KR20210144019A - Program for providing language evaluation interfaces for pronunciation keywords - Google Patents

Abstract

An embodiment of the present invention provides an operating program of a terminal device, which is a program for executing an operating method of a terminal receiving language learning content from a language learning service providing apparatus and outputting the language learning content. The program executes the functions of: outputting a pronunciation learning interface corresponding to the learning content; outputting learning text including pronunciation time intervals through the pronunciation learning interface; receiving user's voice signals corresponding to the learning text; generating a differentiated evaluation interface image for each time interval with respect to a converted word, resulted from a text conversion process of the user's voice signals; and outputting the differentiated evaluation interface image on the learning text. The present invention can enhance accuracy in evaluating language pronunciation and improve a language learning effect.

Description

PROGRAM FOR PROVIDING LANGUAGE EVALUATION INTERFACES FOR PRONUNCIATION KEYWORDS

The present invention relates to a service provision program. More specifically, the present invention relates to a program for providing a learning service interface for pronunciation keywords.

Recently, with the advent of various mobile devices and the development of Internet and multimedia technologies, various methods of language learning and speech evaluation have been developed.

In particular, in the case of foreign languages, as the importance of speaking ability is emphasized, the user's foreign language pronunciation is recorded using the recording function of a multimedia device, and the voice of a native speaker is compared, or a native speaker evaluator directly evaluates the foreign language pronunciation to evaluate the score, etc. A learning system that provides

However, the current language learning methods perform only feature analysis of voice files and compare them with each other to evaluate similarities different from those felt by real people, or because they use a large amount of computation and complex algorithms. There are various problems such as the need to use a high-performance PC processor that is difficult to drive.

In addition, since accurate evaluation of the user's pronunciation is not made, it is difficult to accurately measure the user's learning level or the counterpart's understanding of the currently pronounced sentence, and therefore it is difficult to construct various learning curriculums involved thereafter. There is this.

As such, the content, method, and composition of the language pronunciation evaluation have a great influence on configuring the learning method and learning strategy of the next step by checking the learner's current learning results. If not identified, the learning effect is reduced, and ultimately, there is a problem that has a rather adverse effect on language learning.

On the other hand, STT (Speech To Text) technology is a technology that automatically generates text by voice recognition, and its accuracy is significantly improved with the development of artificial intelligence. There are possible advantages.

However, the current STT technology only converts any one of the texts similar to the actual pronunciation into equivalence, and does not fully reflect the characteristics of each language, the entire sentence or the intention of the conversation, the atmosphere, etc., so the actual converted text is not There is a problem in that cases still exist that are different from the intended phrase of the interlocutor.

Due to these problems, the STT technology itself cannot be fully utilized for language learning.

The present invention was devised to solve the above problems, and by using word information converted from voice signals to text, matching analysis based on the language evaluation model of pronunciation keywords is performed, and overall language pronunciation evaluation is performed. The purpose of this is to provide a program for providing a language evaluation interface of pronunciation keywords that can increase the accuracy of language pronunciation evaluation and improve the learning effect of language learning.

A program according to an embodiment of the present invention for solving the above-described problems is an operation program of a terminal that receives and outputs language learning content from a language learning service providing device, Including a pronunciation learning interface corresponding to the learning content the ability to output; a function of outputting a learning text including a pronunciation time period through the pronunciation learning interface; a function of receiving a user voice signal corresponding to the training text; a function of generating a differential evaluation interface image for each time period of the converted word processed by text conversion of the user's voice signal; and outputting the differential evaluation interface image on the training text.

According to an embodiment of the present invention, the accuracy of language pronunciation evaluation is improved by performing matching analysis based on the language evaluation model of pronunciation keywords using word information converted from voice signals to text, and performing overall language pronunciation evaluation by synthesizing them. It is possible to provide a program for the provision of learning services that can improve the learning effect of high school and language learning.

