KR102568875B1 - Server for providing service for recommending mentor and lecture and method for operation thereof - Google Patents

Abstract

Various embodiments of the present invention relate to a server for recommending mentors and lectures to a mentee and an operation method thereof.
The processor according to an embodiment of the present invention provides a first screen including a menu area related to mentoring and a menu area related to video tutoring to a user device through a communication interface, and a specific mentee who logs in to a website using the user device When the mentoring application in the mentoring-related menu area is selected by the account: i) Check the first binary image generated based on the answers entered by the specific mentee account for all of the predetermined mentee type test questions and ii) using an artificial intelligence model for similar image search, determining a plurality of first binary images having a similarity with a first binary image of a predetermined first value or higher among pre-stored binary images of all mentee accounts, iii) A mentor recommendation list including a specific mentor account with the highest rating among mentor accounts selected a predetermined number of times or more by a plurality of mentee accounts corresponding to a plurality of first binary images is sent to the user device through a communication interface It can be characterized by providing.

Description

Server providing mentor recommendation service and lecture recommendation service and its operating method {SERVER FOR PROVIDING SERVICE FOR RECOMMENDING MENTOR AND LECTURE AND METHOD FOR OPERATION THEREOF}

Various embodiments of the present invention relate to a server for recommending mentors and lectures to a mentee and an operation method thereof.

With the development of communication means, extracurricular classes, which were conducted offline, are changing to a trend that is conducted online (eg, a website or application). By conducting classes online, you can reduce unnecessary and wasted costs.

Patent Publication No. 10-2010-0107179 (published on October 05, 2010) Patent Publication No. 10-2016-0072526 (published on June 23, 2016)

A server and its operating method according to various embodiments of the present invention may analyze the learning type of a mentee account, provide a mentor recommendation list suitable for the corresponding learning type, and recommend lectures using various information registered in the mentee account A list can be provided.

The technical problems to be achieved in the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the description below. You will be able to.

According to an embodiment, a server that processes a request received from a user device, provides requested information to the user device, and supports a website that provides a mentor recommendation service and a lecture recommendation service includes a communication interface, a processor, and a memory operatively connected to the processor, wherein the memory, when executed, causes the processor to display a first screen including a menu area related to mentoring and a menu area related to video tutoring through the communication interface. and when a mentoring application in the mentoring-related menu area is selected by a specific mentee account logged into the website using the user device: the specific mentee account for all of the predetermined mentee type test questions A first binary image generated based on the input answer is checked, and an artificial intelligence model for similar image search is used to determine the first binary image and a predetermined image among pre-stored binary images of all mentee accounts. Determining a plurality of first binary images having a similarity of a first value or more, and selecting a specific score having the highest rating among mentor accounts selected more than a predetermined number of times by a plurality of mentee accounts corresponding to the plurality of first binary images When a mentor recommendation list including a mentor account is provided to the user device through the communication interface, and a specific subject in the video tutoring related menu area is selected by the specific mentee account, a plurality of subjects corresponding to the specific subject A first recommended lecture list including a first recommended lecture most frequently selected from a plurality of first mentee accounts and a second recommended lecture most frequently selected from a plurality of second mentee accounts among lectures is provided to the user through the communication interface. It may store instructions for the device to provide.

According to various embodiments of the present invention, a mentor account suitable for a specific mentee account is recommended using mentor accounts selected by other mentee accounts similar to the learning type of the specific mentee account, and friend information registered in the specific mentee account, school information, It is possible to provide a reliable and cost-effective mentor/lecture recommendation service by recommending lectures suitable for a specific mentee account using grade information.

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

Also other aspects as described above, features and benefits of certain preferred embodiments of the present invention will become more apparent from the following description taken in conjunction with the accompanying drawings.
1 shows a block diagram of an electronic device and network according to various embodiments of the present invention.
FIG. 2 is a flowchart illustrating a method of providing a mentor recommendation list and a recommended lecture list through a web site providing a video mentoring service and a video tutoring service, by an electronic device, according to an exemplary embodiment.
3A to 3D are diagrams illustrating examples for an electronic device to provide a mentor recommendation list, according to an embodiment.
4A to 4D are diagrams illustrating embodiments for providing a list of recommended lectures by an electronic device, according to an embodiment.
5A to 5D are diagrams for explaining an embodiment in which an electronic device classifies a learning type of a mentee account, according to an embodiment.
6A and 6B are diagrams for explaining an embodiment of a mentoring program provided by an electronic device, according to an embodiment.
It should be noted that throughout the drawings, like reference numbers are used to show the same or similar elements, features and structures.

Hereinafter, various embodiments of this document will be described with reference to the accompanying drawings. Examples and terms used therein are not intended to limit the technology described in this document to specific embodiments, and should be understood to include various modifications, equivalents, and/or substitutes of the embodiments. In connection with the description of the drawings, like reference numerals may be used for like elements. Singular expressions may include plural expressions unless the context clearly dictates otherwise. In this document, expressions such as "A or B" or "at least one of A and/or B" may include all possible combinations of the items listed together. Expressions such as "first," "second," "first," or "second," may modify the corresponding components regardless of order or importance, and are used to distinguish one component from another. It is used only and does not limit the corresponding components. When a (e.g., first) element is referred to as being "(functionally or communicatively) coupled to" or "connected to" another (e.g., second) element, that element refers to the other (e.g., second) element. It may be directly connected to the component or connected through another component (eg, a third component).

In this document, "configured (or configured to)" means "suitable for," "having the ability to," "changed to," depending on the situation, for example, hardware or software. ," can be used interchangeably with "made to," "capable of," or "designed to." In some contexts, the expression "device configured to" can mean that the device is "capable of" in conjunction with other devices or components. For example, the phrase "a processor configured (or configured) to perform A, B, and C" may include a dedicated processor (eg, embedded processor) to perform the operation, or by executing one or more software programs stored in a memory device. , may mean a general-purpose processor (eg, CPU or application processor) capable of performing corresponding operations.

