KR102622849B1 - Korean Wave content recommendation system - Google Patents

Abstract

The present invention relates to a Korean Wave content recommendation system implemented to enable repetitive learning and directing of Korean Wave content by analyzing the Korean Wave content that a user has watched and recommending content similar to the Korean Wave content that the user has watched. It is a personal terminal used by an individual user. , a service provision terminal where a dedicated application for receiving Korean Wave content learning and directing services is installed; and a content recommendation server unit that analyzes the Korean Wave content viewed through the service provision terminal and recommends content similar to the Korean Wave content viewed.

Description

{Korean Wave content recommendation system}

The present invention relates to a Korean Wave content recommendation system, and more specifically, a Korean Wave content recommendation system implemented to enable repeated learning and directing of Korean Wave content by analyzing the Korean Wave content that a user has watched and recommending content similar to the Korean Wave content that the user has watched. It's about.

The Korean Wave refers to the phenomenon in which Korean popular culture gained mass popularity, especially in Asia, when Korean television dramas were exported to China in 1996 and pop songs became known two years later. After 2000, there was a preference for not only popular culture such as dramas, pop songs, and movies, but also Korean-related products such as kimchi, red pepper paste, ramen, and home appliances. In a comprehensive sense, all of these phenomena are referred to as the Korean Wave.

Currently, the only way to obtain information about various Korean Wave contents such as music, dramas, movies, cosmetics, and baby products in China is to search for titles or categories on services specialized for specific contents. The Asian market, including China, is very large and is expected to continue to grow rapidly in the future. Although it is possible to target this market through Korean Wave content, there is a limitation in that it is still not easy to obtain information for purchasing Korean Wave content and various goods and services, causing inconvenience.

Meanwhile, the above-mentioned background technology is technical information that the inventor possessed for deriving the present invention or acquired in the process of deriving the present invention, and cannot necessarily be said to be known technology disclosed to the general public before filing the application for the present invention. .

Korean Patent No. 10-1758695 (announced on July 19, 2017)

One aspect of the present invention provides a Korean Wave content recommendation system implemented to enable repetitive learning and directing of Korean Wave content by analyzing Korean Wave content that a user has watched and recommending content similar to the Korean Wave content that the user has watched.

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 Korean Wave content recommendation system according to an embodiment of the present invention is a personal terminal used by an individual user, and includes a service provision terminal in which a dedicated application for receiving Korean Wave content learning and directing services is installed; and a content recommendation server unit that analyzes the Korean Wave content viewed through the service provision terminal and recommends content similar to the Korean Wave content viewed.

In one embodiment, the content recommendation server unit collects viewing history of Korean Wave content and social data of users through the service provision terminal, and extracts social preference information of Korean Wave content by analyzing the collected viewing history and social data. Social preference analysis department; a search unit that uses the social preference information extracted from the social preference analysis unit to provide user-customized multiple search results for multiple types of Korean Wave content in response to a query input from the user; and a recommendation unit that generates and provides a ranking for the Korean Wave content using the social preference information extracted from the social preference analysis unit.

In one embodiment, the content recommendation server unit is provided with a virtual machine that processes actual work for the service provision terminal, generates a random number to generate a temporary password, and sends the temporary password to the previously stored service provision terminal via SMS. When a temporary password is entered through the service provision terminal and the hardware information of the service provision terminal matches hardware information included in pre-stored user information, the connection to the service provision terminal is authenticated, and the service provision terminal is sent. The functions of the virtual machine available in the service provision terminal can be limited according to the connection IP of the service provision terminal or the rank information included in the user information.

In one embodiment, the content recommendation server unit requests and receives an evaluation result text for the authentication processing service from the service provision terminal unit, accumulates and stores the evaluation result text received from the service provision terminal unit, and stores the evaluation result text. Extract the evaluation result text as learning data, learn the learning data with the Word2Vec algorithm, build a neural network to extract context information for the input data, and store in advance a table with ratings for each section of the vector value representing the context information. Input the evaluation result text currently received from the service providing terminal into the neural network to extract the evaluation result vector value, calculate the rating corresponding to the evaluation result vector value in the table, and execute the calculated rating at the service providing terminal. We can guide you through the program.

In one embodiment, the content recommendation server unit may request and receive an evaluation of the service provided by the service provision terminal unit. Here, the service may include a virtualization service, file approval service, smart manager service, and URL automatic redirection service.

The content recommendation server unit may calculate a service rating by analyzing the evaluation result text for the service received from the service providing terminal unit.

For example, the content recommendation server unit can build a neural network that extracts context information for input data. Here, the input data may be evaluation result text.