In addition, according to an embodiment of the present invention, by providing an interface and a data processing module that can be fully utilized for language learning and supplementing the shortcomings in evaluating language pronunciation using the STT technology, without a separate complex and high-performance processor It is possible to provide a program for providing a learning service that can provide a low-cost and high-efficiency voice recognition-based learning service based on the already established STT facility infrastructure.

Further, according to an embodiment of the present invention, it is possible to provide a program for providing a language evaluation interface of pronunciation keywords that can improve the learning effect by checking pronunciation evaluation based on matching analysis in real time and receiving feedback.

1 is a conceptual diagram schematically illustrating an entire system according to an embodiment of the present invention.
2 is a block diagram illustrating in more detail an apparatus for providing a service according to an embodiment of the present invention.
3 is a diagram for explaining a learning evaluation service based on a differential evaluation table according to an embodiment of the present invention.
4 is a flowchart illustrating a service process according to an embodiment of the present invention.
5 is a flowchart illustrating an interface output process according to an embodiment of the present invention.
6 to 9 are exemplary views for explaining a learning interface according to an embodiment of the present invention.

The following is merely illustrative of the principles of the invention. Therefore, those skilled in the art will be able to devise various devices which, although not explicitly described or shown herein, embody the principles of the present invention and are included within the spirit and scope of the present invention. Moreover, it is to be understood that all conditional terms and examples listed herein are, in principle, expressly intended solely for the purpose of enabling the concept of the present invention to be understood, and not limited to the specifically enumerated embodiments and states as such. should be

Moreover, it is to be understood that all detailed description reciting the principles, aspects, and embodiments of the invention, as well as specific embodiments, are intended to cover structural and functional equivalents of such matters. It is also to be understood that such equivalents include not only currently known equivalents, but also equivalents developed in the future, i.e., all devices invented to perform the same function, regardless of structure.

Thus, for example, the block diagrams herein are to be understood as representing conceptual views of illustrative circuitry embodying the principles of the present invention. Similarly, all flowcharts, state transition diagrams, pseudo code, etc. may be tangibly embodied on computer-readable media and be understood to represent various processes performed by a computer or processor, whether or not a computer or processor is explicitly shown. should be

The functions of the various elements shown in the figures including a processor or functional blocks represented by similar concepts may be provided by the use of dedicated hardware as well as hardware having the ability to execute software in association with appropriate software. When provided by a processor, the functionality may be provided by a single dedicated processor, a single shared processor, or a plurality of separate processors, some of which may be shared.

In addition, clear use of terms presented as processor, control, or similar concepts should not be construed as exclusively referring to hardware having the ability to execute software, and without limitation, digital signal processor (DSP) hardware, ROM for storing software. It should be understood to implicitly include (ROM), RAM (RAM) and non-volatile memory. Other common hardware may also be included.

In the claims of the present specification, a component expressed as a means for performing the function described in the detailed description includes, for example, a combination of circuit elements that perform the function or software in any form including firmware/microcode, etc. It is intended to include all methods of performing the functions of the device, coupled with suitable circuitry for executing the software to perform the functions. Since the present invention defined by these claims is combined with the functions provided by the various enumerated means and combined in a manner required by the claims, any means capable of providing the functions are equivalent to those contemplated from the present specification. should be understood as

The above-described objects, features and advantages will become more apparent through the following detailed description in relation to the accompanying drawings, and accordingly, those of ordinary skill in the art to which the present invention pertains can easily implement the technical idea of the present invention. There will be. In addition, in the description of the present invention, if it is determined that a detailed description of a known technology related to the present invention may unnecessarily obscure the gist of the present invention, the detailed description thereof will be omitted.

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

1 is a conceptual diagram schematically illustrating an entire system according to an embodiment of the present invention.

1 is a diagram schematically showing an entire system according to an embodiment of the present invention.

Referring to FIG. 1 , the entire system for providing a learning service based on a learning path according to an embodiment of the present invention includes a learning service providing apparatus 100 , at least one terminal 200 , and a network 300 .