Electronic devices according to various embodiments of the present document include, for example, a smart phone, a tablet PC, a mobile phone, a video phone, an e-book reader, a desktop PC, a laptop PC, a netbook computer, a workstation, a server, a PDA, and a PMP. It may include at least one of a portable multimedia player, an MP3 player, a medical device, a camera, or a wearable device. A wearable device may be in the form of an accessory (e.g. watch, ring, bracelet, anklet, necklace, eyeglasses, contact lens, or head-mounted-device (HMD)), integrated into textiles or clothing (e.g. electronic garment); In some embodiments, the electronic device may include, for example, a television, a digital video disk (DVD) player, Audio, refrigerator, air conditioner, vacuum cleaner, oven, microwave, washing machine, air purifier, set top box, home automation control panel, security control panel, media box (e.g. Samsung HomeSync ^TM , Apple TV ^TM , or Google TV ^TM ) , a game console (eg, Xbox ^TM , PlayStation ^TM ), an electronic dictionary, an electronic key, a camcorder, or an electronic picture frame.

In another embodiment, the electronic device may include various types of medical devices (e.g., various portable medical measuring devices (such as blood glucose meter, heart rate monitor, blood pressure monitor, or body temperature monitor), magnetic resonance angiography (MRA), magnetic resonance imaging (MRI), CT (computed tomography), imager, or ultrasonicator, etc.), navigation device, global navigation satellite system (GNSS), EDR (event data recorder), FDR (flight data recorder), automobile infotainment device, marine electronic equipment (e.g. navigation devices for ships, gyrocompasses, etc.), avionics, security devices, head units for vehicles, industrial or home robots, drones, ATMs in financial institutions, point of sale (POS) in stores of sales), or IoT devices (eg, light bulbs, various sensors, sprinkler devices, fire alarms, thermostats, street lights, toasters, exercise equipment, hot water tanks, heaters, boilers, etc.). According to some embodiments, the electronic device may be a piece of furniture, a building/structure or a vehicle, an electronic board, an electronic signature receiving device, a projector, or various measuring devices (eg, water, electricity, gas, radio wave measuring device, etc.). In various embodiments, the electronic device may be flexible or a combination of two or more of the various devices described above. An electronic device according to an embodiment of the present document is not limited to the aforementioned devices. In this document, the term user may refer to a person using an electronic device or a device using an electronic device (eg, an artificial intelligence electronic device).

Referring to FIG. 1 , an electronic device 101 in a network environment 100 in various embodiments is described. The electronic device 101 may include a bus 110, a processor 120, a memory 130, an input/output interface 150, a display 160, and a communication interface 170. In some embodiments, the electronic device 101 may omit at least one of the components or may additionally include other components. The aforementioned communication interface 170 may be replaced with a communication unit, a transceiver, and the like in the present invention. Memory 130 may correspond to a database.

1 illustrates an electronic device according to an embodiment of the present invention, and detailed descriptions will be made later in this document.

FIG. 2 illustrates a method for an electronic device (eg, the electronic device 101 of FIG. 1 ) to provide a mentor recommendation list and a recommended lecture list through a website providing video mentoring service and video tutoring service, according to an embodiment. It is a flow chart to explain. The web site may refer to an online platform providing a video mentoring service and a video tutoring service.

3A to 3D are diagrams illustrating an example for the electronic device 101 to provide a mentor recommendation list, according to an embodiment, and FIGS. 4A to 4D are diagrams showing an electronic device 101 according to an embodiment. It is a diagram showing an embodiment for providing a list of recommended lectures.

According to an embodiment, the electronic device 101 communicates with a user device (eg, the electronic device 102 of FIG. 1) (eg, a smartphone or a laptop computer) through a communication network, and executes a plurality of actions by the user device 102. It may be a server that provides an application composed of screens or a web site composed of a plurality of web pages. The electronic device 101 may provide the user device 102 with a source code that enables the user device 102 to display each execution screen of a dedicated application or website providing a video mentoring service and a video tutoring service, and , the user device 102 may receive the source code and display an execution screen requested by the user of the user device 102 through the dedicated application or a web browser.

In operation S401, according to an embodiment, the electronic device 101 (eg, the processor 120 of FIG. 1 ) displays a first screen including a menu area related to mentoring and a menu area related to video tutoring to a communication interface (eg, the processor 120 of FIG. 1 ). It can be provided to the user device 102 through the communication interface 170 of 1). For example, referring to FIG. 3A , a menu area 501 related to mentoring including items for requesting a mentoring service and a menu area 502 related to video tutoring including items for requesting a video tutoring service are provided. One screen 500 may be provided to the user device 102 . The mentoring-related menu area 501 and the video tutoring-related menu area 502 can be expanded as the mentee account selects the corresponding item. Hereinafter, the provision of specific objects by the electronic device 101 to the user device 102 means that the user device 102 provides source codes corresponding to specific objects to the user device so that the user device 102 can display the specific objects on the web browser. (102).

In operation S403, according to an embodiment, the electronic device 101 (eg, the processor 120 of FIG. 1) displays a menu area related to mentoring by a specific mentee account logged in to the website using the user device 102. When the mentoring application in 501 is selected, a first binary image generated based on answers input by a specific mentee account for all predetermined mentee type test questions may be checked. For example, referring to FIG. 3A , the electronic device 101 confirms that a specific item (eg, one month to increase self-esteem) in the mentoring-related menu area 501 is selected by a specific mentee account, or selects the specific item. After selecting and completing the payment for the corresponding cost, you can confirm that you have chosen to apply for mentoring.