The content recommendation server unit can accumulate and store the evaluation result text received from the service providing terminal unit, and extract the stored evaluation result text as learning data.

The content recommendation server unit can construct a neural network that learns learning data using the Word2Vec algorithm and extracts context information for input data.

The Word2Vec algorithm may include a neural network language model (NNLM). A neural network language model is basically a neural network consisting of an input layer, projection layer, hidden layer, and output layer. Neural network language models are used to vectorize words. Since the neural network language model is a known technology, a more detailed description will be omitted.

The Word2vec algorithm is for text mining and is an algorithm that determines proximity by looking at the front and back relationships between each word. The Word2vec algorithm is an unsupervised learning algorithm. As the name indicates, the Word2vec algorithm can be a quantitative technique that expresses the meaning of words in vector form. The Word2vec algorithm can express each word as a vector in a space of about 200 dimensions. Using the Word2vec algorithm, you can obtain the vector corresponding to the word for each word. The Word2vec algorithm can enable dramatic improvements in precision in the field of natural language processing compared to other conventional algorithms. Word2vec can learn the meaning of words using the relationships between words and adjacent words in sentences in the input corpus. The Word2vec algorithm is based on an artificial neural network and starts from the premise that words with the same context have close meanings. The Word2vec algorithm learns through text documents, and for one word, other words that appear nearby (about 5 to 10 words before or after it) are taught to the artificial neural network as related words. Because words with related meanings are likely to appear close together in a document, two words may have increasingly closer vectors during repeated learning.

The learning methods of the Word2vec algorithm include the CBOW (Continuous Bag Of Words) method and the skip-gram method. The CBOW method predicts the target word using the context created by surrounding words. The skip-gram method predicts words that may come nearby based on one word. The skip-gram method is known to be more accurate in large datasets.

Therefore, in the embodiment of the present invention, the Word2vec algorithm using the skip-gram method is used. For example, if learning is successfully completed through the Word2vec algorithm, similar words can be located nearby in a high-dimensional space. According to the Word2vec algorithm as described above, the closer the distribution of surrounding words in a learning document is, the more similar the calculated vector values can be, and words with similar calculated vector values can be considered similar. Since the Word2vec algorithm is a known technology, detailed descriptions related to vector value calculation will be omitted.

The content recommendation server unit can pre-store a table in which ratings are given for each section of vector values representing context information, and input the evaluation result text received from the service providing terminal unit into a neural network to extract the evaluation result vector value.

The content recommendation server unit calculates a rating corresponding to the evaluation result vector value from a table that assigns ratings for each section of the vector value representing the context information, and guides the calculated rating through a program executed in the service providing terminal unit. .

In one embodiment, the Korean Wave content recommendation system according to another embodiment of the present invention is a public terminal installed in a multi-use facility and used by an unspecified number of people, and a dedicated application for receiving Korean Wave content learning and directing services is installed. A public use terminal; and a cleaning device that is connected to the public terminal and cleans a display provided at the front of the public terminal.

In one embodiment, the cleaning device includes: a first vertically moving rail extending vertically along one side of the public terminal; a second vertically movable rail opposed to the first vertically movable rail and extending vertically along the other side of the public terminal; a cleaning module that cleans a display provided at the front of the public terminal; One end is connected and engaged with the first vertical movable rail, and the other end is installed on one side of the cleaning module, moves along the first vertical movable rail and is in close contact with the display provided at the front end of the public terminal for cleaning. A first slider that moves the module in the vertical direction and at the same time moves upward to the top of the first vertical movement rail when cleaning of the cleaning module is completed and then rotates to move the cleaning module to the rear end of the public terminal; And one end is installed and engaged with the second vertical movement rail, and the other end is installed on the other side of the cleaning module, and moves along the second vertical movement rail and is in close contact with the display provided at the front end of the public terminal. A second slider that moves the cleaning module up and down, and at the same time, when cleaning of the cleaning module is completed, moves upward to the top of the second vertical movement rail and then rotates to move the cleaning module to the rear end of the public terminal. May include ;.

In one embodiment, the cleaning module is formed in a circular ring shape forming an inner diameter corresponding to the left and right widths of the display provided at the front end of the public terminal and is supported by the first slider and the second slider. Ring-shaped rail; a circular sliding groove extending along the inner peripheral surface of the ring-shaped rail; And one end and the other end are respectively installed and engaged with the circular sliding groove, and when the ring-shaped rail is in close contact with the display provided at the front end of the public terminal, the one end and the other end rotate along the circular sliding groove, respectively, and the public terminal It may include a rotating brush for cleaning the display provided at the front end of the.

