KR20240131867A - Method for providing training content based on a variety of ai management provider for education - Google Patents

Abstract

In a first embodiment of the present invention, a method for providing educational content based on an artificial intelligence management provider performed by a main server comprises: (a) a step of receiving a question input by a user terminal; (b) a step of the main server classifying the category of the question and transmitting it to a most suitable learning model among a plurality of learning models to output an answer to the question; and (c) a step of providing the outputted answer to the user terminal; wherein each learning model is trained using learning data in which different question data and answer data are paired according to the category, and different characters are matched, and when the user terminal provides the answer, it also provides an image of a character corresponding to the learning model that output the answer.

Description

{METHOD FOR PROVIDING TRAINING CONTENT BASED ON A VARIETY OF AI MANAGEMENT PROVIDER FOR EDUCATION}

The present invention relates to an educational content providing method based on an artificial intelligence management provider, and more specifically, to an educational content providing method in which an artificial intelligence learning model learns questions and answers input in advance, generates the learned questions and answers into a plurality of answer models, classifies categories for questions input by a user terminal, and extracts and provides answers from answer models corresponding to the categories.

As AI (artificial intelligence) technology advances, research is being conducted to utilize AI learning models in various fields.

In particular, the field of education, which provides educational content to users, is the most actively conducting research due to the advantage of being able to provide educational content to multiple students using an AI learning model taught by one educator.

In particular, among educational contents using AI learning models, question-and-answer content, where users (students) ask questions and the educator (AI) provides answers, is considered the most suitable and is receiving attention.

In this regard, conventional question-and-answer style education has been carried out simply by having educators store anticipated questions or similar questions in advance and presenting answers set against the questions received from students.

However, this method has the problem that it reduces the efficiency of question-and-answer learning by providing unclear or incorrect answers when the student's answers are not always consistent and written in a different context or grammar.

The present invention is intended to solve the problems of the prior art as described above, and the purpose of the present invention is to generate multiple answer models from questions and answers learned in advance by an artificial intelligence learning model, and to provide answers to questions input by a user terminal by extracting them from the answer models.

However, the technical tasks that this embodiment seeks to accomplish are not limited to the technical tasks described above, and other technical tasks may exist.

As a technical means for achieving the above-described technical task, in a method for providing educational content based on an artificial intelligence management provider performed by a main server according to a first embodiment of the present invention, the method comprises: (a) a step of receiving a question input by a user terminal; (b) a step of the main server classifying the category of the question and transmitting it to the most suitable learning model among a plurality of learning models to output an answer to the question; and (c) a step of providing the outputted answer to the user terminal; wherein each learning model is trained with learning data in which different question data and answer data are paired according to the category, and different characters are matched, and when the user terminal provides the answer, it also provides an image of a character corresponding to the learning model that output the answer.

In addition, the method further comprises a step of collecting learning data by category before the step (a), transmitting the data to an external server, and training the plurality of learning models through the learning data; wherein the plurality of learning models are built on the external server, and the external server is a server that trains the plurality of learning models so that when question data of a specific category is input from the main server, answer data paired with the question data is output by the learning model corresponding to the specific category.

In addition, the step (b) includes: (b-1) a step of classifying a category for the question by the main server through a pre-learned question classification model; (b-2) a step of transmitting the question and the category value to the external server; (b-3) a step of determining which of the multiple learning models to input the question to by the external server with reference to the category value, and inputting the question to the determined model to output an answer; and (b-4) a step of transmitting the outputted answer to the main server.

Additionally, the above categories include how to use educational content, general conversation, English writing, meeting minutes, and class note organization.

In addition, the learning model for the usage of the educational content receives a question about the usage of the educational content from the user terminal and provides an answer, the learning model for the general conversation receives a question about learning, including a study method, a passing essay, and a passing note, from the user terminal and provides an answer corresponding to the question, and the learning model for English writing receives a question about English writing from the user terminal and provides an English writing class and an English writing correction class.