First, at least one terminal 200 may exist in one or a plurality, and different terminals 200 may be connected to the learning service providing apparatus 100 and the network 300 through the network 300 to perform mutual communication.

Here, the communication provided by the network 300 includes a local area network (LAN), a wide area network (WAN), a value added network (VAN), and a personal local area network; PAN), mobile communication network (mobile radiocommunication network), or satellite communication network, etc., can be implemented in all types of wired/wireless networks, for example, mutual communication methods such as mobile communication networks, UPnP (Universal Plug and Play), WiFi, etc. It can provide a network for communication.

Also, the at least one terminal 200 may be a fixed terminal or a portable mobile terminal. As one or more terminals 200, navigation (Navigation), smart phone (smart phone), mobile phone, computer, laptop computer (laptop computer), digital broadcasting terminal, PDA (Personal Digital Assistants), PMP (Portable Multimedia Player), MID (Mobile Internet Device), a tablet PC (Tablet PC), and the like may be exemplified.

In addition, any one terminal 200 may configure communication through the network 300 with different terminals 200 through the learning service providing apparatus 100 . Also, the terminals 200 connected to the network 300 may receive various contents including language learning contents through the network 300 .

To this end, the learning service providing apparatus 100 may relay communication between network service providing servers. In addition, the learning service providing apparatus 100 may remotely or directly control the learning service according to an embodiment of the present invention to be provided through each terminal 200 .

Accordingly, each of the one or more terminals 200 accesses the learning service providing apparatus 100 through the network 300 , and the learning service providing apparatus 100 processes information about the learning state of each terminal 200 . We can provide learning services. Also, the learning service providing apparatus 100 may share various learning-related information or transmit a message in conjunction with an online communication service.

Accordingly, referring to FIG. 1 , the learning service providing apparatus 100 may build a database for providing language learning information and a language learning evaluation service through the network 300 , and the database is used for language learning evaluation. A learning assessment database may be included.

In addition, the learning service providing apparatus 100 may process the language learning content according to a learning goal or a lesson plan using the built-up database, and classify and store the processed language learning content according to a preset type. In addition, the language learning content may include scenario learning content based on language learning evaluation. The language learning evaluation-based scenario learning content may include language learning content that evaluates the accuracy of the user's language pronunciation and the comprehension of the virtual listener as a score, and is developed as a sequential scenario according to the evaluation score.

In particular, the apparatus 100 for providing a learning service according to an embodiment of the present invention performs matching analysis of pronunciation keywords based on a language evaluation model by using word information converted from a voice signal input by a user in response to scenario content. And, by performing the overall language pronunciation evaluation, it is possible to provide learning contents that can increase the accuracy of language pronunciation evaluation and improve the learning effect of language learning. can be established effectively.

To this end, the learning service providing apparatus 100 may be provided with an interface and a data processing module to compensate for the shortcomings in evaluating language pronunciation using the STT technology and to be sufficiently utilized for language learning. Even without a high-performance processor, it is possible to provide a low-cost and high-efficiency voice recognition-based learning service based on the already established STT facility infrastructure.

Meanwhile, the terminal 200 may be a learner's terminal, and the learner may include a display module and an audio output module for receiving and outputting language learning content through the terminal 200 , and a user corresponding to the language learning content It may include a voice input module such as a microphone for inputting voice information.

Also, the input voice signal may be transmitted from the terminal 200 to the learning service providing apparatus 100 through a communication module provided in the terminal 200 .

Here, the voice signal may include, for example, example sentences presented in learning content or answer information to a counterpart's question. In addition, the voice signal may include the input voice waveform data itself, or text data converted from the voice input when the STT (Speech To Text) conversion module is included in the terminal 200 .

When the voice signal received from the terminal 200 includes voice waveform data, the learning service providing apparatus 100 according to an embodiment of the present invention performs STT conversion processing first, and performs matching analysis and evaluation processing corresponding thereto. , and when the voice signal includes converted text data, the matching analysis and evaluation process may be performed without a separate conversion process. Therefore, in an embodiment of the present invention to be described later, the learning service providing apparatus 100 has its own speech signal text conversion processing (STT) module and may be described as performing STT conversion, but the speech signal text conversion processing ( STT) may be pre-processed by the function of the terminal 200 .

