JP2004101637A - Online educational system, information processor, information providing method and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To efficiently give a language education to students of the cource. <P>SOLUTION: A teaching material providing section 61 reads teaching material data out of a teaching material DB 70 and sends the teaching material data to a user terminal. A voice analysis section 62 compares voice feature extracted from the voice data sent from the user terminal with the voice feature extracted from the voice data stored in a model voice DB 71 and generates difference data for voice. A video analysis section 63 compares the feature quantity extracted from video data sent from the user terminal with the feature quantity extracted from the video data stored in a model video DB 72 and generates difference data for video. An advice generating section 64, based on the difference data for voice and/or video, retrieves a teaching information DB 73 and generates advice for giving instructions to the learner. An advice providing section 65 sends the advice to the user terminal. A voice recognition section 66 generates a sentence corresponding to the speech of the learner and sends the sentence to the user terminal so that it can be displayed. <P>COPYRIGHT: (C)2004,JPO

Description

[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention relates to an education system that supports students' learning using a computer or the like, and more particularly, to an online education system capable of implementing language education for students online.
[0002]
[Prior art]
In order to learn a language, it is important to improve the ability to understand the meaning of each word and sentence after acquiring the ability to recognize the other party's story and pronounce correctly. Conventionally, language learning has been performed by a method of understanding grammar from letters using a book or the like. In recent years, language schools and the like, in which a native instructor whose native language is a specific language, provides guidance according to the proficiency of the student through dialogue with the student, have been run as a business. Furthermore, some of these language schools provide services that enable language education between remote locations using a communication system such as that disclosed in Patent Document 1.
[0003]
[Patent Document 1]
JP-A-11-220707
[0004]
[Problems to be solved by the invention]
In order to learn a language quickly, it is desirable to learn basic skills through a word-by-word or general spoken language under a professional instructor and acquire it in a natural way. However, in order for the instructor to educate face-to-face with the trainee, the time and place must be coordinated and reserved.
In this regard, according to the technology disclosed in Patent Literature 1, it is possible to provide education between remote locations, so that it is possible to reduce the locational restriction in face-to-face education.
[0005]
However, even with the technique disclosed in Patent Document 1, the instructor and the student must stay in front of the terminal at the same time. For this reason, time adjustment and reservation are required. In addition, there is a problem in that the number of instructors must be equal to the number of trainees.
[0006]
The present invention has been made in view of the above circumstances, and has as its object to provide an online education system capable of efficiently providing language education to students.
[0007]
[Means for Solving the Problems]
An online education system according to a first aspect of the present invention is an online education system including a terminal device and a server device connected to each other via a network, and includes a model voice that stores voice data indicating an exemplary voice. A database, a model video database that stores video data obtained by capturing an exemplary utterance operation, a guidance information database that stores a plurality of types of guidance information, and audio data indicating the utterance of the student generated by the terminal device, Compared with the audio data stored in the model audio database, audio analysis means for generating an analysis result indicating the difference, the video data generated by the terminal device by capturing the utterance operation of the student, Compares with the video data stored in the model video database and generates an analysis result indicating the difference. Video analysis means, advice creation means for reading guidance information corresponding to the analysis results of the audio analysis means and the video analysis means from the guidance information database to create advice, and providing the advice created by the advice creation means And an advice providing unit for outputting the information on a terminal device.
[0008]
According to the present invention, a comparison result between audio data indicating a student's utterance and audio data indicating an exemplary utterance stored in the model audio database, and video data of a utterance operation of the student are taken. Then, an advice corresponding to a comparison result with video data of a typical utterance operation stored in the model video database and captured is created. The created advice is output by the terminal device, and the language education can be efficiently provided to the student.
[0009]
An information processing apparatus according to a second aspect of the present invention includes: a voice input unit that captures a utterance of a student; an imaging unit that captures a utterance operation of the student; a voice output unit; a display unit; A model voice database that stores voice data indicating model data, a model video database that stores video data obtained by capturing exemplary speech operations, a guidance information database that stores a plurality of types of guidance information, and stored in the model voice database. Model providing means for reading out the voice data being read and outputting an exemplary voice from the voice output means, and recognizing the voice of the student taken in by the voice input means, and a sentence corresponding to the voice of the student. Voice recognition means for displaying the image data on the display means, and video data created by the photographing of the image capturing means in the model video database. Video analysis means for comparing with the video data being processed and generating an analysis result indicating the difference, and advice creating means for reading guidance information corresponding to the analysis result of the video analysis means from the guidance information database and creating advice And advice providing means for outputting the advice created by the advice creating means by at least one of the audio output means and the display means.
