KR20190070682A - System and method for constructing and providing lecture contents - Google Patents

Abstract

The present invention relates to a system for constructing and providing lecture contents and a method thereof. A method for constructing and providing lecture contents according to the present invention comprises: a step of providing a learning contents registration page, and registering learning contents inputted by a lecture enrollee by means of the learning contents registration page; a step of providing a learning module list with respect to a plurality of learning modules, each of which includes a voice processing function, and consecutively arranging at least one among the plurality of learning modules corresponding to a choice of the lecture enrollee; a step of providing a connection menu allowing at least one among the consecutively arranged learning modules to be connected to the registered learning contents, and matching at least one among the consecutively arranged learning modules to at least one learning contents corresponding to the choice of the lecture enrollee to generate lecture contents; a step of, when a learner requests, performing the plurality of learning modules included in the lecture contents in an arranged order by the sound processing function provided in each of the learning modules, whereupon matched learning contents are processed when the matched learning contents exist.

Description

[0001] SYSTEM AND METHOD FOR CONSTRUCTING AND PROVIDING LECTURE CONTENTS [0002]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a system and method for constructing and providing contents of a lecture, and more particularly, to a system and method for constructing lecture contents for allowing a learner to learn a predetermined learning content, ≪ / RTI >

Along with the growth of the market related to learning, there is a surge in the provision of lecture contents online.

These online lecture contents are becoming very popular due to the advantage of easy accessibility for learners, and online lecture contents providers are fiercely competing for more members.

Therefore, it has become a challenge for the content providers to quickly provide lecture content that meets the needs of the learner, which has led to the success or failure of the business. In response to this situation, a service that enables easy creation of online lecture contents .

In recent years, on-line lectures have been provided for not only learning contents to learner but also feedback processing of learner's voice signals. In the conventional modular lecture contents construction method, Since it is not properly included in the content composition process or does not include processing of the learner's voice signal at all, it takes a considerable time due to the problem related to the learner's voice signal processing when constructing the contents of the entire lecture .

In this way, it is difficult to produce the contents to be executed through the voice control command because the learner's utterance is varied, and in order to respond appropriately to the situation, the number of all cases must be defined in a rule-based form.

In other words, it is necessary to predefine not only content planning but also user intent and user utterance cases, and since the number of cases in which the system can answer the user's question needs to be defined in advance, It is difficult for him.

However, conventionally, the process of constructing lecture contents in consideration of voice control commands or learner's voice feedback has been unsatisfactory in terms of user convenience.

Published Patent No. 10-2003-0070718

SUMMARY OF THE INVENTION The present invention has been made to solve the above-mentioned problems, and its object is to provide a lecture content configuration and provision that can easily configure lecture contents considering learner's voice control command or learner's voice feedback processing And to provide a system and a method for the same.

In order to accomplish the above object, a lecture composition and providing system according to the present invention comprises: a learning content registering unit for providing a learning content registration page and registering learning content input from a lecture registrant through the learning content registration page; Each of which includes a plurality of learning modules each including a voice processing function, provides a list of learning modules for the plurality of learning modules, and sequentially arranges at least one of the plurality of learning modules according to the selection of the class registrants A learning module management unit; And a linking menu for linking at least one of the sequentially arranged learning modules with the registered learning contents, wherein at least one of at least one of the sequentially arranged learning modules according to the selection of the enrollee A lecture content generation unit for generating lecture contents by matching with learning contents; A plurality of learning modules included in the lecture contents are performed in the order in which the lecture contents are provided by the learner's speech processing function provided in each learning module, and when the matched learning contents exist, learning And a processing unit.

In order to achieve the above-mentioned object, the present invention provides a content construction and provision method for a lecture, comprising: providing a learning content registration page and registering a learning content input from a lecture registrant through the learning content registration page; Providing a list of learning modules for a plurality of learning modules each including a voice processing function and sequentially arranging at least one of the plurality of learning modules according to the selection of the lecturer; And a linking menu for linking at least one of the sequentially arranged learning modules with the registered learning contents, wherein at least one of at least one of the sequentially arranged learning modules according to the selection of the enrollee Generating lecture contents by matching with learning contents; A plurality of learning modules included in the lecture contents are performed in the arranged order by a voice processing function provided in each learning module at the request of the learner, and when the matched learning contents exist, the matched learning contents are processed / RTI >

As described above, according to the present invention,

The lecture registrant can utilize each learning module provided by the lecture contents composition and provision system in creating and registering lecture contents on-line, thereby shortening the lecture content creation time.

In particular, since each learner module provided by the lecture contents organization and provision system includes a voice processing function, the lecture registrant does not have to worry about a separate voice processing routine for processing the learner's feedback, Increase.