In one embodiment, the rotating brush includes a support bar extending such that one end and the other end are respectively disposed in the circular sliding grooves; an extension body installed along the circumference of the support bar in a cylindrical shape so as to be exposed to the top and bottom of the ring-shaped rail; a cover installed to cover the outside of the extended body; A cleaning cloth installed to cover the outside of the cover so that when the support bar rotates along the circular sliding groove, the display provided at the front of the public terminal can be cleaned while rotating together; a drive motor installed at a right angle to the support bar at an inner stop of the extension body; a first bevel gear installed on the drive shaft of the drive motor by shaft coupling; a first shaft installed along the inside of the support bar so that one end faces the first bevel gear and the other end can be disposed on the other end of the support bar seated in the circular sliding groove; a second shaft installed along the inside of the support bar so that the other end faces the first bevel gear and one end is disposed on one end of the support bar seated in the circular sliding groove; a second bevel gear installed at one end of the first shaft and connected to the first bevel gear by gear engagement; a third bevel gear installed on the other end of the second shaft and connected to the first bevel gear by gear coupling; a first transmission gear installed on the other end of the first shaft; a second transmission gear installed at one end of the second shaft; It is installed and meshed with the first transmission gear by a gear combination, and the lower end is exposed to the lower end of the support bar and then connected to the rack gear installed along the lower side of the circular sliding groove by a gear combination, the first transmission gear 1 A first drive gear that is driven to rotate as the transmission gear rotates and moves while rotating along the rack gear; It is installed and meshed with the second transmission gear by a gear combination, and the lower end is exposed to the lower end of the support bar and then connected to the rack gear by a gear combination, and rotates together as the second transmission gear rotates. a second driving gear that is driven and moves while rotating along the rack gear; A first support sphere rotatably connected to the upper part of the other end of the support bar seated in the circular sliding groove, the upper part of which is exposed upward from the support bar and seated on the upper side of the circular sliding groove to support the support bar. ; and a second support rotatably connected to one end of the support bar seated in the circular sliding groove, the upper portion of which is exposed upward from the support bar and seated on the upper side of the circular sliding groove to support the support bar. It may include a sphere;

In one embodiment, the rotating brush includes a rotation guide gear installed on the second shaft by shaft coupling; A ring-type rack gear installed along the inner peripheral surface of the cover while opposing the rotation guide gear and forming a gear mountain along the inner peripheral surface so as to be engaged with the rotation guide gear by gear combination; and at least one rotation guide ring extending along an inner peripheral surface of the cover and seated in a rotation guide groove formed along an outer side of the extended body.

According to one aspect of the present invention described above, repeated learning and directing of Korean Wave content may be possible by analyzing Korean Wave content that a user has watched and recommending content similar to the Korean Wave content that the user has watched.

The effects of the present invention are not limited to the effects mentioned above, and various effects may be included within the scope apparent to those skilled in the art from the contents described below.

1 is a diagram illustrating a schematic configuration of a Korean Wave content recommendation system according to an embodiment of the present invention.
FIG. 2 is a diagram showing the content recommendation server unit of FIG. 1.
Figure 3 is a diagram illustrating a schematic configuration of a Korean Wave content recommendation system according to another embodiment of the present invention.
Figure 4 is a diagram showing a cleaning device according to the present invention.
Figure 5 is a diagram showing the cleaning module of Figure 4.
Figures 6 to 8 are views showing the rotating brush of Figure 5.

The detailed description of the present invention described below refers to the accompanying drawings, which show by way of example specific embodiments in which the present invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the invention. It should be understood that the various embodiments of the present invention are different from one another but are not necessarily mutually exclusive. For example, specific shapes, structures and characteristics described herein may be implemented in one embodiment without departing from the spirit and scope of the invention. Additionally, it should be understood that the location or arrangement of individual components within each disclosed embodiment may be changed without departing from the spirit and scope of the invention. Accordingly, the detailed description that follows is not intended to be taken in a limiting sense, and the scope of the invention is limited only by the appended claims, together with all equivalents to what those claims assert, if properly described. Similar reference numbers in the drawings refer to identical or similar functions across various aspects.

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

1 is a diagram illustrating a schematic configuration of a Korean Wave content recommendation system according to an embodiment of the present invention.

Referring to FIG. 1, the Korean Wave content recommendation system 10 according to an embodiment of the present invention includes a service providing terminal unit 100 and a content recommendation server unit 200.