Accordingly, the learning service providing apparatus 100 matches and analyzes the user's text-converted voice input signal, and according to the results of the matching analysis and weight application, an evaluation score indicating the degree of understanding of the learning target language by a native speaker. may be calculated, a learning scenario corresponding to the evaluation score may be determined, and next learning content information corresponding thereto may be obtained, and the evaluation score or next learning content information may be provided to the terminal 200 .

Accordingly, the terminal 200 may check the evaluation score for the voice input information input by the user, or receive and output the next learning content information corresponding to the evaluation score from the learning service providing apparatus 100, Learners can check to what level their language can be recognized by the corresponding native speaker, and can be provided with effective learning content according to the scenario appropriate to their level.

In addition, the learning content may be stored corresponding to the user information of the terminal 200 , which may be managed by the service providing apparatus 100 as profile information. The profile information is always provided according to the request of the terminal 200, so that the learner can easily use it to check the list of learning contents, the learning stage, the learning evaluation result, the learning level, and the like.

On the other hand, the learning target language according to the embodiment of the present invention is not limited to English, Korean, etc., but the embodiment of the present invention exemplifies a case in which a foreigner learns Korean. Preferably, it is used for a Korean learning service. could be more effective.

2 is a block diagram illustrating in more detail an apparatus for providing a service according to an embodiment of the present invention.

Referring to FIG. 2 , the apparatus 100 for providing a learning service according to an embodiment of the present invention includes a control unit 110 , a communication unit 120 , a storage unit 130 , a user information management unit 135 , and a learning content management unit 140 . ), a learning evaluation database 137, a keyword unit processing unit 150, a speech signal text conversion unit 160, a pronunciation score matching unit 170 for each conversion unit, a differential evaluation processing unit 180, and a service providing unit 190. can do.

The controller 110 generally controls the overall operation of the learning service providing apparatus 100 . For example, the control unit 110 provides a learning content service, constructs a learning evaluation database, converts speech signals to text, matches pronunciation scores, processes various information such as differential evaluation processing, provides learning evaluation services, manages user information, etc., between related modules. It performs overall communication control and data processing of In FIG. 2 , it is illustrated that the control unit 110 is separately present for control between each component, but all or some functions of the control unit 110 are distributed to each component even if the control unit 110 is not included. It can also be deployed and operated in synchronization.

The communication unit 120 may be connected to the terminal 200 through the network 300 , and may perform data transmission/reception of learning service information for the terminals 200 . The wireless communication unit 110 may include one or more modules that enable wireless communication between the terminal 200 and the server 100 or between the terminal 200 and the network of the communication network 300 in which the terminal 200 is located. . For example, the communication unit 120 may include a mobile communication module, a wired Internet module, a wireless Internet module, a short-range communication module, and the like.

For example, the mobile communication module transmits and receives a radio signal to and from at least one of a base station, an external terminal, and a server on a mobile communication network. The wireless signal may include various types of data according to transmission/reception of a voice call signal, a video call signal, or a text/multimedia message. In addition, the wireless Internet module refers to a module for wireless Internet access, and may be built-in or external to the terminal 200 . As wireless Internet technologies, wireless LAN (WLAN) (Wi-Fi), wireless broadband (Wibro), World Interoperability for Microwave Access (Wimax), High Speed Downlink Packet Access (HSDPA), etc. may be used. The short-range communication module may mean a module for short-distance communication. Bluetooth, Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Ultra Wideband (UWB), ZigBee, etc. may be used as short range communication technologies.

The user information management unit 135 may register and manage user information in response to learning service users according to an embodiment of the present invention. The user information may include the user's personal information, and the user may set each identification information corresponding to the learner. User information may be newly registered, updated, and managed according to a user information registration or update request received from the terminal 200 . In addition, all or part of the user information may be transmitted to the terminal 200 according to the request of the terminal 200 .

