KR102660529B1 - Method and system for mixed-learning monitoring - Google Patents

Abstract

The blended learning monitoring method according to an embodiment of the present invention is a blended learning monitoring method that monitors user learning in a blended learning environment performed by a blended learning monitoring system including at least one processor, based on a plurality of sensor devices. Obtaining a plurality of sensing data; Converting each of the plurality of sensing data into standard data; Saving all standard data including the converted standard data; It includes providing blended learning monitoring information based on the entire stored standard data.

Description

Blended learning monitoring method and system {METHOD AND SYSTEM FOR MIXED-LEARNING MONITORING}

The present invention relates to a blended learning monitoring method and system. More specifically, it relates to a blended learning monitoring method and system for monitoring users in a blended learning environment that links online learning and offline learning.

In general, offline learning has secured the educational service area through schools and institutions (companies and/or organizations, etc.), general private academies, and the tutoring and other workbook markets.

However, group education in schools and institutions based on PBT (paper-based training) learning is a form of learning the same curriculum in the same space, and does not take into account individual learning levels, but is limited by the instructor's fragmented time and provides one-sided learning. As a result, it was an education that did not take the learner's achievement into consideration.

For example, some students understand the content after class, but most students who do not understand the content simply skip the course without re-checking the content.

The biggest problem with this type of constructivist learning is that when a superiority/inferiority situation occurs between peer groups, it is very difficult for members with a sense of inferiority to ask the instructor to retake the course to address their insufficiencies after the class ends.

As a result, there are cases where people try to relearn skills through academies, private tutoring, and workbooks, resulting in a lot of opportunity costs in the learning process, which increases the cost of private education and becomes a major burden on households.

Meanwhile, as the IT industry develops, such offline learning has been expanding to online learning (e-Learning) through the Internet, which allows learning through a new method called online services since 2001.

For example, the EBS College Scholastic Ability Test service, a representative online learning method, has satisfied the needs of many users in that it can deliver lectures by famous instructors in the Seoul area to local students through the Internet, regardless of location, and has met the needs of many users, and has been able to reduce the government's private education expenses. It was implemented with the intention of saving money and served as a catalyst for establishing online learning as a universal learning method.

Since then, online learning has gained popularity among many users because it can be used at a lower price than offline learning, and technology development has continued to provide the same learning effect as offline, and now even interactive education services through video have become common.

In other words, through this continuous growth, online learning has become an axis of the education industry as a supplement and substitute for offline learning, and as a learning method that is equivalent to offline learning methods.

This online learning method has the advantage of enabling repeated learning, not being limited by time or location, and enabling prior learning by taking already recorded courses. However, for middle/lower class students who have difficulty in self-directed learning, such learning This raises problems from a management perspective.

In addition, online learning still has limitations in complementing constructivist learning based on individual learning management and character education that can complement offline face-to-face learning.

Therefore, in order to provide learning history or learning achievement at each individual level, it is essential to develop services through the interface between online learning and offline learning, and each service and system comprised in the self-directed learning management system for the online/offline linked learning service model. This is required.

In other words, offline education and online education need to be provided as complementary and substitute services.

Therefore, in the past, online/offline linked education services have been developed in each city/provincial office of education, such as providing a learning community through a cyber home learning system and a cyber teacher in charge.

However, in this conventional technology field, in most cases, a problem occurs in which most of the learners do not have continuity or persistence in offline and online learning and learning effects.

For example, in general, conventional online/offline linked education services have provided online learning as a form of assistance to offline learning conducted in school classes, and in this case, data on offline learning and data on online learning are lumped together. The situation is that it is not managed properly and is managed under the passive guidance of learners or leaders in each area.

In this way, there have been attempts to develop integrated online/offline linkage solutions and systems through the development of services at each level that link offline education and online education, but due to the lack of profitability of content companies and solution companies, institutional problems, and system limitations, offline education and online education have been separated from each other. The development and introduction of complementary services based on the strengths of education are insufficient.

KR 10-0784298 B1

The present invention was developed to solve the problems described above, and its purpose is to provide a blended learning monitoring method and system for monitoring users in a blended learning environment that links online learning and offline learning.

In detail, the present invention acquires various data related to user learning from a plurality of sensor devices based on at least one sensor that collects various types of sensing data, and monitors the user in the blended learning environment based on the obtained data. The purpose is to provide a blended learning monitoring method and system for monitoring.

However, the technical problems to be achieved by the present invention and embodiments of the present invention are not limited to the technical problems described above, and other technical problems may exist.

The blended learning monitoring method according to an embodiment of the present invention is a blended learning monitoring method that monitors user learning in a blended learning environment performed by a blended learning monitoring system including at least one processor, based on a plurality of sensor devices. Obtaining a plurality of sensing data; Converting each of the plurality of sensing data into standard data; Saving all standard data including the converted standard data; It includes providing blended learning monitoring information based on the entire stored standard data.

At this time, the standard data is data converted from a plurality of different formats of sensing data into one standard data format.

Additionally, the step of converting the standard data includes obtaining the standard data in an xAPI (Experience Application Programming Interface; xAPI) format as the standard data format.

In addition, the step of converting the standard data includes generating a first sentence consisting of “subject, verb, and object” based on the first sensing data of the first sensor device and including it in the first standard data, and a second A step of generating a second sentence consisting of “subject, verb, and object” based on the second sensing data of the sensor device and including it in the second standard data, and “subject, verb,” based on the third sensing data of the learning device. It includes at least two steps among the steps of generating a third sentence composed of “object word” and including it in the third standard data.

In addition, the step of converting the standard data includes including the measured value of the first sensing data of the first sensor device in the first standard data as a “result data” configuration, and the step of including the first standard data of the first sensor device It includes generating a “context” configuration that adds additional meaning to the first sentence based on sensing data and including it in the first standard data.

Additionally, the step of storing all standard data including the converted standard data includes storing a plurality of the converted standard data in a Learning Record Store (LRS).

Additionally, the step of storing the plurality of converted standard data in a Learning Record Store (LRS) includes removing and storing redundant data among the plurality of converted standard data.

In addition, the step of removing and storing redundant data among the plurality of converted standard data includes selecting and storing the upper data determined according to a predetermined standard when the same or different types of data in the plurality of standard data are the same. Includes steps.

In addition, the blended learning monitoring information is information that monitors a user performing learning in the blended learning environment, and includes at least one of learning time monitoring information, learning progress monitoring information, learning ability monitoring information, and learning ability auxiliary parameter monitoring information. Includes.

Meanwhile, the blended learning monitoring system according to an embodiment of the present invention includes at least one processor; and at least one memory; At least one application that includes and is stored in the memory and executed by the at least one processor to perform blended learning monitoring to monitor a user in a blended learning environment that links online learning and offline learning. Obtains a plurality of sensing data from a plurality of sensor devices, and converts the acquired plurality of sensing data into standard data? Converts, stores all standard data including the converted standard data, and provides blended learning monitoring information based on the stored standard data.