Furthermore, each learning module is matched with a module-by-module speech case, so that processing of the speech signal during the learning process of the learner is judged based on the module-by-module speech case matched to each learning module. The speed can be greatly increased.

In addition, since contents of lectures registered by others can be retrieved and recycled while registering only learning contents, utilization of lecture contents can be maximized, and benefits of lecture frequency can be provided, thereby enabling the registration of contents of lectures of good quality.

In the case where there is a past history of learning, it is possible to automatically perform the learning from thereafter, thereby minimizing the inconvenience or hassle of the learner.

Further, since the push message related to the unit that has been learned through the speech recognition network speaker is received by the communication terminal of the learner and the completed learning contents can be displayed according to the user's selection, , And can stimulate learning motivation because they can escape from the monotonous auditory learning for a while.

BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a schematic configuration diagram of an entire system including a content composition and provision system according to an embodiment of the present invention,
FIG. 2 is a functional block diagram of a content composition and provision system of FIG. 1;
FIG. 3 is a control flowchart of the content construction and provision system of FIG. 1,
FIG. 4 and FIG. 5 are views showing an example of a learning module provided by the contents composition and providing system of FIG. 1,
Figs. 6 and 7 are diagrams showing an example of configuring a new lecture content by arranging the learning module of Fig. 5 after selecting a lecture.

Hereinafter, the present invention will be described in detail with reference to the accompanying drawings.

Hereinafter, embodiments of the present invention will be described in order to facilitate understanding of the present invention, and the present invention is not limited to these embodiments. In particular, the present invention can be configured by combining at least any one of individual components, individual functions, or individual steps included in each embodiment.

In particular, some claims of the claims for convenience include alphabets such as '(a)' for convenience, but these alphabets do not define the order of each step.

Hereinafter, each of the signals referred to in the embodiments of the present invention may refer to one signal transmitted through one connection or the like, but may also mean a series of signal groups transmitted for the purpose of performing a specific function . That is, in each embodiment, a plurality of signals transmitted after a predetermined time interval or after receiving a response signal from the counterpart device can be represented by a single signal name for convenience.

A schematic configuration of an entire communication system including a system 100 for composing and providing contents of a lecture according to an embodiment of the present invention is as shown in Fig.

In this figure, the learner using device 210 is a device that is used or operated by a person who wishes to learn the content of a predetermined lecture, and is controlled by voice, for example, as a voice recognition network speaker (aka AI Or may be a portable wireless device, such as a smart phone.

However, in the present embodiment, it is assumed that the learner conducts learning in an auditory manner through a speech recognition network speaker.

In addition, the communication terminal corresponding to the learner, that is, the learner communication terminal 220, receives information necessary for selection of learning contents or learning during learning through the voice recognition network speaker, before learning progress, or after learning progress And may correspond to a communication terminal such as a smart phone, and a more detailed description thereof will be given later.

On the other hand, in the drawing, the lecture registration device 300 registers a predetermined lecture content in the lecture content organization and provision system 100 by a lecturer's registrant, and may correspond to, for example, a computer provided in the home .

The learner using device 210 and the lecture registration device 300 shown in Fig. 1 are merely an example, and can be used for learning or can be used for enrollment of a lecture. It may correspond to the learner using device 210 or the lecture registration device 300. [

On the other hand, the lecture contents organizing and providing system 100 performs a function of registering lecture contents at the request of the lecture registrant, and providing the contents of the lecture to the learner to perform learning.

The provision of the contents by the lecture contents organizing and providing system 100 means that the lecture contents organizing and providing system 100 provides the contents to the learner using device 210. Providing the lecture contents provider with a predetermined page means that the lecture registering device 300, and the lecture contents organizing and providing system 100 is an example of registering and providing contents for learning English.

The lecture composition and provision system 100 according to an embodiment of the present invention provides considerable convenience in constructing a content including a lecture voice processing function, which is described with reference to the detailed components of Fig. 2 do.

FIG. 2 is a functional block diagram of a content construction and provision system 100 according to an embodiment of the present invention.

As shown in the figure, the lecture contents organizing and providing system 100 includes a learning contents registering unit 110, a learning module managing unit 120, a lecture contents generating unit 130, a learning processing unit 140, a service benefit providing unit 150, a content list providing unit 160, and a learning support unit 170.

First, the learning content registration unit 110 provides the learning content registration page to the lecturer registrant, and performs a function of registering the learning content input from the lecturer registrant through the learning content registration page.

Here, the learning contents include contents learned by actual learners. For example, in the case of an English lecture, the learning contents may be a text file, an audio file, an image file, or the like including contextual English conversation.

The process of registering a predetermined content on-line is itself a well-known technique and will not be described in detail.

The learning module management unit 120 includes a plurality of learning modules each including a voice processing function, and provides a learning module list for the plurality of learning modules to the lecturer.