In addition, the learning model for the English writing provides the ranking of the English writing of the user terminal among all user terminals that performed the English writing for the results of the English writing class and the English writing correction class, and the ranking of the writing is determined based on how many times the learning model corrected words in the sentence input by the user terminal and how many times the user terminal input a request for a writing grammar review.

In addition, when the user terminal repeatedly makes a mistake in the spelling of a specific word or a specific grammar a preset number of times during the English writing class and the English writing correction class, the external server determines that the user terminal needs guidance on a study method and transmits information about the current status to the learning model for the guidance on the study method, and the learning model for the guidance on the study method receives the information about the current status as an input value and outputs an answer about a study method for the spelling of the specific word or the specific grammar as an output value, thereby transmitting the information to the user terminal.

In addition, the answer UI includes 1) a question window for entering a question, 2) an answer window where an answer is provided, and 3) a character display area that displays a character corresponding to a learning model that matches the topic of the question and answer. When a question is entered in the question window, the answer window and character display area are not provided, but when an answer is provided after entering a question, the answer window and character display area are displayed together.

In an educational content providing device based on an artificial intelligence management provider performed by a main server, a memory storing a program regarding a method for providing educational content based on an artificial intelligence management provider; and a processor for executing the program, the method comprising: (a) a step of receiving a question input by a user terminal; (b) a step of the main server classifying the category of the question and transmitting it to a most suitable learning model among a plurality of learning models to output an answer to the question; and (c) a step of providing the outputted answer to the user terminal; wherein each learning model is trained with learning data consisting of different question data and answer data in pairs according to the category, and different characters are matched, and the user terminal, when providing the answer, provides an image of a character corresponding to the learning model that output the answer together.

The present invention can generate questions and answers learned in advance by an artificial intelligence learning model into multiple answer models, and can provide answers to questions input by a user terminal by extracting them from the answer models.

Figure 1 is a structural diagram of an educational content providing method based on an artificial intelligence management provider according to one embodiment of the present invention.
FIG. 2 is a structural diagram of a main server of an educational content providing method based on an artificial intelligence management provider according to one embodiment of the present invention.
FIG. 3 is an exemplary diagram showing the structure of an external server and learning models and characters of an educational content providing method based on an artificial intelligence management provider according to one embodiment of the present invention.
FIGS. 4a and 4b are exemplary diagrams showing an answer UI of an educational content providing method based on an artificial intelligence management provider according to one embodiment of the present invention.
FIG. 5 is a flowchart showing the process of an educational content providing method based on an artificial intelligence management provider according to one embodiment of the present invention.
FIG. 6 is an exemplary diagram showing an image generation model of an educational content providing method based on an artificial intelligence management provider according to one embodiment of the present invention.
FIG. 7 is an exemplary diagram showing a study sharing and Q&A area provided during learning of an educational content provision method based on an artificial intelligence management provider according to one embodiment of the present invention.

Hereinafter, with reference to the attached drawings, embodiments of the present invention will be described in detail so that those skilled in the art can easily practice the present invention. However, the present invention may be implemented in various different forms and is not limited to the embodiments described herein. In addition, in order to clearly describe the present invention in the drawings, parts that are not related to the description are omitted, and similar parts are assigned similar drawing reference numerals throughout the specification.

Throughout the specification, when a part is said to be "connected" to another part, this includes not only the case where it is "directly connected" but also the case where it is "electrically connected" with another element in between. Also, when a part is said to "include" a component, this does not mean that it excludes other components, but rather that it can include other components, unless otherwise stated.

In this specification, the term 'unit' includes a unit realized by hardware, a unit realized by software, and a unit realized using both. In addition, one unit may be realized by using two or more pieces of hardware, and two or more units may be realized by one piece of hardware. Meanwhile, the '~ unit' is not limited to software or hardware, and the '~ unit' may be configured to be in an addressable storage medium and may be configured to reproduce one or more processors. Accordingly, as an example, the '~ unit' includes components such as software components, object-oriented software components, class components, and task components, and processes, functions, properties, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functionality provided within the components and '~sub-components' may be combined into a smaller number of components and '~sub-components' or further separated into additional components and '~sub-components'. In addition, the components and '~sub-components' may be implemented to regenerate one or more CPUs within the device or the secure multimedia card.