The blended learning monitoring method and system according to an embodiment of the present invention monitors users in a blended learning environment that links online learning and offline learning, rather than identifying the user's learning activities from either online or offline perspectives. It has the effect of comprehensively and closely monitoring all learning-related activities performed by users both online and offline.

In addition, the blended learning monitoring method and system according to an embodiment of the present invention acquires various data related to the user's learning from a plurality of sensor devices including various sensors, and configures the blended learning environment based on the data obtained in this way. By monitoring the user, there is an effect of obtaining, analyzing, and providing information related to the user's learning from various angles.

However, the effects that can be obtained from the present invention are not limited to the effects mentioned above, and other effects not mentioned can be clearly understood from the description below.

Figure 1 is a conceptual diagram of a blended learning monitoring system according to an embodiment of the present invention.
2 to 4 are examples of a sensor device according to an embodiment of the present invention.
Figure 5 is a conceptual diagram illustrating a blended learning monitoring method according to an embodiment of the present invention.
Figure 6 is a flowchart illustrating a blended learning monitoring method according to an embodiment of the present invention.
Figure 7 is an example of a drawing for explaining standard data according to an embodiment of the present invention.
Figure 8 is an example of blended learning monitoring information output as a graphic image according to an embodiment of the present invention.

Since the present invention can be modified in various ways and can have various embodiments, specific embodiments will be illustrated in the drawings and described in detail in the detailed description. The effects and features of the present invention and methods for achieving them will become clear by referring to the embodiments described in detail below along with the drawings. However, the present invention is not limited to the embodiments disclosed below and may be implemented in various forms. In the following embodiments, terms such as first and second are used not in a limiting sense but for the purpose of distinguishing one component from another component. Additionally, singular expressions include plural expressions unless the context clearly dictates otherwise. Additionally, terms such as include or have mean that the features or components described in the specification exist, and do not preclude the possibility of adding one or more other features or components. Additionally, in the drawings, the sizes of components may be exaggerated or reduced for convenience of explanation. For example, the size and thickness of each component shown in the drawings are shown arbitrarily for convenience of explanation, so the present invention is not necessarily limited to what is shown.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. When describing with reference to the drawings, identical or corresponding components will be assigned the same reference numerals and redundant description thereof will be omitted. .

Figure 1 is a conceptual diagram of a blended learning monitoring system according to an embodiment of the present invention.

Referring to FIG. 1, the blended learning monitoring system according to an embodiment of the present invention may include a first sensor device 100, a second sensor device 200, and a third sensor device 300 (hereinafter, a learning device). You can.

In an embodiment, the first sensor device 100, the second sensor device 200, and the learning device 300 interoperate with each other in a blended learning environment that links online learning and offline learning, based on at least one sensor. A blended learning monitoring service can be provided that monitors users (learners) based on various types of sensing data obtained.

Meanwhile, the first sensor device 100, the second sensor device 200, and the learning device 300 of FIG. 1 may be connected based on a network.

Here, the network refers to a connection structure that allows information exchange between nodes such as the first sensor device 100, the second sensor device 200, and the learning device 300, and is an example of such a network. 3GPP (3rd Generation Partnership Project) network, LTE (Long Term Evolution) network, WIMAX (World Interoperability for Microwave Access) network, Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), Bluetooth network, satellite broadcasting network, analog broadcasting network, DMB (Digital Multimedia Broadcasting) network, etc., but is not limited thereto.

- Sensor Device

In an embodiment of the present invention, a sensor device may be implemented including at least one sensor that acquires various sensing data required for a blended learning monitoring service.

In detail, in an embodiment, the sensor may include an ID sensor, a position sensor, an audio sensor, an inertial sensor, an image sensor, an environmental sensor, a motion sensor, a distance measurement sensor, and/or a biological (bio) sensor. .

Here, the ID sensor according to the embodiment can identify each user based on a specific signal assigned and transmitted for each user.

In an embodiment, such an ID sensor may provide user identification data, location data, and/or counting data (eg, attendance counting data) according to a predetermined standard, etc. based on the sensed data.

In addition, the position sensor according to the embodiment may include a global positioning system (GPS), etc., and various location data (e.g., user location and/or learning space) required for the blended learning monitoring service. location), etc. can be obtained and provided.

In addition, the audio sensor according to the embodiment is a sensor capable of converting an analog sound signal into a digital electrical signal, and includes audio data, user identification data, location data, and/or emotion based on the data sensed in the embodiment. (emotion) data, etc. can be provided.

In addition, the inertial sensor according to the embodiment may include an accelerometer sensor capable of measuring a predetermined force and/or a gyroscope sensor capable of measuring angular velocity, and may include the user's movement or rotation. can be detected.

In an embodiment, such an inertial sensor may provide counting data, motion data, and/or location data according to a predetermined standard based on the sensed data.

Additionally, in an embodiment, an image sensor may perform image sensing to obtain predetermined captured images (for example, images captured while learning is in progress in a learning space, etc.).

In embodiments, such image sensors may provide image data, eye-tracking data, motion data, location data, emotion data, environmental data, counting data, and/or user identification data based on sensed data. You can.

Additionally, an environmental sensor according to an embodiment may detect surrounding environmental information (eg, specific chemical stimulus, humidity and/or temperature, etc.).

In embodiments, such environmental sensors may provide motion data and/or environmental data, etc. based on sensed data.

Additionally, a motion sensor according to an embodiment may detect movement of a sensed object (in an embodiment, a user, etc.), and in an embodiment, based on the sensed data, motion data, location data, Emotion data and/or counting data may be provided.

Additionally, a scanning range-finder according to an embodiment may detect the distance to a specific object (in the embodiment, a user, etc.) within a predetermined space.

In embodiments, such a distance measurement sensor may provide distance measurement data, location data, counting data, and/or motion data based on sensed data.

In addition, the biophysical sensor according to the embodiment may include an electroencephalogram (EEG) sensor, an electrocardiogram (ECG) sensor, and/or a photoplethysmography sensor (PPG), etc. , Biological data information about the user can be obtained based on these sensors.

In an embodiment, the biometric (bio) sensor may provide biometric (bio) data, user identification data, motion data, and/or emotion data, etc. based on the sensed data.

Additionally, software sensors according to the embodiment may obtain and provide logical sensing information, and may provide time stamp data and/or elapsed time data based on the sensed data in the embodiment. You can.

2 to 4 are examples of a sensor device according to an embodiment of the present invention.

Meanwhile, referring to FIGS. 2 to 4, in an embodiment of the present invention, a sensor device implemented including at least one sensor among the plurality of sensors described above includes a first sensor device 100 and a second sensor device. It may include (200) and a learning device (300).

Hereinafter, in an embodiment of the present invention, it will be described that the sensor device includes a first sensor device 100, a second sensor device 200, and a learning device 300. However, this is only an example and may be less or less depending on the embodiment. It may include many sensor devices.

<100: 1st Sensor Device>

Referring further to FIG. 2, the first sensor device 100 according to an embodiment of the present invention may be a portable type computing device.

In detail, in an embodiment, the first sensor device 100 may be implemented as a wearable type computing device, a mobile type computing device, and/or a pocket or pen type computing device.