The service provision terminal unit 100 is a personal terminal used by an individual user, and a dedicated application for receiving Korean Wave content learning and directing services is installed. Using the dedicated application, users can use various Korean Wave content providers (600). ) to include Korean Wave content provided by.

Here, the user terminal 100 may be composed of one or more, and is widely used by the general public, such as desktop computers (PCs), laptops, smart phones, tablet PCs, etc. It is a broad concept that refers to various types of information communication devices and multimedia devices that support wired and wireless networks, such as mobile communication terminals.

And, the network N may include, for example, wireless communication, wired communication, optical ultrasonic waves, or a combination thereof. Body area network (BAN), satellite communication, cellular communication, Bluetooth, Near Field Communication (NFC), Infrared Data Association standard (IrDA), Wireless Fidelity (WiFi), and Worldwide Interoperability for Microwave access (WiMAX) are included in the communication path. Ethernet, Digital Subscriber Line (DSL), Fiber to the Home (FTTH), and Plain Old Telephone Service (POTS) are examples of wired communications that can be included in a communication network. Additionally, a communication network can traverse multiple network topologies and distances. For example, a communication network may include a direct connection, a personal area network (PAN), a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), or any combination thereof. Additionally, it can be done through a low power wide area network including LoRaWAN, NB-Fi, and RPMA. However, the description of the network (N) is not limited to the above-mentioned communication network, and any latest data communication network may be applied.

The content recommendation server unit 200 analyzes Korean Wave content viewed through the service provision terminal unit 100 and recommends content similar to the Korean Wave content viewed.

In one embodiment, the content recommendation server unit 200 is provided with a virtual machine (not shown in the drawing for convenience of explanation) that processes actual work for the service provision terminal unit 100, and generates a random number to create a temporary password. A user generates a password, sends a temporary password via SMS to the pre-stored service provision terminal 100, enters the temporary password through the service provision terminal 100, and has hardware information of the service provision terminal 100 already stored. If it matches the hardware information included in the information, the connection of the service providing terminal 100 is authenticated, and the service providing terminal ( 100), you can set restrictions on the available virtual machine functions.

In one embodiment, the content recommendation server unit 200 requests and receives an evaluation result text for the authentication processing service from the service provision terminal unit 100, and receives the evaluation result text received from the service provision terminal unit 100. Accumulated and stored, the stored evaluation result text is extracted as learning data, the learning data is learned using the Word2Vec algorithm, a neural network is constructed to extract context information for the input data, and a rating is calculated for each section of the vector value representing the context information. The given table is stored in advance, the evaluation result text currently received from the service provision terminal 100 is input into the neural network, an evaluation result vector value is extracted, a rating corresponding to the evaluation result vector value is calculated from the table, and the calculated The rating can be provided through a program run on the service provision terminal 100.

In one embodiment, the content recommendation server unit 200 may request an evaluation of a service provided by the service provision terminal unit 100 and receive input. Here, the service may include a virtualization service, file approval service, smart manager service, and URL automatic redirection service.

The content recommendation server unit 200 may calculate a service rating by analyzing the evaluation result text for the service received from the service provision terminal unit 100.

For example, the content recommendation server unit 200 may construct a neural network that extracts context information for input data. Here, the input data may be evaluation result text.

The content recommendation server unit 200 can accumulate and store the evaluation result text received from the service providing terminal unit 100, and extract the stored evaluation result text as learning data.

The content recommendation server unit 200 can learn learning data using the Word2Vec algorithm to build a neural network that extracts context information about input data.

The Word2Vec algorithm may include a neural network language model (NNLM). A neural network language model is basically a neural network consisting of an input layer, projection layer, hidden layer, and output layer. Neural network language models are used to vectorize words. Since the neural network language model is a known technology, a more detailed description will be omitted.

The Word2vec algorithm is for text mining and is an algorithm that determines proximity by looking at the front and back relationships between each word. The Word2vec algorithm is an unsupervised learning algorithm. As the name indicates, the Word2vec algorithm can be a quantitative technique that expresses the meaning of words in vector form. The Word2vec algorithm can express each word as a vector in a space of about 200 dimensions. Using the Word2vec algorithm, you can obtain the vector corresponding to the word for each word. The Word2vec algorithm can enable dramatic improvements in precision in the field of natural language processing compared to other conventional algorithms. Word2vec can learn the meaning of words using the relationships between words and adjacent words in sentences in the input corpus. The Word2vec algorithm is based on an artificial neural network and starts from the premise that words with the same context have close meanings. The Word2vec algorithm learns through text documents, and for one word, other words that appear nearby (about 5 to 10 words before or after it) are taught to the artificial neural network as related words. Because words with related meanings are likely to appear close together in a document, two words may have increasingly closer vectors during repeated learning.

