KR102538341B1 - Artificial intelligence tutoring system with customized learning resource provision function - Google Patents

Abstract

The present invention is an artificial intelligence tutoring system for remotely connecting a learner's first terminal and a teacher's second terminal to support the learner's learning and the teacher's teaching in a non-face-to-face environment, wherein the first and second terminals and While communicating by establishing a network with the web and external servers, based on the solve history of the learners' evaluation questions obtained from the first terminal, the challenge type evaluation item data for each learner and the list data of a group of learners with similar solving histories Extracting, matching the extracted challenge-type evaluation item data and list data to generate random recommendation item information, and mapping the generated recommendation item information to pre-specified curriculum data to improve future learning of the learner and the teacher a control unit configured to further generate customizing information for guiding future teaching, and to output a preset notification signal according to the customizing information; and a notification unit provided in the first and second terminals to visually display on an arbitrary screen according to a notification signal output from the control unit, wherein the challenge type evaluation item data includes an incorrect answer probability exceeding a preset reference value Characterized in that the data consists of evaluation questions having
In a more stable learning environment, there is an effect that allows the progress of the evaluation that can inspire learners' sense of challenge.

Description

Artificial intelligence tutoring system with customized educational material provision function {ARTIFICIAL INTELLIGENCE TUTORING SYSTEM WITH CUSTOMIZED LEARNING RESOURCE PROVISION FUNCTION}

The present invention extracts challenge-type evaluation item data for each learner and list data of a group of learners with similar solving histories based on the solve histories of the learners' evaluation questions, and extracts the extracted challenge-type evaluation item data and list data mutually. Through a configuration that creates recommended item information by matching and provides customized educational materials by mapping pre-designated curriculum data to the generated recommended item information, the progress of the evaluation that can inspire learners’ sense of challenge in a more stable learning environment It is about an artificial intelligence tutoring system with a function of providing customized educational materials.

In general, artificial intelligence (AI) assistants understand and execute the intentions of commands uttered by users, and the convenience of voice interfaces that control peripheral devices is the main feature, whereas AI tutoring systems provide learners with the intervention of teachers and instructors. The main feature is the context-oriented active response that identifies the necessary situation and provides diagnosis and prescription appropriate to the situation.

Currently, the domestic education technology market, which includes technology for artificial intelligence tutoring, is expanding, but its growth rate is low compared to the global market, and the proportion of small businesses is high.

For example, sales are concentrated in a small number of large operators, while sales of small operators, which account for half of the total number of operators, account for only 1.6%, resulting in polarization within the industry. It takes over a business, launches services using artificial intelligence technology and robot technology, and seeks new opportunities by directly discovering and supporting promising edutech startups.

Accordingly, edutech startups are growing in various fields such as customized learning services, game-based learning, foreign language education, and coding education based on their technological prowess. The use of artificial intelligence (AI) to provide

Among these, conventionally commercialized customized learning technologies rely on linkage between learning contents or simply count the number of wrong problems to diagnose weak concepts, so there is a problem in that the diagnosis of learner's learning ability is not sophisticated.

In addition, as the current technology, in the future management of the learner's learning results, the level of understanding (understanding) and propensity by learning area / unit of the learner are reflected as it is, and artificial intelligence based on machine learning or deep learning technology is strengthened. There is an absence of a learning/teaching guide system that has gone through an intelligent learning process and an accurate analysis process.

For example, (a) of FIG. 1 is a picture showing a conventional linear learning path, which has a disadvantage in that all learners must learn the same curriculum.

Therefore, in order to solve the above problems and disadvantages, etc., an algorithm that sequentially recommends appropriate questions and learning contents according to the learner's personal characteristics and environment, such as the LRR (Learning Resource Recommendation) model, etc. Through this, as shown in (b) of FIG. 1, an adaptive learning path capable of efficient learning is achieved by appropriately selecting and providing necessary content based on the learner's level of understanding, thereby achieving a uniformed There is an increasing need for technology that can solve various issues (data sparsity, etc.) arising from the existing learning policy that provided the curriculum, and furthermore, achieve personalized/adaptive learning suitable for each learner's level and needs. am.

