FIG. 1B is a conceptual diagram of a content management system of the present invention, and FIG. 2 is a flow chart of a content classification management method according to an embodiment of the present invention.

1A, 1B, and 2, the content management system 1 includes a content extraction unit 1a, a content classification unit 1b, and a storage unit 1c. The content management system 1 provides a service that collects and categorizes content from a plurality of servers and provides it to a user, and the service may be provided in various ways, such as an application, a website, and a chrome extension.

The plurality of servers correspond to a platform that provides content. The platform includes services for uploading and sharing content, such as SNS (Social Network Service) and the web. For example, the platform uploads text, images, videos, music, specific links, etc., and shares them online with multiple users (e.g., Facebook, Instagram, Twitter, blog, KakaoTalk Story). , Naver Band, Daum Cafe, etc.), a search engine that provides search results such as news, web pages, shopping, advertisement services, etc. by entering a search word (for example, Daum, Naver, Google portal services, etc.), data between specific users It includes a message transmission service (application) for transmitting and receiving, and the type is not limited thereto. Content provided by each platform can be distinguished by a unique URL address, and a user can store the content by using the URL address of the content. The service platform may be provided in computer devices including mobile terminals such as mobile phones and tablets, PCs, and TVs.

The platform provides content through a server and receives interest information from a plurality of users. The interest information may correspond to a user's opinion on each content. For example, the interest information may correspond to'like','share','save', and comment input in connection with the content. In addition, when the URL address (link) of the content is delivered and stored in a specific server, it is considered that the content is tagged with interest information.

The platform can provide a service that allows users to view information tagged with interest information on each platform at once, and in this case, the user can check contents to which interest information is assigned within the platform.

'Sharing' according to an embodiment of the present invention includes storing a URL (Uniform Resource Locator) address of a specific content in a specific server. The'sharing' may correspond to storing information of the specific content in the user's personal server, and the specific content information is stored and delivered using a URL address. For example, this may be the case when content is delivered to a specific storage space (server) of a user assigned on a messenger application or content is sent to a user's e-mail address.

The content extraction unit 1a receives content from the plurality of servers and extracts content tagged with interest information (S10). The content extracting unit 1a includes a seeding unit for extracting the URL address of the platform server and a crawling unit for collecting content. The seeding unit extracts the URL address of the server, classifies and stores the type of platform, and delivers the stored information to the crawling unit.

The crawling unit may collect content by accessing not only an open web but also an ID/PW type closed web. The crawl unit may be driven by at least one of a nutch, an open application program interface (API), a rich site summary (RSS), and a web scrapper.

The content extraction unit 1a may extract content based on specific user information together with the interest information. Only content tagged with interest information input by a specific user may be extracted. In this case, the content extraction unit 1a extracts only the content through the user's ID/PW information and the content in which the interest information is inputted by a specific computer device. When the URL address is stored in a specific server by the user, the content extracting unit 1a extracts content corresponding to the URL address.

According to an embodiment, the content extracting unit 1a may extract only content tagged with specific interest information assigned as a user's preference. In this case, data reflecting the user's taste may be formed as the collected and classified contents.

The content extraction unit 1a may be controlled to extract content according to a preset period, or may be controlled to extract content based on a control command related to reception of interest information. The content extracting unit 1a may extract not only the information of the content itself, but also data about the platform providing the content, when the content was formed (date), and when the interest information was added.

Alternatively, the content extraction unit 1a may extract all content tagged with interest information irrespective of the user. That is, by entering the information of interest by a number of users, data on the content that a number of users are interested in can be generated through the collected contents over time, which can be used in various industries such as content creators and marketing parts. have.

The content classification unit 1b classifies the content based on text and image information included in the collected content (S20). The content classification unit 1b classifies the content according to a preset reference category, and the preset reference category corresponds to a content user using the content management system 1 and a demand company using the classified content. have.

For example, the criterion category may be set as politics, education, humor/community, economy/real estate, sports, entertainment, IT/knowledge, shopping, restaurant, musical/theatrical/, and others, but is not limited thereto. Integration, deletion, and addition are possible.

According to an embodiment of the present invention, a user's control command for storing the URL address of the content, a captured image, etc. of the content in the memory of the computer device may be included in the interest information. In this case, the content extracting unit 1a may extract content tagged with interest information from data included in the user's memory device. The content extracting unit 1a also includes data stored through a function for capturing images output to the output unit by the user, copying text, etc., or data stored in an application for recording and storing data by the user, such as a memo application. It can be extracted as content.