The learning methods of the Word2vec algorithm include the CBOW (Continuous Bag Of Words) method and the skip-gram method. The CBOW method predicts the target word using the context created by surrounding words. The skip-gram method predicts words that may come nearby based on one word. The skip-gram method is known to be more accurate in large datasets.

Therefore, in the embodiment of the present invention, the Word2vec algorithm using the skip-gram method is used. For example, if learning is successfully completed through the Word2vec algorithm, similar words can be located nearby in a high-dimensional space. According to the Word2vec algorithm as described above, the closer the distribution of surrounding words in a learning document is, the more similar the calculated vector values can be, and words with similar calculated vector values can be considered similar. Since the Word2vec algorithm is a known technology, detailed descriptions related to vector value calculation will be omitted.

The content recommendation server unit 200 may store in advance a table in which ratings are given for each section of the vector value representing the context information, and input the evaluation result text received from the service providing terminal unit 100 into the neural network to provide the evaluation result vector value. It can be extracted.

The content recommendation server unit 200 calculates a rating corresponding to the evaluation result vector value from a table that assigns ratings for each section of the vector value representing the context information, and runs a program that executes the calculated rating in the service providing terminal unit 100. You can guide through it.

The Korean Wave content recommendation system 10 according to an embodiment of the present invention, which has the above-described configuration, analyzes the Korean Wave content that the user has watched and recommends content similar to the Korean Wave content that the user has watched, thereby repeatedly learning and directing the Korean Wave content. This may be possible.

FIG. 2 is a diagram showing the content recommendation server unit of FIG. 1.

Referring to FIG. 2 , the content recommendation server unit 200 includes a social preference analysis unit 210, a search unit 220, and a recommendation unit 230.

The social preference analysis unit 210 collects viewing history and social data of users through the service provision terminal 100 for Korean Wave content, and analyzes the collected viewing history and social data to provide social preference information for Korean Wave content. Extract.

The search unit 220 uses the social preference information extracted from the social preference analysis unit 210 to provide user-customized multiple search results for multiple types of Korean Wave content in response to a query input from the user.

The recommendation unit 230 uses the social preference information extracted from the social preference analysis unit 210 to generate and provide rankings for Korean Wave content.

The content recommendation server unit 200, which has the above-described configuration, extracts social taste information from Korean users' social data regarding Korean Wave content and uses this to provide user-customized multiple search results and rankings for Korean Wave content. , can improve search satisfaction by providing optimized search results to users entering query terms, provide highly reliable information about various types of Korean Wave content, and rank the latest trends in Korean Wave using social data. can be reflected in

In addition, according to the present invention, by providing user-customized multiple search results for Korean Wave content, rankings, and information about Korean Wave content by translating them into the user's language, it is possible to search for Korean Wave content in the user's native language such as English, Chinese, or Thai. It is possible to easily check rankings and maximize user satisfaction by utilizing social taste information of Korean users, which is difficult for users to access on their own.

Figure 3 is a diagram illustrating a schematic configuration of a Korean Wave content recommendation system according to another embodiment of the present invention.

Referring to FIG. 3, the Korean Wave content recommendation system 20 according to another embodiment of the present invention includes a service provision terminal unit 100, a content recommendation server unit 200, a public use terminal 300, and a cleaning device 400. ) includes.

Here, since the service providing terminal unit 100 and the content recommendation server unit 200 are the same as the components in FIG. 1, their description will be omitted to avoid duplication of explanation.

The public terminal 300 is a multimedia terminal such as a kiosk for tourists who have entered the Republic of Korea and are not yet familiar with the local situation or unfamiliar with domestic applications. It is a public terminal installed in a multi-use facility and used by an unspecified number of people. A dedicated application is installed to provide Korean Wave content learning and directing services.

The cleaning device 400 is installed connected to the public terminal 300 and cleans the display 310 provided at the front of the public terminal 300.

The Korean Wave content recommendation system 20 according to another embodiment of the present invention, which has the configuration described above, allows foreigners who are not familiar with the local situation in Korea to enjoy Korean Wave content using the public terminal 300. there is.

Figure 4 is a diagram showing a cleaning device according to the present invention.

Referring to FIG. 4, the cleaning device 400 includes a first vertical movement rail 410, a second vertical movement rail 420, a cleaning module 430, a first slider 440, and a second slider 450. Includes.

The first vertical movement rail 410 is formed to extend vertically up and down along one side of the public terminal 300.

The second vertical movement rail 420 is formed to face the first vertical movement rail 410 and extend vertically along the other side of the public terminal 300.