Republic of Korea Patent Registration No. 10-2056822 (Title of Invention: Method and Device for Providing Learning Services)

Therefore, the present invention has been devised to solve the above problems, and extracts challenge-type evaluation item data for each learner and list data of a group of learners with similar solving histories based on the solve history of the learners' evaluation questions. and generate recommended item information by matching the extracted challenge-type evaluation item data and list data with each other, and map pre-specified curriculum data to the generated recommendation item information to provide customized educational materials for a more stable learning environment. The purpose is to provide an artificial intelligence tutoring system that has a function of providing customized educational materials that can proceed with an evaluation that can inspire learners' sense of challenge.

In addition, from the learner's point of view, the present invention can achieve learning of unknown parts and new knowledge among existing learned knowledge, can prevent rapid changes in the difficulty of questions at the time of learning, and at the same time, excessively easy or difficult The purpose is to provide an artificial intelligence tutoring system with a function of providing customized educational materials that can enhance students' voluntary participation in learning by appropriately mixing the difficulty level to prevent items from being recommended.

In addition, the present invention effectively estimates the level of understanding of each learner from the viewpoint of the educational platform, and has a function of providing customized educational materials that can contribute to improving the satisfaction of learners and enhancing trust in the educational platform through a configuration that maximizes the level of understanding of each learner. The purpose is to provide an artificial intelligence tutoring system.

However, the technical problem to be achieved in the present invention is not limited to the above-mentioned technical problems, and other technical problems not mentioned will become clear to those skilled in the art from the description below. You will be able to understand.

The present invention, which is a technical means for achieving the above object, is artificial intelligence for supporting the learning of the learner and the teaching of the teacher in a non-face-to-face environment by remotely connecting the first terminal of the learner and the second terminal of the teacher. In the tutoring system, based on the solution history of the learners' evaluation questions obtained from the first terminal while communicating by establishing a network with the first and second terminals, the web, and the external server, data for each learner's challenge type evaluation question , Extracting list data of a group of learners with similar solving histories, generating random recommendation item information by matching the extracted challenge type evaluation item data and list data with each other, and converting the generated recommendation item information into pre-specified curriculum data a control unit for generating further customizing information for guiding future learning of the learner and future teaching of the teacher by mapping to and outputting a preset notification signal according to the customizing information; and a notification unit provided in the first and second terminals to visually display on an arbitrary screen according to a notification signal output from the control unit, wherein the challenge type evaluation item data exceeds a preset reference value. It may be data composed of evaluation questions with a probability of incorrect answers.

In addition, the curriculum data may be data about a curriculum including grade, semester, unit, and chapter.

In addition, the customizing information may include data for at least one customized guide for learning/teaching among recommended evaluation items, recommended contents, and recommended curricula.

In addition, the control unit may include: a data generator for obtaining and converting into data a solution history including at least one of correct answers, incorrect answers, and unsolved questions for the learners' evaluation questions from the first terminal; a database unit for recording the solution history data generated by the data generation unit and storing and managing curriculum data designated in advance by the second terminal or the external server; a first data extractor configured to extract challenge-type evaluation item data by learning a pre-programmed first model based on machine learning based on the solution history data recorded in the database unit; a second data extractor configured to extract the list data by learning a pre-programmed second model based on machine learning based on the solution history data recorded in the database unit; and generating random recommended item information by mutually matching the challenge type evaluation item data and the list data extracted through the first and second data extractors, and providing the generated recommended item information to the curriculum stored in the database unit. Further generating customizing information for guiding future learning of the learner and future teaching of the teacher by mapping to data, and a notification signal output unit configured to output a notification signal corresponding to the customized information.

In addition, the first model of the first data extraction unit applies a collaborative filtering (CF) algorithm, and the second model of the second data extraction unit has a nearest neighbor search (ANN) algorithm. can be applied

In addition, the second data extraction unit embeds the solve history data of the learners in a vector space, receives the solution history data of any one target learner, and lists a group consisting of learners having the most similar solving history. List data for can be extracted.

