JP7466251B1 - Learning support system and learning support method - Google Patents

Abstract

[Problem] To provide a technology that realizes learning support by effectively calling out to students. [Solution] A learning support system that provides students with a lecture consisting of video and audio by an avatar lecturer, which is a virtual person modeled after a lecturer, stores student attribute information that is information about the attributes of the students, identifies specific timing in the provision of a lecture to a student as a calling timing, which is a timing when the avatar lecturer speaks to the student through video and audio, identifies a calling topic that is a topic of calling to be provided at the calling timing based on the student attribute information and/or the calling timing, identifies a calling manner that is a manner to be used for calling based on the student attribute information, and outputs a call based on the calling topic and the calling manner at the calling timing. [Selected Figure] Figure 1

Description

The present invention relates to technology that supports learning using a computer system.

Patent Document 1 discloses a learning system that provides lectures including video and audio. The learning system judges whether or not a student is concentrating on a lecture based on images acquired to film the student attending the lecture, records concentration judgment result information based on the result of the judgment, judges whether or not the student understands the contents of the lecture based on the images and the concentration judgment result information, records understanding judgment result information based on the result of the judgment, and controls the lecture based on the concentration judgment result information and the understanding judgment result information. Since the lecture is controlled according to the student's level of concentration and level of understanding, it is possible to support effective learning for each student.

JP 2021-018316 A

When a real human instructor teaches face-to-face to students, it is known that if the instructor gives appropriate encouragement at the right time, it can increase the students' motivation and concentration, improving the effectiveness of their learning. However, in the field of technology that uses computers to provide lectures through video and audio from avatar instructors, little research has been done on how to provide effective encouragement.

One objective of this disclosure is to provide technology that provides learning support to students by providing effective encouragement.

A learning support system according to one embodiment of the present invention is a learning support system that provides a lecture consisting of video and audio to a student by an avatar lecturer, which is a virtual person simulating a lecturer, and has a student attribute information storage unit that stores student attribute information, which is information related to the attributes of the student; a call-out timing identification unit that identifies a specific timing in the provision of the lecture to the student as a call-out timing, which is a timing when the avatar lecturer speaks to the student by video and audio; a call-out topic identification unit that identifies a call-out topic to be provided at the call-out timing based on the student attribute information and/or the call-out timing; a call-out mode identification unit that identifies a call-out mode, which is a mode used for the call, based on the student attribute information; and a call-out output unit that outputs the call-out topic and the call-out mode at the call-out timing.

One aspect of the present disclosure makes it possible to provide learning support to students by providing effective encouragement.

1 is a block diagram showing a functional configuration of a learning support system according to a first embodiment. FIG. 2 is a block diagram showing a hardware configuration of the learning support system. FIG. 13 is a diagram showing a table of attendee attribute information. 13 is a flowchart of a call process. 13 is a flowchart of a process of identifying a topic to be spoken to; FIG. 13 is a diagram showing a pre-lecture topic list. FIG. 13 shows a post-lecture topic list. FIG. 11 is a block diagram showing a functional configuration of a learning support system according to a second embodiment. FIG. 11 is a diagram showing an example of concentration determination result information.

The following describes an embodiment of the present invention with reference to the drawings.

First Embodiment
The learning support system of this embodiment is a computer system that provides students with lecture content consisting of video and audio by a virtual person (hereinafter also referred to as an "avatar lecturer") who resembles a lecturer. The learning support system also improves the effectiveness of the students' learning by having the avatar lecturer speak to the students at specific times during the provision of the lecture content.

Figure 1 is a block diagram showing the functional configuration of a learning support system according to the first embodiment.

Referring to FIG. 1, the learning support system 10 has a lecture output unit 19, a call timing identification unit 11, a call topic identification unit 12, a call manner identification unit 13, a call output unit 14, and a memory unit 15. The memory unit 15 stores data prepared in advance that is necessary to execute the service. As an example, the processing of the lecture output unit 19, the call timing identification unit 11, the call topic identification unit 12, the call manner identification unit 13, and the call output unit 14 is defined by a software program, and is realized by the processor executing the software program.