The "user terminal" mentioned below may be implemented as a computer or portable terminal that can access a server or other terminal via a network. Here, the computer may include, for example, a notebook, desktop, laptop, VR HMD (e.g., HTC VIVE, Oculus Rift, GearVR, DayDream, PSVR, etc.) equipped with a WEB Browser. Here, the VR HMD includes all of a PC-use (e.g., HTC VIVE, Oculus Rift, FOVE, Deepon, etc.), a mobile-use (e.g., GearVR, DayDream, Storm Magic, Google Cardboard, etc.), a console-use (PSVR), and a Stand Alone model (e.g., Deepon, PICO, etc.) that is implemented independently. Portable terminals are wireless communication devices that ensure portability and mobility, for example, and may include not only smart phones, tablet PCs, and wearable devices, but also various devices equipped with communication modules such as Bluetooth (BLE, Bluetooth Low Energy), NFC, RFID, ultrasonic, infrared, WiFi, and LiFi. In addition, "network" refers to a connection structure that enables information exchange between each node, such as terminals and servers, and includes a local area network (LAN), a wide area network (WAN), the Internet (WWW: World Wide Web), wired and wireless data communication networks, telephone networks, and wired and wireless television communication networks. Examples of wireless data communication networks include, but are not limited to, 3G, 4G, 5G, 3GPP (3rd Generation Partnership Project), LTE (Long Term Evolution), WIMAX (World Interoperability for Microwave Access), Wi-Fi, Bluetooth, infrared, ultrasonic, visible light communication (VLC), and LiFi.

First, the structure of an educational content providing method based on an artificial intelligence management provider according to one embodiment of the present invention will be described with reference to FIG. 1.

According to Fig. 1, an educational content providing method based on an artificial intelligence management provider according to one embodiment of the present invention includes a main server (100), an external server (200), a user terminal (300), and an administrator terminal (400). However, the structure of the present invention is not limited thereto.

The main server (100) receives data on questions and answers from the administrator terminal (400) and performs learning, and can receive questions in the form of text or images from the user terminal (300). The structure of the main server (100) will be described below with reference to FIG. 2.

Referring to FIG. 2, the main server (100) of the educational content providing method based on an artificial intelligence management provider according to one embodiment of the present invention may include a memory (110), a processor (120), and a communication module (130). However, the structure of the main server (100) of the present invention is not limited thereto.

The memory (110) can store at least one of information and data input to the communication module (130), information and data required for functions performed by the processor (120), and data generated according to the execution of the processor (120). The memory (110) should be interpreted as a general term for a nonvolatile storage device that maintains stored information even when power is not supplied and a volatile storage device that requires power to maintain the stored information. In addition, the memory (110) can perform a function of temporarily or permanently storing data processed by the processor (120). The memory (110) can include a magnetic storage media or a flash storage media in addition to a volatile storage device that requires power to maintain stored information, but the scope of the present invention is not limited thereto.

The memory (110) stores an educational content providing program, and receives information entered by the user terminal (300) within the educational content through the processor (120) and links it to the program. The name of the program is set for convenience of explanation, and the name itself does not limit the function of the program.

The processor (120) is configured to execute an educational content providing program stored in the memory (110). The processor (120) may include various types of devices that control and process data. The processor (120) may mean a data processing device built into hardware that has a physically structured circuit to perform a function expressed by a code or command included in the program. In one example, the processor (120) may be implemented in the form of a microprocessor, a central processing unit (CPU), a processor core, a multiprocessor, an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), etc., but the scope of the present invention is not limited thereto.

The processor (120) is configured to perform detailed processes of an educational content providing method based on an artificial intelligence management provider as described below.