In addition, the control unit may further include an understanding extraction unit for extracting understanding information for each curriculum of the learners by mutually matching the solution history data recorded in the database unit with curriculum data stored in the database unit. The notification signal output unit may allow the understanding level information extracted by the understanding level extraction unit to be reflected together in the generation of the customization information.

The artificial intelligence tutoring system having a function of providing customized educational materials according to the present invention extracts challenge-type evaluation item data for each learner and list data of a group of learners with similar solving histories based on the solve history of the learners' evaluation questions. and generate recommended item information by matching the extracted challenge-type evaluation item data and list data with each other, and map pre-specified curriculum data to the generated recommendation item information to provide customized educational materials for a more stable learning environment. There is an effect that enables the progress of the evaluation that can inspire learners' sense of challenge.

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

1 is an image showing a comparison between a linear learning path according to the prior art and an adaptive learning path related to the present invention.
2 is a diagram showing an external configuration and usage example of an artificial intelligence tutoring system having a function of providing customized educational materials according to an embodiment of the present invention.
Figure 3 is a block diagram schematically showing the electronic configuration of the artificial intelligence tutoring system.
Figure 4 is a block diagram schematically showing the sub-components constituting the control unit of the artificial intelligence tutoring system according to Figure 3;
5 is an image showing data flow by the control unit according to FIG. 3;
FIG. 6 is a diagram and an image exemplarily illustrating a service architecture of a Learning Resource Recommendation (LRR) model in which the control unit according to FIG. 3 is actually implemented;
7 is an image showing a table in which three scenarios in which the artificial intelligence tutoring system is implemented are classified according to classification elements in relation to the present invention.
8 is an image illustrating a description of a first scenario among three scenarios according to FIG. 7;
9 is an image showing a description of a second scenario among three scenarios according to FIG. 7;
10 is an image illustrating a description of a third scenario among three scenarios according to FIG. 7;

Hereinafter, with reference to the accompanying drawings, embodiments of the present invention will be described in detail so that those skilled in the art can easily carry out the present invention. However, since the description of the present invention is only an embodiment for structural or functional description, the scope of the present invention should not be construed as being limited by the embodiments described in the text. That is, since the embodiment can be changed in various ways and can have various forms, it should be understood that the scope of the present invention includes equivalents capable of realizing the technical idea. In addition, since the object or effect presented in the present invention does not mean that a specific embodiment should include all of them or only such effects, the scope of the present invention should not be construed as being limited thereto.

The meaning of terms described in the present invention should be understood as follows.

Terms such as "first" and "second" are used to distinguish one component from another, and the scope of rights should not be limited by these terms. For example, a first element may be termed a second element, and similarly, a second element may be termed a first element. It should be understood that when an element is referred to as “connected” to another element, it may be directly connected to the other element, but other elements may exist in the middle. On the other hand, when an element is referred to as being “directly connected” to another element, it should be understood that no intervening elements exist. Meanwhile, other expressions describing the relationship between components, such as “between” and “immediately between” or “adjacent to” and “directly adjacent to” should be interpreted similarly.

Singular expressions should be understood to include plural expressions unless the context clearly dictates otherwise, and terms such as “comprise” or “having” refer to a described feature, number, step, operation, component, part, or It should be understood that it is intended to indicate that a combination exists, and does not preclude the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

All terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs, unless defined otherwise. Terms defined in commonly used dictionaries should be interpreted as consistent with meanings in the context of related art, and cannot be interpreted as having ideal or excessively formal meanings unless explicitly defined in the present invention.