[0010]
According to the present invention, the advice corresponding to the comparison result between the video data of the utterance operation of the student and the video data of the exemplary utterance operation stored in the model video database is created. The created advice is output from at least one of the audio output unit and the display unit. Also, by reading out the voice data stored in the model voice database, a typical voice is output from the voice output means. Further, the utterance of the student is recognized, and a sentence corresponding to the utterance of the student is displayed on the display means.
Thereby, the language education can be efficiently provided to the students.
[0011]
The model providing unit includes a unit that reads out video data stored in the model video database and causes the display unit to display an image of an exemplary utterance operation. An image of the utterance operation by the person may be displayed.
[0012]
An information processing apparatus according to a third aspect of the present invention is an information processing apparatus connected to a terminal device via a network, and includes: a model voice database storing voice data indicating a typical voice; A model video database that stores video data obtained by capturing the utterance operation, a guidance information database that stores a plurality of types of guidance information, and by reading the audio data stored in the model voice database and sending it to the terminal device, Model providing means for outputting an exemplary utterance in the terminal device, and recognizes the utterance of the student from the voice data sent from the terminal device, and displays a sentence corresponding to the utterance of the student on the terminal device. Voice recognition means for causing the video data transmitted from the terminal device to be the video data stored in the model video database. A video analysis means for generating an analysis result indicating the difference, an advice creation means for reading guidance information corresponding to the analysis result of the video analysis means from the guidance information database and creating an advice, and the advice creation means And an advice providing unit that outputs advice for instructing a student at the terminal device by sending the advice created by the above to the terminal device.
[0013]
According to a fourth aspect of the present invention, there is provided an information providing method, wherein a computer system including a model voice database, a model video database, and a guidance information database stores voice data indicating an exemplary utterance in the model voice database. Storing video data of an exemplary utterance operation in the model video database, storing a plurality of types of guidance information in the guidance information database, reading audio data stored in the model voice database, Output a typical utterance, recognize the utterance of the student, display a sentence corresponding to the utterance of the student, video data created by shooting the utterance operation of the student, the model video database Compared with the stored video data, the difference is used as the analysis result, and guidance information corresponding to the analysis result is provided. Create advice read from the serial guidance information database, and outputs the advice was created by the video and / or audio.
[0014]
A program according to a fifth aspect of the present invention is a computer-readable storage medium storing a computer, comprising: a voice input unit that captures a utterance of a student; an imaging unit that captures a utterance operation of the student; a voice output unit; A model voice database that stores voice data indicating utterances, a model video database that stores video data obtained by capturing exemplary voice actions, a guidance information database that stores a plurality of types of guidance information, and stored in the model voice database. Model providing means for reading out the voice data that has been input and outputting an exemplary voice from the voice output means, and recognizing the voice of the student taken in by the voice input means, and responding to the voice of the student. Voice recognition means for displaying a sentence on the display means, and video data created by photographing by the imaging means, A video analysis unit that compares the video data stored in the database and generates an analysis result indicating the difference, and reads guidance information corresponding to the analysis result of the video analysis unit from the guidance information database to create an advice An advice creating unit and an advice providing unit that outputs the advice created by the advice creating unit by at least one of the audio output unit and the display unit.
[0015]
BEST MODE FOR CARRYING OUT THE INVENTION
Hereinafter, an online education system according to an embodiment of the present invention will be described in detail with reference to the drawings.
FIG. 1 is a diagram showing a configuration of an online education system according to an embodiment of the present invention.
As shown in FIG. 1, the online education system according to the embodiment of the present invention includes a user terminal 10, a network 20, and a service provider 30. The user terminal 10 and the service provider 30 are connected to each other via a network 20, such as a public line or the Internet. In the following, for simplicity of description, it is assumed that there is only one user terminal 10, but this is not a limitation, and a plurality of user terminals 10 may exist.