For example, the first sensor device 100 may be a wearable computing device such as smart glasses display or head mounted display (HMD) and/or a smart phone, a mobile phone, a digital broadcasting terminal, It may be a mobile type computing device such as personal digital assistants (PDAs), portable multimedia players (PMPs), or tablet PCs.

In an embodiment, this first sensor device 100 may obtain user tracking information necessary for a blended learning monitoring service.

Here, tracking information according to the embodiment refers to continuous tracking of the user in order to obtain sensing data (in the embodiment, the user's location, movement, biological (bio) and/or audio data, etc.) required to provide a blended learning monitoring service. This may be information tracked by .

In detail, in the embodiment, the first sensor device 100 is a plurality of devices including at least one ID sensor, a position sensor, an inertial sensor, a motion sensor, a biometric sensor, an audio sensor, and/or a software sensor. may include sensors.

Additionally, the first sensor device 100 may obtain tracking information about the user carrying the first sensor device 100 based on the at least one sensor described above.

For example, the first sensor device 100 includes location data indicating whether the user is located in a preset learning space (e.g., school, academy, reading room, library, etc.) based on a location sensor and a software sensor; Elapsed time data and/or time stamp data indicating how long the user stayed in the relevant learning space can be obtained and provided.

That is, the first sensor device 100 may be a tracker that is easy for the user to carry around, and may include a location sensor such as GPS to detect the user's location data.

Additionally, the first sensor device 100 may be a tracker that can be attached to a tool related to learning. In this case, it may include an inertial sensor or/and a motion sensor to detect movement information according to the user's use of the tool during learning. .

- <200: 2nd Sensor Device>

Referring further to FIG. 3, the second sensor device 200 according to an embodiment of the present invention is fixedly installed on a predetermined area (in the embodiment, a preset learning space and/or learning device 300, etc.). It can be implemented with at least one sensor.

In detail, in the embodiment, the second sensor device 200 includes an image sensor (eg, Camera, CCTV, and/or CAM, etc.), an audio sensor, an ID signal reception sensor, and/or a software sensor disposed in a predetermined area. It may include etc.

Additionally, the second sensor device 200 may acquire various sensing data based on the second sensor device 200 based on at least one of the above sensors.

For example, the second sensor device 200 installed in a first learning space (eg, a school classroom) may obtain and provide data on the elapsed time that the first user resides in the first learning space.

Through this, the second sensor device 200 can obtain more reliable monitoring data about the user in a blended learning environment.

In another embodiment, the second sensor device 200 is a CAM camera such as a webcam, axis cam, or stereo cam that is fixed or detachable during sensing, and can be positioned at a location to photograph the learning space as needed by the user. Can be installed.

<Learning device (300: 3rd Sensor Device)>

Referring further to FIG. 4, the learning device 300 according to an embodiment of the present invention may be a computing device on which a blended learning monitoring application (hereinafter referred to as monitoring application) that provides a blended learning monitoring service is installed.

Additionally, in the embodiment, the learning device 300 may function as a central sensor device that functions as a hub for a plurality of sensor devices.

That is, in an embodiment of the present invention, the learning device 300 monitors users in a blended learning environment that links online learning and offline learning based on sensing data obtained from at least one sensor in conjunction with other sensor devices. Monitoring services can be provided.

Specifically, in the embodiment, the learning device 300 may provide online learning content.

In detail, the learning device 300 may provide online learning content, which is online-based learning content (for example, online video lectures and/or online mock exam test content, etc.), by displaying and outputting it according to a predetermined method.

In an embodiment, the learning device 300 may display and provide offline auxiliary content (eg, textbook PDF output content, etc.), which is online content that assists offline learning.

Additionally, in the embodiment, the learning device 300 may provide a user input interface.

In detail, the learning device 300 may provide a user input interface that can acquire additional data required for a blended learning monitoring service based on user input, in addition to data acquired based on at least one sensor.

For example, the learning device 300 acquires additional data, such as the most interesting learning subject information, the most difficult learning subject information, today's target learning amount setting information, and/or user memo information, based on the user input interface. can do.

Additionally, in the embodiment, the learning device 300 may visualize and provide blended learning monitoring information.

In detail, the learning device 300 may display and provide blended learning monitoring information obtained based on sensing data collected from at least one sensor device.

Here, the blended learning monitoring information according to the embodiment may be information monitored by integrating learning performed throughout online and offline.

In detail, in the embodiment, the blended learning monitoring information may include learning time monitoring information, learning progress monitoring information, learning ability monitoring information, and/or learning ability auxiliary parameter monitoring information.

In an embodiment, this blended learning monitoring information may be information derived through analysis performed based on standard data that has standardized at least one or more sensing data collected in different packet formats.

Specifically, in the embodiment, the learning device 300 uses standard data based on a plurality of sensing data as input and performs mixed learning based on a deep learning neural network (artificial intelligence) trained to output the mixed learning monitoring information. Monitoring information can be obtained.

That is, in the embodiment, the learning device 300 may acquire mixed learning monitoring information based on predetermined standard data based on artificial intelligence that performs deep learning based on the deep learning neural network previously learned as above. . A detailed explanation of this is provided in the blended learning monitoring method described later.

Meanwhile, in the embodiment, the learning device 300 may be implemented to include at least one sensor that detects various sensing data required for the blended learning monitoring service.

In an embodiment, the learning device 300 may include an ID sensor, a position sensor, an inertial sensor, a motion sensor, an audio sensor, an image sensor, and/or a software sensor.

Additionally, the learning device 300 may acquire various sensing data based on the learning device 300 based on at least one sensor as described above.

In an embodiment, the learning device 300 may acquire location data, movement data, audio data, eye-tracking data, time stamp data, and/or elapsed time data based on a plurality of sensors.

In an embodiment of the present invention, the learning device 300 as described above includes at least one memory that stores various applications, data, and/or commands for providing a blended learning monitoring service, and at least one memory for data processing. It can be implemented as a predetermined computing device including the above processor.

In an embodiment, the learning device 300 includes at least one memory and at least one processor, and may include a mobile type computing device and/or a desktop type computing device with at least one monitoring application installed on the memory. there is.

Here, the mobile type computing device may be a mobile device such as a smart phone or tablet PC with a monitoring application installed.

For example, mobile type computing devices may include smart phones, mobile phones, digital broadcasting terminals, personal digital assistants (PDAs), portable multimedia players (PMPs), and tablet PCs.

In addition, a desktop type computing device is a program for executing a blended learning monitoring service based on wired/wireless communication, such as a fixed desktop PC with a monitoring application installed, a laptop computer, or a personal computer such as an ultrabook. This may include installed devices, etc.

- Blended learning monitoring method

Hereinafter, a method for monitoring users in a blended learning environment that links online learning and offline learning by the blended learning monitoring system (hereinafter referred to as monitoring system) according to an embodiment of the present invention will be described in detail with reference to FIGS. 5 to 8 attached. Explain.

