Learning motivation determination system, learning motivation determination device, learning motivation determination method, learning motivation determination program

Abstract

To provide a learning motivation determination system, learning motivation determination server, learning motivation determination method, and learning motivation determination program that can be also applied to existing e-learning without using a special device, and can improve learning efficiency in various e-learning by improving learners' learning motivation before taking classes.SOLUTION: A learning motivation determination system 1 includes: a terminal input unit 22 that acquires and transmits image information obtained by capturing an image of a learner and voice information obtained by recording voice of the learner; a terminal output unit 23 that displays and reproduces content that can be viewed by the learner; an analysis unit 12 that analyzes the image information and the voice information to calculate a learning motivation value correlating with the learner's learning motivation; a determination unit 13 that compares the learning motivation value with a predetermined threshold value; and an advice selection unit 14 that selects advice corresponding to the learning motivation value when the learning motivation value is less than the predetermined threshold value, and provides the advice to the learner via the terminal output unit 23.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a learning motivation determination system, a learning motivation determination device, a learning motivation determination method, and a learning motivation determination program that determine a learner's learning motivation before taking learning content via a network, and provide advice to improve learning motivation or allow the learner to start taking the content depending on the determination result. [Background technology]

[0002] In recent years, e-learning has come to be used as a form of learning in which learning content is provided and distributed via storage media such as DVDs or the Internet, in contrast to the traditional face-to-face learning format. Recently, many types of e-learning have also appeared, such as "microlearning," which is short, short, 5- to 15-minute segments that allow students to study in their spare time. This type of e-learning has the advantages of allowing students to study at a time that is convenient for them, regardless of time or place, and that the quality of education is consistent as long as the same learning materials are used, but it has the disadvantage that learning efficiency depends in part on individual motivation.

[0003] For this reason, for example, there have been disclosed an electronic teaching material learning support device, an electronic teaching material learning support system, and an electronic teaching material learning support program (see Patent Document 1) that monitor the psychological and mental state of a learner, estimate the psychological state, and based on this, support learning by providing electronic teaching materials that correspond to the current psychological state, and a learning support device (see Patent Document 2) that supplies high-concentration oxygen from an oxygen supply device to the learner's mouth during periods when important learning content is being covered, thereby improving the learner's concentration. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2006-23506 A [Patent Document 2] JP 2007-236847 A Summary of the Invention [Problem to be solved by the invention]

[0005] However, the invention of Patent Document 1 has problems such as an increase in content production costs because multiple contents are required to match the psychological state of the learner, and if the learner's concentration level is originally low, the number of contents to be taken and the learning time increase, placing a heavy burden on the learner. In addition, since the psychological state and learning contents must be managed for each learner, the system becomes complicated, and at the same time, since the management function is built into the system, it cannot be applied to e-learning provided by other businesses.

[0006] In addition, the invention of Patent Document 2 has the problem that the course must be taken at a location where an oxygen supply device is available, which means that the learner must either bear the cost of purchasing the device or cannot enjoy the advantage of e-learning, which is the ability to take courses anywhere.

[0007] The present invention has been made to solve these problems, and its purpose is to provide a learning motivation assessment system, learning motivation assessment server, learning motivation assessment method, and learning motivation assessment program that can be applied to existing e-learning without the use of special equipment, and that can improve the learning efficiency of various e-learning programs by increasing the learner's motivation to learn before taking the course. [Means for solving the problem]

[0008] In order to achieve the above object, the present invention provides a learning motivation determination system for determining the learning motivation of an e-learning learner before the learner takes the course, and for obtaining at least one of image information obtained by capturing an image of the learner and audio information obtained by recording the voice of the learner. Collaboration Department and , small an analysis unit that analyzes at least one of the audio information and the image information to calculate a learning motivation value that correlates with the learning motivation of the learner; A learning motivation assessment content is reproduced on the terminal device of the learner, and the learning motivation assessment content is analyzed based on either the audio information or the image information acquired during the reproduction of the learning motivation assessment content.a determination unit that compares the learning motivation value with a predetermined threshold value; and a determination unit that, when the learning motivation value is less than the predetermined threshold value, determines whether or not the learning motivation value is greater than the predetermined threshold value. advice Select and select advice The above Terminal equipment a suggestion section for displaying the a distribution unit that distributes learning content to the terminal device when the learning motivation value is equal to or greater than the predetermined threshold value; Equipped with.