The content classification unit 1b includes an artificial intelligence classification engine that classifies content into categories. The artificial intelligence classification engine uses natural language processing functions, text mining, machine learning, and deep learning technologies, and analyzes text and images included in the extracted content to analyze each category. They can be classified by category. The content classification unit 1b may be learned through a plurality of content data, and the content data may be provided by a consumer and a demand company who wants to use the classified content.

By using a natural language processing function, text included in content and comments can be classified and analyzed to correspond to category information. In addition, content can be classified using visual information other than text through a learning model using a specific correlation (pattern) in information included in images and videos. In the case of video content, text can be extracted from a title linked to the video content, or the content of the video can be analyzed and classified by category through an image analysis of an image, extraction of included voice, and natural language processing functions.

For example, through the natural language processing function, comments entered by the user for content can be classified into positive expressions or negative expressions, and categories can be classified by grasping the contents included in the content.

3A is a flowchart illustrating a method of classifying content by category by a content classification unit, and 3B is a conceptual diagram for providing customized classification result data for a demand company.

3A and 3B, information on a plurality of platforms including content and reference category information are collected (S210). The platform information and the reference category information may be provided by the demand company 3 (S211), and the content classification unit 1b may classify the content according to the reference category required by the demand company 3 Artificial intelligence engines can be trained. For example, the reference category information may be set to correspond to categories classified into 11 categories.

A learning data set is generated based on the content (S220), and classification of the content is learned using the learning data set (S230). Correct answer category information is set for individual content, and the correct answer category information may be set as a category selected by a plurality of workers to generate a learning data set. The training data set can consist of about 300,000 contents, and it is matched with reference category information (about 11 classified categories) provided from the demand company 3 using text mining and machine learning technology. It learns to be able to be, and provides the learned artificial intelligence engine to the demanding company (3) (S221).

The content classification unit 1b uses the artificial intelligence engine learned according to the platform information and the reference category provided by the demand company 3, and the classified result data of the content (S241) provided from the demand company 3 Can be provided (S242).

In this case, the content classified by the content classification unit 1b may not pass through the content extraction unit 1a. That is, all the content data provided by the demand company 3 can be classified according to the reference category.

Or, of all the content data provided by the demand company (3), extract only the content tagged with interest information, or the content tagged with specific interest information specified by the demand company (3) (for example,'Like', save, share, The artificial intelligence engine may be trained by extracting only contents including comments) among comments.

According to this embodiment, in the case of attempting to classify content included in a specific platform (server) into a specific category, a more accurately classified result data is provided through a customized artificial intelligence engine according to the needs of the demanding company (3). I can. Accordingly, it is possible to provide an artificial intelligence classification engine suitable for a specific platform including the type of content (text, image, video, etc.) and the included configuration (title, text, comment, interest information, function, etc.).

Although not specifically shown in the drawings, the content extraction unit 1b includes an artificial intelligence classification engine learned using content data included in a plurality of platforms, and different artificial intelligence classification engines are extracted for each specific platform. Content can be classified.

The storage unit 1c stores the classified content by tagging it with classification information (S30). The storage unit 1c corresponds to a storage unit of a specific server, storage device, or computer device. The content tagged with the classification information is provided to the demanding company 3 in the form of data, or is output through the output unit of the computer device (S40). When the content is related to a plurality of categories, a plurality of classification information may be tagged to the content.

The classification information corresponds to the category in which the content is classified, and may be generated based on data included in the content set or collected by the consumer company 3 and the user. The classification information may be formed in stages such as large classification, medium classification, and small classification according to the classification range.

4 is a flowchart illustrating a method of storing and providing classified content.

2 and 4, the step of storing the classified content (S30) includes processing the content by the storage unit 1c (S310).

According to an embodiment, the storage unit 1c may store an image of a content and a URL address of the content together. The image of the content may correspond to a partially captured screen, a thumbnail image, etc. when the content is an image. When the content is classified and provided, only the image of the content is output to the content output device 3 and can be linked with a corresponding URL address.

In this case, the user can intuitively check the content that has been checked in the past and assigned specific interest information through the image, and can immediately access the specific content without reactivating the platform (server).

According to an embodiment, the storage unit 1c converts the content into a specific type of file, such as text, URL address, image, PDF file, editable file format, etc., or some information (e.g., video Title, some thumbnail images of content, keywords of article content, etc.) can be converted and saved in an extracted form. In this case, the user can check the content even without accessing a specific platform (server), and since additional editing of the content is easy, it is advantageous for reprocessing of information.