For example, the learning module provided by the learning module management unit 120 includes a playback module, a question and answer module, and an English pronunciation evaluation module as basic modules, and includes at least one application module utilizing the basic module Can be. Each of the application modules includes a voice processing function as well as the basic module. The learning module managing unit 120 performs a function of sequentially arranging at least one of the plurality of learning modules according to the selection of the lecturer. Specific examples utilizing these basic modules and application modules will be described later.

Here, the voice processing function provided in each learning module may be at least one of a multimedia file playback function, a TTS (Text To Speech) function, a STT (Speech To Text) function, and a pronunciation recognition function. The ignition case may be matched.

For example, each learning module can be sequentially processed according to the progress of learning as described later, and the analysis and processing of the user's voice can be processed more accurately and promptly because it is defined in the speaking case for each module.

Meanwhile, the lecture content generation unit 130 provides a connection menu for connecting at least any one of the learning modules sequentially arranged by the learning module management unit 120 to the learning content registered by the learning content registration unit 110 do.

Accordingly, the lecture content creator 130 may associate at least one of the learning modules sequentially arranged according to the selection of the lecture registrant, And finally generates a lecture content.

That is, the content of the generated lecture is substantially managed by the learning content registered by the learning content registration unit 110, a plurality of learning modules whose placement order is determined by the learning module management unit 120, Each learning module contains all the matching information of the learning contents.

At this time, the lecture content generation unit 130 may register the lecture specified by the lecture registrant to the content of the lecture that generates the lecture, and a more detailed description using this classification will be described later.

The content of the generated lecture can be provided to the learner for online learning.

That is, the learning processing unit 140 performs a plurality of learning modules included in the lecture contents at the learner's request by the audio processing functions provided in the respective learning modules in the order in which they are arranged, And performs the function of processing the learning contents.

Here, the performance by the voice processing function provided in each learning module means that the multimedia contents are played back by using the multimedia file playback function and the voice signal is transmitted or the multimedia contents are played using the TTS (Text To Speech) function At least one of the steps of generating and sending out a voice signal after recognizing the character, converting the voice received from the learner into text by using the STT (Speech To Text) function, or recognizing the pronunciation of the learner using the pronunciation recognition function It can mean a process.

In particular, when it is necessary to process a speech signal input from a learner during the execution of each learning module, the learning processing unit 140 can determine the speech signal based on the module-based speech case matched to the learning module that has been processed immediately or at the current time.

That is, as described above, each learning module is matched with a module-by-module speech case. The learning processing unit 140 extracts a speech case matched to the learning module that is currently or immediately proceeded, It is possible to more accurately and quickly analyze the contents of the learner in comparison with the extracted speech case.

That is, when there is no module-specific speech case, the learning processing unit 140 has to compare the speech inputted from the learner with all kinds of contents referred to by the human. However, as in the present embodiment, The processing speed and accuracy can be increased since the content to be uttered to the learner according to the learning progress status is compared only with the utterance case matched to the learning module that has been performed at present or immediately to be performed.

The function of the learning processing unit 140 is described below.

When a learning request for a specific lecture content is received from the learner through the voice recognition network speaker 210, the learning processing unit 140 outputs the voice output signal for each learning stage according to the content of the lecture to the voice recognition network speaker 210 Lt; / RTI >

Specifically, the learning processing unit 140 receives a speech signal for learning control (start learning, stop learning, end learning, etc.) from the learner through the speech recognition network speaker 210, that is, the learning control speech signal Control speech signal of the learner corresponds to the pre-registered speech-phrase information in consideration of the current learning progress stage, and if the learning control speech signal of the learner corresponds to the already registered speech-phrase information The lecture contents corresponding to the lecture contents are determined and the learning modules are executed in the order in which they are arranged in the respective learning stages based on the information on the plurality of learning modules included in the determined lecture contents, Learning through the recognition network speaker 210 can be performed.

For example, in a storage unit (not shown), a learner's voice command for controlling learning progress through the speech recognition network speaker 210, that is, speech information corresponding to the learning control speech signal, Herein, 'information on the current learning progress of the learner' includes not only whether or not the learning has been started through the speech recognition network speaker 210 at present, And whether learning is being carried out.

The 'information on the current learning progress level of the learner' may correspond to the information about the degree of learning so far regardless of whether the learning is performed through the speech recognition network speaker 210 at present.

In this case, the above-mentioned utterance phrase information includes a lecture selection control phrase corresponding to a learner's utterance for selecting or calling a specific lecture, a reproduction control phrase corresponding to a learner's utterance for reproducing a specific lecture, A lecture stop control phrase corresponding to a learner's utterance for stopping the lecture, a lecture completion control phrase corresponding to learner's utterance for ending lecture reproduction, a lecture corresponding to learner's utterance for confirming lecture-related information And an information check control phrase.