[0009] In order to achieve the above object, the present invention provides a learning motivation determination device that determines the learning motivation of an e-learning learner before the learner takes the course, comprising: a linking unit that acquires at least one of image information of the learner and audio information of the learner; an analysis unit that analyzes at least one of image information of the learner and audio information of the learner to calculate a learning motivation value that correlates with the learner's learning motivation; A learning motivation assessment content is reproduced on the terminal device of the learner, and the learning motivation assessment content is analyzed based on either the audio information or the image information acquired during the reproduction of the learning motivation assessment content. a determination unit that compares the learning motivation value with a predetermined threshold value; and a determination unit that, when the learning motivation value is less than the predetermined threshold value, determines whether or not the learning motivation value is greater than the predetermined threshold value. advice Select and select advice of To the terminal device a proposal unit for outputting the proposal; a distribution unit that distributes learning content to the terminal device when the learning motivation value is equal to or greater than the predetermined threshold value; Equipped with.

[0010] In order to achieve the above object, a learning motivation determination method according to the present invention is a learning motivation determination method in which a computer determines the learning motivation of an e-learning learner before taking the course, the method comprising: acquiring at least one of image information of the learner and audio information of the learner; an analysis step of analyzing at least one of image information of the learner and audio information of the learner to calculate a learning motivation value that correlates with the learner's learning motivation; A learning motivation assessment content is reproduced on the terminal device of the learner, and the learning motivation assessment content is analyzed based on either the audio information or the image information acquired during the reproduction of the learning motivation assessment content. a determination step of comparing the learning motivation value with a predetermined threshold value, and when the learning motivation value is less than the predetermined threshold value, advice Select and select advice of To the terminal device A proposed step to output; delivering learning content to the terminal device when the learning motivation value is equal to or greater than the predetermined threshold; Equipped with.

[0011] In order to achieve the above object, a learning motivation determination program according to the present invention is a learning motivation determination program for causing a computer to determine the learning motivation of an e-learning learner before the learner takes the course, comprising: acquiring at least one of image information of the learner and audio information of the learner; an analysis step of analyzing at least one of image information of the learner and audio information of the learner to calculate a learning motivation value that correlates with the learner's learning motivation; A learning motivation assessment content is reproduced on the terminal device of the learner, and the learning motivation assessment content is analyzed based on either the audio information or the image information acquired during the reproduction of the learning motivation assessment content. a determination step of comparing the learning motivation value with a predetermined threshold value, and when the learning motivation value is less than the predetermined threshold value, advice Select and select advice of To the terminal device A proposed step to output; delivering learning content to the terminal device when the learning motivation value is equal to or greater than the predetermined threshold; It is a program for causing a computer to execute the above. Effect of the Invention

[0012] According to the present invention, which uses the above-mentioned means, it can be applied to existing e-learning without using any special equipment, and by increasing the learner's motivation to learn before taking the course, it is possible to improve the learning efficiency in various e-learning programs. [Brief description of the drawings]

[0013] [Figure 1] 1 is a system configuration diagram showing a learning motivation determination system according to an embodiment of the present invention. [Diagram 2] 4 is a flowchart showing a learning motivation determination routine of the learning motivation determination system according to the embodiment of the present invention. [Diagram 3] FIG. 1 is a schematic block diagram showing a configuration of a computer according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0015] <Configuration> FIG. 1 is a system configuration diagram showing a learning motivation determination system 1 including a learning motivation determination server 11 according to an embodiment of the present invention. The learning motivation determination system 1 is a learning motivation determination system that determines the learning motivation of a learner of e-learning before the learner takes the course. Specifically, the learning motivation determination system 1 is a system that calculates a learning motivation value as a state value correlating with the learner's learning motivation before the learner takes the e-learning course provided by the e-learning provider, and if the learning motivation value is lower than a predetermined threshold, provides the learner with advice according to the learning motivation value to improve the learning motivation. Also, if the learning motivation value is equal to or higher than a predetermined threshold, the learner is permitted to take the e-learning course. The learning motivation includes at least one of the learner's emotions, concentration, and fatigue level, or a combination of these. The learning motivation value is calculated based on the result of analyzing an image including the learner's voice or face.

[0016] As shown in Fig. 1, the learning motivation determination system 1 according to this embodiment is configured by connecting a learning motivation determination server 11 operated by a business providing a learning motivation determination service, a learner terminal device 21 (hereinafter simply referred to as terminal device 21) which is a terminal device used by a learner, and an e-learning server 31 operated by an e-learning business via a network NW such as the Internet or a VPN (Virtual Private Network). For the sake of simplicity of explanation, Fig. 1 shows only terminal device 21 assuming one learner, but the learning motivation determination server 11 can be connected to terminal devices 21 of multiple users via the network NW. Similarly, the learning motivation determination server 11 can be connected to multiple e-learning servers 31.