[0016]
The user terminal 10 is an information processing terminal device represented by, for example, a notebook or desktop personal computer, a PDA (Personal Digital Assistants), or the like.
FIG. 2 is a diagram illustrating a configuration of the user terminal 10.
As shown in FIG. 2, the user terminal 10 includes a user interface 11, a control unit 12, a storage unit 13, and a communication interface 14.
[0017]
The user interface 11 includes, for example, a microphone 11a, a CCD camera 11b, a display device 11c, a keyboard 11d, a mouse 11e, a speaker 11f, and the like. And to output audio.
[0018]
The control unit 12 is configured using a microprocessor such as a CPU (Central Processing Unit) and controls the operation of the entire user terminal 10.
[0019]
The storage unit 13 includes, for example, a semiconductor memory and a hard disk device, and stores an operation program executed by the control unit 12, various setting data, and the like.
[0020]
The communication interface 14 is configured using, for example, a network card, a cable connector, a wireless unit, and the like, and communicates with the service provider 30 via the network 20 under the control of the control unit 12.
[0021]
As shown in FIG. 3, the service provider 30 includes a server 40 and a database (hereinafter, referred to as “DB”) 50.
The server 40 has, for example, a function as an application server and a function as a database server. Note that the server 40 does not need to be physically configured by one computer system, and may be configured by using a plurality of computers.
[0022]
The server 40 accepts access from the user terminal 10 via the network 20 and provides the user of the user terminal 10 who will be a student of the online education with information serving as a teaching material of the online education combining video and audio. Make it possible. In addition, the server 40 receives a command, an audio signal, and a video signal sent from the user terminal 10 and executes various processes for more efficiently implementing online education. As shown in FIG. 3, the server 40 includes a control unit 41, a storage unit 42, and a communication interface 43.
[0023]
The control unit 41 controls the operation of the server 40 as a whole. Here, the control unit 41 reads out and executes an operation program stored in the storage unit 42, a teaching material providing unit 61, an audio analysis unit 62, a video analysis unit 63 , An advice creating unit 64, an advice providing unit 65, and a voice recognition unit 66.
[0024]
The curriculum setting unit 60 performs self-reporting by the user of the user terminal 10, the result of a regularly performed test, or the type of advice provided by the advice providing unit 65 to the student through the user terminal 10. Judge the language skills of the students and set the learning content according to each student.
[0025]
The teaching material providing unit 61 specifies the teaching material data to be read from the teaching material DB 70 included in the DB 50 based on the curriculum set by the curriculum setting unit 60 and the analysis results of the audio analyzing unit 62 and the video analyzing unit 63. The teaching material data read from the teaching material DB 70 by the teaching material providing unit 61 is sent to the user terminal 10 via the network 20 by the communication interface 43.
[0026]
The voice analysis unit 62 extracts a feature amount of a voice signal from voice data transmitted from the user terminal 10 and analyzes voice generated by the student. For example, the audio analysis unit 62 extracts acoustic physical information such as the frequency, amplitude, and pitch of the audio signal by digital signal analysis of the audio data transmitted from the user terminal 10. As a result, speech characteristics of pronunciation, such as intonation, stress, accent, speed, etc., of the speech uttered by the student are extracted.
Further, the voice analysis unit 62 compares the voice feature extracted from the voice data sent from the user terminal 10 with the voice feature extracted from the voice data stored in the model voice DB 71 provided in the DB 50, and indicates the difference. Create difference data for audio.
[0027]
The video analyzing unit 63 extracts a feature amount of a moving image or a still image from the video data transmitted from the user terminal 10 and analyzes the utterance operation of the student. For example, the video analysis unit 63 extracts a motion feature amount based on the shape and color of the lips in the student's utterance operation using the color appearance probability distribution (color histogram) and the color co-occurrence frequency distribution (color correlogram). Here, the color appearance probability distribution is a distribution of the probability that various colors appear in pixels in an image composed of video signals constituting one frame. Further, the color co-occurrence frequency distribution is a distribution of appearance probabilities of color combinations between pixels separated by a certain distance in an image.