The cleaning module 430 cleans the display 310 provided at the front of the public terminal 300.

The first slider 440 has one end engaged and connected to the first vertical movement rail 410 and the other end installed on one side of the cleaning module 430, so that it moves along the first vertical movement rail 410 and is used as a public terminal. The cleaning module 430 is moved up and down while in close contact with the display 310 provided at the front of 300, and at the same time, when cleaning of the cleaning module 430 is completed, as shown in (b) of FIG. Likewise, it moves upward to the top of the first vertical moving rail 410 and then rotates to move the cleaning module 430 to the rear end of the public terminal 300.

The second slider 450 has one end engaged and connected to the second vertical movement rail 420 and the other end installed on the other side of the cleaning module 430, so that it moves along the second vertical movement rail 420 and is used as a public terminal. The cleaning module 430 is moved up and down while in close contact with the display 310 provided at the front of 300, and at the same time, when cleaning of the cleaning module 430 is completed, as shown in (b) of FIG. Likewise, it moves upward to the top of the second vertical moving rail 420 and then rotates to move the cleaning module 430 to the rear end of the public terminal 300.

The cleaning device 400 having the above-described configuration ensures that the public terminal 300 used by an unspecified number of people is always kept clean, thereby improving the durability of the device and preventing the spread of infectious diseases in advance. there is.

Figure 5 is a diagram showing the cleaning module of Figure 4.

Referring to FIG. 5, the cleaning module 430 includes a ring-shaped rail 431, a circular sliding groove 432, and a rotating brush 500.

The ring-shaped rail 431 is formed in a circular ring shape forming an inner diameter corresponding to the left and right widths of the display 310 provided at the front end of the public terminal 300, and is used to connect the first slider 440 and the second slider ( It is supported by 450, and components such as a circular sliding groove 432 and a rotating brush 500 are installed.

The circular sliding groove 432 extends along the inner peripheral surface of the ring-shaped rail 431 so that both ends of the rotating brush 500 are connected to each other and can rotate inside the ring-shaped rail 431.

The rotating brush 500 is installed with one end and the other end engaged with the circular sliding groove 432, and when the ring-shaped rail 431 is in close contact with the display 310 provided at the front end of the public terminal 300, one end and The other ends rotate along the circular sliding grooves 432 to clean the display 310 provided at the front end of the public terminal 300.

The cleaning module 430 having the above-described configuration ensures that the public terminal 300 used by an unspecified number of people is always kept clean using the rotating brush 500 that rotates in multiple directions, thus improving the durability of the device. Not only can it improve, but it can also prevent the spread of infectious diseases.

Figures 6 to 8 are views showing the rotating brush of Figure 5.

6 to 8, the rotating brush 500 includes a support bar 501, an extended body 502, a cover 503, a cleaning cloth 504, a drive motor 505, and a first bevel gear 506. ), first shaft 507, second shaft 508, second bevel gear 509, third bevel gear 510, first transmission gear 511, second transmission gear 512, first It includes a driving gear 513, a second driving gear 514, a first support sphere 515, and a second support sphere 516.

The support bar 501 is formed to extend so that one end and the other end are respectively disposed in the circular sliding grooves 432.

The extension body 502 is installed along the circumference of the support bar 501 in a cylindrical shape so as to be exposed to the upper and lower ends of the ring-shaped rail 431.

The cover 503 is installed to cover the outside of the extended body 502.

The cleaning cloth 504 rotates together with the support bar 501 when it rotates along the circular sliding groove 432, so that the display 310 provided at the front of the public terminal 300 can be cleaned. It covers the outside and is installed so that it can be attached and detached using a detachable means such as Velcro.

The drive motor 505 is installed at a right angle to the support bar 501 at the inner middle of the extension body 502 and drives the first bevel gear 506 to rotate.

The first bevel gear 506 is installed on the drive shaft of the drive motor 505 by shaft coupling to rotate the second bevel gear 509 and the third bevel gear 510.

The first shaft 507 is located on the inside of the support bar 501 so that one end faces the first bevel gear 506 and the other end can be disposed on the other end of the support bar 501, which is seated in the circular sliding groove 432. It is installed according to

The second shaft 508 is located on the inside of the support bar 501 so that the other end faces the first bevel gear 506 and one end is disposed at one end of the support bar 501, which is seated in the circular sliding groove 432. It is installed according to

The second bevel gear 509 is installed at one end of the first shaft 507 and is connected to the first bevel gear 506 by gear engagement.

The third bevel gear 510 is installed on the other end of the second shaft 508 and is connected to the first bevel gear 506 by gear engagement.