Therefore, when the learning control speech signal is received from the speech recognition network speaker 210, the learning processing unit 140 refers to the information stored in the storage unit, and the learning control speech signal of the received learner corresponds to the already registered speech phrase information Can be judged based on the present learning progress stage.

The learning processing unit 140 refers to the data of the storage unit in which the types of the utterance phrase (text or image, etc.) for each learning progress stage are matched, It is possible to determine the speech phrase information corresponding to the learning control speech signal of the learner for each learning progress step.

The learning processing unit 140 stores the learning progress history of the content of each lecture in which learning is performed through the speech recognition network speaker 210 in the storage unit and refers to the learning progress history stored in the storage unit Learning through the speech recognition network speaker 210 may be performed.

For example, if the learner speaks 'Speak to a basic English conversation' on the speech recognition network speaker 210 and receives a learning control speech signal, the learning processing unit 140 generates 'basic English conversation' corresponding to the learning control speech signal, If the learner has previously learned a part of the 'basic English conversation' lecture content, the learning processing unit 140 may extract the lecture voice signal corresponding to the content of the lecture, The lecture speech signal from the lecture can be extracted and transmitted to the speech recognition network speaker 210.

This is a kind of eavesdropping function, which allows the learner to maximize learning efficiency because he or she does not have to search for the contents previously learned by him / herself.

For example, if the learning history is only shown, the learner can check the learning history and then reproduce the contents from the next learning contents. If the learning progress history exists as described above, It is possible to minimize the inconvenience of the learner.

Of course, if a learner directly specifies a specific learning location, he / she may follow the learner's choice.

For example, in a case where the learner has been learning until 5 minutes and 30 seconds of the 'second lecture' of 'basic English conversation', and the speech recognition network speaker says 'play basic English conversation', the learning processing unit 130 The second lecture of 'Basic English Conversation' 5 minutes and 30 seconds later. In another example, the learner can take the same situation (the 'second lecture' of 'Basic English Conversation' 5 Minute), the learning processing unit 140 recognizes that the speech recognition network speaker is in the state of learning 'Basic English Conversation ", even though the previous learning progress history exists From the "third lecture", it is possible to process the learning process.

On the other hand, the learning support unit 170 extracts a speech tag list including at least one speech tag phrase information that can be processed in the current learning progress stage through the speech recognition network speaker 210, and outputs the extracted speech tag list to the learner To another communication terminal (220).

For example, the learning support unit 170 may be configured to provide speech information for selecting a specific learning content before a learner starts learning about lecture contents or while learning a lecture content, that is, A list of utterance phrases including phrase information (utterance phrase information) that should be communicated to the communication terminal 210 can be extracted and transmitted to a separate communication terminal 220 corresponding to the learner.

The learning support unit 170 may provide a list of speech phrases including the speech information for each learning progress stage to a separate communication terminal 220 that can visually confirm the learning progress. can do.

Here, the learning support unit 170 must be aware of the identification information of the communication terminal 220 in order to communicate with a separate communication terminal 220 for the learner. It may correspond to the terminal phone number matched with the network speaker 210 and stored in advance, or may correspond to session information generated based on the login process.

When the learning processing unit 140 communicates with the speech recognition network speaker 210 and proceeds to the learning as described above, the learning support unit 170 transmits the speech output signal corresponding to the speech output signal to the speech recognition network speaker 210 The learning contents may be transmitted to a separate communication terminal 220 corresponding to the learner.

For example, when the learning processing unit transmits the English content voice output to the voice recognition network speaker 210, the learning support unit 170 can transmit the text fingerprint corresponding to the English content voice output to the separate communication terminal 220 It is.

In particular, when the learning process for the predetermined unit is completed through the speech recognition network speaker 210, the learning support unit 170 generates a review push message corresponding to the completed specific unit and transmits the review push message to the communication terminal 220).

Here, the division of 'specific unit' is classified according to its own standards in advance, and it is not necessarily limited to those classified in the same manner as the first and second classes.

The review push message may include an Internet address corresponding to a specific unit whose learning progress has been completed through the speech recognition network speaker 210 or an application identification number for executing a specific application stored in the communication terminal 220 .

In this case, the communication terminal 220 displays a review push message to allow the learner to select the learner, and when the learner selects the specific learner, the specific application corresponding to the review push message is executed, ) To request the completion of the learning progress.

When the communication terminal (in particular, the specific application described above) 220 transmits a learning content request signal according to the push message to the lecture contents organization and providing system, the learning support unit 170 performs learning through the voice recognition network speaker 210 Can extract the learning content for the completed specific unit and transmit it to the communication terminal 220.