The user information management unit 135 may classify and manage user information according to learning goals and learning levels. The user information may include, for example, at least one of the learner's date of birth, gender, name, mobile phone number, address, and profile information, and corresponds to a learning goal corresponding to the learner, learning content list information, and the learning content list evaluation history and score information.

However, since registration of user information is not an essential component for the service of the present invention, the user information management unit 135 according to an embodiment of the present invention provides access information of the user using the service, the terminal even if there is no separate user registration. Identification information or email information may be used as anonymous learner identification information.

The storage unit 130 may store control data for the operation of the control unit 110 and information managed by each component in a predetermined storage space. In an embodiment of the present invention, the storage unit 130 may store and manage content and evaluation data processed by the learning content management unit 140 and the learning evaluation database 137 .

Meanwhile, the learning content management unit 140 may set and manage the learning content provided by the service providing unit 190 in response to the user in the terminal 200 . In an embodiment of the present invention, the learning content may be language learning content. In addition, the language learning content may include virtual conversation content according to a lesson scenario, and may be classified and managed according to difficulty or level.

For example, the learning content may be chapter-specific conversational content set according to a specific learning scenario (eg, ordering coffee at a cafe, etc.), and each conversation may include language content between a counterpart and a user according to a specific scenario. have. Here, the language content may be composed of at least one of a conversation voice, a conversation image, and a conversation text.

Also, the learning content may include quiz content for level evaluation. In this case, the learning content may include example content for pronunciation evaluation. Here, the example content may be composed of at least one of example voice, example text, and example text.

Accordingly, the service providing unit 190 processes the learning content managed by the learning content management unit 140 to suit the user managed by the user information management unit 135, and provides a language learning service using the processed learning content to the terminal ( 200) can be provided.

The terminal 200 may output the learning content through a learning interface. In addition, when the terminal 200 receives the pronunciation input corresponding to the learning content, the terminal 200 may transmit a corresponding voice signal to the service providing unit 190 through the communication unit 120 .

More specifically, for example, the learning content may include pronunciation practice, sentence practice, and quiz practice content based on a learning scenario, and the user may input various voice signals through the terminal 200 .

Pronunciation practice content is practice content for learning the pronunciation of the expression by following example sentences corresponding to the learning scenario. You can (ex. How are you? practice speaking in the following order: “How are you > How are you? > How are you?”).

Sentence practice content is practice content to re-pronounce the entire sentence of an example sentence corresponding to a learning scenario. After a person in the video output from the terminal 200 explains the meaning of the expression, the sentence structure, etc., the voice signal for the entire sentence may include practice content that allows the user to input .

In addition, the quiz practice content is practice content that presents a question according to a situation according to a learning scenario and answers it. A person in the image output from the terminal 200 speaks the meaning of expression, sentence structure, situation, etc., and the student It may include practice content in the form of quizzes that encourages correct answers or requires responses in specific scenarios.

Then, when the user's voice signal corresponding to the learning content is received, the service providing unit 190 includes a keyword unit processing unit 150 , a voice signal text converting unit 160 , a pronunciation score matching unit 170 for each conversion unit, and a differential The pronunciation evaluation score evaluated through the data processing of the evaluation processing unit 180 may be provided to the terminal 200, and the terminal 200 determines whether to pass based on a preset pass score, and provides evaluation information corresponding thereto , whether to retry user input, learning scenarios and lesson goals can be determined.

Here, as described above, the voice signal may include an example voice signal for which a pronunciation input is requested directly from the learning content, or a conversation voice signal for answering a question of the counterpart.

In addition, the voice signal may include the input voice waveform data itself, or text data converted from the voice input when the STT (Speech To Text) conversion module is included in the terminal 200 .