Figure 2 is a block diagram showing the hardware configuration of the learning support system.

Referring to FIG. 2, the learning support system 10 is composed of a server 20 and an information terminal such as a personal computer or a smartphone that can connect to the server 20 via a communication network such as the Internet. A student 90 connects to the server 20 using a browser 33 on an information terminal 30 and uses a service provided by the server 20. The service is a service that provides content related to learning. The service is realized by the various parts shown in FIG. 1.

As shown in FIG. 2, the server 20 has, as its hardware, a processing device 21, a main memory 22, a storage device 23, a communication device 24, an input device 25, and a display device 26, which are connected to a bus 27.

The storage device 23 stores data in a writable and readable manner. The storage unit 15 shown in Fig. 1 is realized by this storage device 23. The processing device 21 is a processor that reads the data stored in the storage device 23 into the main memory 22 and executes the processing of the software program using the main memory 22. The processing device 21 realizes the lecture output unit 19, the calling timing identification unit 11, the calling topic identification unit 12, the calling manner identification unit 13, and the calling output unit 14 shown in Fig. 1.
The communication device 24 transmits information processed by the processing device 21 via a communication network including wired and/or wireless communication, and also transmits information received via the communication network to the processing device 21. The received information is used for software processing in the processing device 21. The input device 25 is a device that accepts information input by an operator using a keyboard, mouse, etc., and the input information is used for software processing in the processing device 21. The display device 26 is a device that displays image and text information on a display screen in conjunction with software processing by the processing device 21. The input device 25 and display device 26 are provided mainly for use by an administrator (not shown) rather than the students 90.

Returning to FIG. 1, the memory unit 15 pre-stores lecture content, student attribute information, a pre-lecture topic list, and a post-lecture topic list. As lecture content, content containing lectures for each unit of content to be learned is prepared. As student attribute information, information on the attributes of each student 90 is recorded. The pre-lecture topic list is a list of topics used in greetings provided before the lecture content is provided. The post-lecture topic list is a list of topics used in greetings provided after the lecture content is provided.

Figure 3 shows a table of participant attribute information.

In the table of student attribute information D01, the student number (No.), name, address, preferences, date of birth, and desired dialect of each student 90 are registered. The name indicates the name of the student 90. The address indicates the address of the student 90. The preference indicates the preference of the student 90. The date of birth indicates the date of birth of the student 90. The desired dialect indicates the dialect that the student 90 wishes the avatar instructor to use. A dialect is a language system used in a specific region. For example, a student 90 with student number 1 is named "Patent Ichiro", lives in "Nagoya City, Aichi Prefecture...", likes "cats" and the "Chunichi Dragons", was born on October 1, 2001, and wishes the avatar instructor to use "Nagoya dialect."

The lecture output unit 19 provides the lecture content stored in the memory unit 15 to the students 90 via the browser 33 of the information terminal 30 according to the requests and learning progress of each student 90.

The calling timing identification unit 11, the calling topic identification unit 12, the calling manner identification unit 13, and the calling output unit 14 work together to execute a series of processes for calling out to the students 90. Hereinafter, this series of processes is also referred to as the calling process.

Figure 4 is a flowchart of the call process.

In step 101, the call timing specification unit 11 specifies a specific timing in the provision of lecture content to the student 90 as a call timing, which is a timing when the avatar lecturer calls out to the student 90 by video and audio. The call timing specification unit 11 specifies, for example, a pre-lecture timing, which is a timing before the start of the provision of the lecture content, as the call timing. Calling out before the lecture is an important timing that affects the effectiveness of the subsequent lecture. By making an appropriate call at that timing, it is possible to start providing the lecture in a state where the student 90 is highly motivated and focused. In addition, the call timing specification unit 11 specifies, for example, a post-lecture timing, which is a timing after the end of the provision of the lecture content, as the call timing. Not only listening to the lecture, but also reviewing the lecture content and practicing problems related to the lecture can effectively improve academic ability. By making an appropriate call at that timing, it is possible to increase the motivation of the student 90 for learning after receiving the lecture.