Figure 5 is a conceptual diagram for explaining a blended learning monitoring method according to an embodiment of the present invention, and Figure 6 is a flowchart for explaining a blended learning monitoring method according to an embodiment of the present invention.

Referring to FIGS. 5 and 6, in an embodiment of the present invention, the monitoring system can acquire sensing data. (S101)

In detail, in an embodiment, the monitoring system may acquire at least one or more sensing data based on a plurality of sensor devices.

In an embodiment, the monitoring system may include first sensing data obtained from at least one sensor of the first sensor device 100, second sensing data obtained from at least one sensor of the second sensor device 200, and/or Third sensing data obtained from at least one sensor of the learning device 300 may be obtained.

For example, the monitoring system may acquire user identification data, location data, counting data, movement data, biological (bio) data, audio data, time stamp data, and/or elapsed time data as first sensing data. .

Additionally, in the example, the monitoring system acquires image data, user identification data, location data, motion data, emotion data, counting data, environmental data, audio data, time stamp data, and/or elapsed time data as second sensing data. can do.

In addition, the monitoring system exemplarily includes location data, movement data, audio data, eye-tracking data, time stamp data, elapsed time data, and/or online learning content data (e.g., online learning content data) as third sensing data. Learning content log record data, provision time data, and/or progress data, etc.) can be obtained.

In this way, the monitoring system can acquire various data related to the user's learning in real time based on a plurality of sensor devices and continuously track the various learning environments that the user uses both online and offline. Through this, all learning activities related to users can be monitored without omission, regardless of whether they are online or offline.

In addition, the monitoring system uses sensors that collect sensing data in various forms from various perspectives (e.g., from a perspective of monitoring user movements, from a perspective of monitoring learning content provision time, and/or from a perspective of monitoring learning locations, etc.). By acquiring data related to the user's learning, information related to the user's learning can be obtained, analyzed, and provided from various angles.

Additionally, in the embodiment, the monitoring system may generate standard data by converting the sensing data obtained as above. (S103)

Here, standard data according to the embodiment may mean data obtained by converting the format of a plurality of sensing data having heterogeneous formats (i.e., different packet formats) into a predetermined standard data format.

In general, a plurality of sensing data acquired from at least one sensor device may have heterogeneous formats (different packet formats).

For example, each of a plurality of sensing data including user identification data, image data, biometric (bio) data, time stamp data, and online learning content data may be implemented in different formats.

Due to this diversity of packet formats, it may be difficult to maintain consistency in the binary arrangement of the sensing data when performing certain system processing in the monitoring system.

Therefore, in an embodiment of the present invention, the monitoring system can generate standard data, which is standardized data, by converting the packet format of the plurality of acquired sensing data into a predetermined standard data format.

Figure 7 is an example of a drawing for explaining standard data according to an embodiment of the present invention.

In detail, referring to FIG. 7, in the embodiment, the monitoring system may acquire standard data for a plurality of sensing data using the xAPI (Experience Application Programming Interface; xAPI) format as a standard data format.

Here, xAPI refers to a standard API that collects experience data related to learning, and manages various learning-related experiences in a single format by converting the acquired data into a sentence format consisting of “subject, verb, and object.” can do.

In detail, in an embodiment, the monitoring system converts the acquired plurality of sensing data into xAPI format (for example, “subject, verb, object” format), and converts the plurality of sensing data having heterogeneous packet formats into a single format. It can be converted to standard data.

At this time, in the embodiment, the monitoring system assigns meaning to the sentence format of “subject, verb, and object,” which is the main component of standard data, as well as “result data,” which is data measured from a sensor as an additional component, and the format of the sentence. It may further include “context” configuration, etc.

For example, the monitoring system may use a plurality of acquired sensing data such as 'User identification data = 1st user', 'Location data = 1st learning space', 'Online learning content data = 1st chapter of 1st learning subject'. , 'Image data = the first user gazes at the screen of the learning device 300', 'Eye tracking data = the eyes of the first user gaze at the screen of the learning device 300', and 'Elapsed time data = the first time. ', standard data can be generated by converting the plurality of sensing data into the xAPI format of “The first user studied the first chapter of the first learning subject in the first learning space for the first time.” there is.

In this way, the monitoring system converts and standardizes the sensing data acquired in various formats from a plurality of sensors into a predetermined data format (in the embodiment, xAPI format), converts the sensing data acquired in a sporadic form into a consistent form. It can be processed and managed, and through this, the acquired data can be systematically managed and its usability and usability can be increased.

Table 1 below is an example of a standard data format.

Property Type Description Required REMART id UUID UUID assigned by LRS if not set by the learning record provider. Recommended ID sensor motion sensor actor Object The learner or group entity is the object of the statement. Required ID sensor motion sensor verb Object Actions taken by the learner. Required audio sensor
Inertial sensor
ID sensor
Image sensor Environmental sensor
motion sensor
measuring sensor
environmental sensor
software sensor object Object The activity, agent, or other statement that is the subject of the statement. Required result Object Result object, additional details representing the measured result. Optional context Object Context that gives more meaning to the statement.
Example: a team working with actors, a scenario set in a flight simulator Optional timestamp Timestamp Timestamp of when the event described in this policy occurred. If not provided, set by LRS. Optional stored Timestamp The time stamp when this statement was recorded. Set in LRS. Set by LRS authority Object Any agent or group claiming this statement is true. Verified by LRS based on certification. If not provided or a strong trust relationship is not established between the learning record provider and the LRS, it will be set by the LRS. Optional version Version The relevant xAPI version of the Statement, formatted according to semantic version 1.0.0. Not Recommended attachments Ordered array of Attachment Objects Statement attachment header Optional

Additionally, in an embodiment, the monitoring system may remove and store redundant data in the obtained standard data. (S105)

That is, in the embodiment, the monitoring system may remove redundant data in the standard data obtained as above according to a predetermined standard and store it in memory (database).

At this time, in the embodiment, the monitoring system may store at least one or more standard data based on LRS (Learning Record Store).

Here, LRS may refer to a space that stores standard data converted to xAPI format.

In detail, in an embodiment, when a plurality of standard data exists, the monitoring system may perform a redundant data processing process for the plurality of corresponding standard data.

At this time, the duplicate data processing process according to the embodiment may be a process of filtering and removing duplicate data from a plurality of standard data.

In more detail, the monitoring system is: 1) If the same type of data in a plurality of standard data is the same, it is monitored according to a predetermined standard (e.g., in the order of small data size, high data accuracy, or preset priority device order, etc.). Accordingly, the determined high-order data can be stored in memory (database, LRS in the embodiment).

For example, in the monitoring system, the preset priority device is the first sensor device 100, and the location data of the first sensor device 100 in the first standard data and the learning device 300 in the second standard data If the location data is the same (same type of data is the same), the location data can be integrated and stored as the location data of the first sensor device 100, which is a preset priority device.

Here, the method of integrating and storing data may be a method of including information that the location of the learning device 300 is the same as the location data information of the first sensor device 100 in the context configuration of the standard data.

Additionally, the monitoring system may 2) store all of the data in a memory (database, LRS in the embodiment) if the same type of data in the plurality of standard data are different from each other.