Alternatively, the video analysis unit 63 sets a block area in each of the previous frame and the subsequent frame, and uses the block matching method of estimating a motion vector using the center point of the highly correlated block area as a corresponding point in the previous and next frames. The movements of the lips and tongue in the utterance movement of may be analyzed.
In addition, the video analysis unit 63 compares the feature amount extracted from the video data sent from the user terminal 10 with the feature amount extracted from the video data stored in the model video DB 72 included in the DB 50, and indicates a difference therebetween. Create difference data for video.
[0028]
The advice creating unit 64 searches for the guidance information DB 73 included in the DB 50 based on the audio difference data created by the audio analysis unit 62 and the video difference data created by the video analysis unit 63, and It is for creating advice to guide the elderly.
[0029]
The advice providing unit 65 transmits the advice created by the advice creating unit 64 to the user terminal 10 via the network 20 via the communication interface 43, so that the advice can be provided to the student at the user terminal 10. Things.
[0030]
The voice recognition unit 66 includes, for example, a predetermined word dictionary, refers to the word dictionary based on the feature amount of the voice data sent from the user terminal 10, extracts words close to the utterance of the student, and combines them. Thus, utterance sentence data indicating a sentence corresponding to the utterance of the student is created.
[0031]
The storage unit 42 is configured from an external storage device including a semiconductor memory, a hard disk device, an optical disk playback device, and the like. The storage unit 42 stores an operation program executed by the control unit 41 and various setting data. Provide area.
[0032]
The communication interface 43 communicates with the user terminal 10 via the network 20 under the control of the control unit 41, and transmits and receives various types of information.
[0033]
The server 40 accesses the DB 50 as a DB server.
The DB 50 includes a teaching material DB 70, a model audio DB 71, a model video DB 72, and a guidance information DB 73.
[0034]
The learning material DB 70 stores a plurality of types of learning material data provided to the user terminal 10 as the language learning material in association with the language learning level. FIG. 4 is a diagram illustrating a configuration example of data stored in the teaching material DB 70.
Here, the teaching material data includes text data indicating a learning sentence example, which is a sentence of the language to be learned, and moving image data indicating exemplary movements of the tongue and lips when uttering each learning sentence example. ing. Each teaching material data is associated with audio data indicating an exemplary utterance stored in the model audio DB 71 and video data indicating an exemplary utterance operation stored in the model video DB 72. .
[0035]
The model sound DB 71 stores sound data that is sound material indicating an exemplary utterance.
Here, the voice data stored in the model voice DB 71 is created by recording in advance the utterances of each learning sentence example by a native instructor whose native language is the language to be learned.
[0036]
The model video DB 72 stores video data that is video material indicating an exemplary utterance operation.
Here, the video data stored in the model video DB 72 is created by photographing the utterance operation of each learning sentence example by a native instructor in advance.
[0037]
FIG. 5 is a diagram illustrating a configuration example of data stored in the guidance information DB 73.
As shown in FIG. 5, the guidance information DB 73 stores, for each learning sentence example provided as a teaching material, a plurality of types of difference model data, guidance text data indicating a plurality of types of guidance sentences, and video materials displayed for guidance. It is stored in association with video reference data or the like for identification.
[0038]
Here, the difference model data is data indicating a difference between a speech operation that is likely to be erroneous when a student utters each learning sentence example and an exemplary speech operation when a native instructor utters each learning sentence example. is there. For example, by taking a difference between a voice signal when a pronunciation of [r] in each learning sentence is pronounced as [l] and a voice signal indicating a typical utterance, one of the difference model data for voice is obtained. One is configured. In addition, with respect to a video signal generated by capturing an utterance operation in which the pronunciation of [r] in each learning sentence example is pronounced as [l], a video created by capturing a native exemplary utterance operation By taking the difference from the signal, one of the difference model data for video is formed. That is, the difference model data includes difference model data for audio and difference model data for video.
[0039]
The video material reference data is data indicating a reference destination (for example, an address or a video ID) of video data stored in the model video DB 72. That is, the video material reference data allows the advice creating unit 64 to refer to video data indicating a typical utterance operation that is considered appropriate for correcting an error included in the utterance operation of the student.