The communication module (130) can perform information transmission and reception with an external database or an external device. Here, the external device can be a user terminal (300) and an administrator terminal (400). The communication module (130) can include a device including hardware and software required to transmit and receive signals such as control signals or data signals through wired or wireless connections with other network devices.

The communication module (130) transmits the educational content provision program stored in the memory (110) provided by the processor (120) of the server (100) to an external database or external device so that it can be linked.

The external server (200) will be described with reference to FIG. 3 below.

FIG. 3 is an exemplary diagram showing the structure of an external server (200) of an educational content providing method based on an artificial intelligence management provider according to one embodiment of the present invention and learning models and characters.

According to FIG. 3, the external server (200) of the present invention may be constructed with multiple learning models including a first learning model, a second learning model, a third learning model, and a fourth learning model. However, the structure of the external server (200) is not limited thereto. In addition, the external server (200) may learn multiple learning models so that when question data of a specific category is input from the main server (100), answer data paired with the question data is output by a learning model corresponding to the specific category. In addition, different characters (201) may be provided to match each learning model. When an answer is provided to a question of a user terminal (300), these characters may provide an image of the character (201) together with the learning model that output the answer. Each learning model may be any one of supervised learning, unsupervised learning, and reinforcement learning models, and in the case of a supervised learning model, a label value may be assigned to a pair of question data and answer data and input, thereby allowing the learning model to output a desired output value.

The user terminal (300) may include a smartphone, tablet PC, notebook (laptop), and desktop computer configured with a screen and capable of performing input. However, the user terminal (300) is not limited thereto. The user terminal (300) may transmit a question configured in the form of text or an image to the server (100) and confirm an answer provided by the server (100).

The administrator terminal (400) may include a smartphone, tablet PC, notebook (laptop), and desktop computer configured with a screen capable of performing input. However, the administrator terminal (400) is not limited thereto. The administrator terminal (400) inputs a plurality of questions and answers to the server (100).

The following Figures 4a and 4b are exemplary diagrams showing an answer UI of an educational content providing method based on an artificial intelligence management provider according to one embodiment of the present invention.

According to Fig. 4a, a question window (500) for entering a question can be displayed in one area of the answer UI of the present invention. However, the location of the question window (500) is not limited to Fig. 4a. The user terminal (300) can input "Tell me whether the sentence "PLEASE GIVES MI BYCICLE" is grammatically correct" into the provided question window (500) as in Fig. 4a. Then, the question can be transmitted by inputting the transmission button located in one area of the question window (500).

According to FIG. 4b, a question window (500) for entering a question in one area of the answer UI of the present invention, an answer window (600) for providing an answer, and a character display area for displaying a character (201) corresponding to a learning model that matches the subject of the question and answer can be displayed. However, the positions of the question window (500), the answer window (600), and the character display area are not limited thereto. When the user terminal (300) in FIG. 4a enters a question and presses the transmit button, the main server (100) transmits "PLEASE GIVE ME A BICYCLE." output from the external server (200) to the user terminal (300) as the answer window (600), as shown in FIG. 4b. At this time, the character (201) is displayed adjacent to the answer window (600).

At this time, when a question is entered in the question window (500) as in Fig. 4a, the answer window (600) and the character display area are not provided, but when an answer is provided after entering a question, the answer window (600) and the character display area may be displayed together.

Accordingly, in the answer window (600), the question entered by the user terminal (300) in the question window (500), the answer extracted from the external server (200) through the main server (100), and the character (201) matching the learning model including the answer can be displayed together.

Hereinafter, with reference to FIG. 5, a description will be given of a sequence showing the process of an educational content providing method based on an artificial intelligence management provider according to one embodiment of the present invention.

First, the administrator terminal (400) inputs question data and answer data by category into the main server (100) (S510). Then, the question data and answer data by category collected by the main server (100) are input into the AI engine of the external server (200) to perform learning (S520). Then, the external server (200) constructs the first learning model, the second learning model, the third learning model, and the fourth learning model (S530).