For example, the monitoring system, if the location data of the first sensor device 100 in the first standard data and the location data of the learning device 300 in the second standard data are different from each other (same type of data are different from each other), Both the location data of the first sensor device 100 and the location data of the learning device 300 can be stored.

As another example, the monitoring system stores location information based on the first sensor device 100, and includes in the context configuration that the location data of the learning device 300 and the location data of the first sensor device 100 are different. Heterogeneous data can be integrated and stored as one data in the specified manner.

In addition, the monitoring system: 3) If heterogeneous data within a plurality of standard data are the same, according to a predetermined standard (e.g., small data size, high data accuracy, or preset priority device order, etc.) The determined high-level data can be stored in a memory (database, LRS in the embodiment).

In other words, the monitoring system matches and stores heterogeneous data of the same information that can be analyzed as the same learning information, and when heterogeneous data of the same information is received, storage can be optimized through data integration or deletion of one data. there is.

For example, the monitoring system may determine that the online learning content data of the first standard data represents the output of offline auxiliary content (e.g., textbook PDF output content, etc.) for the first chapter of the first subject, and the audio data of the second standard data. If it represents the voice data for the first chapter of the first subject (the heterogeneous data are the same), the data can be integrated and stored as online learning content of the first standard data with smaller data size and higher accuracy. .

That is, the monitoring system matches and stores first standard data and second standard data acquired by different sensors in a heterogeneous device or one device as the same information data, and the first standard data and the second standard data are predetermined. If received within the time, a storage method that integrates the first standard data and the second standard data can be set and then stored according to the set method. As an example of a storage method, the sentence structure of “subject, verb, object” of the first standard data can be maintained, and the second standard data can be abbreviated and stored in the additional structure “result data” or “context”.

As an example of abbreviation, the second standard data can be converted into a sentence structure format and then stored in the context. Additionally, a new sentence combining a sentence of the first standard data and a sentence of the second standard data can be created and stored in the context.

Additionally, the sensor data value of the second standard data may be included in the result data.

Additionally, the monitoring system may 4) store all of the data in a memory (database, LRS in the embodiment) if the heterogeneous data within the plurality of standard data are different from each other.

For example, the monitoring system may determine that the online learning content data of the first standard data represents the output of offline auxiliary content (e.g., textbook PDF output content, etc.) for the first chapter of the first subject, and the audio data of the second standard data. If represents audio data for the first chapter of a second subject (the types of data are different from each other), both the online learning content data and the audio data can be stored.

In this way, the monitoring system can improve data quality and minimize unnecessary memory space consumption by removing and storing redundant data in standard data obtained based on various sensing data according to a predetermined method.

Additionally, in the embodiment, the monitoring system may provide blended learning monitoring information by analyzing the standard data stored as above. (S107)

Here, the blended learning monitoring information according to the embodiment may be information that is monitored by linking the user's learning activities performed throughout online and offline.

In detail, in the embodiment, the monitoring system acquires mixed learning monitoring information based on a deep learning neural network (artificial intelligence) trained to input standard data based on a plurality of sensing data and output the mixed learning monitoring information. can do.

That is, in the embodiment, the monitoring system may acquire mixed learning monitoring information based on predetermined standard data based on artificial intelligence that performs deep learning based on the deep learning neural network previously learned as above.

More specifically, in the embodiment, the monitoring system monitors mixed learning, including learning time monitoring information, learning progress monitoring information, learning ability monitoring information, and/or learning ability auxiliary parameter monitoring information, based on deep learning based on standard data. Information can be generated.

Specifically, the monitoring system can: 1) obtain learning time monitoring information based on deep learning based on standard data.

Here, the learning time monitoring information according to the embodiment may be information that monitors the learning time during which the user performed online/offline learning.

More specifically, in the embodiment, the monitoring system monitors online learning time information and offline learning time information for each predetermined learning subject and chapter, and provides online and offline integrated learning time information for each subject and online and offline integrated learning time for each chapter within the subject. Information can be obtained.

In an embodiment, the monitoring system may acquire the learning time monitoring information based on deep learning through a deep learning neural network.

At this time, the deep learning neural network that performs the deep learning may be a deep learning neural network that has been pre-trained to calculate and output online and/or offline learning time based on input standard data.

In detail, in the embodiment, the monitoring system may set a standard data type for generating online learning time information and a standard data type for generating offline learning time information.

In an embodiment, the monitoring system sets the first data among the third sensing data of the learning device 300 as the tenth standard data and the second data of the second sensor device 200 in order to obtain online learning time information. The second sensing data can be set as the 20th standard data.

More specifically, in the embodiment, the monitoring system filters the 10th standard data and 20th standard data associated with online learning time information from the entire standard data, and uses the filtered 10th standard data and 20th standard data to provide online learning time information. It can be input into the deep learning neural network to be extracted.

Therefore, the monitoring system may output online learning time information, online learning time information for each subject, or/and online learning time information for each chapter within the subject based on deep learning based on the deep learning neural network.

Online learning time information Below, the process of the monitoring system outputting online learning time information is explained in detail.

In detail, the monitoring system may obtain online learning time information based on deep learning by inputting the 10th standard data for the third sensing data and the 20th standard data for the second sensing data.

For example, the 10th standard data for the 3rd sensing data is 'proceeding the first chapter (e.g., log chapter) of the first learning subject (e.g., mathematics) on the first user's learning device 300. It may be 'providing online learning content for 1 hour', and the 20th standard data for the second sensing data may be 'the first user looks at the learning device 300 for 50 minutes'.

And in the example, the monitoring system may input the 10th standard data and 20th standard data obtained as above into a pre-trained deep learning neural network.

Therefore, in the example, the monitoring system provides information on the online study time performed by the first user for the first chapter of the first subject, based on a deep learning neural network that receives the 10th standard data and the 20th standard data. It can be printed as ‘50 minutes’.

In other words, the monitoring system can monitor accurate online learning time by integrating data from heterogeneous devices and/or heterogeneous data formats into standard data and then inputting preset standard data from all standard data into deep learning.

Meanwhile, in the embodiment, the monitoring system sets the third data among the third sensing data of the learning device 300 as the 30th standard data and the first sensor device 100 in order to obtain offline learning time information. 1 The fourth data among the sensing data can be set as the 40th standard data.

That is, in the embodiment, the monitoring system filters the 30th standard data and 40th standard data associated with offline learning time information from all standard data, and extracts offline learning time information from the filtered 30th standard data and 40th standard data. can be input to the deep learning neural network.

Therefore, the monitoring system may output offline learning time information, offline learning time information for each subject, or/and offline learning time information for each chapter within the subject based on deep learning based on the deep learning neural network.

Specifically, to describe in detail the process by which the monitoring system outputs offline learning time information, in the embodiment, the monitoring system outputs the 30th standard data for the third sensing data and the 40th standard data for the first sensing data. It can be input into a deep learning neural network.

And the monitoring system can obtain offline learning time information by performing deep learning based on the deep learning neural network.