1 is an image showing a comparison between a linear learning path according to the prior art and an adaptive learning path related to the present invention, and FIG. 2 is an external view of an artificial intelligence tutoring system having a function of providing customized educational materials according to an embodiment of the present invention. Figure 3 is a block diagram schematically showing the electronic configuration of the artificial intelligence tutoring system, Figure 4 is a schematic diagram of the sub-configuration constituting the control unit of the artificial intelligence tutoring system according to Figure 3 5 is an image showing data flow by the control unit according to FIG. 3, and FIG. 6 is an example of a service architecture of a Learning Resource Recommendation (LRR) model in which the control unit according to FIG. 3 is actually implemented. 7 is an image showing a table in which three scenarios in which the artificial intelligence tutoring system is implemented are classified according to classification elements in relation to the present invention, and FIG. 8 is among the three scenarios according to FIG. 7 An image showing a description of a first scenario, FIG. 9 is an image showing a description of a second scenario among three scenarios according to FIG. 7, and FIG. 10 is a description of a third scenario among three scenarios according to FIG. is an image that represents

As shown in FIGS. 2 and 3, the artificial intelligence tutoring system 100 having a function of providing customized educational materials according to the present invention supports the learning of learners (L) and the teaching of teachers (T) in a non-face-to-face environment In the artificial intelligence tutoring system for tutoring, it can be configured to include a first terminal 110, a second terminal 120, a web 130, an external server 140, a control unit 150, and a notification unit 160 there is.

However, the components shown in FIGS. 2 and 3 are only the minimum configuration necessary for the present invention, and an artificial intelligence tutoring system having more additional components may be implemented.

The first terminal 110 is configured to include various known input devices (not shown) such as a keyboard, a pad, and a mouse. According to a preferred embodiment of the present invention, the first terminal 110 is located on the learner (L) and Provides an input environment in which the solution history for the evaluation questions of ) is input to the web 130, the external server 140, and the control unit 150.

In addition, the second terminal 120 is configured to remotely communicate with the above-described first terminal 110, and may have the same components as the first terminal 110, and according to the present invention, It is located in the teacher T to provide an input environment in which the teacher T can input curriculum data to be described later into the web 130, the external server 140, and the control unit 150.

Here, the first and second terminals 110 and 120 may be configured in plurality, and preferably, a tablet may be applied, but it is not limited thereto, and a PC, a smart phone, and the like may be applied.

Since the configurations of the first and second terminals 110 and 120 correspond to general terminal devices, detailed configurations are not shown in the drawings, and detailed descriptions thereof will be omitted.

The web 130 is an Internet service configured to support various multimedia such as text, graphics, images, sound, and video. According to the present invention, the web 130 is connected to the first and second terminals 110 and 120, It can be configured so that various known educational contents are provided to learners (L) and teachers (T) who respectively use the 2 terminals (110, 120).

Preferably, the external server 140 is configured to correspond to the aforementioned web 130 and forms a network with the first and second terminals 110 and 120, the web 130, and the control unit 150. In conjunction with (130), it performs a function of servicing a program preset in the control unit 150.

Here, the curriculum data may be designated in advance by the external server 140, and the program may be an educational program composed of various data related to education, which is a well-known technology, based on conventional knowledge in the related field. Of course, it can be freely modified and designed by those skilled in the art.

Referring to FIG. 4 , the controller 150 builds a network with the first and second terminals 110 and 120, the web 130, and the external server 140 to obtain data from the first terminal 110 while communicating. Based on the solving history of the evaluation questions of the learners (L), the challenge type evaluation item data for each learner and the list data of a group of learners with similar solving histories are extracted, and the extracted challenge type evaluation item data and list data Customizing information for guiding future learning of the learner (L) and future teaching of the teacher (T) by mapping the generated recommended item information to pre-specified curriculum data. It further generates, but performs a function of outputting a preset notification signal according to the customization information.