Thereafter, the communication terminal 220 can display the contents of learning received from the learning support unit 170. Accordingly, the learner can recognize the text document for the unit that has just been learned through the speech recognition network speaker 210, So that it can be reviewed while checking through the terminal 220.

This push message has the effect of improving learner 's learning efficiency and inspiring learning motivation.

(Text, images, and the like) for the completed unit is received through the communication terminal of the user each time the learning for the predetermined unit (for example, each unit) preset by the speech recognition network speaker is completed. The learner visually confirms the learning contents which were only audible through the speech recognition network speaker through the communication terminal, and thus the learning efficiency is raised. Further, learning is performed sequentially by using both the auditory and visual aspects, will be.

Meanwhile, the lecture contents organizing and providing system 100 according to an embodiment of the present invention can generate lecture contents by different lecture registrants instead of only one lecture registrant creating lecture contents. In this case, The registrant can borrow at least a part of the structure of the lecture contents already created and registered by the registrant of another lecture.

Hereinafter, such a function will be described again with reference to the functional blocks of FIG.

Assuming that the lecture contents have already been created and registered by the registrant of the first lecture, if there is a request from the registrant of another lecture (that is, the registrant of the second lecture), the learning module management section 120 Specifically, a plurality of learning modules included in the lecture contents registered by the registrant of the first lecture may be arranged in the order in which the lecture contents are arranged in the lecture contents For example, a computer).

In addition, the lecture content generation unit 130 may be configured such that a plurality of learning modules included in the lecture contents of the registrant of the first lecture are sequentially arranged according to a request of the registrant of the second lecture, In accordance with the selection of the registrant of the second lecture, a learning module which is sequentially arranged in advance (that is, a learning module included in the lecture contents generated by the registrant of the first lecture) ) With at least one newly registered learning content by the registrant of the second lecture to generate a new lecture content.

In other words, the registrant of the second lecture recalls the lecture contents registered by the registrant of the first lecture without having to make the entire process from the beginning, and only the learning contents matched to the respective lecture modules are re- It is possible to construct a new lecture content by matching.

For example, if the lecture contents registered by the registrants of the first lecture are English lecture contents and the lecture contents to be registered by the registrants of the lecture are the lecture contents of the Chinese lecture, The content of the lecture can be retrieved, and the content configuration of the lecture can be maintained, and only the learning contents matched to each learning module can be matched back to Chinese.

Of course, the registrant of the second lecture may change at least one of the learning modules arranged in the content of the lecturer of the first lecture to another learning module or add a new learning module.

Accordingly, the registrant of the second lecture can shorten a considerable amount of time in creating and registering new lecture contents.

When the lecture content is reused by the registrant of another lecture, the lecture contents organizing and providing system 100 provides a predetermined benefit to the person who has registered the contents of the recycled lecture. )to be.

For example, as described above, when the registrant of the second lecture registers the content of the lecture contents registered by the registrant of the first lecture and registers the new lecture contents, the service benefit providing unit 150 provides the service re- Of the service.

Here, the service benefits to be provided to the registrants of the first lecture may include various forms of providing economic benefits, directly or indirectly, to the registrants of the first lecture, such as a service charge rate discount, a point payment, and a free coupon dispatch.

When a lecture content list request signal including a specific classification is received from a person who intends to register a new lecture content (that is, a lecture registration prospective person) with reference to a lecture contents structure of another person, And extracts and provides a list of the contents of the lecture matched to the lecture contents.

At this time, the content list provider 160 of the lecture can sort and display the list on the basis of the frequency used for the content composition of the new lecture by the registrant of the other lecture.

For example, if there is a request for a list of lecture contents classified as 'English lecture' from a lecture registration candidate, the lecture contents list providing unit 160 extracts a lecture contents list classified as 'English lecture' In consideration of the recycling frequency of the contents of the lecture included in the list.

For example, the content list classified as 'English lecture' includes lecture contents such as 'lingo English', 'TOEIC Full Score Strategy', 'TOEIC Listening Attack', and 'Lost Speaking', and the content of each lecture is recycled (Ie, the ratio used or referenced in the creation of the other lectures) is 2 times for "Beginning English", 7 times for "TOEIC score", 4 times for TOEIC listening, 15 times for " The list can be arranged in the order of "missing speech," "TOEIC score strategy," "TOEIC listening," and "English for beginners."

As a result, the lecturer can easily identify the lecture contents that are used most frequently by the registrants of other lectures, and can utilize the contents of the lecture contents to shorten the time for constructing lecture contents And acquire information about the way it is popular with learners.

Hereinafter, the overall control flow of the lecture content construction and provision system 100 according to an embodiment of the present invention will be described with reference to FIG.

First, the lecture content composition and providing system 100 provides a lecture registrant with a learning registration content registration page (step S1).