The main server (100) can collect question data and answer data by category from the administrator terminal (400). Here, question data and answer data configured in pairs can be referred to as learning data. The collected category-specific learning data can be transmitted to an external server (200) to perform learning by matching the learning data to a learning model corresponding to the category among multiple learning models. At this time, the categories can include how to use educational content, general conversation, English writing, meeting minutes, and class note organization, but the categories are not limited thereto.

When explained by category, the learning model for how to use educational content receives questions about how to use educational content from a user terminal (300) and provides answers, the learning model for general conversation receives questions about learning, including study methods, passing essays, and passing notes, from a user terminal (300) and provides answers, and the learning model for English writing receives questions about English writing from a user terminal (300) and provides English writing classes and English writing correction classes.

Next, the main server (100) receives a question input by the user terminal (300) (S540). The user terminal (300) can input a question in the question window (500) of the answer UI provided to the user terminal (300) as described in Fig. 4 above and transmit it to the main server (100).

Next, the main server (100) classifies the question category and transmits the question and the category to the external server (200) (S550). The main server (100) can recognize words included in the question received from the user terminal (300), classify the category, and transmit the question and the category to the external server (200).

Next, the external server (200) refers to the category to determine which of the multiple answer models to input the question to, and inputs the question to the determined model to output the answer (S560). The external server (200) refers to the category value to determine which of the multiple learning models to input the question to, and inputs the question to the determined model to output the answer. The output answer can be transmitted to the main server (100).

Next, the answer output by the external server (200) is provided to the user terminal (300) (S570). The main server (100) can receive the answer output from the external server (200) and provide it to the user terminal (300).

Referring to FIG. 6 below, an image generation model of an educational content providing method based on an artificial intelligence management provider according to one embodiment of the present invention will be described.

According to FIG. 6, in the process S510 to S570 of FIG. 5 of the present invention, in response to a question, ① a description of an imagined image is received from a user terminal (300), ② an image generation model corresponding to a learning model generates an image corresponding to the description of the image, and the generated image can be provided to the user terminal (300). Although not shown in FIG. 6, if the image generated by the image generation model is different from the description of the image, the user terminal (300) can request a modification of the image. In addition, if an image identical to the image described by the user terminal (300) is generated, the image can be provided together to another user terminal (300).

Referring to FIG. 7 below, a study sharing and Q&A area provided during learning of an educational content provision method based on an artificial intelligence management provider according to one embodiment of the present invention will be described.

The answer UI of the present invention described above with reference to FIGS. 4A and 4B is a screen provided for questions and answers of a user terminal (300), and FIG. 7 is a screen provided for questions and answers of a user terminal (300) during learning. According to FIG. 7, the screen provided to the user terminal (300) during learning may include a study sharing area (301) and a question-and-answer area (302). In the study sharing area (301), study screens of other user terminals including CAM1, CAM2, ??, CAM9, ??, and CAMn are shared, and a question window (500) is provided in the question-and-answer area (302). When the user terminal (300) has a question while performing learning, the user terminal (300) inputs a question into the question window (500) of the question-and-answer area (302) and transmits it, and the main server (100) can provide an answer output from an external server (200) to the user terminal (300).

As a first additional embodiment of the present invention, a learning model for English writing can provide a ranking of English writing of a user terminal (300) among all user terminals (300) that performed English writing based on the results of English writing classes and English writing correction classes. The ranking of writing can be determined based on how many times the learning model corrected words in sentences input by the user terminal (300) and how many times the user terminal (300) input a request for writing grammar review.