More specifically, the control unit 150 obtains a solution history including at least one of correct answers, incorrect answers, and unsolved questions for the evaluation questions of the learners (L) from the first terminal 110 and converts the data into data. generating unit 151; A database unit 152 for recording the solution history data generated by the data generator 151 and storing and managing curriculum data previously specified by the second terminal 120 or the external server 140; a first data extraction unit 153 for learning a pre-programmed machine learning-based first model based on the solution history data recorded in the database unit 152 and extracting the challenge-type evaluation item data; a second data extraction unit 154 for extracting the list data by learning a pre-programmed second model based on machine learning based on the solution history data recorded in the database unit 152; and generating random recommendation item information by mutually matching the challenge type evaluation item data and list data extracted through the first and second data extractors 153 and 154, respectively, and converting the generated recommendation item information into the data. Mapping to the curriculum data stored in the base unit 152 to further generate customized information for guiding future learning of the learner (L) and future teaching of the teacher (T), and a notification signal corresponding to the customized information is output. It may be configured to include a notification signal output unit 156 for controlling to be.

Here, the challenge-type evaluation item data is preferably data consisting of evaluation items having an incorrect answer probability exceeding a preset reference value, and the curriculum data is data about a curriculum including grade, semester, unit, and chapter it is desirable

In addition, according to the present invention, the customizing information may include data for a customized guide for learning/teaching at least one of recommended evaluation items, recommended contents, and recommended curricula.

A collaborative filtering (CF) algorithm is applied to the first model of the first data extractor 153, and an approximate nearest neighbor search (ANN) is applied to the second model of the second data extractor 154. Neighbors) algorithm is preferably applied.

Furthermore, the second data extractor 154 embeds the solution history data of the learners (L) in a vector space, receives the solution history data of any one target learner (L), and receives the most similar solution history. List data for a list of a group of learners (L) having can be extracted.

On the other hand, according to the present invention, the control unit 150 mutually matches the solution history data recorded in the database unit 152 and the curriculum data stored in the database unit 152 to understand each learner's curriculum. It may further include an understanding level extractor 155 for extracting degree information. At this time, the notification signal output unit 156 generates the customizing information by generating the level of understanding information extracted by the level of understanding level extractor 155. can be reflected together.

The notification unit 160 visually displays preset text and images on an arbitrary screen according to a notification signal output from the notification signal output unit 154 of the control unit 150. Preferably, the learner ( It is preferable to be configured to be provided in the first terminal 110 of L) and the second terminal 120 of the teacher T, respectively.

The notification unit 160 may include a liquid crystal display (LCD), a thin film transistor-liquid crystal display (TFT LCD), an organic light-emitting diode (OLED), and a flexible display. It may be configured to include at least one of (flexible display) and 3D display.

Hereinafter, three scenarios in which the artificial intelligence tutoring system of the present invention is implemented will be described with reference to FIGS. 7 to 10.

The first scenario is item recommendation, which recommends items under a given curriculum (or Knowledge Concept; KC) for efficient diagnostic evaluation. As shown in FIG. 8, in a situation where a learning goal (ρ) that determines the overall difficulty of the test is given, a risk (q) value is defined for each item q. The risk value at this time is defined as a convex combination of the item's difficulty c and the item's frequency p. As the adaptive factor a(t) is updated whenever a learner solves an item, the difficulty level of the item to be tested is appropriately adjusted based on the probability of correct answers of the latest N items.

The second scenario is curriculum recommendation, which provides an appropriate curriculum based on the degree of understanding estimated from past histories whenever a learner's evaluation is completed. At this time, as shown in FIG. 9, a distance in understanding between the current curriculum and the candidate curriculum is calculated, and the curricula are proposed in descending order of understanding while being close to the current curriculum. This can be seen as a way to maximize students' understanding.

In addition to the default recommendation, it also provides curriculum recommendations that are most difficult for other students (difficulty), have a high frequency of questions (popularity), and have been challenged by students similar to the learner (collaborative fitlering). By providing various recommendation options, it is possible to obtain the effect of broadening the range of choices for students and providing various recommendation results.

The third scenario is a combination of the first scenario (item recommendation) and the second scenario (curriculum recommendation), and as shown in FIG. 10, a curriculum and an item are adaptively recommended within one test.