[0017] The learning motivation assessment server 11 comprises an analysis unit 12, a assessment unit 13, an advice selection unit 14, a collaboration unit 15, a learner database 16, a assessment content database 17, and an advice database 18 (hereinafter, database may be abbreviated to DB), which are internally connected to each other so that they can communicate with each other.

[0018] The analysis unit 12 has a function of analyzing voice information of the learner and image information including the learner's face received from the learner's terminal device 21 described later to derive voice analysis results and image analysis results. For image analysis, the analysis unit 12 uses a trained model (so-called AI) for facial expression recognition that has been obtained by pattern matching or machine learning (e.g., deep learning). The trained model for facial expression recognition extracts the contour of the learner's face and feature points for each part of the face that appear in the image, and tracks the movement of the feature points to recognize the learner's facial expression (facial expression recognition) and quantify the learner's emotions, concentration level, fatigue, etc. that are correlated with the learner's motivation to learn. In addition, the analysis unit 12 can recognize a specific facial expression, such as the learner's smile, as facial expression recognition, and may quantify emotions, concentration level, fatigue, etc. that are correlated with the learner's motivation to learn from the recognized smile.

[0019] Regarding the voice analysis, for example, the analysis unit 12 quantifies the emotions, concentration, fatigue, etc., which are correlated with the learner's motivation to learn, using a trained model for voice analysis (so-called AI) that is generated by machine learning (e.g., deep learning) based on the distribution of frequency components of the learner's voice using a matching algorithm or a training model for voice analysis. Note that display recognition and voice analysis may be combined for machine learning (e.g., deep learning), and in this embodiment, a learning motivation calculation AI is used that is capable of outputting a learning motivation value E that is a quantification of emotions, concentration, fatigue, etc., which are correlated with the learner's motivation to learn, generated by machine learning based on display recognition and voice analysis combined.

[0020] The analysis unit 12 also has a function of identifying the learner using voice analysis and image analysis. For image analysis, the analysis unit 12 uses a trained model (so-called AI) for personal authentication that has been subjected to pattern matching or machine learning (for example, deep learning). The trained model for personal authentication identifies the learner by extracting the contour of the learner's face and feature points for each part of the face, and creates a first ID for a new learner as necessary by consulting a first ID stored in a learner DB described later. The analysis unit 12 can also estimate attribute information such as the gender and age of the learner by image analysis, and store the first ID in the learner DB in association with the first ID. Similarly, for voice analysis, the analysis unit 12 can analyze the frequency included in the voice information of the learner to obtain a voiceprint to identify the learner or estimate attribute information such as the gender and age of the learner. In this way, the learning motivation determination server 11 manages the learner independently of the outside. That is, even if information for identifying the learner (such as authentication information) held by the terminal device 21 or the e-learning server 31 cannot be obtained, the learner can be identified. This makes it possible to customize the advice selection function described below for each learner and to shorten the time required to exchange the learner's authentication information over the network NW. On the other hand, the analysis unit 12 may identify the learner from the terminal device 21 using fingerprint authentication, face authentication, voice authentication (voiceprint authentication), or biometric information, or may obtain the learner's authentication information from the e-learning server 31.

[0021] The judgment unit 13 has a function of comparing a learning motivation value E based on the image analysis result and the audio analysis result calculated by the analysis unit 12 with a predetermined threshold value Et to judge whether the learner has an appropriate learning motivation. Specifically, the judgment unit 13 has a function of judging whether the learning motivation value E is equal to or greater than a predetermined threshold value Et (a course start permission condition). Furthermore, when the judgment unit judges that the course start permission condition is satisfied, it generates a distribution start permission flag.

[0022] The predetermined threshold value Et is a reference value for judging whether a learner has an appropriate motivation to learn that is appropriate for taking the target e-learning course. For example, if the learning motivation value E is equal to or greater than the predetermined threshold value Et, it is judged that the learner has an appropriate motivation to learn, and if the learning motivation value E is less than the predetermined threshold value Et, it is judged that the learner does not have an appropriate motivation to learn. Specifically, the predetermined threshold value Et can be a value preset in the learning motivation judgment server 11, a value designated by the e-learning server 31, or a value linked to the learner or learning content and adjusted to the characteristics of the learner or learning content. For example, the predetermined threshold value Et is adjusted to be low for a learner whose learning motivation is difficult to read from facial expressions or voice and whose learning motivation value E is generally low, or the predetermined threshold value Et is set high for learning content that requires a higher learning motivation. Information on the predetermined threshold value Et according to such learners or learning contents is stored, for example, in the learner DB 16, judgment content DB 17, and advice DB 18 described later, or in a storage unit (not shown), and the judgment unit 13 extracts and sets the predetermined threshold value Et from such DBs or storage units. Furthermore, the judgment unit 13 stores and manages the number of times n (n is a natural number equal to or greater than 1) the judgment subroutine is executed, which will be described later. Furthermore, the judgment unit 13 has a built-in timer to monitor the execution time of the judgment subroutine. In this way, the judgment unit 13 has a forced termination function for the learning motivation determination, which controls a timeout due to exceeding a predetermined number of executions or the lapse of a predetermined execution time. Furthermore, when the judgment unit 13 executes a forced termination of the learning motivation determination, it generates a forced termination flag.