According to an embodiment, when a user registers as a member of the website according to the present invention, the user has a mentee account corresponding to the student, a guardian account corresponding to the student's guardian, or a mentor corresponding to the teacher. ) You can register a user on the website by selecting one of the accounts and registering as a member. When the user completes membership registration with the mentee account, the electronic device 101 may provide predetermined mentee type test questions to the user device 102 corresponding to the mentee account, and the mentee may provide answers to the test questions. It can be written and provided to the electronic device 101 . For example, referring to FIG. 3B , the electronic device 101 may provide predetermined mentee type test questions (eg, concentration test questions) 510 to the user device 102 corresponding to a specific mentee account. and answers input by a specific mentee account can be obtained from the user device 102 . The electronic device 101 may classify the learning type of a specific mentee account based on answers input by the specific mentee account for the mentee type test questions. A specific embodiment of classifying the learning type will be described later with reference to FIGS. 5A to 5D.

According to an embodiment, the electronic device 101 may generate a first binary image based on answers input by a specific mentee account for all predetermined mentee type test questions. For example, referring to FIG. 3C , when there are 16 test questions 510 and an answer to each question can be selected as A, B, C, or D, the electronic device 101 provides a mentee account This input designates answer A as '00', answer B as '01', answer C as '10', and answer D as '11' to obtain a 4x8 pixel first binary An image 520 may be generated. The electronic device 101 may store the generated first binary image 520 together with binary images of other mentee accounts in a memory (eg, the memory 130 of FIG. 1 ).

In operation S405, according to an embodiment, the electronic device 101 (eg, the processor 120 of FIG. 1 ) uses an artificial intelligence model for similar image retrieval to select one binary from pre-stored binary images of all mentee accounts. A plurality of first binary images having a similarity to the image 520 and a predetermined first value or higher may be determined. The artificial intelligence model may use a convolutional neural network-based image retrieval (CNN) algorithm. The similarity can have a value between 0 and 1. The closer the similarity is to 0, the more similar it is to the first binary image 520, and the closer the similarity is to 1, the more similar it is to the first binary image 520. . The electronic device 101 compares the first binary image 520 with each of the pre-stored binary images corresponding to each of all the mentee accounts using the artificial intelligence model, and obtains a predetermined first value (eg, 0.8). A plurality of first binary images having the above degree of similarity may be determined. The predetermined first value may be selected by a manager of the electronic device 101 .

In operation S407, according to an embodiment, the electronic device 101 (eg, the processor 120 of FIG. 1 ) selects a mentor selected more than a predetermined number of times by a plurality of mentee accounts corresponding to the plurality of first binary images. A mentor recommendation list including a specific mentor account having the highest rating among accounts may be provided to the user device 102 through the communication interface 170 .

For example, referring to FIG. 3D , the electronic device 101 may check a plurality of mentee accounts corresponding to a plurality of determined first binary images, and a predetermined number of times (eg: 5 times) among the selected mentor accounts, a specific mentor account 531 having the highest rating may be identified, and a mentor recommendation list 530 including the identified specific mentor account 531 may be provided to the user device 102 . can According to an embodiment, the specific mentor account 531 may include a thumbnail image of a specific mentor and user information about the specific mentor.

According to one embodiment, the number of selections for the mentor account may be counted when the mentee account pays the mentoring service fee for the mentor account. The predetermined number of times may be selected by a manager of the electronic device 101 .

According to an embodiment, each mentee account may register a rating for the corresponding mentor account after completing the mentoring process.

According to one embodiment, the mentor recommendation list 530 may be displayed adjacent to the right side of the mentoring related menu area 501 .

The reason for performing operations S403 to S407 is that prior to a specific mentee selecting a mentor without prior information, a mentor with the highest rating among mentors selected by other mentees similar to the specific mentee's learning type is recommended to the specific mentee. , To provide a mentoring service suitable for the specific mentee.

In operation S409, according to an embodiment, the electronic device 101 (eg, the processor 120 of FIG. 1) further adds additional mentor accounts by using the second binary image corresponding to the confirmed specific mentor account 531. The mentor recommendation list 530 including the list may be provided to the user device 102 .

According to an embodiment, the electronic device 101 may check the second binary image generated based on the answers input by the specific mentor account 531 for all predetermined mentor type test questions. When a user completes membership registration with a mentor account, the electronic device 101 may provide predetermined mentor type test questions to other user devices corresponding to the mentor account (eg, the electronic device 104 of FIG. 1), and , the corresponding mentor may prepare answers to the test questions and provide them to the electronic device 101 . The electronic device 101 may generate a second binary image based on answers input by a specific mentee account for all predetermined mentee type test questions. A method of generating the first binary image 520 of operation S403 may be used as a method of generating the second binary image. The electronic device 101 may classify the teaching type of the specific mentor account 531 based on the answers input by the specific mentor account 531 to the mentor type test questions. The electronic device 101 may store binary images of mentor accounts in a memory (eg, the memory 130 of FIG. 1 ).

According to an embodiment, the electronic device 101 selects a plurality of second binary images having a similarity of a predetermined second value or more to the second binary image from among binary images of all mentor accounts by using an image similarity search algorithm. can decide The method of determining the plurality of second binary images may use the method of determining the plurality of first binary images of operation S405.

According to an embodiment, the electronic device 101 may provide the user device 102 with the mentor recommendation list 530 further including a plurality of mentor accounts corresponding to the plurality of second binary images. The reason for performing operation S409 is to recommend a specific mentor account 531 according to operation S407, while recommending other mentor accounts similar in teaching method to the specific mentor account 531 to a specific mentee, so that while suitable for the specific mentee, To recommend a variety of mentors.