In step 102, the call topic identification unit 12 identifies a call topic, which is a topic of call to be provided to the student 90 at the call timing, based on the student attribute information D01 and/or the call timing. Hereinafter, this process of identifying the call topic is also referred to as a call topic identification process.

Figure 5 is a flowchart of the process for identifying topics of conversation.

In step 201, the calling topic identification unit 12 determines whether the identified calling timing is before the lecture or after the lecture.

If the call timing is before the lecture, in step 202, the call topic identification unit 12 determines one or more call topics from the pre-lecture topic list.

Figure 6 shows a list of pre-lecture topics.

In the pre-lecture topic list D02, "encouragement," "real-time topics," and "interesting topics" are set as suitable topics for encouraging students before starting the lecture content. "Encouragement" is a topic that directly increases the motivation of the students. "Real-time topics" are real-time topics that are likely to interest the students, such as the weather and news in the students' local area and the results of sports for the day. Actual real-time weather, news, and sports results information can be obtained, for example, from external sites. "Interesting topics" are topics related to things that the students like, such as if the students like cats, then talking about pet cats would be appropriate. "Real-time topics" and "interesting topics" are considered to have the effect of directing the students' attention to the lecture.

The method by which the call topic identification unit 12 determines one or more call topics from the pre-lecture topic list D02 is not particularly limited. For example, the call topic identification unit 12 may randomly select one or more call topics from the pre-lecture topic list D02. Alternatively, the call topic identification unit 12 may sequentially select call topics by cycling through the topics in the pre-lecture topic list D02.

If the call timing is post-lecture, in step 203, the call topic identification unit 12 determines one or more call topics from the post-lecture topic list.

Figure 7 shows the post-lecture topic list.

In the post-lecture topic list D03, "appreciation" and "interesting topics" are set as suitable topics for encouraging students after finishing the lecture content. "Appreciation" is a topic that expresses appreciation for attending the lecture and increases motivation for future learning. "Interesting topics" are topics related to things that the student likes, and are thought to have the effect of relieving the student's fatigue and increasing motivation for future learning.

The method by which the call-out topic identification unit 12 determines one or more call-out topics from the post-lecture topic list D03 is not particularly limited. For example, the call-out topic identification unit 12 may randomly select one or more call-out topics from the post-lecture topic list D03. Alternatively, the call-out topic identification unit 12 may sequentially select call-out topics by cycling through the topics in the post-lecture topic list D03.

Returning to FIG. 4, in step 103, the addressing manner identification unit 13 identifies an addressing manner that is a manner used to address the student 90 based on the student attribute information D01. In the present embodiment, the addressing manner is, as an example, an addressing language system that is a language system used to address the student 90. For example, if a desired dialect (language system) is registered in the student attribute information D01, the addressing manner identification unit 13 may identify the language system as the addressing language system for the student 90. Also, if a desired dialect (language system) is not registered in the student attribute information D01, the addressing manner identification unit 13 may identify the dialect of the area indicated by the address registered in the student attribute information D01 as the addressing language system for the student 90. Alternatively, if a desired dialect (language system) is not registered in the student attribute information D01, the addressing manner identification unit 13 may identify standard Japanese as the addressing language system for the student 90.

The calling style specification unit 13 may select one of the language systems as the calling language system, or may combine multiple language systems to form the calling language system. For example, in the student attribute information D01 of FIG. 3, the student "Patent Ichiro" with student number "1" desires "Nagoya dialect" and has a preference for "cats," so the calling style specification unit 13 may specify a calling style that combines "Nagoya dialect" and a word (animal language) that imitates "cats." As an example, it is possible to call out, "Hello, Patent Ichiro. It's really hot in Nagoya today. Are you feeling okay? Your favorite team, the Chunichi Dragons, won last night, meow. Let's study hard, Patent Ichiro. Let's start the lecture, meow."

Next, in step 104, the call output unit 14 outputs the video and audio of the call based on the call topic and the call manner at the call timing to the student 90 via the browser 33 of the information terminal 30.