[0023] The advice selection unit 14 (suggestion unit) has a function of selecting advice A (proposal) according to the learning motivation value E when the learning motivation value E is less than a predetermined threshold value Et, i.e., does not satisfy the attendance permission condition. Specifically, the advice selection unit 14 has a function of selecting advice A that is likely to increase the learning motivation of the learner according to the value of the learning motivation value E from a plurality of pieces of advice stored in the advice DB 18. As an algorithm for selecting advice that is likely to increase the learning motivation of the learner, there is a method based on the improvement tendency of the learning motivation value for advice provided in the past. For example, a learned model (so-called AI) that machine-learns (e.g., deep learning) correlation of the effect of advice on the learning motivation value from the first learning motivation value E1 calculated initially, the first advice A1 selected in the case of the first learning motivation value E1, and the second learning motivation value E2 calculated after the provision of the first advice A1 can be used. In addition, the advice selection unit 14 transmits the selected advice A to the terminal device 21 of the learner via the linking unit 15. In this way, the selected advice A is displayed and played on the terminal output unit 23 and provided to the learner.

[0024] The linking unit 15 controls the exchange of information between the learning motivation determination server 11, the terminal device 21, and the e-learning server 31. When the learning motivation value E is equal to or greater than a predetermined threshold value Et (satisfies the attendance permission condition), the linking unit 15 has a function of transmitting learning motivation information including a learning content distribution start permission flag or a forced termination flag to the e-learning distribution unit 32 of the e-learning server 31 to link with the e-learning server 31. The linking unit 15 also has a function of linking with the outside, as indicated by the horizontal dashed lines in the flowchart shown in Fig. 3 described later, such as receiving a learning motivation determination request from the e-learning server 31, distributing learning motivation determination content to the learner's terminal device 21, and receiving image information and audio information of the learner acquired by the learner's terminal device 21.

[0025] The learner DB 16 stores learner information about each learner who uses the learning motivation determination system 1. The learner information includes, for each learner, a first ID given by the learning motivation determination server 11 to each learner, gender, age, and the like as attribute information of the learner, a second ID corresponding to the terminal device 21 used by the learner, a usage history of the learning motivation determination system 1, a third ID and usage history corresponding to the e-learning used by the learner, and the like. The usage history of the learning motivation determination system 1 includes a learning motivation value E determined in the past and a history of advice A selected, and the like. Note that some of the learner information, such as the second ID and the third ID, may be received from the terminal device 21 or the e-learning server 31 and stored, or may be acquired and stored by inputting the information by the learner when using the learning motivation determination system 1 for the first time.

[0026] The judgment content DB 17 stores contents to be displayed and played on the terminal device 21 of the learner for the purpose of acquiring voice information and image information of the learner necessary for judging the willingness to learn. For example, immediately after the start of the willingness to learn judgment, a greeting expressed by text or animation such as "Hello, we will start an ice breaker for about one minute" is displayed and played, and then appropriate questions are displayed and played to have the learner answer orally while acquiring images and videos of the learner's voice and face. The contents may be composed of videos, animations, texts, voices, or a combination of these, and may be created and stored in advance. In addition, as for the texts and voices, they may be displayed as sentences automatically generated in real time by an engine equipped with a natural language processing function according to the learning willingness value E, or may be read out by a synthetic voice.

[0027] The advice DB 18 stores a plurality of pieces of advice, such as general advice encouraging deep breathing, stretching, playing music, changing one's mood, actions that are effective in waking oneself up, light exercise, etc., and advice specific to a learning field. The advice stored in the advice DB 18 may be categorized according to the learning motivation value E, and the execution time or number of executions of the advice content may be set according to the learning motivation value E.

[0028] The information stored in these three databases, the learner DB 16, the judgment content DB 17, and the advice DB 18, may be input in advance in the learning motivation judgment server 11, or may be acquired by inputting and updating from the outside via the network NW as needed. Note that, although the learner DB 16, the judgment content DB 17, and the advice DB 18 are separate in this embodiment, they may be DBs in which the respective information is stored integrally.