For example, the monitoring system uses the 30th standard data for the 3rd sensing data to indicate that 'the first user's learning device 300 is learning the first subject of the first subject in the first learning space (e.g., the first subject learning classroom). 'Offline auxiliary content for the chapter is provided for 1 hour' can be obtained, and 'the first user stays in the first learning space for 1 hour' can be obtained as the 40th standard data for the first sensing data.

Additionally, in the example, the monitoring system may input the 30th standard data and 40th standard data obtained as above into the pre-trained deep learning neural network.

Therefore, in the example, the monitoring system provides information on the offline learning time performed by the first user for the first chapter of the first subject, based on a deep learning neural network that receives the 30th standard data and the 40th standard data. It can be obtained in ‘1 hour’.

In other words, the monitoring system can monitor accurate offline learning time by integrating data from heterogeneous devices and/or heterogeneous data formats into standard data and then inputting preset standard data from all standard data into deep learning.

Next, in the embodiment, the monitoring system may integrate online learning time information and offline learning time information.

For example, when the monitoring system detects conflicting learning time information between online learning time information and offline learning time information, it deletes one of the learning time information and then performs calculations to calculate the final learning time information. You can do so, and at this time, you can classify and add up the study time information for each subject/chapter.

That is, in the embodiment, the monitoring system may integrate the online learning time information and offline learning time information obtained as above to obtain total online/offline learning time information for each subject and chapter.

For example, the monitoring system combines the online learning time information and offline learning time information when the online learning time for Chapter 1 of subject 1 is '50 minutes' and the offline learning time is '1 hour'. Thus, the total online/offline study time information for the first chapter of the first subject can be obtained as '1 hour and 50 minutes'.

Additionally, in an embodiment, the monitoring system may provide online learning time information and/or offline learning time information obtained as described above in a predetermined manner (eg, display output, etc.).

In this way, the monitoring system monitors the user's learning time in a blended learning environment that integrates online and offline learning environments, so that the user's learning amount is not only determined from either the online or offline perspective, but the user can learn both online and offline. The user's learning amount can be closely monitored based on all learning time actually performed.

Additionally, in the embodiment, the monitoring system may 2) obtain learning progress monitoring information based on deep learning based on standard data.

Here, the learning progress monitoring information according to the embodiment may be information that monitors the learning progress status achieved by the user by performing online/offline learning.

In detail, in the embodiment, the monitoring system can monitor online learning progress information and offline learning progress information for each predetermined learning subject and chapter.

In addition, through this, the monitoring system can obtain online and offline integrated learning progress information for each subject and online and offline integrated learning progress information for each chapter within the subject.

In an embodiment, the monitoring system may acquire the learning progress monitoring information based on deep learning through a deep learning neural network.

At this time, the deep learning neural network that performs the deep learning may be a deep learning neural network that has been pre-trained to calculate and output online and/or offline learning progress based on input standard data.

In detail, in the embodiment, the monitoring system may set a standard data type for generating online learning progress information and a standard data type for generating offline learning progress information.

In an embodiment, in order to obtain online learning progress information, the monitoring system sets the 5th data among the 3rd sensing data of the learning device 300 as the 50th standard data and the 2nd data of the second sensor device 200. Among the sensing data, the 6th data can be set as the 60th standard data.

In detail, in an embodiment, the monitoring system filters the 50th standard data and 60th standard data associated with online learning progress information from the entire standard data, and extracts online learning progress information from the filtered 50th standard data and 60th standard data. can be input to the deep learning neural network.

Therefore, the monitoring system may output online learning progress information, online learning progress information for each subject, or/and online learning progress information for each chapter within the subject based on deep learning based on the deep learning neural network.

Hereinafter, the process by which the monitoring system outputs online learning progress information will be described in detail.

In detail, in an embodiment, the monitoring system may obtain online learning progress information based on deep learning by inputting the 50th standard data for the third sensing data and the 60th standard data for the second sensing data.

For example, the 50th standard data for the 3rd sensing data is 'at least some of the 1st to 10th chapters (e.g., 1st to 5th chapters) included in the first subject in the first user's learning device 300. 'There is a learning completed log record' is obtained, and the 60th standard data for the second sensing data is 'The first user's total learning time (e.g., 50 minutes) of the learned chapters (e.g., chapters 1 to 5) ) may be 'watching the learning device 300 for a period of time or more'.

And the monitoring system can input the 50th standard data and 60th standard data obtained as above into a pre-trained deep learning neural network.

Therefore, the monitoring system, based on a deep learning neural network that receives the 50th standard data and the 60th standard data, displays online learning progress information by chapter for the first subject of the first user as 'the learned chapter ( For example, chapters 1 to 5) can be obtained.

In other words, the monitoring system can monitor accurate online learning progress by integrating data from heterogeneous devices and/or heterogeneous data formats into standard data and then inputting preset standard data from all standard data into deep learning.

Meanwhile, in the embodiment, the monitoring system sets the 7th data among the 3rd sensing data of the learning device 300 as the 70th standard data and sets the 8th data among the first sensing data of the first sensor device 100 as the 70th standard data. 8 You can obtain offline learning progress information by setting it as standard data.

In detail, the monitoring system filters the 70th standard data and 80th standard data associated with offline learning progress information from the entire standard data, and extracts offline learning progress information from the filtered 70th standard data and 80th standard data. It can be input into a learning neural network.

Therefore, the monitoring system may output offline learning progress information, offline learning progress information for each subject, or/and offline learning progress information for each chapter within the subject based on deep learning based on the deep learning neural network.

In detail, in the embodiment, the monitoring system may input the 70th standard data for the third sensing data and the 80th standard data for the first sensing data into the deep learning neural network, through which the offline learning time information can be obtained.

For example, the 70th standard data for the third sensing data is 'at least some of the first to ten chapters (e.g., first to fifth chapters) included in the first subject in the first user's learning device 300. 'There is a log record of completed learning' is obtained, and the 80th standard data for the first sensing data is 'The first user reads the completed chapter (e.g., the first subject learning classroom) in the first learning space (e.g., the first subject learning classroom). It is possible to obtain 'staying for more than the total study time (eg, 50 minutes) of 6 to 10 chapters).

And in the example, the monitoring system may input the 70th standard data and 80th standard data obtained as above into a pre-trained deep learning neural network.

In addition, in the example, the monitoring system, based on a deep learning neural network that receives the 70th standard data and the 80th standard data, provides chapter-specific offline learning progress information for the first subject of the first user as 'the learning It can be obtained through completed chapters (e.g., chapters 6 to 10).

In other words, the monitoring system can monitor accurate offline learning progress by integrating data from heterogeneous devices and/or heterogeneous data formats into standard data and then inputting preset standard data from all standard data into deep learning.

Additionally, in an embodiment, the monitoring system may provide online learning progress information and/or offline learning progress information obtained as described above in a predetermined manner (eg, display output, etc.).

Additionally, in an embodiment, the monitoring system may integrate online learning progress information and offline learning progress information.

For example, when the monitoring system detects conflicting learning progress information between online and offline learning progress information, it deletes one of the learning progress information and then performs calculations to calculate the final learning progress information. You can do so, and at this time, you can classify and add up the learning progress information for each subject/chapter.