Thereafter, the lecture contents organizing and providing system 100 registers and stores the learning contents inputted by the lecture registrant (step S3).

Thereafter, the lecture contents organizing and providing system 100 provides a list of at least one learning modules to the lecture registrants (step S5), wherein each learning module includes the voice processing function, respectively.

Subsequently, the lecture content organizing and providing system 100 sequentially arranges at least a part of the plurality of learning modules according to the selection of the lecture registrants (step S7), and then connects the sequentially arranged learning modules to the learning contents To the lecturer registrant (step S9).

Then, the lecture contents organizing and providing system 100 generates and registers the whole lecture contents by matching the sequentially arranged learning modules with the lecture contents according to the lecture registrar's selection (step S11).

After the lecture contents are generated and registered, if there is a learning request for the lecture contents from the learner, the lecture contents organizing and providing system 100 displays the lecture contents arranged in the lecture contents in the arranged order in the speech processing function (Step S13).

Hereinafter, an example of each learning module and a process of constructing the entire lecture contents using such a learning module will be described with reference to FIG. 4 to FIG.

4 and 5 show an example of modules previously registered in the lecture contents organizing and providing system 100 according to an embodiment of the present invention.

4 (a), a question and answer module (Fig. 4 (b-1) and Fig. 4 (b)) corresponds to a basic module, and Fig. 5 corresponds to an application module using such a basic module. b-2)), and an English pronunciation evaluation module (Fig. 4 (c)).

The playback module is used, for example, to play a specified voice file or to read a text file, which is used in, for example, playing a problem, reading a moving picture, giving a lecture, notifying a lecture start / end.

Next, the Answer and Answer module is used in, for example, solving TOEIC problems, solving quizzes and test questions, and talking with AI speakers. It is a module that helps students to ask questions, plays voice files or reads text files It queries the learner and performs the function of recognizing the learner's voice answer through STT.

The Q & A module can be divided into a rule-based form for performing STT processing or a method for analyzing using an inference model.

Finally, the English pronunciation evaluation module is used, for example, in the pronunciation score confirmation function, the pronunciation feedback function, the pronunciation confrontation function, and the like, and is a module for providing information on the pronunciation of a learner. And recognizes the learner's voice answer through the pronunciation recognition solution.

Such a basic module can be implemented as an application module in the most efficient manner. The functions of the application module shown in FIG. 5 will be described as follows.

5 (a)) is a module that can be started according to the learner's utterance command and provides an introduction to the lecture, and the type phrase module (Fig. 5 (b) And a lecture reproducing module (Fig. 5 (c)) is a module that reproduces the lecture contents but may be reproduced by the learner utterance command.

Next, the problem solving module (Fig. 5 (d)) provides a learner with multiple choice questions and answers questions, performs a function of providing feedback to the learner's answer, (e)) is to listen to a sentence or a word and give a sentence or word to the learner and provide feedback on the learner's utterance (for example, 'Great' when more than 70% (Fig. 5 (f)). The module allows the learner to listen to the sentence and continue the dialogue accordingly. The learner can continue the conversation using the rule-based data according to the learner's utterance And the free speech module (FIG. 5 (g)) provides a function to allow conversation to continue by inference (NLP / NLU) according to user utterance.

Next, the pronunciation score module (FIG. 5 (h)) tells the learner the pronunciation of the native speaker and then follows the learner's pronunciation. The learner evaluates the learner's utterance through the pronunciation recognition solution, (Fig. 5 (i)) also allows the learner to listen to the native speaker and follow the learner. The learner evaluates the learner's utterance through the pronunciation recognition solution, (Fig. 5 (j)) provides a confrontation mode (for two persons) between learners using a pronunciation total score, and is a program for each learner to speak After the content is evaluated through the pronunciation recognition solution, the function of providing the pronunciation score and the winner information as the final result is performed.

FIG. 6 and FIG. 7 show a state in which a lecture registrant arbitrarily selects one of these learning modules and constitutes one lecture content.

First, FIG. 6 shows an example of a one-sided lecture content, in which the start phrase model, the lecture playback module, and the end phrase module are arranged in this order.

In other words, when learning is performed using the lecture contents of FIG. 6, the lecture contents organizing and providing system 100 first executes the start phrase module so that the learner can hear the start phrase, To the learner, and finally, the learner is informed that the lecture is finished by executing the kind phrase module.

As described above, at least one learning content (e.g., a speech file or a text file for learning) may be matched to each learning module (in particular, the lecture reproducing module) The learning contents can be processed.

FIG. 7 is a flowchart illustrating a method of solving a problem in a lecture content. When learning is performed using the lecture contents, the lecture contents organizing and providing system 100 first executes a start phrase module so that a start phrase can be heard by the learner. Then, the lecture reproduction module is executed to transmit the lecture contents to the learner. The learner performs the problem solving process by executing the problem solving module. Finally, the lecture module is executed to inform the learner that the lecture is finished do.