[0029] The terminal device 21 is a terminal device such as a PC, a smartphone, a tablet PC, or a mobile phone, and includes a terminal input unit 22 and a terminal output unit 23. The terminal device 21 may access the learning motivation determination server 11 by dedicated application software installed on the terminal. The terminal device 21 may also access the learning motivation determination server 11 by using an operating environment (API (Application Programming Interface), platform, etc.) provided by the learning motivation determination server 11.

[0030] The terminal input unit 22 is a microphone, a camera, a character input means, a fingerprint sensor, etc., provided in the terminal device 21, and has functions such as acquiring the learner's voice, an image including the learner's face, text entered by the learner, and the learner's fingerprint. The character input means may be a touch panel integrated with the display means of the terminal output unit 23, or a keyboard independent of the terminal device 21.

[0031] The terminal output unit 23 is a speaker, a display screen, a vibration generating mechanism, etc. provided in the terminal device 21, and has a function of displaying and playing back audio and moving images of the content distributed from the learning motivation determination server 11 and the e-learning server 31, and a function of emitting warning sounds and warning vibrations. The display screen is, for example, a liquid crystal display or an organic EL display in a smartphone. It may also be a display device independent of the terminal device 21.

[0032] The e-learning server 31 includes an e-learning distribution unit 32 and a learning content database 33 that stores e-learning learning contents, and these are internally connected to be able to communicate with each other. The learning contents are not particularly limited, and may be, for example, for food education, English, examinations, qualification study, etc. The e-learning distribution unit 32 has a function of transmitting a learning motivation determination request to the learning motivation determination server 11 when receiving an e-learning start request from the learner's terminal device 21, waiting for a distribution start permission from the learning motivation determination server 11, and finally distributing the learning contents to the learner's terminal device 21. The e-learning distribution unit 32 also has a function of authenticating the learner when receiving the request to start the course. The learner's authentication information may be transmitted to the learning motivation determination server 11 together with the learning motivation determination request.

[0033] <Processing flow> Next, a description will be given with reference to the flow chart of FIG. 2 showing a routine for determining a learner's motivation to learn.

[0034] First, in step S101, the learner accesses the e-learning server 31 from the terminal device 21 and transmits learner authentication information and a request to start taking a class.

[0035] In the next step S102, the e-learning server 31 transmits a learning motivation determination request to the learning motivation determination server 11 together with the learner authentication information.

[0036] In the next step S103, the judgment unit 13 of the learning motivation judgment server 11 initializes a timer for the number of executions n of the judgment subroutine and the execution time.

[0037] In the next step S104, the judgment unit 13 of the learning motivation judgment server 11 starts a judgment subroutine. Here, the judgment unit 13 performs a forced termination judgment when starting the judgment subroutine. Specifically, if the number of executions n of the judgment subroutine is less than a predetermined value or the execution time is less than a predetermined time, the judgment unit 13 judges that the forced termination condition is not satisfied and proceeds to the next step S105, otherwise, it judges that the forced termination condition is satisfied and proceeds to step S112.

[0038] In step S105, the judgment unit 13 of the learning motivation judgment server 11 transmits the learning motivation judgment content Cn (n indicates the number of times it has been executed) extracted from the judgment content DB 17 to the learner's terminal device 21 via the collaboration unit 15, and plays the learning motivation judgment content via the display screen or speaker, etc. of the terminal output unit 23 of the terminal device 21.

[0039] In step S106, the learner's terminal device 21 displays and plays the learning motivation assessment content Cn, and acquires the learner's voice information or image information including the learner's face via the camera or microphone of the terminal input unit 22, and transmits it to the learning motivation assessment server 11.

[0040] In step S107, the learning motivation determination server 11 performs image analysis and voice analysis in the analysis unit 12 using the voice information and image information of the learner received from the terminal device 21 (analysis step).

[0041] In step S108, the learning motivation determination server 11 calculates the learning motivation value En of the learner by the learning motivation calculation AI based on the image analysis result and the audio analysis result in step S107 in the analysis unit 12 (analysis step).

[0042] In step S109, the learning motivation determination server 11, in the determination unit 13, determines whether the learning motivation value En is equal to or greater than a predetermined threshold value Et (determination step). If the determination result is true (Yes), that is, if the learning motivation value En is equal to or greater than the predetermined threshold value Et, it is determined that the subject has an appropriate learning motivation, and the determination subroutine is terminated and the process proceeds to S112. If the determination result is false (No), that is, if the learning motivation value En is less than the threshold value Et, it is determined that the subject does not have an appropriate learning motivation, and the process proceeds to S110.