The first transmission gear 511 is installed at the other end of the first shaft 507.

The second transmission gear 512 is installed at one end of the second shaft 508.

The first driving gear 513 is installed and connected to the first transmission gear 511 by gear coupling, and as shown in FIG. 8, the lower end is exposed to the lower end of the support bar 501 and has a circular sliding groove ( 432), it is connected and connected to the rack gear (R) installed along the lower side by a gear combination, and is rotated together as the first transmission gear 511 rotates and moves while rotating along the rack gear (R).

The second drive gear 514 is installed and engaged with the second transmission gear 512 by gear coupling, and as shown in FIG. 8, the lower end is exposed to the lower end of the support bar 501 and is then connected to the rack gear (R). ) is connected and installed by engaging gears, and is rotated together as the second transmission gear 512 rotates and moves while rotating along the rack gear (R).

Here, the first driving gear 513 and the second driving gear 514 form an inclination angle so as to be engaged with the gear mountain of the rack gear (R) forming an inclined surface, as shown in (b) of FIG. 8. It would be desirable to form a gear mountain that

The first support sphere 515 is rotatably connected to the upper part of the other end of the support bar 501 seated in the circular sliding groove 432, and the upper part is exposed upward from the support bar 501 to form a circular sliding groove ( It is seated on the upper side of 432 and supports the support bar 501.

The second support sphere 516 is rotatably connected to one end of the support bar 501 seated in the circular sliding groove 432, and the upper part is exposed upward from the support bar 501 to form a circular sliding groove ( It is seated on the upper side of 432 and supports the support bar 501.

The rotating brush 500 having the above-described configuration may further include a rotation guiding gear 517, a ring-type rack gear 518, and at least one rotation guiding ring 519.

The rotation guide gear 517 is installed on the second shaft 508 by axial coupling.

The ring-type rack gear 518 is installed along the inner peripheral surface of the cover 503 while opposing the rotation guide gear 517, and forms a gear mountain along the inner peripheral surface so that it can be engaged with the rotation guide gear 517 by gear combination. It is rotated by the rotation induction gear 517 to rotate and drive the cover 503.

At least one rotation guide ring 519 extends along the inner peripheral surface of the cover 503 and is seated in the rotation guide groove 502 formed along the outer side of the extended body 502.

The rotating brush 500 having the above-described configuration can effectively clean the display 310 provided at the front of the public terminal 300 by rotating along the inside of the ring-shaped rail 431 and rotating on its own. there is.

The above-described embodiments are for illustrative purposes, and those of ordinary skill in the technical field to which the above-described embodiments belong can easily transform them into other specific forms without changing the technical idea or essential features of the above-described embodiments. You will be able to understand that Therefore, the above-described embodiments should be understood in all respects as illustrative and not restrictive. For example, each component described as unitary may be implemented in a distributed manner, and similarly, components described as distributed may also be implemented in a combined form.

The scope sought to be protected through this specification is indicated by the patent claims described later rather than the detailed description above, and should be interpreted to include the meaning and scope of the claims and all changes or modified forms derived from the equivalent concept. .

10, 20: Korean Wave content recommendation system
100: Service provision terminal
200: Content recommendation server unit
300: Public use terminal
400: cleaning device

Claims (2)