According to an embodiment, the storage unit 1c includes the type of data (text, image, video) included in the content, the type of interest information ('like','share','storage', etc.), and the content. Contents can be processed in different forms according to at least one of the types of platforms (servers) and settings selected by users (consumers).

According to the present embodiments, it is easy to check and utilize contents formed in different forms, and for users who need data on the trends of collected contents, unnecessary storage capacity is reduced by reducing the storage and output of detailed contents of the contents. Can be minimized.

According to an embodiment, content collected, classified, and stored may be removed from the storage unit 1c by a user's selection, and may be manually edited to be classified into different categories based on a user's control command. Accordingly, the user can automatically check the collected and classified content, edit it in a convenient manner, and utilize the stored data.

2 and 4, the step (S40) of providing (output) content tagged with the classification information includes a step (S410) of receiving a content output mode.

The content output mode includes an open mode in which collected content is stored to be viewed by multiple users other than the user, and a private mode in which only the user can check. The content output mode may be set differently for each collected content or for each category.

When the open mode is selected, the storage unit 1c stores the content in an open server (S420). The open server is formed so that a plurality of users other than the user can access and browse. The open server may be classified for each specific user, and multiple users may check contents collected by a specific user by category. In the open mode, the storage unit 1c may store the content by classifying it by preset time section, and the time section may be set in units of a week, a month, or a year.

According to an embodiment, the open server may receive and store reaction information for content collected for each category. Here, the reaction information may correspond to'like','comment','share','save', and the like. Accordingly, the user can not only collect content of interest by category, but also easily share it with other users.

Although not specifically shown in the drawings, the user can directly store and share content on the server of the service platform by the content management system 1, and in this case, the content management system 1 Perform the step of classifying.

When the private mode is selected, the classified content is stored in a private type in a preset server (S430).

According to the present embodiment, since contents tagged with interest information can be stored for each category, various contents of different types can be checked at once without the inconvenience of re-searching or organizing contents required by the user on the corresponding platform. You can create your own database for specific categories. Since the extracted content includes information on the time when the content was created, when the interest information was tagged, and when the content was extracted, the storage unit 1c can collect and organize the extracted content over time. have. Accordingly, the user can check the information and category information collected over time. In addition, when contents are extracted based on the interest information of a plurality of users, it is possible to grasp the trends of contents and related categories that are of interest to the public.

5 is a flowchart illustrating a method of providing advertisement data through a user behavior pattern.

Referring to FIG. 5, the content management system 1 forms a content tagged with classification information (S40), and generates a user's behavior pattern (S71). The user's behavioral pattern is related to the user's frequency of use of specific content, and can be determined by the types of categories in which the content is classified, the type of platform (server) related to the collected content, and the expression of interest information (positive or negative). have.

The content management system 1 matches the received advertisement data with the behavior pattern (S72), and provides the matched advertisement data with the collected content (S73).

Advertisement data is collected from the advertisement providing unit 2, and the advertisement providing unit 2 may correspond to an advertiser. The advertisement providing unit 2 may provide advertisement data to be provided to the user to the content management system 1. That is, the content management system 1 can recruit advertisers based on the category information of the content. For example, the content management system 1 may extract the five category information most tagged to the collected content, and provide advertisement data related to the category information to the user.

Accordingly, it is possible to improve the advertising effect by providing advertisement data for areas of high interest in which the user collects information such as storage and sharing.

6 is a flowchart illustrating a method of providing related content based on category information.

Referring to FIG. 6, while providing content tagged with classification information (S40), related content related to classification information is collected (S81). The related content may be collected from a specific server that collected the content, or may be collected from a service platform other than a specific server. The related content may include advertisement data collected from an advertiser.

For example, the related content may include a URL address of an online purchase site, user review information, advertisement data for similar products, and the like for a product included in the content to which the user has given interest information.

The related content may be output together with the collected content stored in the storage unit 1c. The content and the related content may be output together on a platform that accumulates content by the content management system 1 (S83). Accordingly, new related contents can be checked along with contents collected by the user and classified by category, and related new contents can be provided without the need for additional search through other platforms.

Meanwhile, the related content may be provided through each platform (server) by data of the related content generated by the content management system 1 (S82). In this case, the related content corresponds to content in a format provided by each platform (server). For example, if the content collected by the content management system 1 corresponds to the content of the Facebook platform, the related content can be output when the user uses the Facebook platform.