[0043] In step S110, the learning motivation determination server 11, in the advice selection unit 14, selects advice An from a plurality of advices stored in the advice DB 18 based on the learning motivation value En, and provides (outputs) the advice An to the terminal device 21 (suggestion step).

[0044] In step S111, the learning motivation determination server 11 increments the number of executions n of the determination subroutine by n+1, returns to S104, and repeats the determination subroutine. In other words, when the advice An is used to improve the learning motivation value En of the learner and the learning motivation value En is improved to a predetermined threshold value Et or more, or when the forced termination condition in step S104 is satisfied, the process proceeds to step S112.

[0045] In step S112, if it is determined in step S109 that the learner's learning motivation value En is equal to or greater than the threshold value Et, learning motivation determination server 11 transmits learning motivation information with a distribution start permission flag to e-learning server 31 via collaboration unit 15, and terminates the routine in learning motivation determination server 11. On the other hand, if the forced termination determination condition is met in the forced termination determination in step S103, learning motivation determination server 11 transmits learning motivation information with a forced termination flag to e-learning server 31 via collaboration unit 15, and terminates the routine in learning motivation determination server 11.

[0046] In step S113, the e-learning server 31 that has received the learning motivation information starts transmitting e-learning learning content to the terminal device 21 depending on the presence or absence of the distribution start permission flag and the forced termination flag, and ends the routine in the e-learning server 31. For example, when the e-learning server 31 receives learning motivation information with the distribution start permission flag attached, it transmits to the terminal device 21 learning content corresponding to the course start request received from the terminal device 21 in step S101. On the other hand, when the e-learning server 31 receives learning motivation information with the forced termination flag attached, since the learner's learning motivation does not reach or exceed the predetermined threshold value Et, it transmits to the terminal device 21, for example, a notification that the learning content will not be provided, or transmits to the terminal device 21 content that is different from the course start request and is intended for learners with low learning motivation.

[0047] In step S114, terminal device 21 displays and plays back the study content or notification distributed by e-learning server 31, and then ends this routine in terminal device 21.

[0048] As described above, in the learning motivation determination system 1 of this embodiment, when a learner requests to start taking e-learning, the e-learning server 31 requests a learning motivation determination from the learning motivation determination server 11. Then, the learning motivation determination server 11 analyzes an image including the learner's voice and face acquired via the terminal device 21 to calculate a learning motivation value E that correlates with learning motivation, determines the conditions for permission to start taking the course by comparing with a predetermined threshold value Et, and provides advice A tailored to the learning motivation value E if the learning motivation value E is less than the predetermined threshold value Et, and permits the e-learning server 31 to start distribution if the learning motivation value E is equal to or greater than the predetermined threshold value Et.

[0049] In other words, the learning motivation determination system 1 delivers learning content to a learner if the learner has an appropriate learning motivation to take the e-learning learning content before taking the learning content, thereby achieving high learning efficiency. On the other hand, if the learner has low learning motivation before taking the learning content, advice A is provided to the learner to improve his or her learning motivation. Since the learning motivation determination system 1 determines the learning motivation before taking the learning content, it is highly versatile and does not require any changes to the e-learning itself or special devices.

[0050] As a result, the learning motivation determination system 1 can be applied to existing e-learning without the use of special equipment, and by improving the learner's learning motivation before taking the course, it is possible to improve the learning effectiveness of the learner in various e-learning courses.

[0051] The analysis unit 12 of the learning motivation assessment server 11 recognizes the facial expressions of the learner in the image information of the learner and the audio information of the learner's voice, and calculates the learning motivation value correlated with learning motivation from the distribution of frequency components of the learner's voice, using a trained model that has been machine-learned to calculate the learning motivation value E. By using such a trained model based on image information and audio information, the learning motivation value E can be easily calculated without the need for complex algorithms, and a more accurate assessment of learning motivation can be made.

[0052] Furthermore, the determination unit 13 can set a predetermined threshold value Et depending on the learner or the learning content, thereby making it possible to appropriately determine the learning motivation depending on each learner or each learning content.

[0053] Moreover, the advice selection unit 14 can select optimal advice by selecting advice based on the improvement trend of the learning motivation value for suggestions provided in the past, thereby efficiently improving the learner's learning motivation.

[0054] Although the embodiment of the present invention has been described above, the aspects of the present invention are not limited to this embodiment.