In operation S411, according to an embodiment, the electronic device 101 (eg, the processor 120 of FIG. 1) selects a specific subject within the video tutoring related menu area 502 by a specific mentee account. The first recommended lecture list including the first recommended lecture most selected from a plurality of first mentee accounts and the second recommended lecture most selected from a plurality of second mentee accounts among a plurality of lectures corresponding to the communication It can be provided to the user device through the interface 170. The electronic device 101 may check a specific subject selected by a specific mentee account through a user interface for searching for lectures in the video tutoring related menu area 502 . For example, referring to FIGS. 3A and 4A , when the mentee account selects an elementary video tutoring item in a menu area 502 related to video tutoring on the first screen 500, the electronic device 101 displays a video in elementary video tutoring. A lecture search user interface 600 for searching for lectures may be provided to the user device 102, and a subject selection item 601 and a lecture time selection item 602 included in the search user interface 600 , and information inputted through the textbook information input item 603 can be confirmed. According to an embodiment, the search user interface 600 may be included in the image tutoring related menu area 502 .

According to an embodiment, the electronic device 101 (eg, the processor 120 of FIG. 1 ), when a specific subject in the video tutoring related menu area 502 is selected by a specific mentee account, as a friend to the specific mentee account. A plurality of second mentee accounts having the same school information and grade information as the first recommended lecture selected the most from the plurality of first mentee accounts, which are pre-registered accounts, and school information and grade information pre-registered in a specific mentee account A first recommended lecture list including the most selected second recommended lectures from may be provided to the user device 102 .

According to one embodiment, each mentee account can add (friend register) other mentee accounts (eg, classmates) in the website at the time of membership registration or after membership registration, and also provide school information and Grade information may be stored (registered) in the electronic device 101 .

According to one embodiment, the number of selections for the recommended lecture may be counted when the mentee account pays for the lecture for the recommended lecture. For example, referring to FIG. 4A , in response to a specific subject 620 (eg, Korean language) being selected by a specific mentee account through the subject selection item 601 included in the search user interface 600, The electronic device 101 may check a plurality of lectures provided in Korean subjects of elementary school video tutoring, and among the plurality of lectures, a first recommended lecture 611 most selected from the plurality of first mentee accounts and the plurality of lectures The first recommended lecture list 610 including the most selected second recommended lectures 612 from the second mentee accounts of the user device 102 may be provided. According to an embodiment, the first recommended lecture list 610 may be displayed adjacent to a right side of a menu area 502 related to video tutoring including a search user interface 600 .

According to an embodiment, the electronic device 101 (eg, the processor 120 of FIG. 1 ) provides a first mentor account providing a first recommended lecture 611 or a second mentor account providing a second recommended lecture 612 . If at least one of the mentor accounts matches the specific mentor account 531, the mentor recommendation list 530 and the first recommended lecture list 610 are set so that the specific mentor account 531 and the corresponding recommended lecture are highlighted in the same color. It can be provided to the user device 102 . For example, referring to FIG. 4B , when a first recommended lecture 611 is provided by a first mentor account (not shown) and a second recommended lecture 612 is provided by a specific mentor account 531 , The electronic device 101 selects a mentor recommendation list 530 and a first recommended lecture list 610 so as to highlight 604 the specific mentor account 531 and the second recommended lecture 612 in the same color (eg, yellow). ) to the user device 102 .

The reason for performing the S411 operation is that adolescent students value a sense of belonging, so the most selected lecture (ie, the first recommended lecture) by friends registered to a specific student (specific mentee account) is recommended, and the same lecture as the specific student is recommended. This is to provide a video tutoring service suitable for the specific student by recommending the most selected lecture (ie, the second recommended lecture) according to the school and grade level to the specific student.

In operation S413, according to an embodiment, after the specific subject 620 is selected, the electronic device 101 (eg, the processor 120 of FIG. 1) additionally sets a specific lecture time for the specific subject 620. In response to being selected, the first recommended lecture list 610 may be updated. For example, referring to FIG. 4C , after a specific subject 620 (eg Korean language) is selected, a specific lecture time ( 621) (eg, 14:00 to 16:00) is additionally selected, the electronic device 101 selects a first recommended lecture 611 and a second recommended lecture 612 from the first recommended lecture list 610. may be removed, and at least one lecture available for a specific lecture time 621 may be determined from among a plurality of lectures corresponding to the specific subject 620 . Thereafter, the electronic device 101 selects a third recommended lecture 613 most selected from the plurality of first mentee accounts and a fourth recommended lecture most selected from the plurality of second mentee accounts among the at least one lecture. The first recommended lecture list 610 may be updated to include 614 .

In operation S415, according to an embodiment, the electronic device 101 (eg, the processor 120 of FIG. 1) returns to the specific subject 620 after the specific subject 620 and the specific lecture time 621 are selected. The first recommended lecture list 610 may be updated in response to additional input of specific textbook information. For example, referring to FIG. 4D , textbook information in the search user interface 600 after a specific subject 620 (eg Korean) and a specific lecture time 621 (eg 14:00 to 16:00) are selected. In response to additional input of specific textbook information 622 (eg, textbook name 'A', author 'B', publisher 'C') by a specific mentee account through the input item 603, the electronic device 101 Removes the third recommended lecture 613 and the fourth recommended lecture 614 from the first recommended lecture list 610, and one or more lectures adopting the same textbook information as the specific textbook information 622 from among the at least one lecture can determine them. Thereafter, the electronic device 101 displays a fifth recommended lecture 615 most selected from the plurality of first mentee accounts and a sixth recommended lecture most selected from the plurality of second mentee accounts among the one or more lectures. The first recommended lecture list 610 may be updated to include 616 . The above-described first recommended lectures 611 to sixth recommended lectures 616 may be different from each other or at least partially the same.

The reason for performing S413 operation and S415 operation is that when a specific mentee changes a condition related to a subject (eg, subject, time, textbook), lectures corresponding to the changed condition are recommended to the specific mentee as soon as the condition is changed, This is to recommend various lectures suitable for the specific mentee.