When the voice signal received from the terminal 200 includes voice waveform data, the voice signal text conversion unit 160 may first perform text conversion (STT) processing of the voice signal. Here, the function of converting speech into text may utilize a well-known speech recognition and text conversion technology using a separate speech recognition server device or a cloud service device. Here, the speech signal may be converted into converted text that can be evaluated for each unit according to a preset conversion keyword unit.

Then, the keyword unit processing unit 150 sets pronunciation keywords in units of evaluation keywords corresponding to the voice signals to be evaluated among the learning contents, and transmits the set pronunciation keyword related data to the pronunciation score matching unit 170 for each conversion unit.

Accordingly, the pronunciation score matching unit 170 for each conversion unit matches the text-converted speech signal output from the speech signal text conversion unit 160 with the evaluation keyword unit for each conversion unit based on the pronunciation keyword related data, and matches Pronunciation scores are obtained according to whether or not there is, and output to the differential evaluation processing unit 180 .

Here, the pronunciation score matching unit 170 for each conversion unit may obtain a converted word as a text-converted speech signal, determine a primary pronunciation score according to whether the converted word and the evaluation keyword match, and the conversion The word, the evaluation target keyword, and the first pronunciation score may be transmitted to the differential evaluation processing unit 180 .

As described above, if the foreign language pronunciation is evaluated only by matching the STT with the target text, the pronunciation score is determined as 0 points when text recognition such as “1 time” is performed for the evaluation keyword such as “seven o’clock” Problems may arise. This is because, according to the level of listening of native speakers, the pronunciation of a text as described above is not perfect, but it can be recognized as "seven o'clock". If the evaluation of the wrong pronunciation score is repeated, even though the meaning of the conversation is sufficiently conveyed, it is impossible to continue the conversation content based on the scenario, etc., and there is a big problem that the learner also learns in the wrong direction.

Accordingly, the differential evaluation processing unit 180 stores and manages a differential evaluation table corresponding to the primary pronunciation score for each conversion unit obtained by matching in the learning evaluation database 137, and based on the differential evaluation table, the By applying the converted word, the keyword to be evaluated, and the differential evaluation weight corresponding to the first pronunciation score, the characteristics of each language, the intention of the entire sentence or conversation, the atmosphere, etc. are sufficiently reflected, and the actual converted text is the intention of the interlocutor. Even if it is different from one phrase, an appropriate evaluation should be made according to the recognizability of a native speaker.

The differential evaluation table may include a weight score table for each converted word to reflect this point, and may further include a keyword weight table determined according to the importance of keywords in a sentence.

3 is a diagram for explaining a learning evaluation service based on a differential evaluation table according to an embodiment of the present invention.

Referring to FIG. 3 , the differential evaluation table may include a score weight table for each converted word and a keyword weight table in a sentence.

For example, as shown in FIG. 3 , when the evaluation target sentence is “see you at seven o’clock” as a response to the first query “what time will we meet” according to the first learning scenario, the converted word is shown in FIG. 3 It can be composed of “at seven o’clock” as in the table of (A), “at” as in the table of FIG. 3(B), and “see you” as in the table of FIG. 3(C), and the weight for each keyword is shown in FIG. As shown in (D), it can be set to 0.6, 0.1, or 0.3. Such a differential evaluation table may be pre-stored in the learning evaluation database 137, and the table may be configured to correspond to each learning content or converted words.

Also, as described above, the score weight table for each converted word may include words that can be understood by a native speaker according to the language evaluation model, even if an erroneous expression is made by the STT conversion. 3 shows examples of such converted words, and a differential score for each converted word may be assigned as a weight.

Accordingly, the differential evaluation processing unit 180 may determine the evaluation score for the entire sentence by applying the differential evaluation weight corresponding to the score matched by the pronunciation score matching unit 170 . For example, the converted word of the voice signal corresponding to the keyword word "seven o'clock" to be evaluated in the pronunciation score matching unit 170 is "one time", and thus the primary pronunciation score of the pronunciation score matching unit 170 is If the score is 50 out of 100, the differential evaluation processing unit 180 may determine that the word is assigned with a weight of 0.8 based on the differential evaluation table, and may be corrected and applied as 80 points.