As a second additional embodiment of the present invention, a learning model for English writing can be such that, if a user terminal (300) repeatedly makes a mistake in the spelling of a specific word or a specific grammar more than a preset number of times during an English writing class or an English writing correction class, an external server (200) can determine that the user terminal (300) needs study method guidance and can transmit information about the current status (for example, the spelling of the word OO is incorrect 5 times or more, or the TO infinitive grammar is incorrect 7 times or more) to a learning model for study method guidance. The learning model for study method guidance receives information about the current status as an input value, and outputs an answer about a study method that can solve the problem as an output value, thereby transmitting the information to the user terminal (300). A character regarding grammar correction can appear on the user terminal (300) and the answer can be provided, and if an error in the same grammar or word spelling is detected, another character can appear and provide an answer that provides advice about a study method.

As a third additional embodiment of the present invention, a character to be used by the user terminal (300) can be selected or customized and created from among the characters provided in multiple forms. For example, the user terminal (300) can select one of the set characters consisting of a man, a woman, an animal, etc., or can customize the character by determining the shape of the face, the shape and color of the head, the shape and color of the eyes, the shape of the nose, the shape of the mouth, accessories, etc. to create its own character.

As a fourth additional embodiment of the present invention, it is possible to train the administrator terminal (400) to provide answers with different vocabulary or tones for each specific character. To this end, learning can be performed by inputting different question data and answer data into each learning model. If the vocabulary or tones (i.e., style) of the answer are different from the target, feedback on the answer can be input into the learning model, and re-learning can be performed. According to this repetitive learning, the user terminal (300) can receive answers from characters with a personality matching the category of the question according to the answer style of the character.

For example, when a user terminal (300) asks a question about everyday life or a study method, a friendly tone of voice can be provided as if a friend or senior is explaining something, and when asking a question about English writing or English writing correction, a response can be provided in the tone of a teacher who teaches learning, such as suggesting detailed and accurate writing and correction, and pointing out expressions that are easy to make mistakes in.

As a fifth additional embodiment of the present invention, a learning model for general conversation can analyze a question from a user terminal (300) to collect words included in the question from the user terminal (300), distinguish frequently used words to determine the area of interest of the user terminal (300), and provide an answer to the question from the user terminal (300) tailored to the area of interest.

As a sixth additional embodiment of the present invention, when the user terminal (300) repeatedly inputs a question more than a preset number of times, a notification can be sent to the administrator terminal (400) to check whether the answer to the question of the user terminal (300) is incorrect. This is because the answer to the question input by the user terminal (300) may not be displayed correctly, so the administrator terminal (400) can check and correct the answer.

As an eighth additional embodiment of the present invention, the learning model for English writing can search for and provide sentences similar to the question on the Internet when there is no answer corresponding to the question of the user terminal (300) in the learning data. At this time, the learning model for English writing determines whether the sentence searched for on the Internet has any grammatical errors and provides the sentences.

As a seventh additional embodiment of the present invention, when a user terminal (300) inputs a sentence that is not a question, the main server (100) provides a different answer corresponding to the sentence or determines a question desired by the user terminal (300) from the sentence and provides it in reverse.

For example, if the user terminal (300) inputs "PLEASE GIVES MI BICICLE", a different response such as "That is not a correct sentence" may be provided instead of correcting the sentence. Accordingly, if the user terminal (300) inputs "Tell me the correct grammar", the response "PLEASE GIVE ME A BICYCLE" may be provided.

Or, when "PLEASE GIVES MI BICICLE" is entered, a question may be asked in return, "Can you tell me the correct grammar for "PLEASE GIVES MI BICICLE"?" In this case, if the user terminal (300) enters "yes" or "yes", the answer "PLEASE GIVE ME A BICYCLE" may be provided.