[0055] In the learning motivation determination system 1 of the above embodiment, the learning motivation determination server 11 and the e-learning server 31 are provided separately, but they may be integrated. For example, it is possible to provide only the learning motivation determination function to an e-learning distribution provider and incorporate it into existing e-learning distribution. Also, for example, a dedicated terminal for e-learning may be provided as a device that has all of the functions of the learning motivation determination server 11, learner terminal device 21, and e-learning server 31 integrated into one device.

[0056] In addition, in the above embodiment, in order to simplify the explanation, only one predetermined threshold value Et is set for the learning motivation value E, but multiple predetermined threshold values ​​for the learning motivation value may be set in stages. For example, by setting two threshold values, a first threshold value Et1 and a second threshold value Et2 (>Et1), it is possible to determine the learning motivation in three stages, such as a first learning motivation range where the learning motivation is relatively low when the learning motivation is less than the first threshold value Et1, a second learning motivation range where the learning motivation is medium when the learning motivation is equal to or greater than the first threshold value Et and less than the second threshold value Et2, and a third learning motivation range where the learning motivation is relatively high when the learning motivation value E is equal to or greater than the second threshold value Et2. In addition, by making the advice in the advice DB to correspond to the learning motivation range, advice for a major change of mood may be selected when the learning motivation value E calculated by the analysis unit is in the first learning motivation range, advice for a minor change of mood may be selected when the learning motivation value E is in the second learning motivation range, and permission for the distribution of e-learning may be given as it is when the learning motivation value E is in the third learning motivation range.

[0057] Furthermore, in the above embodiment, one learning motivation value E is calculated, but the learning motivation value may be calculated from each of the image analysis result and the audio analysis result. That is, for example, a learning motivation value based on the image analysis result and a learning motivation value based on the audio analysis result may be calculated, and a predetermined threshold value may be set for each of them, so that e-learning is permitted when each learning motivation value is equal to or greater than the predetermined threshold value. Also, the learning motivation value may be calculated from only either the image analysis result or the audio analysis result.

[0058] In addition, in the above embodiment, an AI that has learned only the correlation between the learning motivation value E and the selected advice A is used as the algorithm for selecting advice, but the AI ​​may be customized for each learner ID. This allows the most suitable advice to be selected for the learner, and the time required to improve learning motivation can be further shortened. Furthermore, the AI ​​may be customized based on attribute information such as the learner's age and gender, or the e-learning content, without identifying individuals. This shortens the analysis time and reduces the learner's stress caused by the waiting time for the learning motivation determination.

[0059] In the above embodiment, the e-learning server 31 delivers learning content according to the presence or absence of the forced termination flag, but the same learning content may be delivered regardless of the presence or absence of the forced termination flag. In other words, the learning motivation assessment can be regarded as a time for warming up or breaking the ice, and the learning can be started regardless of the state after that, so as not to spoil the learner's opportunity to take the course.

[0060] <Program> Here, the program for realizing each function constituting the learning motivation determination server 11 according to this embodiment will be described in detail.

[0061] The learning motivation determination server 11 is implemented in a computer 801 shown in Fig. 3. The operation of each component of the learning motivation determination server 11 is stored in the form of a program in an auxiliary storage device 804. A CPU 802 reads the program from the auxiliary storage device 804, loads it in a main storage device 803, and executes the above-mentioned processing according to the program. The CPU 802 also secures a storage area corresponding to the above-mentioned storage unit in the main storage device 803 according to the program.

[0062] Specifically, the program is a learning motivation determination program that causes a computer 801 to determine the learning motivation of an e-learning learner before taking the course, and executes an analysis step of analyzing at least either image information of the learner or audio information of the learner's voice to calculate a learning motivation value that correlates with the learner's learning motivation, a determination step of comparing the learning motivation value with a predetermined threshold value, and a proposal step of selecting a proposal corresponding to the learning motivation value and outputting the selected proposal if the learning motivation value is less than the predetermined threshold value.

[0063] The auxiliary storage device 804 is an example of a non-transient tangible medium. Other examples of non-transient tangible media include a magnetic disk, a magneto-optical disk, a CD-ROM, a DVD-ROM, and a semiconductor memory connected via an interface. In addition, when this program is distributed to the computer 801 via a network, the computer 801 that receives the program may load the program into the main storage device 803 and execute the above process.

[0064] The program may be for implementing part of the above-mentioned functions. Furthermore, the program may be a so-called differential file (differential program) that implements the above-mentioned functions in combination with another program already stored in the auxiliary storage device 804.