According to the present embodiments, new information necessary for the user may be additionally provided by recommending content that the user is expected to be interested in based on the type of content that the user is interested in.

7 is a block diagram of an apparatus according to an exemplary embodiment.

The processor 102 may include one or more cores (not shown) and a graphic processing unit (not shown) and/or a connection path (eg, a bus) for transmitting and receiving signals with other components. .

The processor 102 according to an embodiment executes one or more instructions stored in the memory 104 to perform the method described with reference to FIGS. 2 to 7.

Meanwhile, the processor 102 temporarily and/or permanently stores a signal (or data) processed inside the processor 102, and a RAM (Random Access Memory, not shown) and a ROM (Read-Only Memory) , Not shown) may further include. In addition, the processor 102 may be implemented in the form of a system on chip (SoC) including at least one of a graphic processing unit, RAM, and ROM.

The memory 104 may store programs (one or more instructions) for processing and controlling the processor 102. Programs stored in the memory 104 may be divided into a plurality of modules according to functions.

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

Components of the present invention may be implemented as a program (or application) and stored in a medium to be executed by being combined with a computer that is hardware. Components of the present invention may be implemented as software programming or software elements, and similarly, embodiments include various algorithms implemented with a combination of data structures, processes, routines or other programming elements, including C, C++ , Java, assembler, or the like may be implemented in a programming or scripting language. Functional aspects can be implemented with an algorithm running on one or more processors.

In the above, embodiments of the present invention have been described with reference to the accompanying drawings, but those skilled in the art to which the present invention pertains can be implemented in other specific forms without changing the technical spirit or essential features. You will be able to understand. Therefore, the embodiments described above are illustrative in all respects, and should be understood as non-limiting.

1: Content management system
1a: content extraction unit
1b: content classification unit
1c: storage

Claims (12)

Extracting content tagged with interest information input by a user from among a plurality of contents stored in a plurality of different servers;
Classifying into at least one of a plurality of preset categories by using at least one of text, image, and video data included in the extracted content;
Including the step of tagging and storing at least one classification information in the content,
Classifying into at least one of a plurality of preset categories using text and image data included in the extracted content,
Analyzing the content using at least one of a text mining technique learned to classify text included in the text through a natural language processing function and a machine learning technique learned to classify an image,
Classifying into at least one of a plurality of preset categories using text and image data included in the extracted content,
Receiving platform information and reference category information for providing content from a consumer;
Generating a training data set using the content included in the platform information; And
And generating an artificial intelligence classification engine learned through the learning data set. delete delete The method of claim 1,
The step of extracting content tagged with interest information input by a user from among a plurality of contents stored in a plurality of different servers,
And extracting content corresponding to the URL address when the URL address is stored in a specific server. The method of claim 1,
The interest information corresponds to data stored in the server by the user,
The interest information corresponds to at least one of evaluation data for the content, data for transmission to the plurality of different servers, and text data input in association with the content. The method of claim 5,
The content classification management method, characterized in that the extracted content includes data stored in a storage device by a user. The method of claim 1,
The content classification management method further comprising the step of generating a behavior pattern of the user based on the classification information tagged to the collected content. The method of claim 7,
And providing the collected advertisement data with the collected content by matching the collected advertisement data with the behavior pattern. The method of claim 1,
The step of tagging and storing at least one classification information in the content,
Receiving a content output mode; And
When the received content output mode is an open mode, storing the content in an open server that can be viewed by other users, and when the received content output mode is a private mode, storing the content in a private server Content classification management method comprising a. The method of claim 9,
The content classification management method, characterized in that the content tagged with the classification information is converted into at least one of an image, text, and PDF electronic file and stored. The method of claim 1,
Further comprising the step of providing related content related to the classification information,
The content classification management method, characterized in that the related content is collected from the plurality of servers. A content extraction unit for extracting content tagged with interest information input by a user from among contents stored in a plurality of different servers;
A content classification unit for classifying at least one of a plurality of preset categories by using at least one of text, image, and image data included in the extracted content; And
And a storage unit for tagging and storing at least one classification information in the content,
It characterized in that the content is provided for each category,
The content classification unit analyzes the content using at least one of a text mining technique learned to classify text included in the text through a natural language processing function and a machine learning technique learned to classify an image,
The content classification unit receives platform information and reference category information for providing content from a consumer, generates a learning data set using the content included in the platform information, and generates an artificial intelligence classification engine learned through the learning data set. Content management system to create.

Images