Second Embodiment
The learning support system of the second embodiment has the same functions as the first embodiment, and in addition, it acquires the status of students attending a lecture from images and audio of the students, and uses the acquired information on the students' status to control subsequent encouragement, thereby improving the effectiveness of encouragement.

The learning support system of the second embodiment has the same configuration and operation as that of the first embodiment, so the following mainly describes the differences between the first embodiment and the second embodiment.

Figure 8 is a block diagram showing the functional configuration of the learning support system according to the second embodiment. The hardware configuration of the learning support system of the second embodiment is similar to that of the first embodiment shown in Figure 2.

In the second embodiment, the learning support system 10 has a concentration determination unit 16 in addition to a lecture output unit 19, a call-out timing determination unit 11, a call-out topic determination unit 12, a call-out manner determination unit 13, a call-out output unit 14, and a memory unit 15. The concentration determination unit 16, like the lecture output unit 19, the call-out timing determination unit 11, the call-out topic determination unit 12, and the call-out manner determination unit 13, is realized by a processing device 21, which is a processor that executes the processing of a software program.

The concentration determination unit 16 determines whether the student 90 is concentrating on the lecture based on an image captured by the camera 31 of the information terminal 30 to photograph the student 90, and records concentration determination result information based on the result of the determination. There are no particular limitations on the method of concentration determination, but for example, if the following conditions are met: the student 90 is in front of the terminal, has a good posture, has his/her eyes open, and is looking at the screen, he/she may be determined to be concentrating.

Figure 9 is a diagram showing an example of concentration judgment result information. Here, concentration judgment result information related to calling out before a lecture and a method for calculating the same will be described, but concentration judgment result information related to calling out after a lecture and a method for calculating the same may also be used. In the case of calling out before a lecture, concentration judgment is made based on an image of the student in the lecture after the calling out, but in the case of calling out after a lecture, concentration judgment can be made based on an image of the student in the review or practice questions after the lecture.

In the concentration determination result information D04, the concentration level for each time of the topic and the concentration level by topic are recorded in association with each topic of the call to start the lecture content. The method of calculating the concentration level by topic is not particularly limited, but for example, the concentration determination unit 16 may calculate and accumulate the concentration level for each time, which is the concentration level for the subsequent lecture, each time a call is made on the topic, and calculate the average value of the accumulated concentration levels for each time by topic to set it as the concentration level by topic. In addition, the method of calculating the concentration level for each time is also not particularly limited, but for example, the concentration determination unit 16 may determine whether the students are concentrating or not based on the image at regular intervals, record a concentration flag indicating whether they are concentrating or not, and perform a five-level evaluation based on the ratio of the number of times of concentration and non-concentration during the lecture, and set the evaluation result as the concentration level for each time. In addition, the concentration determination unit 14 may update the concentration level by topic each time a call is made, or may update it at a specified period of time.

In the example of Figure 9, for the topic "encouragement", the concentration levels for each episode are 4, 5, 5, 5, 4, 4, 5..., and the concentration level by topic is 4.5. In this example, the concentration level for each episode is expressed on a five-level scale from "1" to "5". "5" indicates the highest concentration and "1" indicates the lowest concentration. For the topic "real-time topics", the concentration levels for each episode are 4, 3, 3, 3, 4, 3, 3..., and the concentration level by topic is 3.2. For the topic "preference topics", the concentration levels for each episode are 3, 4, 4, 4, 3, 4..., and the concentration level by topic is 3.8.

The calling topic identification unit 12 selects a calling topic for the pre-lecture timing and a calling topic for the post-lecture timing based on the concentration judgment result information corresponding to the lecture of the student 90 after the calling. The method of selecting the calling topic is not particularly limited, but for example, the calling topic identification unit 12 may select subsequent topics so that the ratio of topics with high topic-specific concentration is high and the ratio of topics with low topic-specific concentration is low. For example, the calling topic identification unit 12 may select topics so that the ratio of each topic matches the ratio of the concentration of each topic to the total topic-specific concentration. This makes it possible to provide students with many effective calls without excessive concentration on the same topic and while allowing the topic-specific concentration to be updated.