As an eighth additional embodiment of the present invention, the tendency of a user who inputs a question through a user terminal (300) can be analyzed. For example, when a question is input into a preset learning model, a learning model can be trained to output a result value as one of eight tendencies: Creativity, Collaboration, Critical Thinking, Compassion, Sincerity, Passion, Global Citizenship, and Friendship. For example, after the user's question is vectorized, weights for Creativity, Collaboration, Critical Thinking, Compassion, Sincerity, Passion, Global Citizenship, and Friendship can be set for words converted into vectors or vocabulary in a conclusion, and learning can be performed so that the learning model can change these weights by itself to perform learning. Here, a supervised learning model and a reinforcement learning model can be used. And, the level value for each user's tendency can be expressed numerically. The learning model of the external server can provide the output user's tendency and its level value to the main server, and the main server can provide it to the user terminal. The user can objectively understand his or her tendency by checking these indicators. The main server can calculate the average level of the user's questions created during a certain period. The main server can extract questions that have a level that is different from the average level of the user's questions created during a certain period by a preset value or more, and exclude such questions from the data of the user tendency analysis. Accordingly, the main server can increase the accuracy of the user tendency analysis. Afterwards, the main server can complete the user's tendency analysis for a certain period, and then search for mentors (experts) that match the user's tendency in the DB and provide them to the user terminal. For example, if the user's tendency is determined to have a value of level 4 for Passion, the academy instructors who received passionate lecture evaluations from the academy instructor list can be extracted as a mentor list and then provided to the user terminal.

As a ninth additional embodiment of the present invention, a user terminal can perform general conversation, and at this time, an artificial intelligence learning model (a learning model for general conversation) can be trained to conduct a conversation in a manner that suits its own tendencies. For example, for an input sentence of "I'm hungry," the learning model can answer one of the following: 1) a problem-solving type answer: "Then go to a restaurant and eat." 2) an experience-sharing type answer: "I'm hungry too." 3) an emotional answer: "I'm so hungry that I want to stop studying right away." However, since each user has a different tendency and has different friends, each user's tendency to want to receive an answer will also be different. The user can train the learning model to provide an answer that suits his or her own tendencies. For example, if the user likes the output sentence output from an external server and transmitted through the main server after inputting a specific input sentence, the user can provide positive feedback to the learning model by inputting a positive button configured next to the conversation window. However, if the user does not like the output sentence, the user can provide negative feedback by entering a negative button, and the learning model can provide a different answer again. At this time, the external server can set identification information for each user terminal and store in advance which answer is preferred for each identification information based on the input for the positive and negative buttons. After that, when the user asks a specific question, the learning model can output multiple answers, set a score and category (emotional type, problem-solving type, experience-sharing type, etc.) for each answer, and select the answer that the user is most likely to prefer by referring to the history of the positive and negative buttons previously entered by the user. During this process, if the user inputs "In that case, I would just answer that I would be very upset," the learning model can recognize that the phrase "I would answer that" in the sentence indicates a specific answer and remember the answer that the user wants.

An embodiment of the present invention may also be implemented in the form of a recording medium containing computer-executable instructions, such as program modules, that are executed by a computer. The computer-readable medium may be any available medium that can be accessed by a computer, and includes both volatile and nonvolatile media, removable and non-removable media. In addition, the computer-readable medium may include all computer storage media. The computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information, such as computer-readable instructions, data structures, program modules, or other data.

Although the methods and systems of the present invention have been described with respect to specific embodiments, some or all of their components or operations may be implemented using a computer system having a general-purpose hardware architecture.

The above description of the present invention is for illustrative purposes, and those skilled in the art will understand that the present invention can be easily modified into other specific forms without changing the technical idea or essential characteristics of the present invention. Therefore, it should be understood that the embodiments described above are exemplary in all respects and not restrictive. For example, each component described as a single component may be implemented in a distributed manner, and likewise, components described as distributed may be implemented in a combined manner.

The scope of the present invention is indicated by the claims described below rather than the detailed description above, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present invention.