As described above, the registrant of the lecture can shorten the lecture contents constitution time since the registrant of the lecture simply arranges the respective modules provided with the respective voice processing functions in accordance with the manner desired by them, as shown in Fig. 6 or Fig.

In particular, since each module has a speech processing function, and the speech cases for the respective modules are matched, accuracy and speed in processing learner's voice feedback can be improved.

Meanwhile, it goes without saying that the process of performing each of the above-described embodiments can be performed by a program or an application stored in a predetermined recording medium (for example, a computer-readable). Here, the recording medium includes an electronic recording medium such as a RAM (Random Access Memory), a magnetic recording medium such as a hard disk, and an optical recording medium such as a CD (Compact Disk).

At this time, the program stored in the recording medium may be executed on hardware such as a computer or a smart phone to perform each of the above embodiments. In particular, at least one of the functional blocks of the contents construction and provision system of the lecture according to the present invention described above can be implemented by such a program or an application.

The present invention is not limited to the above-described specific embodiments, and various modifications and changes may be made without departing from the gist of the present invention. It is to be understood that such variations and modifications are intended to be included in the scope of the appended claims.

100: Lecture contents composition and provision system
210: learner use device 220: learner communication terminal
300: lecture registration device 110: learning content registration part
120: learning module management unit 130: lecture content generation unit 140: learning processing unit 150:
160: Lecture Contents List Offering 170: Learning Support Section

Claims (22)