[0040]
Hereinafter, the operation of the online education system according to the embodiment of the present invention will be described.
In this online education system, a user of the user terminal 10 who is a student of the online education inputs a command from a keyboard 11d provided in a user interface 11 of the user terminal 10, or clicks an icon by operating a mouse 11e. For example, a command to start language learning is input.
When a command to start language learning is input, the control unit 12 reads out an operation program for online education from the storage unit 13 and executes it. The control unit 12 displays, for example, a screen as shown in FIG. 6 on the display device 11c included in the user interface 11 according to the operation program read from the storage unit 13.
[0041]
The screen shown in FIG. 6 includes a display area Da in which a plurality of still images of the student's face are displayed, a display area Db in which a plurality of still images indicating the movement of the lips are displayed, and voices of the student. And a display area Dc in which the recognized result is displayed in text. The screen shown in FIG. 6 is provided with a display area Dd for displaying a waveform of a voice input from the microphone 11a, a display area De for displaying a learning sentence example as a teaching material and a message as an advice, and the like. .
[0042]
The still image displayed in the display area Da is created by the control unit 12 extracting a frame image at a predetermined timing from a moving image captured by the CCD camera 11b. The still image displayed in the display area Db indicates the lip movement in the student's utterance operation or the lip movement in the exemplary utterance operation.
[0043]
Further, when executing the operation program for online education, the control unit 12 accesses the service provider 30 via the network 20 by the communication interface 14 and requests the start of language learning.
[0044]
It is assumed that the service provider 30 receives a learning start request from the user terminal 10. In this case, in the server 40, for example, the control unit 41 reads out the application program for online education from the storage unit 42 and executes it, thereby starting the processing shown in the flowchart of FIG.
[0045]
When the process shown in the flowchart of FIG. 7 is started, the control unit 41 sets learning contents according to each student by the curriculum setting unit 60 (step S1). At this time, the curriculum setting unit 60 determines the language ability of the student based on the self-report of the student, the result of a test that is regularly performed, or the type of advice already provided at the user terminal 10. Judgment is made and learning contents are set according to each student. The learning content set by the curriculum setting unit 60 is notified to the teaching material providing unit 61.
[0046]
The learning material providing unit 61 searches the learning material DB 70 to read the learning material data corresponding to the learning content notified from the curriculum setting unit 60 (Step S2). The teaching material data read by the teaching material providing unit 61 is sent to the user terminal 10 via the network 20 by the communication interface 43 (Step S3). At this time, the teaching material providing unit 61 may read out audio data indicating an exemplary utterance corresponding to the teaching material data sent to the user terminal 10 from the model audio DB 71 and send it to the user terminal 10 together with the teaching material data. Further, the teaching material providing unit 61 may read video data indicating an exemplary utterance operation corresponding to the teaching material data sent to the user terminal 10 from the model video DB 72 and send the video data to the user terminal 10 together with the teaching material data.
[0047]
In the user terminal 10, the control unit 12 controls the user interface 11, so that information serving as a teaching material is provided to the student in accordance with the teaching material data transmitted from the service provider 30. For example, a learning sentence example corresponding to text data in the teaching material data is displayed in the display area De of the screen shown in FIG. Further, the movement of the tongue and the lips in the exemplary utterance operation is displayed as a still image for each predetermined frame in the display area Db of the screen shown in FIG. 6 corresponding to the moving image data in the teaching material data. .
[0048]
Further, when receiving the voice data indicating the exemplary utterance together with the teaching material data, the control unit 12 may display the waveform of the voice indicated by the voice data in the display area Dd. In addition, the control unit 12 may cause the speaker 11f to output an exemplary utterance.
Further, when the control unit 12 receives video data indicating an exemplary utterance operation together with the teaching material data, the control unit 12 may cause the video indicated by the video data to be displayed in the display area Da, the display area Db, or the like. At this time, the model of the utterance operation can be presented to the student at the user terminal 10 by outputting the exemplary utterance and the image indicating the exemplary utterance operation in cooperation with each other.