A personal terminal used by an individual user, which includes a service provision terminal where a dedicated application for receiving Korean Wave content learning and directing services is installed; and
It includes a content recommendation server unit that analyzes Korean Wave content viewed through the service provision terminal and recommends content similar to the Korean Wave content viewed,
The content recommendation server unit,
It is provided with a virtual machine that processes actual work for the service provision terminal, generates a random number to generate a temporary password, sends the pre-stored temporary password to the service provision terminal by SMS, and sends the temporary password through the service provision terminal. is input, and if the hardware information of the service providing terminal matches the hardware information included in the pre-stored user information, the connection of the service providing terminal is authenticated, and the connection IP or user information included in the service providing terminal is processed. Limits the functions of virtual machines available at the service provision terminal according to rank information,
The content recommendation server unit,
Request and receive an evaluation result text for the authentication processing service from the service providing terminal, accumulate and store the evaluation result text received from the service providing terminal, extract the stored evaluation result text as learning data, and Word2Vec Build a neural network that learns learning data using an algorithm to extract context information for the input data, stores in advance a table with ratings for each section of the vector value representing the context information, and stores the information currently received from the service providing terminal in the neural network. By inputting the evaluation result text, the evaluation result vector value is extracted, a rating corresponding to the evaluation result vector value is calculated from a table, and the calculated rating is guided through a program executed in the service providing terminal,
The content recommendation server unit,
Requests and inputs an evaluation of the service provided through the service provision terminal,
The above service is,
Includes virtualization service, file approval service, smart manager service, and URL automatic redirection service.
The content recommendation server unit,
The evaluation result text for the service received from the service provision terminal is analyzed to calculate the service rating,
The content recommendation server unit,
Accumulating and storing the evaluation result text received from the service providing terminal, extracting the stored evaluation result text as learning data,
The content recommendation server unit,
A neural network is built to extract context information about input data by learning the training data using the Word2Vec algorithm.
A public terminal installed in a multi-use facility and used by an unspecified number of people, in which a dedicated application for providing Korean Wave content learning and directing services is installed; And a cleaning device installed connected to the public terminal to clean the display provided at the front of the public terminal,
The cleaning device is,
a first vertically moving rail extending vertically along one side of the public terminal; a second vertically movable rail opposed to the first vertically movable rail and extending vertically along the other side of the public terminal; a cleaning module that cleans a display provided at the front of the public terminal; One end is connected and engaged with the first vertical movable rail, and the other end is installed on one side of the cleaning module, moves along the first vertical movable rail and is in close contact with the display provided at the front end of the public terminal for cleaning. A first slider that moves the module in the vertical direction and at the same time moves upward to the top of the first vertical movement rail when cleaning of the cleaning module is completed and then rotates to move the cleaning module to the rear end of the public terminal; And one end is installed and engaged with the second vertical movement rail, and the other end is installed on the other side of the cleaning module, and moves along the second vertical movement rail and is in close contact with the display provided at the front end of the public terminal. A second slider that moves the cleaning module up and down, and at the same time, when cleaning of the cleaning module is completed, moves upward to the top of the second vertical movement rail and then rotates to move the cleaning module to the rear end of the public terminal. Contains ;,
The cleaning module is,
a ring-shaped rail formed in the shape of a circular ring forming an inner diameter corresponding to the left and right widths of the display provided at the front end of the public terminal and supported by the first slider and the second slider; a circular sliding groove extending along the inner peripheral surface of the ring-shaped rail; And one end and the other end are respectively installed and engaged with the circular sliding groove, and when the ring-shaped rail is in close contact with the display provided at the front end of the public terminal, the one end and the other end rotate along the circular sliding groove, respectively, and the public terminal Includes a rotating brush for cleaning the display provided at the front end of
The rotating brush is,
a support bar extending such that one end and the other end are respectively disposed in the circular sliding grooves; an extension body installed along the circumference of the support bar in a cylindrical shape so as to be exposed to the top and bottom of the ring-shaped rail; a cover installed to cover the outside of the extended body; A cleaning cloth installed to cover the outside of the cover so that when the support bar rotates along the circular sliding groove, the display provided at the front of the public terminal can be cleaned while rotating together; a drive motor installed at a right angle to the support bar at an inner stop of the extension body; a first bevel gear installed on the drive shaft of the drive motor by shaft coupling; a first shaft installed along the inside of the support bar so that one end faces the first bevel gear and the other end can be disposed on the other end of the support bar seated in the circular sliding groove; a second shaft installed along the inside of the support bar so that the other end faces the first bevel gear and one end is disposed on one end of the support bar seated in the circular sliding groove; a second bevel gear installed at one end of the first shaft and connected to the first bevel gear by gear engagement; a third bevel gear installed on the other end of the second shaft and connected to the first bevel gear by gear coupling; a first transmission gear installed on the other end of the first shaft; a second transmission gear installed at one end of the second shaft; It is installed and meshed with the first transmission gear by a gear combination, and the lower end is exposed to the bottom of the support bar and then connected to the rack gear installed along the lower side of the circular sliding groove by a gear combination, the first transmission gear 1 A first drive gear that is driven to rotate as the transmission gear rotates and moves while rotating along the rack gear; It is installed and meshed with the second transmission gear by a gear combination, and the lower end is exposed to the lower end of the support bar and then connected to the rack gear by a gear combination, and rotates together as the second transmission gear rotates. a second driving gear that is driven and moves while rotating along the rack gear; A first support sphere rotatably connected to the upper part of the other end of the support bar seated in the circular sliding groove, the upper part of which is exposed upward from the support bar and seated on the upper side of the circular sliding groove to support the support bar. ; and a second support rotatably connected to one end of the support bar seated in the circular sliding groove, the upper portion of which is exposed upward from the support bar and seated on the upper side of the circular sliding groove to support the support bar. A Korean Wave content recommendation system including a specification.
delete