Detailed descriptions of the preferred embodiments of the present invention disclosed as described above are provided to enable those skilled in the art to implement and practice the present invention. Although the above has been described with reference to preferred embodiments of the present invention, those skilled in the art will understand that the present invention can be variously modified and changed without departing from the scope of the present invention. For example, those skilled in the art can use each configuration described in the above-described embodiments in a manner of combining with each other. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

The present invention may be embodied in other specific forms without departing from the spirit and essential characteristics of the present invention. Accordingly, the above detailed description should not be construed as limiting in all respects and should be considered as illustrative. The scope of the present invention should be determined by reasonable interpretation of the appended claims, and all changes within the equivalent scope of the present invention are included in the scope of the present invention. The invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein. In addition, claims that do not have an explicit citation relationship in the claims may be combined to form an embodiment or may be included as new claims by amendment after filing.

100: AI tutoring system
110: first terminal
120: second terminal
130: web
140: external server
150: control unit
151: data generation unit
152: database unit
153: first data extraction unit
154: second data extraction unit
155: understanding degree extraction unit
156: notification signal output unit
160: notification unit
L: learner
T: teacher

Claims (7)

In an artificial intelligence tutoring system for remotely connecting a learner's first terminal and a teacher's second terminal to support the learner's learning and the teacher's teaching in a non-face-to-face environment,
Based on the solution history for the evaluation questions of the learners obtained from the first terminal while communicating by establishing a network with the first and second terminals, the web, and the external server, the challenge type evaluation question data for each learner and the similar solving history List data of a group of learners having a list is extracted, the extracted challenge-type evaluation item data and the list data are mutually matched to generate random recommendation item information, and the generated recommendation item information is mapped to pre-designated curriculum data so that the learner A controller for further generating customizing information for guiding future learning and future teaching of the teacher, and outputting a preset notification signal according to the customizing information; and
A notification unit provided in the first and second terminals to visually display on an arbitrary screen according to a notification signal output from the control unit;
The challenge type evaluation item data,
Characterized in that it is data consisting of evaluation questions having an incorrect answer probability exceeding a preset reference value,
The curriculum data,
Characterized in that it is data about the curriculum including grade, semester, unit, chapter,
The customization information,
Characterized in that it includes data for a customized guide for learning/teaching at least one of recommended evaluation items, recommended content, and recommended curriculum,
The control unit,
a data generating unit that obtains and converts a solution history including at least one of correct answers, incorrect answers, and unsolved answers to the learners' evaluation questions from the first terminal into data;
a database unit for recording the solution history data generated by the data generation unit and storing and managing curriculum data designated in advance by the second terminal or the external server;
a first data extractor configured to extract challenge-type evaluation item data by learning a pre-programmed first model based on machine learning based on the solution history data recorded in the database unit;
a second data extractor configured to extract the list data by learning a pre-programmed second model based on machine learning based on the solution history data recorded in the database unit; and
Random recommendation item information is generated by mutually matching the challenge type evaluation item data and the list data extracted through the first and second data extractors, respectively, and the generated recommendation item information is stored in the database unit as curriculum data. And further generating customizing information for guiding future learning of the learner and future teaching of the teacher by mapping to a notification signal output unit for controlling output of a notification signal corresponding to the customizing information.
The first model of the first data extraction unit,
Collaborative Filtering (CF) algorithm is applied,
The second model of the second data extraction unit,
Characterized in that an Approximate Nearest Neighbors (ANN) algorithm is applied,
The second data extraction unit,
Embedding the learners' solution history data in a vector space, receiving the solution history data of any one target learner and extracting list data for a list of learners with the most similar solve history as
The control unit,
Characterized in that it further comprises an understanding extraction unit for extracting understanding information for each curriculum of each learner by mutually matching the solution history data recorded in the database unit with curriculum data stored in the database unit,
The notification signal output unit,
An artificial intelligence tutoring system having a function of providing customized educational materials, characterized in that the understanding level information extracted by the level of understanding extraction unit is reflected together in the generation of the customizing information. delete delete delete delete delete delete

Images