[0049]
In the user terminal 10, when a user of the user terminal 10 as a student performs an utterance operation, a voice is captured by a microphone 11a provided in the user interface 11, and a video is captured by photographing with a CCD camera 11b. The control unit 12 controls the display device 11c to display the waveform of the sound input from the microphone 11a in the display area Dd. The control unit 12 controls the display device 11c to display a plurality of still images of the student's face in the display area Da, and shows the movement of the lips in the student's utterance operation in the display area Db. Display multiple still images.
[0050]
The control unit 12 of the user terminal 10 encodes audio input from the microphone 11a to create audio data, and digitizes an image captured by shooting with the CCD camera 11b to create image data. The audio data and the video data thus created are sent to the service provider 30 via the network 20 by the communication interface 14.
[0051]
The server 40, which has received the audio data and the video data from the user terminal 10, analyzes the voice emitted by the student by the audio analysis unit 62 of the control unit 41, and the video analysis unit 63 analyzes the video captured by the CCD camera 11b. Analysis is performed (step S4).
More specifically, the voice analysis unit 62 compares the voice feature extracted from the voice data sent from the user terminal 10 with the voice feature extracted from the voice data corresponding to the typical utterance read from the model voice DB 71. Then, audio difference data indicating the difference is created. In addition, the video analysis unit 63 extracts feature amounts indicating the shape, color, and movement of the lips from the video data transmitted from the user terminal 10. The video analysis unit 63 compares the extracted feature amount with the feature amount extracted from the video data corresponding to the exemplary utterance operation read from the model video DB 72 for each frame, and video difference data indicating the difference. Create The difference data for audio created by the audio analysis unit 62 and the difference data for video created by the video analysis unit 63 are sent to the advice creation unit 64.
[0052]
Further, the voice recognition unit 66 recognizes the utterance of the student using the voice data transmitted from the user terminal 10 (step S5).
More specifically, the voice recognition unit 66 extracts a feature amount of the voice data sent from the user terminal 10 and combines a word close to the utterance of the student to generate a sentence corresponding to the utterance operation of the student. The utterance sentence data shown is created. The utterance sentence data created by the voice recognition unit 66 is sent to the user terminal 10 via the network 20 by the communication interface 43.
The user terminal 10 that has received the uttered sentence data causes the control unit 12 to control the display device 11c of the user interface 11 so that the sentence indicated by the uttered sentence data is displayed as text in the display area Dc of the screen illustrated in FIG. .
[0053]
The advice creating unit 64 creates advice for instructing the student based on the difference data received from the audio analyzing unit 62 and the video analyzing unit 63 (Step S6).
More specifically, the advice creating unit 64 compares the difference data for audio received from the audio analysis unit 62 and the difference data for video received from the video analysis unit 63 with the difference data stored in the guidance information DB 73, respectively. Compare with model data. At this time, the advice creating unit 64 sequentially reads a plurality of types of difference model data classified as learning sentence examples of the teaching material data sent to the user terminal 10 in step S2 from the guidance information DB 73. The difference model data for speech included in the read difference model data is compared with the difference data for speech created by the speech analysis unit 62. The video difference model data included in the read difference model data is compared with the video difference data created by the video analysis unit 63.
[0054]
As a result of this comparison, the advice creating unit 64 specifies the difference model data that has the closest (small difference) to the difference data received from the audio analysis unit 62 and the video analysis unit 63. The advice creating unit 64 reads the instruction sentence data and the video material reference data stored in association with the specified difference model data. The advice creating unit 64 reads out the video data from the reference destination indicated in the video material reference data, that is, the model video DB 72, and configures the advice in combination with the guidance sentence data.
If the difference data for audio and video is within a predetermined appropriate range, the advice creating unit 64 creates a message such as “Perfect !!” as advice, for example.
[0055]
The advice created by the advice creating unit 64 is sent to the advice providing unit 65.
The advice providing unit 65 sends the advice created by the advice creating unit 64 to the user terminal 10 via the network 20 by the communication interface 43 (Step S7).
[0056]
The control unit 12 controls the user interface 11 of the user terminal 10 that has received the advice including the instruction sentence data and the video data indicating the exemplary utterance operation, and outputs the advice for instructing the student.