For the pre-lecture timing, the call topic identification unit 12 aggregates the call topic provided to the student 90 and the concentration judgment result information corresponding to the lecture of the student 90 after the call based on the call topic, calculates the correlation between them, and selects the call topic to be provided for the pre-lecture timing based on the correlation.

For example, if a student is asked about current events in baseball before a lecture as a topic of interest, and the student's level of concentration during the lecture is high, then the frequency of asking about current events in baseball before the lecture may be increased. Also, if a student is asked about cats before a lecture, and the student's level of concentration during the lecture is high, then the frequency of asking about cats before the lecture may be increased. If a student is asked about food before a lecture, and the student's level of concentration during the lecture is high, then the frequency of asking about food before the lecture may be increased.

For the post-lecture timing, the call topic identification unit 12 selects a call topic to be provided at the post-lecture timing of a lecture based on the concentration judgment result information corresponding to the lecture of the student 90.

Third Embodiment
The learning support system of the third embodiment sets a personality for the avatar instructor that matches the student, and talks to the student based on that personality. It is known that in the real world, if a student likes or feels close to the instructor, the student's concentration in the lecture and motivation to study increases, but since an avatar instructor is different from an instructor who is a real person, it is difficult for the student to like or feel close to the avatar instructor. In this embodiment, by giving the avatar instructor a personality, it is possible to make the student more likely to like or feel close to the avatar instructor.

The learning support system of the third embodiment has the same configuration and operation as that of the first embodiment, so the following mainly describes the parts of the third embodiment that are different from the first embodiment.

The functional and hardware configurations of the learning support system according to the third embodiment are similar to those of the first embodiment shown in Figures 1 and 2, respectively.

In the third embodiment, the calling style identification unit 13 sets a personality for the avatar instructor based on the student attribute information of the student 90, and identifies a calling style based on the personality. As a result, the calling provided to the student 90 from the calling output unit 14 is a call from the avatar instructor with the set personality. The personality can be set, for example, based on preferences, character, attitude, speaking style, etc.

For example, the speaking style identification unit 13 may set the avatar instructor to have a personality with similar tastes to the student 90 based on the student attribute information of the student 90, and identify the speaking style based on that personality. This makes it easier for the student to feel a sense of closeness to the avatar instructor.

For example, if a student is a dog lover, then it is conceivable to set a dog-loving preference as the personality of the avatar instructor. Then, when speaking to students about topics related to their preferences, the dog-loving avatar instructor will speak about dogs, and students will be more likely to feel a good impression and affinity towards the avatar instructor.

<Additional Notes>
Although the embodiments of the present invention have been described above, the present invention is not limited to these embodiments, and these embodiments may be used in combination or some of the configurations may be changed within the scope of the technical concept of the present invention.

The above-described embodiment also includes the following items. However, the items included in the above-described embodiment are not limited to those listed below.

(Item 1)
A learning support system in which a lecture consisting of video and audio is provided to students by an avatar lecturer, which is a virtual character modeled after a lecturer, comprising: a student attribute information storage unit which stores student attribute information, which is information relating to the attributes of the students; a call-out timing identification unit which identifies a specific timing in the provision of the lecture to the student as a call-out timing, which is a timing when the avatar lecturer speaks to the student by video and audio; a call-out topic identification unit which identifies a call-out topic, which is a topic of call to be provided at the call-out timing, based on the student attribute information and/or the call-out timing; a call-out style identification unit which identifies a call-out style, which is a style used for the call, based on the student attribute information; and a call-out output unit which outputs the call-out topic and the call-out style at the call-out timing.

This allows for prompts on appropriate topics at appropriate times and in appropriate ways as the lecture is delivered, making it possible to provide effective prompts that improve the learning outcomes of students.

(Item 2)
In the learning support system described in item 1, the calling style is a calling language system that is a language system used for calling. According to this, calling is performed in a language of a specific language system such as a dialect, so that effective calling can be performed.

(Item 3)
In the learning support system described in item 2, the student attribute information includes information on the address of the student and information on a desired language system that is a language system desired by the student, and the calling style specification unit specifies the calling language system based on the address and the desired language system. This allows the student to be called out in a local dialect or in a favorable manner, making it possible to call out effectively.