5A to 5D are diagrams for explaining an embodiment in which an electronic device (eg, the electronic device 101 of FIG. 1 ) classifies a learning type of a mentee account, according to an embodiment.

The electronic device 101 provides predetermined mentee type test items (eg, the test items 510 of FIG. 3B ) to a user device (eg, the electronic device 102 of FIG. 1 ) corresponding to a specific mentee account. and answers entered by a specific mentee account may be obtained from the user device 102 . The electronic device 101 may classify the learning type of a specific mentee account based on answers input by the specific mentee account for the mentee type test questions. For example, the electronic device 101 analyzes the answers to the test questions 510 and classifies the learning type of the specific mentee account into four categories (eg, learning tendency, learning willingness, learning style, and learning behavior). 5A to 5D for specific classification forms within each category.

6A and 6B are diagrams for explaining an embodiment of a mentoring program provided by an electronic device (eg, the electronic device 101 of FIG. 1 ) according to an embodiment.

Each mentor account can prepare a 52-week mentoring program by referring to the learning type of the mentee account by classifying it into four categories (e.g., self-esteem enhancement, career vision, learning coaching, and time planning), and each category may be conducted as a 13-week course. For a specific mentoring process, refer to FIG. 6A. After that, each of the mentor accounts may conduct an additional emotional coaching process with the student corresponding to the mentee account after completing the 52-week mentoring program. For a detailed emotion coaching process, refer to FIG. 6B.

According to an embodiment, a server that processes a request received from a user device, provides requested information to the user device, and supports a website that provides a mentor recommendation service and a lecture recommendation service includes a communication interface, a processor, and a memory operatively connected to the processor, wherein the memory, when executed, causes the processor to display a first screen including a menu area related to mentoring and a menu area related to video tutoring through the communication interface. and when a mentoring application in the mentoring-related menu area is selected by a specific mentee account logged into the website using the user device: the specific mentee account for all of the predetermined mentee type test questions A first binary image generated based on the input answer is checked, and an artificial intelligence model for similar image search is used to determine the first binary image and a predetermined image among pre-stored binary images of all mentee accounts. Determining a plurality of first binary images having a similarity of a first value or more, and selecting a specific score having the highest rating among mentor accounts selected more than a predetermined number of times by a plurality of mentee accounts corresponding to the plurality of first binary images When a mentor recommendation list including a mentor account is provided to the user device through the communication interface, and a specific subject in the video tutoring related menu area is selected by the specific mentee account, a plurality of subjects corresponding to the specific subject A first recommended lecture list including a first recommended lecture most frequently selected from a plurality of first mentee accounts and a second recommended lecture most frequently selected from a plurality of second mentee accounts among lectures is provided to the user through the communication interface. It may store instructions for the device to provide. The plurality of first mentee accounts are accounts registered as friends in advance in the specific mentee account, and the plurality of second mentee accounts have the same school information and grade information as those previously registered in the specific mentee account. accounts may have.

delete

According to an embodiment, the instructions include: the processor checks a second binary image generated based on an answer input by the specific mentor account for all predetermined mentor type test items, and the image similarity search algorithm Using , a plurality of second binary images having a similarity to the second binary image and a predetermined second value or higher are determined among binary images of all mentor accounts, and a plurality of binary images corresponding to the plurality of second binary images. The mentor recommendation list further including mentor accounts of may be provided to the user device.

According to an embodiment, the mentor recommendation list may be displayed adjacent to the right side of the mentoring related menu area, and the first recommended lecture list 610 may be displayed adjacent to the right side of the video tutoring related menu area.

According to an embodiment, the instructions may cause the processor to determine whether at least one of a first mentor account providing the first recommended lecture or a second mentor account providing the second recommended lecture matches the specific mentor account. In this case, the mentor recommendation list and the first recommended lecture list may be provided to the user device so that the specific mentor account and the corresponding recommended lecture are highlighted in the same color.

According to an embodiment, the instructions may cause the processor to select the first recommended lecture in the first recommended lecture list in response to an additional selection of a specific lecture time for the specific subject after the specific subject is selected. and removing the second recommended lecture, determining at least one lecture available at the specific lecture time from among the plurality of lectures, and determining the most selected lecture from the plurality of first users among the at least one lecture. The list of first recommended lectures may be updated to include 3 recommended lectures and a fourth recommended lecture most selected from the plurality of second mentee accounts.

According to an embodiment, the instructions may be performed by the processor in the first recommended lecture list in response to additional input of specific textbook information for the specific subject after the specific subject and the specific lecture time are selected. removing the third recommended lecture and the fourth recommended lecture, determining one or more lectures adopting the same textbook information as the specific textbook information among the at least one lecture available at the specific lecture time, and the one or more lectures Among them, the first recommended lecture list may be updated to include the fifth recommended lecture most selected from the plurality of first mentee accounts and the sixth recommended lecture most selected from the plurality of second mentee accounts. there is.

In addition, an embodiment of the present invention may further include the following features.

According to an embodiment, the electronic device 101 of the present invention is intended for a user who does not properly use a video mentoring service and/or a video tutoring service, but wants to fill time by simply accessing an online environment where a plurality of users are connected. Further classification and/or judging features may be proposed. This is a kind of ghost accessor, that is, access to an online platform (e.g., video mentoring service and/or video tutoring service), but actually properly participating in the video mentoring service and/or video tutoring service on the online platform. It can be seen as an embodiment for finding a person who has significance only in attendance, not in existence. For example, there is a case where a picture including the user's appearance (appearance) is placed in front of the camera of the user device, or an image of the user's appearance (appearance) is reproduced. The European visitor may be referred to as a non-participating user, a non-participating visitor, and a non-active participant.