That is, in the embodiment, the monitoring system may integrate the online learning progress information and offline learning progress information obtained as above to obtain total online/offline learning progress information for each subject and chapter.

For example, if the online learning progress information by chapter for the first subject of the first user is 'Chapters 1 to 5' and the offline learning progress information is 'Chapters 6 to 10', the online learning progress information is 'Chapters 6 to 10'. By integrating learning progress information and offline learning progress information, the total learning progress information on/offline for each chapter for the first subject of the first user can be obtained as 'chapters 1 to 10'.

In this way, the monitoring system collectively determines the extent to which the user has progressed in learning both online and offline in the blended learning environment, so that even if the user performs the learning while moving online and offline, the progress of the learning is integrated. Through this, appropriate learning tailored to the user's learning progress can be provided both online and offline.

Additionally, in the embodiment, the monitoring system may acquire learning ability monitoring information based on 3) deep learning based on standard data.

Here, the learning ability monitoring information according to the embodiment may be information that analyzes and monitors the user's learning ability for a given learning subject.

In detail, in the embodiment, the monitoring system may acquire the learning ability monitoring information based on deep learning through a deep learning neural network.

At this time, the deep learning neural network that performs the deep learning may be a deep learning neural network that has been pre-trained to calculate and output learning ability monitoring information based on input standard data.

In detail, in the embodiment, the monitoring system may set standard data types for generating learning ability monitoring information.

In an embodiment, the monitoring system sets the 91st data among the third sensing data of the learning device 300 as the 91st standard data and sets the 92nd data among the second sensing data of the second sensor device 200 as the 92nd data. It can be set as standard data, and the 93rd data among the first sensing data of the first sensor device 100 can be set as the 93rd standard data.

In detail, in the embodiment, the monitoring system filters the 91st to 93rd standard data associated with learning ability monitoring information from the entire standard data, and extracts learning ability monitoring information from the filtered 91st to 93rd standard data. It can be input into a neural network.

Therefore, the monitoring system can output learning ability monitoring information based on deep learning based on the deep learning neural network.

For example, the monitoring system uses the 91st standard data as 'the first user stays in the first learning space where the first subject is studied for the first time, and the first user's brain wave data while learning the first subject'. It is possible to obtain 'the numerical value is the first numerical value, the heart rate data value is the second numerical value, and the sweat secretion data is the third numerical value.'

Additionally, as an example, the monitoring system may obtain 'the first user looks at the screen of the learning device 300 during the first time while learning the first subject' as the 92nd standard data.

In addition, as an example, the monitoring system may obtain 'the result score data of the first user performing the online mock exam test content for the first subject is the first numerical value' as the 93rd standard data.

Additionally, in the example, the monitoring system may input the 91st to 93rd standard data obtained as above into the pre-trained deep learning neural network.

And in the example, the monitoring system monitors learning ability monitoring information for the first user based on a deep learning neural network that receives the 91st to 93rd standard data according to a predetermined standard (e.g., a preset level and/or grade, etc.) ) can be obtained according to.

In this way, the monitoring system determines the user's learning ability based on standard data obtained in relation to the user's learning life in a blended learning environment, based on reliable data that monitors the user throughout online and offline. It is possible to identify the user's learning capabilities, control the speed of learning content provided to the user based on the identified user's learning capabilities, and guide the user in the optimal learning direction.

In addition, the monitoring system integrates data from heterogeneous devices and/or heterogeneous data formats into standard data and then inputs preset standard data from all standard data into deep learning to obtain accurate learning ability monitoring information. .

Additionally, in the embodiment, the monitoring system may acquire learning ability auxiliary parameter monitoring information based on 4) deep learning based on standard data.

Here, the learning ability auxiliary parameter monitoring information according to the embodiment is information that analyzes and monitors auxiliary factors that affect the user's learning ability (in the embodiment, self-direction, interest, patience, and/or problem-solving ability, etc.) You can.

In detail, in the embodiment, the monitoring system may acquire the learning ability auxiliary parameter monitoring information based on deep learning through a deep learning neural network.

At this time, the deep learning neural network that performs the deep learning may be a deep learning neural network that has been pre-trained to calculate and output learning ability auxiliary parameter monitoring information based on input standard data.

In detail, the monitoring system in the embodiment may set standard data types for generating learning ability auxiliary parameter monitoring information.

In more detail, in an embodiment, the monitoring system may set the 94th to 96th data among the 1st to 3rd sensing data as the 94th to 96th standard data.

That is, in the embodiment, the monitoring system filters the 94th to 96th standard data associated with learning ability auxiliary parameter monitoring information from the entire standard data, and extracts learning ability auxiliary parameter monitoring information from the filtered 94th to 96th standard data. can be input to the deep learning neural network.

Through this, the monitoring system can output learning ability auxiliary parameter monitoring information based on deep learning based on the deep learning neural network.

For example, the monitoring system uses the 94th standard data as 'the first user stays in the first learning space where the first subject is studied for the first time, and the first user's brain wave data while learning the first subject'. It is possible to obtain 'the numerical value is the first numerical value, the heart rate data value is the second numerical value, and the sweat secretion data is the third numerical value.'

In addition, in the example, the monitoring system can acquire 'the hand movement while the first user is learning the first subject is the same as the first motion data, and the body movement is the same as the second motion data' as the 95th standard data. there is.

In addition, in the example, the monitoring system uses the 96th standard data, 'The most interesting learning subject information obtained based on the user input interface provided based on the learning device 300 of the first user is the same as the first input, and the most difficult 'Learning subject information is the same as the second input, today's target learning amount setting information is the same as the third input, and user memo information is the same as the fourth input' can be obtained.

In addition, in the example, the monitoring system may input the 94th to 96th standard data obtained as above into the pre-trained deep learning neural network, and based on the deep learning neural network that received the 94th to 96th standard data, Learning ability auxiliary parameter monitoring information for the first user according to a predetermined standard may be obtained.

For example, the monitoring system monitors the user's self-direction, interest, patience, or problem-solving ability based on a deep learning neural network that receives the 94th to 96th standard data according to a predetermined standard (e.g., a preset score range). etc.) can be obtained by following.

In this way, the monitoring system, in addition to information directly related to learning, supports learning ability auxiliary parameters (in embodiments, self-direction, interest, patience, and/or problem-solving ability, etc.) that assist the user to efficiently perform learning. By providing analysis information, it is possible to provide learning analysis information for users by considering not only discrete data but also psychological and value-oriented data.

In addition, through this, the monitoring system integrates data such as heterogeneous devices and/or heterogeneous data formats into standard data, then inputs preset standard data from all standard data into deep learning to provide accurate learning ability auxiliary parameter monitoring information. It can be obtained.

In addition, in the embodiment, the monitoring system monitors learning performed throughout online and offline based on the learning time monitoring information, learning progress monitoring information, learning ability monitoring information, and/or learning ability auxiliary parameter monitoring information obtained as above. Blended learning monitoring information, which is integrated monitoring information, can be created.