(a) providing a learning content registration page and registering learning content input from a lecturer registrant through the learning content registration page;
(b) providing a learning module list for a plurality of learning modules each including a voice processing function, and sequentially arranging at least one of the plurality of learning modules according to the selection of the lecturer;
(c) providing a connection menu for connecting at least one of the sequentially arranged learning modules with the registered learning contents, and selecting at least one of the sequentially arranged learning modules according to a selection of the class registrant Generating lecture contents by matching with one of the learning contents;
(d) a plurality of learning modules included in the lecture contents at the request of the learner are performed in the arranged order by the voice processing function provided in each learning module, and when the matched learning contents exist, And processing the content of the lecture. The method according to claim 1,
A plurality of learning modules included in the lecture contents registered by the registrant of the lecture are sequentially arranged, and at least one of the sequentially arranged learning modules is arranged by the registrant of the other lecture And a linking menu for linking the newly registered learning contents to the newly registered learning contents, and providing at least one of the sequentially arranged learning modules to at least one of the learning contents newly registered by the registrant of the other class And generating a new lecture content by matching the new lecture content with the new lecture content. 3. The method of claim 2,
And providing the learner with a service benefit corresponding to the frequency used by the registrant of the other lecture. The method according to claim 1,
In the step (c), the classification specified by the registrant of the lecture is matched to the content of the lecture to be generated,
When a lecture contents list request signal including a specific classification is received from a lecture registration candidate, a list of lecture contents matched to the specific lecture is extracted, and a list of the lecture contents matching the specific lecture is extracted by the registrant of another lecture, And arranging and displaying the contents on a basis. The method according to claim 1,
Wherein the voice processing function in the step (b) is at least one of a multimedia file playback function, a TTS (Text To Speech) function, a STT (Speech To Text) function, and a pronunciation recognition function. The method according to claim 1,
Each learning module is matched with a module-specific ignition case,
In the step (d), when it is necessary to process a voice signal inputted from a learner during the execution of each learning module, it is determined in consideration of a module-based speech case matched to a learning module that has proceeded immediately or at a current time Configuration and delivery method. The method according to claim 1,
The step (d)
(d1) receiving a learning control speech signal from the learner via a speech recognition network speaker;
(d2) judging whether the learning control speech signal of the learner received in the step (d1) corresponds to the already registered speech phrase information in consideration of the current learning progress stage;
(d3) judging a lecture content corresponding to the speech phrase information if the learning control speech signal of the learner corresponds to the pre-registered speech phrase information as a result of the determination in the step (d2);
(d4) the learning modules are executed in the order in which they are arranged on the basis of the information about the plurality of learning modules included in the content of the lecture determined in the step (d3) And a control step of controlling the contents of the lecture. 8. The method of claim 7,
(e) extracting a speech tag list including at least one speech tag phrase information that can be processed in the current learning progress step through the speech recognition network speaker;
(f) transmitting the list of speech phrases extracted in the step (e) to a separate communication terminal corresponding to the learner. 9. The method of claim 8,
Generating a review push message corresponding to the completed specific unit when the learning progress for the predetermined unit is completed through the voice recognition network speaker and transmitting the generated push push message to the communication terminal corresponding to the learner;
When a learning content request signal according to the push message is received from the communication terminal corresponding to the learner, the learning contents for the specific unit in which the learning progress through the voice recognition network speaker is completed is extracted and transmitted to the communication terminal corresponding to the learner Further comprising the steps of: determining whether or not the contents of the lecture are included in the content; 8. The method of claim 7,
Further comprising the step of storing a learning progress history of contents of each lecture in which learning is performed through the speech recognition network speaker,
Wherein, in the step (d4), if there is a learning progress history for the lecture contents determined in the step (d3), the learning is performed after the learned position. A computer-readable recording medium storing a program for executing the method according to any one of claims 1 to 10. 10. An application program stored on a computer readable medium for executing the method of any one of claims 1 to 10 in combination with hardware. A learning content registration unit for providing a learning content registration page and registering the learning content inputted from the lecture registrant through the learning content registration page;
Each of which includes a plurality of learning modules each including a voice processing function, provides a list of learning modules for the plurality of learning modules, and sequentially arranges at least one of the plurality of learning modules according to the selection of the class registrants A learning module management unit;
And a linking menu for linking at least one of the sequentially arranged learning modules with the registered learning contents, wherein at least one of at least one of the sequentially arranged learning modules according to the selection of the enrollee A lecture content generation unit for generating lecture contents by matching with learning contents;
A plurality of learning modules included in the lecture contents are performed in the order in which the lecture contents are provided by the learner's speech processing function provided in each learning module, and when the matched learning contents exist, learning And a processing unit for processing the content of the lecture. 14. The method of claim 13,
Wherein the learning module management unit sequentially arranges a plurality of learning modules included in the lecture contents registered by the lecturer's registrant when there is a request from the registrant of the other lecture,
Wherein the lecture content generation unit is configured to generate a lecture content based on a plurality of learning modules included in the lecture contents of the lecturer registrants in sequence according to a request of the registrant of the other lecture, At least one of the sequentially arranged learning modules is matched with at least one learning content newly registered by the registrant of the other class according to the selection of the registrant of the other class And the content of the new lecture is generated. 15. The method of claim 14,
Further comprising a service benefit providing unit for providing the service registrant with a service benefit corresponding to the frequency used by the registrant of the other class. 14. The method of claim 13,
Wherein the lecture content generation unit matches the lecture designated by the lecture registrant to the lecture content to be generated,
When a lecture contents list request signal including a specific classification is received from a lecture registration candidate, a list of lecture contents matched to the specific lecture is extracted, and a list of the lecture contents matching the specific lecture is extracted by the registrant of another lecture, And a lecture content list providing section for displaying the lecture contents by arranging and displaying them on a basis. 14. The method of claim 13,
Wherein the voice processing function is at least one of a multimedia file playback function, a TTS (Text To Speech) function, a STT (Speech To Text) function, and a pronunciation recognition function. 14. The method of claim 13,
Each learning module is matched with a module-specific ignition case,
Wherein the learning processing unit makes a decision based on a module-by-module speech case matched to a learning module which has been processed immediately or at a current time when processing of a speech signal input from a learner is required during each learning module execution, Delivery system. 14. The method of claim 13,
When the learning control speech signal is received from the learner through the speech recognition network speaker, the learning processing unit determines whether the learning control speech signal of the learner corresponds to the previously registered speech phrase information, considering the current learning progress stage, If the learning control speech signal of the learner corresponds to the pre-registered speech tag information, the lecture contents corresponding to the speech tag information are determined, and based on the information about the plurality of learning modules included in the determined lecture content, So that learning is performed through the speech recognition network speaker by causing each learning module to be executed in the order in which the learning modules are arranged. 20. The method of claim 19,
A learning support section for extracting a list of speech phrases including at least one speech tag phrase information that can be processed in the current learning progress stage through the speech recognition network speaker and transmitting the extracted speech tag list to a separate communication terminal corresponding to the learner, Further comprising the steps of: 21. The method of claim 20,
The learning support unit generates a review push message corresponding to the completed specific unit and transmits the review push message to the communication terminal corresponding to the learner when the learning progress for the preset specific unit is completed through the voice recognition network speaker, When the learning contents request signal according to the push message is received from the communication terminal corresponding to the learner, the learning contents for the specific unit whose learning progress is completed through the voice recognition network speaker is extracted and transmitted to the communication terminal corresponding to the learner A system for constructing and providing a content of a lecture characterized by: 20. The method of claim 19,
Wherein the learning processing unit stores a learning progress history of contents of each lecture in which learning is performed through the speech recognition network speaker and refers to the learning progress history so that learning is performed through the speech recognition network speaker after the learned position The content of the lecture and the content of the lecture.

Images