For example, a web page and/or a mobile app related to the online platform of the present invention may be operated and/or managed through the electronic device 101 . Meanwhile, the web page and / or mobile app is executed in the user device, and the user can use and / or control it. Also, the electronic device 101 may be implemented as a server, and the user device may be implemented as a portable terminal.

For example, the electronic device 101 may receive information on a plurality of apps (applications) installed on the user device from the user device, and the information on the plurality of apps may be received from the user device. It may include the name, app description (or app guide), category, capacity, usage time (eg average usage time, cumulative usage time), etc.

For example, the electronic device 101 determines whether a similar app corresponding to the mobile app for the online platform of the present invention is installed in the user device 101 based on the information about the plurality of apps. can do.

In this case, similar apps may be defined as apps having the same at least one of the name and category of the apps. Also, similar apps in the present invention may include apps that provide (and/or service) at least two of a non-face-to-face service, a mentoring service, and a video tutoring service.

Also, the electronic device 101 may check how many similar apps are installed in the user device. Also, the electronic device 101 may compare the number of similar apps installed on the user device with a predetermined reference value. In this case, the reference value may be adjusted (and/or reset) in consideration of the degree of similarity described below.

In addition, an embodiment of the present invention may further include the following features.

For example, the electronic device 101 determines whether the user is a user who has retaken a course within a predetermined period of time by using an image of the user captured through a 2D camera of the user device (eg, a first course image). can do.

For example, the electronic device 101 operates the user device while each execution screen of a dedicated application (= mobile app) and/or website providing a video mentoring service and/or video tutoring service is executed in the user device. Course images (eg, first enrollment images) captured by the user may be collected.

In addition, while the electronic device 101 is executing each execution screen of a dedicated application (= mobile app) and/or website providing a video mentoring service and/or a video tutoring service, the other user devices are executed. It is possible to collect lecture images (eg, existing lecture images) taken by each other user of the copy in use.

For example, the electronic device 101 extracts texture features and/or shape features of an object (user) in collected first course images (and/or existing course images). A database indexed to a corresponding image may be constructed by processing according to a criterion for merging and converting the processing result into an index according to a criterion for merging.

For example, the electronic device 101 may process an object of collected lecture images (eg, first lecture images and/or existing lecture images). This is to label an object based on an image without depending on other text information and to provide a search result based on similarity of objects in the image. To this end, the electronic device 101 may extract features of the collected lecture images and index feature information of the lecture images for search efficiency. More specifically, the electronic device 101 may detect (interest point detection) a feature region of the pupil images.

The feature region refers to a descriptor of a feature of the course images for determining whether or not the same or similar between course images (eg, first course images and/or existing course images), that is, extracting a feature descriptor. refers to the main area For example, the feature region may be a contour line included in the pupil images, a corner such as a corner among the contour lines, a blob distinguished from the surrounding region, a region that is invariant or covariant according to deformation of the pupil images, or darker than the surrounding brightness. or poles with bright features, and patches (pieces) of pupil images or entire frames of pupil images may be targeted.

Also, the electronic device 101 may extract a feature descriptor from a feature region (Descriptor Extraction). The feature descriptor is a vector value representing features of the student images (eg, first student images and/or previous student images). Such a feature descriptor may be calculated using the position of a feature region of a corresponding image, or brightness, color, sharpness, gradation, scale, or pattern information of a feature region. For example, a feature descriptor may convert a brightness value, a change value of brightness, or a distribution value of a feature region into a vector for calculation. According to an embodiment, the feature descriptor for the course images is not only a local descriptor based on the feature region as above, but also a global descriptor, a frequency descriptor, a binary descriptor, or a binary descriptor. It can be expressed as a neural network descriptor. More specifically, the feature descriptor converts and extracts brightness, color, sharpness, gradient, scale, pattern information, etc. of all of the images taken, or each of the regions obtained by dividing the images according to an arbitrary criterion, or each of the feature regions into vector values. May contain global descriptors. For example, the feature descriptor is a frequency descriptor that converts the number of pre-classified specific descriptors included in course images, the number of included global features such as a conventionally defined color table into vector values, and extracts each frequency descriptor. Binary descriptor, neural network layer that extracts whether descriptors are included or whether the size of each element value constituting the descriptor is larger or smaller than a specific value in bit units and converts it to an integer type for use may include a neural network descriptor that extracts image information used for learning or classification in According to an embodiment, a feature information vector extracted from pupil images may be converted into a low-dimensional one. For example, feature information extracted through an artificial neural network corresponds to high-dimensional vector information, and it is appropriate to convert it into a low-dimensional vector within an appropriate range in consideration of resources required for search. To this end, the electronic device 101 extracts texture features (ie, texture features) and shape features from the collected student images, merges vector values of the features, and expresses the image as a single descriptor. . The feature texture feature may be extracted using a Gabor filter, and the shape feature may be extracted using a HOG filter. Afterwards, the generated feature information vector may be indexed to a corresponding image. An operation of extracting a texture feature, calculating a vector of the texture feature, extracting a shape feature, and calculating a vector of the shape feature will be described later through [Equation 1] and [Equation 2] below. .

For example, the electronic device 101 may pre-process an enrollment image (eg, a first enrollment image and/or an existing enrollment image) of a user. Unlike the subsequent image processing, the pre-processing of the course image may change the scale, size, or resolution of the course image itself according to a preset format for retrieval. According to an embodiment, the electronic device 101 may convert a student image or an object (user) in the student image into grayscale. The electronic device 101 may extract texture features and shape features from the pupil image, and since the features are not dependent on color values, converting them into gray scales in which only saturation values and contrast values exist is required for subsequent processing. This is because the amount of resources can be reduced.