100: Main server 110: Memory
120: Processor 130: Communication Module
200: External server 201: Character
300: User terminal 301: Study sharing area
302: Question and Answer Area 400: Admin Terminal
500: Question window 600: Answer window

Claims (9)

In a method for providing educational content based on an artificial intelligence management provider performed by a main server,
(a) a step of receiving a question input by a user terminal;
(b) a step in which the main server classifies the category of the question and transmits it to the most suitable learning model among multiple learning models to output an answer to the question; and
(c) a step of providing the printed answer to the user terminal;
Including,
Each learning model is trained with learning data consisting of different question data and answer data pairs according to the above categories, and different characters are matched.
The above user terminal provides an educational content providing method based on an artificial intelligence management provider, which provides an image of a character corresponding to the learning model that output the above answer when providing the above answer. In paragraph 1,
Before step (a) above
A step of collecting learning data by the above categories, transmitting it to an external server, and training the multiple learning models through the learning data;
Including, but not limited to,
A method for providing educational content based on an artificial intelligence management provider, wherein the external server has the plurality of learning models built thereon, and the external server is a server that learns the plurality of learning models so that when question data of a specific category is input from the main server, answer data paired with the question data is output by a learning model corresponding to the specific category. In paragraph 1,
Step (b) above,
(b-1) A step in which the main server classifies the category for the question using a pre-learned question classification model;
(b-2) A step of transmitting the above question and the above category value to the external server;
(b-3) a step in which the external server determines which of the multiple learning models to input the question to by referring to the category value, and inputs the question to the determined model to output an answer; and
(b-4) A step of transmitting the printed answer to the main server;
A method for providing educational content based on an artificial intelligence management provider, including: In the third paragraph,
The above categories include methods for providing educational content based on an artificial intelligence management provider, including how to use educational content, general conversation, English writing, meeting minutes, and organizing class notes. In paragraph 4,
The learning model for the usage of the above educational content receives questions about the usage of the educational content from the user terminal and provides answers.
The learning model for the above general conversation receives questions about learning, including study methods, passing notes, and passing notes, from the user terminal, and provides answers corresponding to the questions.
The learning model for the above English writing is an educational content providing method based on an artificial intelligence management provider, which receives questions about English writing from the user terminal and provides English writing classes and English writing correction classes. In paragraph 5,
The learning model for the above English writing is
About the results of the above English writing class and English writing correction class
Among all user terminals that performed the above English writing, the ranking of the above English writing of the user terminal is also provided.
A method for providing educational content based on an artificial intelligence management provider, wherein the ranking of the above writing is determined based on how many words the learning model corrected for the sentences input by the user terminal and how many requests for grammar review of the writing were entered by the user terminal. In paragraph 6,
The learning model for the above English writing is
If the user terminal repeatedly makes a mistake in the spelling of a specific word or a specific grammar more than a preset number of times during the above English writing class and English writing correction class,
The above external server determines that the user terminal needs guidance on how to study,
As a learning model for the above study method guidance, information on the current status is provided.
The learning model for the above study method guidance receives information about the current status as input values,
An educational content providing method based on an artificial intelligence management provider, wherein the method outputs an answer regarding the spelling of a specific word or a study method for a specific grammar as an output value and transmits it to the user terminal. In paragraph 1,
The answer UI includes 1) a question window for entering a question, 2) an answer window where an answer is provided, and 3) a character display area that displays a character corresponding to a learning model that matches the topic of the question and answer.
A method for providing educational content based on an artificial intelligence management provider, wherein when a question is entered in a question window, an answer window and a character display area are not provided, but when an answer is provided after entering a question, the answer window and the character display area are displayed together. In an educational content provision device based on an artificial intelligence management provider performed by a main server,
A memory storing a program for providing educational content based on an artificial intelligence management provider; and
comprising a processor for executing the above program,
The above method
(a) a step of receiving a question input by a user terminal;
(b) a step in which the main server classifies the category of the question and transmits it to the most suitable learning model among multiple learning models to output an answer to the question; and
(c) a step of providing the printed answer to the user terminal;
Including,
Each learning model is trained with learning data consisting of different question data and answer data pairs according to the above categories, and different characters are matched.
The above user terminal is an educational content providing device based on an artificial intelligence management provider that provides an image of a character corresponding to the learning model that output the above answer when providing the above answer.

Images