(Item 4)
In the learning support system described in item 2, the student attribute information includes information on the student's address and information on the student's favorite animal, which is the student's favorite animal, and the calling language system is a combination of a dialect, which is a language system unique to each region, and animal words that add onomatopoeia that imitate animal sounds or mimetic words that imitate animal behavior to the end of words, and the calling manner identification unit identifies the calling language system based on the dialect determined from the address and the animal words determined from the student's favorite animal.

(Item 5)
In the learning support system described in item 1, the addressing style specification unit sets a personality for the avatar instructor based on the student attribute information of the student, and specifies an addressing style based on the personality. By providing the avatar instructor with a personality, the student can easily feel a good impression and affinity for the avatar instructor.

(Item 6)
In the learning support system described in item 5, the addressing style specification unit sets a personality having similar tastes to the student for the avatar instructor based on the student attribute information of the student, and specifies an addressing style based on the personality. This makes the student feel closer to the avatar instructor.

(Item 7)
In the learning support system described in item 1, the call timing specification unit specifies a pre-lecture timing, which is a timing before the start of the lecture, as the call timing. According to this, by making an appropriate call to the student at the pre-lecture timing, it is possible to start the lecture in a state where the student's motivation and concentration are high.

(Item 8)
In the learning support system described in item 7, the call topic identification unit selects, as the call topic to be provided at the pre-lecture timing, a call topic that highly motivates the students for the lecture to be provided thereafter. This makes it possible to effectively increase the motivation of the students before the lecture.

(Item 9)
The learning support system described in item 8 further comprises a concentration judgment unit that judges whether the student is concentrating on the lecture based on an image acquired to photograph the student attending the lecture and records concentration judgment result information based on the result of the judgment, and the calling topic identification unit selects a calling topic to be provided at the pre-lecture timing based on the relationship between the calling topic and the concentration judgment result information corresponding to the lecture after the calling based on the calling topic. This makes it possible to select a highly effective calling based on an actually measured result.

(Item 10)
In the learning system described in item 1, the concentration determination unit calculates a topic-specific concentration degree indicating the degree of concentration of the student on the lecture after the call for each of the call topics, and the call topic identification unit selects the call topic such that the ratio of topics with a high topic-specific concentration degree is lower than the ratio of topics with a low topic-specific concentration degree. This makes it possible to give the student many effective calls without excessive concentration on the same topic and while enabling the topic-specific concentration degree to be updated.

(Item 11)
In the learning system described in item 10, the call-out topic identification unit selects call-out topics such that the ratio of each of the call-out topics matches the ratio of the concentration degree of the call-out topic to the total value of the concentration degrees by topic.

(Item 12)
In the learning support system described in item 1, the call-out timing specification unit specifies a post-lecture timing, which is a timing after the provision of the lecture, as the call-out timing. According to this, by making an appropriate call to the student after the lecture, it is possible to increase the student's motivation for learning after the lecture.

(Item 13)
A learning support method in which a lecture consisting of video and audio is provided to students by an avatar lecturer, which is a virtual character modeled after a lecturer, using a computer having a processing device and a storage device, wherein the storage device stores student attribute information, which is information relating to the attributes of the students, and the processing device identifies a specific timing in the provision of the lecture to the students as a calling timing, which is a timing at which the avatar lecturer speaks to the students using video and audio, identifies a calling topic, which is a topic of the calling to be provided at the calling timing, based on the student attribute information and/or the calling timing, identifies a calling manner, which is a manner to be used for the calling, based on the student attribute information, and outputs the calling topic and the calling manner at the calling timing.