For example, the electronic device 101 may extract a texture feature by applying a Gabor filter to the user in the pupil image. More specifically, the electronic device 101 may transform the pupil image into a frequency space and perform Gabor filtering to extract a texture feature. Texture in an image, that is, texture information, has been studied for a long time as one of the important visual characteristics representing the characteristics of the image. Texture features of these images can be used as key low-level descriptors in extracting labels from images, indexing and abstracting extracted labels. In addition, the texture features of the image can be important for content-based search in tile or textile databases. The Gabor filter is an algorithm used to extract a feature vector from an image and corresponds to a bandpass filter (BPF) based on a Gaussian function.

The Gabor filter may extract a 2D vector for a texture feature from an object (user) in the pupil image according to [Equation 1] to [Equation 3] below.

[Equation 1]

[Equation 2]

[Equation 3]

Also, the electronic device 101 may extract a shape feature from an object in a student image. For example, the electronic device 101 may extract the shape features by applying a Histograms of Oriented Gradients (HOG) algorithm. The HOG feature may exist in various versions, but the main concept is an algorithm that calculates local features of an object and extracts shape features of an object from an image using intensity uniform distribution of the features of the object.

For example, the electronic device 101 may extract a low-dimensional vector for a shape feature from an object in a pupil image according to [Equation 4] to [Equation 7] below.

[Equation 4]

[Equation 5]

[Equation 6]

[Equation 7]

Thereafter, the electronic device 101 may calculate a similarity with objects (users) in existing lecture images in the database by merging vectors of the extracted features. According to an embodiment, the electronic device 101 searches a set of feature descriptors of objects in existing course images, and determines whether the existing course images and the user's first course image are the same or similar. can On the other hand, existing lecture images are captured before obtaining the user's first lecture image, and may be stored in the database.

For example, when the electronic device 101 reverse-indexes object information in a plurality of images corresponding to each category on the basis of all categories, feature descriptors of a first course image among the plurality of images The search can be processed in a way to select a specific image that is pointed out the most. Through this search, the electronic device 101 determines whether the distance between the feature descriptor vector value of the object (user) in the specific image and the feature descriptor vector value of the object (user) in the first course image is within a preset threshold value. can do.

For example, the electronic device 101 may calculate a distance value between an object vector in the first student image and an object vector in a specific image according to [Equation 8] below, and based on this, among a plurality of images collected An object in a specific image having a similarity with an object in the first student image and a threshold value or higher may be searched for.

[Equation 8]

For example, the electronic device 101 has a similarity with an object (ie, user) in the first student image among a plurality of images collected for a period of time prior to a predetermined time from the point in time at which the first student image was obtained. If there is an image including an object, a procedure for checking whether the corresponding user is a ghost visitor may be performed.

On the other hand, for convenience of explanation, it is assumed that the time difference between the time when the first lecture video is captured through the user device and the time when the electronic device 101 receives the first lecture video from the user device is '0'. In this case, an ultra-fine time difference for signal transmission and reception may exist, but it is omitted because it is a negligible value.

For example, the electronic device 101 determines the degree of similarity between an object (ie, a user) in the first student image and a first threshold value or higher among a plurality of images collected for a period before a predetermined time from when the first student image was acquired. If there is an image including an object having , the following procedures may be performed. First, the electronic device 101 may determine whether the first threshold value is checked every predetermined period to see whether an image exists. In addition, the electronic device 101 notifies (and/or warns) the mentor when the number of times that the first threshold is checked (existence of the first threshold image) exceeds the predetermined reference number (☜ 1st condition) at each predetermined period. A message may be generated and provided to the mentor through an online platform.

For example, the electronic device 101 determines the degree of similarity between an object (ie, a user) in the first student image and a second threshold value or higher among a plurality of images collected for a period before a predetermined time from the point in time at which the first student image was acquired. If there is an image including an object having (☜ second condition), a message notifying (and/or warning) to the mentor may be generated and provided to the mentor through an online platform (at which time, a message to be checked every predetermined period) may be generated. procedure is omitted). For example, the second threshold may be set to a higher value than the first threshold.

Upon receiving the notification (and/or warning) message, the mentor may determine whether the mentee is actually participating by conducting separate questions and answers to the mentee, the target user. Here, the corresponding mentee may refer to a mentee who is a target of the notification message by satisfying the first condition and/or the second condition. For example, the mentor who has received the notification (and/or warning) message may deliver a question message (for confirmation) to the mentee, the target of observation, through an online platform. That is, the question message may be delivered from the electronic device 101 to the terminal of the mentee to be observed.

For example, if the mentee, the mentor's observation target, does not respond to the question message for a predetermined period of time, the electronic device 101 may determine that the observation target, the mentee, is a ghost visitor.

For example, when a mentee, the mentor's observation target, responds only with a text message (or chatting), message, emoticon, etc., and any one of the first condition or the second condition is satisfied, the electronic device 101 is the observation target It can be determined that the mentee is a ghost visitor.

For example, when the mentee to be observed answers with a voice (in the video closed state), if the first condition and the second condition are satisfied, the electronic device 101 determines that the mentee to be observed is a ghost visitor can judge

For example, when the mentee to be observed responds with video and/or voice (in a video open state), the electronic device 101 determines that the mentee to be observed is not a ghost visitor but a true connecter. can judge

As described above, for the mentee determined to be a ghost visitor, the electronic device 101 may control to give a penalty, such as deducting points on the online platform, restricting access, or disallowing mentoring with a specific mentee.

Meanwhile, a detailed description of an electronic device according to an embodiment of the present invention will be described below with reference to FIG. 1 .

Referring to FIG. 1 , a bus 110 may include circuitry that connects components 110 to 170 to each other and transfers communication (eg, control messages or data) between components. The processor 120 may include one or more of a central processing unit, an application processor, or a communication processor (CP). The processor 120 may, for example, execute calculations or data processing related to control and/or communication of at least one other component of the electronic device 101 .