For example, the control unit 12 controls the display device 11c to display the guidance sentence indicated by the guidance sentence data in the display area De of the screen illustrated in FIG. Further, the control unit 12 may control the display device 11c to display an image of a typical utterance operation indicated by the image data included in the advice in the display area Da, the display area Db, or the like.
Further, the control unit 12 may output the guidance sentence indicated by the guidance sentence data as a voice by controlling the speaker 11f.
[0057]
Thereafter, the process returns to step S1.
That is, the curriculum setting unit 60 determines the student's language ability based on the type of advice sent by the advice providing unit 65 to the user terminal 10 in step S7, and determines the learning content according to the student's language ability. Set.
[0058]
When the student operates the keyboard 11d or the mouse 11e to input a command to end the language learning at the user terminal 10, a request to end the learning is sent from the user terminal 10 to the service provider 30. Then, the processing shown in the flowchart of FIG. 6 is terminated.
Thus, by operating the user terminal 10 to access the service provider 30 at a desired time, the learner can receive interactive language education without a leader.
[0059]
As described above, according to the present invention, the learning content according to the student's language ability is set, and the user terminal 10 can output an exemplary utterance and an exemplary utterance operation. Furthermore, appropriate advice for instructing the student can be output from the user terminal 10 according to the difference between the student's utterance operation and the exemplary utterance operation.
Thereby, the language education can be efficiently provided to the students.
[0060]
The present invention is not limited to the above embodiment, and various modifications and applications are possible.
In the above embodiment, the online education system in which the user terminal 10 and the service provider 30 are connected to each other via the network 20 has been described. However, the present invention is not limited to this. For example, one (stand-alone) computer system may have the functions of the user terminal 10, the server 40, and the DB 50 described above. That is, the CPU provided in one computer system executes the operation program stored in the predetermined storage device, and thereby the same as the control unit 12 of the user terminal 10 and the control unit 41 of the server 40 described above. You may make it operate.
[0061]
Further, in the above embodiment, the advice creation unit 64 creates advice using both the audio difference data created by the audio analysis unit 62 and the video difference data created by the video analysis unit 63. It was explained as. However, the present invention is not limited to this, and the advice may be created using only one of the difference data for audio and the difference data for video. That is, the advice creation unit 64 compares the difference data for audio received from the audio analysis unit 62 with the difference model data stored in the guidance information DB 73, or the difference data for video received from the video analysis unit 63. The instruction sentence data and the video material reference data may be read according to only one of the comparison result between the instruction sentence data and the difference model data stored in the instruction information DB.
[0062]
A computer or a group of computers functions as the above-mentioned online education system, or all or a part of an operation program necessary for executing the above-mentioned processing is stored in a recording medium (IC memory, optical disk, magnetic disk, magneto-optical disk ) May be recorded and distributed / distributed. Further, the above-described operation program may be stored in an FTP (File Transfer Protocol) server on the Internet, and may be superimposed on, for example, a carrier wave, downloaded to a computer system, and installed.
[0063]
【The invention's effect】
As described above, according to the present invention, language education can be efficiently provided to a student.
[Brief description of the drawings]
FIG. 1 is a diagram showing a configuration of an online education system according to an embodiment of the present invention.
FIG. 2 is a diagram illustrating a configuration of a user terminal.
FIG. 3 is a diagram showing a configuration of a service provider.
FIG. 4 is a diagram illustrating a configuration example of data stored in a teaching material DB;
FIG. 5 is a diagram illustrating a configuration example of data stored in a guidance information DB.
FIG. 6 is a diagram illustrating an example of a screen displayed on a display device.
FIG. 7 is a flowchart illustrating a process executed by a server.