10: Learning support system, 11: Timing identification unit, 12: Topic identification unit, 13: Behavior identification unit, 14: Output unit, 15: Memory unit, 16: Concentration judgment unit, 19: Lecture output unit, 20: Server, 21: Processing device, 22: Main memory, 23: Storage device, 24: Communication device, 25: Input device, 26: Display device, 27: Bus, 30: Information terminal, 31: Camera, 33: Browser, 90: Student, D01: Student attribute information, D02: Pre-lecture topic list, D03: Post-lecture topic list

Claims (10)

A learning support system that provides a lecture consisting of video and audio to students by an avatar lecturer, which is a virtual person modeled after a lecturer,
a student attribute information storage unit that stores student attribute information that is information related to the attributes of students;
a call-out topic specification unit that specifies a call-out topic to be provided at the call-out timing based on the student attribute information and/or a specific timing in providing the lecture to the student, the call-out timing being a timing at which the avatar lecturer speaks to the student by video and audio;
a calling style specification unit that specifies a calling style to be used for the calling based on the student attribute information;
a call output unit that outputs a call according to the call topic and the call mode at the call timing;
having
The calling style is a calling language system that is a language system used for calling,
The student attribute information includes address information of the student and information on a desired language system, which is a language system desired by the student,
the addressing style specification unit specifies the addressing language system based on the address and the desired language system .
Learning support system. A learning support system that provides a lecture consisting of video and audio to students by an avatar lecturer, which is a virtual person modeled after a lecturer,
a student attribute information storage unit that stores student attribute information that is information related to the attributes of students;
a call-out topic specification unit that specifies a call-out topic to be provided at the call-out timing based on the student attribute information and/or a specific timing in providing the lecture to the student, the call-out timing being a timing at which the avatar lecturer speaks to the student by video and audio;
a calling style specification unit that specifies a calling style to be used for the calling based on the student attribute information;
a call output unit that outputs a call according to the call topic and the call mode at the call timing;
having
The calling style is a calling language system that is a language system used for calling,
The student attribute information includes address information of the student and information on a favorite animal of the student, which is a favorite animal of the student,
The voice language system is a combination of a dialect, which is a language system peculiar to each region, and an animal language, which adds an onomatopoeia that imitates the sound of an animal or an onomatopoeia that imitates the action of an animal to the end of a word,
the calling style specification unit specifies the calling language system based on a dialect determined from the address and an animal word determined from the favorite animal ;
Learning support system. A learning support system that provides a lecture consisting of video and audio to students by an avatar lecturer, which is a virtual person modeled after a lecturer,
a student attribute information storage unit that stores student attribute information that is information related to the attributes of students;
a call-out topic specification unit that specifies a call-out topic to be provided at the call-out timing based on the student attribute information and/or a specific timing in providing the lecture to the student, the call-out timing being a timing at which the avatar lecturer speaks to the student by video and audio;
a calling style specification unit that specifies a calling style to be used for the calling based on the student attribute information;
a call output unit that outputs a call according to the call topic and the call mode at the call timing;
having
the addressing style specification unit sets a personality having similar tastes to the student for the avatar instructor based on the student attribute information of the student, and specifies an addressing style based on the personality .
Learning support system. A learning support system that provides a lecture consisting of video and audio to students by an avatar lecturer, which is a virtual person modeled after a lecturer,
a student attribute information storage unit that stores student attribute information that is information related to the attributes of students;
a call-out topic specification unit that specifies a call-out topic to be provided at the call-out timing based on the student attribute information and/or a specific timing in providing the lecture to the student, the call-out timing being a timing at which the avatar lecturer speaks to the student by video and audio;
a calling style specification unit that specifies a calling style to be used for the calling based on the student attribute information;
a call output unit that outputs a call according to the call topic and the call mode at the call timing;
having
The timing for calling out is a pre-lecture timing, which is a timing before the start of providing the lecture,
The learning support system further includes a concentration judgment unit that judges whether the student is concentrating on the lecture based on an image acquired to photograph the student attending the lecture, and records concentration judgment result information based on the result of the judgment,
The calling topic specification unit selects a calling topic to be provided at the pre-lecture timing based on a relationship between the calling topic and concentration determination result information corresponding to the lecture after the calling by the calling topic .