Memory 130 may include volatile and/or non-volatile memory. The memory 130 may store, for example, commands or data related to at least one other component of the electronic device 101 . According to one embodiment, memory 130 may store software and/or programs 140 . The program 140 may include, for example, a kernel 141, middleware 143, an application programming interface (API) 145, and/or an application program (or “application”) 147, and the like. . At least part of the kernel 141, middleware 143, or API 145 may be referred to as an operating system. Kernel 141, for example, includes system resources (eg, middleware 143, API 145, or application program 147) used to execute operations or functions implemented in other programs (eg, middleware 143, API 145, or application program 147). : The bus 110, the processor 120, or the memory 130, etc.) can be controlled or managed. In addition, the kernel 141 may provide an interface capable of controlling or managing system resources by accessing individual components of the electronic device 101 from the middleware 143, API 145, or application program 147. can

The display 160 may be, for example, a liquid crystal display (LCD), a light emitting diode (LED) display, an organic light emitting diode (OLED) display, a microelectromechanical system (MEMS) display, or an electronic paper display. can include The display 160 may display various types of content (eg, text, image, video, icon, and/or symbol) to the user. The display 160 may include a touch screen, and may receive, for example, a touch, gesture, proximity, or hovering input using an electronic pen or a part of the user's body. The communication interface 170 establishes communication between the electronic device 101 and an external device (eg, the first external electronic device 102 , the second external electronic device 104 , or the server 106 ). can For example, the communication interface 170 may be connected to the network 162 through wireless or wired communication to communicate with an external device (eg, the second external electronic device 104 or the server 106).

Wireless communication is, for example, LTE, LTE-A (LTE Advance), CDMA (code division multiple access), WCDMA (wideband CDMA), UMTS (universal mobile telecommunications system), WiBro (Wireless Broadband), or GSM (Global System for Mobile Communications) may include cellular communication using at least one of the like.

The term "module" used in this document includes a unit composed of hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit, for example. A “module” may be an integrally constructed component or a minimal unit or part thereof that performs one or more functions. A "module" may be implemented mechanically or electronically, for example, a known or future developed application-specific integrated circuit (ASIC) chip, field-programmable gate arrays (FPGAs), or A programmable logic device may be included. At least some of the devices (eg, modules or functions thereof) or methods (eg, operations) according to various embodiments are instructions stored in a computer-readable storage medium (eg, the memory 130) in the form of program modules. can be implemented as When the command is executed by a processor (eg, the processor 120), the processor may perform a function corresponding to the command. Computer-readable recording media include hard disks, floppy disks, magnetic media (e.g. magnetic tape), optical recording media (e.g. CD-ROM, DVD, magneto-optical media (e.g. floptical disks), built-in memory, etc.) A command may include code generated by a compiler or code executable by an interpreter A module or program module according to various embodiments may include at least one or more of the above-described components or , some may be omitted, or may further include other elements.According to various embodiments, operations performed by modules, program modules, or other elements may be executed sequentially, in parallel, iteratively, or heuristically, or at least Some actions may be performed in a different order, omitted, or other actions may be added.

And the embodiments disclosed in this document are presented for explanation and understanding of the disclosed technical content, and do not limit the scope of the present disclosure. Therefore, the scope of the present disclosure should be construed to include all changes or various other embodiments based on the technical spirit of the present disclosure.

Claims (3)

A server that processes a request received from a user device, provides the requested information to the user device, and supports a website that provides a mentor recommendation service and a lecture recommendation service,
transceiver; and a processor; including,
The processor:
Providing a first screen including a menu area related to mentoring and a menu area related to video tutoring to the user device through the transceiver;
㉮ When a mentoring application in the mentoring-related menu area is selected by a specific mentee account logged into the website using the user device:
Checking a first binary image generated based on answers entered by the specific mentee account for all of the predetermined mentee type test questions;
Using an artificial intelligence model for similar image search, determining a plurality of first binary images having a degree of similarity equal to or greater than a predetermined first value to the first binary image among pre-stored binary images of all mentee accounts;
Providing a mentor recommendation list including a specific mentor account having the highest rating among mentor accounts selected a predetermined number of times or more by a plurality of mentee accounts corresponding to the plurality of first binary images to the user device through the transceiver do,
B When a specific subject in the video tutoring related menu area is selected by the specific mentee account:
A first recommended lecture list including a first recommended lecture most selected from a plurality of first mentee accounts and a second recommended lecture most selected from a plurality of second mentee accounts among a plurality of lectures corresponding to the specific subject Control to provide to the user device through the transceiver,
The plurality of first mentee accounts are accounts registered as friends in advance in the specific mentee account, and the plurality of second mentee accounts have the same school information and grade information as those previously registered in the specific mentee account. accounts with
The processor:
Checking a second binary image generated based on answers entered by the specific mentor account for all of the predetermined mentor type test questions;
Using an image similarity search algorithm, determining a plurality of second binary images having a similarity with the second binary image of a predetermined second value or higher among binary images of all mentor accounts;
Control to provide the mentor recommendation list, which further includes a plurality of mentor accounts corresponding to the plurality of second binary images, to the user device;
When at least one of the first mentor account providing the first recommended lecture and the second mentor account providing the second recommended lecture matches the specific mentor account, the specific mentor account and the corresponding recommended lecture are colored the same color. A server that controls to provide the mentor recommendation list and the first recommended lecture list to the user device to be highlighted.
delete According to claim 1,
The processor:
In response to additionally selecting a specific lecture time for the specific subject after the specific subject is selected, the first recommended lecture and the second recommended lecture are removed from the list of first recommended lectures, and the plurality of lectures Determine at least one lecture available at the specific lecture time among them,
Controlling to update the first recommended lecture list to include a third recommended lecture most selected from a plurality of users among the at least one lecture and a fourth recommended lecture most selected from the plurality of second mentee accounts, server.