[Explanation of symbols]
10 User terminal
20 Network
30 Service Provider
40 servers
50 Database (DB)
60 Curriculum setting section
61 Teaching Material Provision Department
62 Voice Analysis Unit
63 Video analysis unit
64 Advice Creation Department
65 Advice Provision Department
66 Voice Recognition Unit
70 Teaching Material DB
71 Model Voice DB
72 Model Video DB
73 Guidance Information DB

Claims (6)

An online education system including a terminal device and a server device connected to each other via a network,
A model voice database storing voice data indicating exemplary utterances,
A model video database that stores video data of exemplary speech actions,
A guidance information database storing a plurality of types of guidance information,
Speech analysis means for comparing the speech data indicating the utterance of the student generated by the terminal device with the speech data stored in the model speech database, and generating an analysis result indicating the difference,
Video analysis means for comparing the video data generated by the terminal device by capturing the utterance operation of the student with the video data stored in the model video database, and generating an analysis result indicating the difference,
Advice creation means for creating guidance by reading guidance information corresponding to the analysis result of the audio analysis means and the video analysis means from the guidance information database,
An online education system comprising: an advice providing unit that outputs the advice created by the advice creating unit to the terminal device. Voice input means for capturing the utterance of the student,
Imaging means for photographing the utterance action of the student;
Audio output means;
Display means;
A model voice database storing voice data indicating exemplary utterances,
A model video database that stores video data of exemplary speech actions,
A guidance information database storing a plurality of types of guidance information,
A model providing unit that reads out audio data stored in the model audio database and outputs an exemplary utterance from the audio output unit;
Voice recognition means for recognizing the utterance of the student taken in by the voice input means and displaying a sentence corresponding to the utterance of the student on the display means;
Video analysis means for comparing the video data created by the imaging of the imaging means with the video data stored in the model video database and generating an analysis result indicating the difference,
Advice creation means for creating guidance by reading guidance information corresponding to the analysis result of the video analysis means from the guidance information database;
An information processing apparatus comprising: an advice providing unit configured to output an advice created by the advice creating unit by at least one of the voice output unit and the display unit. The model providing means includes means for reading out video data stored in the model video database and displaying an image of an exemplary utterance operation on the display means,
The information processing apparatus according to claim 2, wherein the display unit displays an image of the utterance operation of the student photographed by the imaging unit. An information processing device connected to a terminal device via a network,
A model voice database storing voice data indicating exemplary voices,
A model video database that stores video data of exemplary voice actions,
A guidance information database storing a plurality of types of guidance information,
A model providing unit that reads out the audio data stored in the model audio database and sends it to the terminal device, so that the terminal device outputs an exemplary utterance,
Voice recognition means for recognizing the utterance of the student from the voice data sent from the terminal device, and displaying a sentence corresponding to the utterance of the student on the terminal device,
Video analysis means for comparing the video data sent from the terminal device with video data stored in the model video database and generating an analysis result indicating the difference,
Advice creation means for creating guidance by reading guidance information corresponding to the analysis result of the video analysis means from the guidance information database;
An information processing apparatus, comprising: an advice providing unit configured to output advice for instructing a student on the terminal device by sending the advice created by the advice creating unit to the terminal device. A computer system comprising a model audio database, a model video database, and a guidance information database,
Speech data indicating an exemplary utterance is stored in the model speech database,
Storing video data of an exemplary utterance operation in the model video database,
Store a plurality of types of guidance information in the guidance information database,
Read the voice data stored in the model voice database, output an exemplary utterance,
Recognize the student's utterance, display the text corresponding to the student's utterance,
The video data created by capturing the student's utterance operation is compared with the video data stored in the model video database, and the difference is used as an analysis result.
The guidance information corresponding to the analysis result is read from the guidance information database to create an advice,
An information providing method characterized by outputting the created advice in video and / or audio. Computer
Voice input means for capturing the utterance of the student,
Imaging means for photographing the utterance action of the student;
Audio output means;
Display means;
A model voice database storing voice data indicating exemplary utterances,
A model video database that stores video data of exemplary speech actions,
A guidance information database storing a plurality of types of guidance information,
A model providing unit that reads out audio data stored in the model audio database and outputs an exemplary utterance from the audio output unit;
Voice recognition means for recognizing the utterance of the student taken in by the voice input means and displaying a sentence corresponding to the utterance of the student on the display means;
Video analysis means for comparing the video data created by the imaging of the imaging means with the video data stored in the model video database and generating an analysis result indicating the difference,
Advice creation means for creating guidance by reading guidance information corresponding to the analysis result of the video analysis means from the guidance information database;
A program for functioning as advice providing means for outputting the advice created by the advice creating means by at least one of the audio output means and the display means.

Images