Learning support system. the concentration determination unit calculates a topic-specific concentration degree indicating a concentration degree of the student on the lecture after the calling for each of the called topics,
the calling topic identification unit selects the calling topic such that a ratio of topics having a high topic-specific concentration degree is lower than a ratio of topics having a low topic-specific concentration degree.
The learning support system according to claim 4 . the calling topic identification unit selects a calling topic such that a ratio of each of the calling topics matches a ratio of a concentration degree of the calling topic to a total value of the concentration degrees by topic.
The learning support system according to claim 5 . A learning support method for providing a lecture consisting of video and audio to students by an avatar lecturer, which is a virtual person modeled after a lecturer, using a computer having a processing device and a storage device, comprising:
The storage device stores attendee attribute information which is information regarding attributes of attendees,
The processing device comprises:
identifying a calling topic to be provided at the calling timing based on the student attribute information and/or a calling timing which is a specific timing in providing the lecture to the student and is a timing at which the avatar lecturer calls out to the student by video and audio, and
Identifying a calling style to be used for the calling based on the student attribute information;
outputting a call according to the call topic and the call manner at the call timing;
In the method,
The calling style is a calling language system that is a language system used for calling,
The student attribute information includes address information of the student and information on a desired language system, which is a language system desired by the student,
the processing device identifies the speech language system based on the address and the desired language system;
Learning support methods. A learning support method for providing a lecture consisting of video and audio to students by an avatar lecturer, which is a virtual person modeled after a lecturer, using a computer having a processing device and a storage device, comprising:
The storage device stores attendee attribute information which is information regarding attributes of attendees,
The processing device comprises:
identifying a calling topic to be provided at the calling timing based on the student attribute information and/or a calling timing which is a specific timing in providing the lecture to the student and is a timing at which the avatar lecturer calls out to the student by video and audio, and
Identifying a calling style to be used for the calling based on the student attribute information;
outputting a call according to the call topic and the call manner at the call timing;
In the method,
The calling style is a calling language system that is a language system used for calling,
The student attribute information includes address information of the student and information on a favorite animal of the student, which is a favorite animal of the student,
The voice language system is a combination of a dialect, which is a language system peculiar to each region, and an animal language, which adds an onomatopoeia that imitates the sound of an animal or an onomatopoeia that imitates the action of an animal to the end of a word,
the processing device specifies the voice-calling language system based on a dialect determined from the address and an animal word determined from the favorite animal;
Learning support methods. A learning support method for providing a lecture consisting of video and audio to students by an avatar lecturer, which is a virtual person modeled after a lecturer, using a computer having a processing device and a storage device, comprising:
The storage device stores attendee attribute information which is information regarding attributes of attendees,
The processing device comprises:
identifying a calling topic to be provided at the calling timing based on the student attribute information and/or a calling timing which is a specific timing in providing the lecture to the student and is a timing at which the avatar lecturer calls out to the student by video and audio, and
Identifying a calling style to be used for the calling based on the student attribute information;
outputting a call according to the call topic and the call manner at the call timing;
In the method,
the processing device sets a personality having similar tastes to the student for the avatar instructor based on the student attribute information of the student, and specifies a manner of speaking to the student based on the personality;
Learning support methods. A learning support method for providing a lecture consisting of video and audio to students by an avatar lecturer, which is a virtual person modeled after a lecturer, using a computer having a processing device and a storage device, comprising:
The storage device stores attendee attribute information which is information relating to attributes of attendees,
The processing device comprises:
identifying a calling topic to be provided at the calling timing based on the student attribute information and/or a calling timing which is a specific timing in providing the lecture to the student and is a timing at which the avatar lecturer calls out to the student by video and audio, and
Identifying a calling style to be used for the calling based on the student attribute information;
outputting a call according to the call topic and the call manner at the call timing;
In the method,
The timing for calling out is a pre-lecture timing, which is a timing before the start of providing the lecture,
The processing device judges whether the students are concentrating on the lecture based on an image acquired to photograph the students attending the lecture, and records concentration judgment result information based on the result of the judgment.
selecting a calling topic to be provided at the pre-lecture timing based on a relationship between the calling topic and concentration determination result information corresponding to the lecture after the calling by the calling topic;
Learning support methods.

Images