[0065] The embodiments described above can be embodied in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and modifications are within the scope of the invention and its equivalents as defined in the claims, as well as the scope and spirit of the invention. [Explanation of symbols]

[0066] 1. Learning motivation assessment system 11 Learning motivation assessment server 12 Analysis Department 13 Judgment section 14 Advice Selection Section (Suggestion Section) 15 Collaboration Department 16 Learner Database 17 Judgment Content Database 18 Advice Database 21 Student terminal equipment 22 Terminal input section 23 Terminal output section 31 e-learning server 32 E-Learning Distribution Department 33 Learning Content Database NW Network

Claims

1. A learning motivation determination system for determining the learning motivation of an e-learning learner before the learner takes a course, comprising: a linking unit that acquires at least one of image information of the learner and audio information of the learner; an analysis unit that analyzes at least one of the audio information and the image information to calculate a learning motivation value that correlates with the learning motivation of the learner; a determination unit that reproduces a learning motivation assessment content on the terminal device of the learner, and compares the learning motivation value analyzed based on either the audio information or the image information acquired during the reproduction of the learning motivation assessment content with a predetermined threshold value; a suggestion unit that selects advice corresponding to the learning motivation value when the learning motivation value is less than the predetermined threshold value, and displays the selected advice on the terminal device; a distribution unit that distributes learning content to the terminal device when the learning motivation value is equal to or greater than the predetermined threshold value; A learning motivation determination system comprising:

2. The learning motivation determination system of claim 1, wherein the analysis unit calculates the learning motivation value using a trained model for facial expression recognition that has been machine-learned to recognize the facial expressions of the learner appearing in the image of the learner and calculate the learning motivation value that correlates with the learning motivation for the learner.

3. The learning motivation determination system of claim 1 or 2, wherein the analysis unit calculates the learning motivation value using a trained model for voice recognition that has been machine-learned to calculate the learning motivation value that correlates with learning motivation from the distribution of frequency components of the learner's voice for audio information that records the learner's voice.

4. The system for determining learning motivation according to claim 1 , wherein the determination unit sets a predetermined threshold value depending on the learner or the learning content.

5. The learning motivation determination system according to claim 1 , wherein the suggestion unit selects the advice based on a trend of improvement in the learning motivation value in response to advice provided in the past.

6. A learning motivation determination device for determining the learning motivation of an e-learning learner before the learner takes a course, comprising: a linking unit that acquires at least one of image information of the learner and audio information of the learner; an analysis unit that analyzes at least one of image information of the learner and audio information of the learner to calculate a learning motivation value that correlates with the learner's learning motivation; a determination unit that reproduces a learning motivation assessment content on the terminal device of the learner, and compares the learning motivation value analyzed based on either the audio information or the image information acquired during the reproduction of the learning motivation assessment content with a predetermined threshold value; a suggestion unit that selects advice according to the learning motivation value when the learning motivation value is less than the predetermined threshold value, and outputs the selected advice to the terminal device; a distribution unit that distributes learning content to the terminal device when the learning motivation value is equal to or greater than the predetermined threshold value; A learning motivation determination device comprising:

7. A method for determining the learning motivation of an e-learning learner before the learner starts taking the course, comprising: acquiring at least one of image information of the learner and audio information of the learner; an analysis step of analyzing at least one of image information of the learner and audio information of the learner to calculate a learning motivation value that correlates with the learner's learning motivation; a determination step of playing a learning motivation assessment content on the terminal device of the learner, and comparing the learning motivation value analyzed based on either the audio information or the image information acquired during the playback of the learning motivation assessment content with a predetermined threshold value; a suggestion step of selecting advice corresponding to the learning motivation value when the learning motivation value is less than the predetermined threshold value, and outputting the selected advice to the terminal device; delivering learning content to the terminal device when the learning motivation value is equal to or greater than the predetermined threshold; A method for determining learning motivation comprising the steps of:

8. A learning motivation assessment program for causing a computer to assess the learning motivation of an e-learning learner before the learner takes the course, comprising: acquiring at least one of image information of the learner and audio information of the learner; an analysis step of analyzing at least one of image information of the learner and audio information of the learner to calculate a learning motivation value that correlates with the learner's learning motivation; a determination step of playing a learning motivation assessment content on the terminal device of the learner, and comparing the learning motivation value analyzed based on either the audio information or the image information acquired during the playback of the learning motivation assessment content with a predetermined threshold value; a suggestion step of selecting advice corresponding to the learning motivation value when the learning motivation value is less than the predetermined threshold value, and outputting the selected advice to the terminal device; delivering learning content to the terminal device when the learning motivation value is equal to or greater than the predetermined threshold; A learning motivation assessment program that causes a computer to execute the above.

Images