Figure 8 is an example of blended learning monitoring information output as a graphic image according to an embodiment of the present invention.

Additionally, referring to FIG. 8, in the embodiment, the monitoring system may provide the blended learning monitoring information obtained as above according to a predetermined method.

In an embodiment, the monitoring system may provide blended learning monitoring information by visualizing it as a graphic image including a certain graph and/or an avatar and outputting it to a display.

In this way, the monitoring system visualizes and provides blended learning monitoring information that comprehensively monitors the learning activities performed by the user in the blended learning environment in various ways, thereby providing the user's learning status and analysis information performed throughout online and offline. can be recognized easily and intuitively from various viewpoints.

As described above, the blended learning monitoring method and system according to an embodiment of the present invention monitors the user in a blended learning environment that links online learning and offline learning, thereby identifying the user's learning activities from either an online or offline perspective. Rather, it has the effect of comprehensively and closely monitoring all learning-related activities performed by users both online and offline.

In addition, the blended learning monitoring method and system according to an embodiment of the present invention acquires various data related to the user's learning from a plurality of sensor devices including various sensors, and configures the blended learning environment based on the data obtained in this way. By monitoring the user, there is an effect of obtaining, analyzing, and providing information related to the user's learning from various angles.

Additionally, the embodiments according to the present invention described above may be implemented in the form of program instructions that can be executed through various computer components and recorded on a computer-readable recording medium. The computer-readable recording medium may include program instructions, data files, data structures, etc., singly or in combination. Program instructions recorded on the computer-readable recording medium may be specially designed and configured for the present invention, or may be known and usable by those skilled in the computer software field. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, and magneto-optical media such as floptical disks. medium), and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, etc. Examples of program instructions include not only machine language code such as that created by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like. A hardware device can be converted into one or more software modules to perform processing according to the invention and vice versa.

The specific implementations described in the present invention are examples and do not limit the scope of the present invention in any way. For the sake of brevity of the specification, descriptions of conventional electronic components, control systems, software, and other functional aspects of the systems may be omitted. In addition, the connections or connection members of lines between components shown in the drawings exemplify functional connections and/or physical or circuit connections, and in actual devices, various functional connections or physical connections may be replaced or added. Can be represented as connections, or circuit connections. Additionally, if there is no specific mention such as “essential,” “important,” etc., it may not be a necessary component for the application of the present invention.

In addition, although the detailed description of the present invention has been described with reference to preferred embodiments of the present invention, those skilled in the art or those skilled in the art will understand the spirit of the present invention as described in the patent claims to be described later. It will be understood that the present invention can be modified and changed in various ways without departing from the technical scope. Therefore, the technical scope of the present invention should not be limited to what is described in the detailed description of the specification, but should be defined by the scope of the claims.

Claims (10)

A blended learning monitoring method for monitoring user learning in a blended learning environment performed by a blended learning monitoring system including at least one processor, comprising:
Obtaining a plurality of sensing data based on a plurality of sensor devices;
Converting each of the plurality of sensing data into standard data;
Saving all standard data including the converted standard data;
Comprising the step of providing blended learning monitoring information based on the entire stored standard data,
The step of acquiring the plurality of sensing data includes:
Obtaining first sensing data including user identification data and location data from a first sensor device, obtaining second sensing data including image data from a second sensor device, and online learning content from the learning device. A step of acquiring third sensing data including data,
The step of storing the entire standard data is,
If data of the same context configuration in each standard data converted from the first to third sensing data matches each other, storing the upper data determined according to a predetermined standard in integrated standard data, If the data of the same context configuration of each standard data converted from the first to third sensing data is different from each other, the context configuration includes the fact that each of the standard data and the data of the context configuration are different from each other. Including the step of storing all standard data,
The step of providing the blended learning monitoring information is,
Calculating online learning time information and offline learning time information for each plurality of learning subjects and each chapter of each learning subject based on the stored standard data, and calculating each learning time information and offline learning time information based on the calculated online learning time information and offline learning time information. It includes the step of generating and providing blended learning monitoring information that monitors the online and offline integrated learning amount and online and offline integrated learning progress for each chapter of the learning subject,
The step of generating and providing the blended learning monitoring information is,
A step of inputting standard data for a plurality of sensing data into a pre-trained deep learning neural network to output online learning time information for each chapter of each learning subject, and integrating the online learning time information and the offline learning time information to create a basic learning time information. The integrated online and offline learning amount is calculated for each chapter of each learning subject, and the steps are included.
The step of monitoring the integrated learning time information is,
Analyzing online learning time information for each chapter of each learning subject to determine chapters that have been completed online; Analyzing offline learning time information for each chapter of each learning subject to determine chapters that have been completed offline; Comprising the step of generating total learning progress information by integrating the chapters learned online and the chapters completed offline,
Filtering preset standard data related to learning ability from the stored standard data, and generating learning ability monitoring information indicating the user's learning ability for a predetermined learning subject through the filtered standard data; ,
Filter preset standard data related to learning ability auxiliary parameters from the stored standard data, and analyze the filtered standard data through a pre-trained deep learning neural network to determine auxiliary factors that affect the user's learning ability. Obtaining learning ability auxiliary parameter information, wherein the filtered standard data includes biological data information measured from the user during learning,
Provides to generate and display blended learning monitoring information that integrates and monitors learning performed throughout online and offline by combining the integrated learning amount, the total learning progress information, the learning ability monitoring information, and the learning ability auxiliary parameter information. containing the steps of
Blended learning monitoring method. According to claim 1,
The standard data is,
This is data converted from multiple different formats of sensing data into one standard data format.
Blended learning monitoring method. According to claim 2,
The step of converting the standard data is,
Comprising the step of obtaining the standard data using xAPI (Experience Application Programming Interface; xAPI) format as the standard data format.
Blended learning monitoring method. According to claim 3,
The step of converting the standard data is,
Generating a first sentence consisting of “subject, verb, and object” based on the first sensing data of the first sensor device and including it in the first standard data;
Generating a second sentence consisting of “subject, verb, and object” based on the second sensing data of the second sensor device and including it in the second standard data;
Generating a third sentence consisting of “subject, verb, and object” based on the third sensing data of the learning device and including at least two steps in the third standard data
Blended learning monitoring method. According to claim 4,
The step of converting the standard data is,
Including the measured value of the first sensing data of the first sensor device in the first standard data as a “result data” configuration;
Generating a “context” configuration that adds additional meaning to the first sentence based on the first sensing data of the first sensor device and including it in the first standard data,
The result data is data that is included as an additional component in addition to the “subject, verb, and object” that are the components of the standard data.
Blended learning monitoring method. According to claim 1,
The step of storing the entire standard data including the converted standard data,
Comprising the step of storing a plurality of the converted standard data in LRS (Learning Record Store)
Blended learning monitoring method. According to claim 6,
The step of storing the plurality of converted standard data in LRS (Learning Record Store),
Comprising the step of removing and storing redundant data among the plurality of converted standard data.
Blended learning monitoring method. delete delete delete

Images