Then, the differential evaluation processing unit 180 applies a keyword weight of 0.6 in the entire sentence of "seven o'clock" to the 80 points, and performs the same operation on other keywords to calculate the sum of the scores of each keyword, Pronunciation evaluation of dialogue can be handled appropriately. The evaluation result information may be transmitted to the service providing unit 190 , and the service providing unit 190 may perform a learning content service update process according to the evaluation result and provide it to the terminal 200 .

For example, the differential evaluation processing unit 180, (keyword 1 score * weight + keyword 2 score * weight ... keyword N score * weight) * 100% of the bar, (1*06+0*01+) 0*03) * 100% When the result is 60%, learning level information such as A, B, and C corresponding to the pronunciation success or the 60% may be calculated as evaluation result information.

Also, for example, the service providing unit 190 may use the evaluation result information as a condition for entering the second learning scenario as shown in FIG. 3 . For example, when it is determined that the response to the query 1 is appropriate because the response to the question 1 has a predetermined evaluation score or more, the service providing unit 190 may update the learning content to lead to the learning scenario for the next query 2 . In addition, when it is determined that the response to Question 1 is not appropriate because it is below a certain evaluation score, the learning content may be updated to lead to the Material 1 scenario.

Accordingly, even though the user pronounces the word correctly to some extent, the error that was treated as a pronunciation failure due to the problem of converting words differently according to various cases (the same pronunciation of numbers or other words, etc.) by STT technology is solved. and provide a correct pronunciation evaluation to the user.

In addition, even if the pronunciation is wrong, it is possible to accurately determine the learning level and optimize the efficient learning process by determining the differential level rather than the simple pass failure through differential evaluation considering that native speakers can understand contextually what it means. can provide

4 is a flowchart illustrating a service process according to an embodiment of the present invention.

Referring to FIG. 4 , first, the learning service providing apparatus 100 registers user information corresponding to the learner's terminal 200 ( S101 ).

Thereafter, the learning service providing apparatus 100 sets the learning evaluation target pronunciation keyword according to the provision of the learning content provided through the service providing unit 190 ( S103 ).

Then, the learning service providing apparatus 100 performs text conversion processing of the voice signal input to the terminal 200 in response to the learning content through the voice signal text conversion unit 160 (S105).

Thereafter, the learning service providing apparatus 100 calculates a primary pronunciation score by processing pronunciation score matching for each transformation unit corresponding to the voice signal through the pronunciation score matching unit 170 for each transformation unit ( S107 ).

Then, the learning service providing apparatus 100 responds to the entire sentence by applying the pronunciation differential evaluation process using the first pronunciation score, the converted word, and the evaluation target keyword and the weight for each word through the differential evaluation processing unit 180 . to calculate the evaluation result (S109).

Thereafter, the learning service providing apparatus 100 determines a next learning service scenario corresponding to the evaluation result through the service providing unit 190 ( S111 ).

5 is a flowchart for explaining an interface output process according to an embodiment of the present invention, and FIGS. 6 to 10 are exemplary views for explaining a learning interface according to an embodiment of the present invention.

The service providing unit 190 according to an embodiment of the present invention may generate various graphical user interfaces (GUIs) for providing learning content and using the learning service, and may provide it to the terminals 200 of the connected users.

To this end, the service providing unit 190 may transmit the interface driving data to the terminal 200 through a wired/wireless network according to a communication method through the communication unit 120 . The interface may be implemented as a graphic object of a displayable form in the terminal 200, and may be displayed in various ways according to a user input.

Accordingly, referring to FIG. 5 , the terminal 200 according to an embodiment of the present invention outputs a pronunciation learning interface according to the learning content provided by the learning service providing apparatus 100 ( S201 ).

Thereafter, the terminal 200 outputs the learning text including the pronunciation time period through the pronunciation learning interface of the learning service providing apparatus 100 ( S203 ).

Then, the terminal 200 receives a user voice signal corresponding to the training text (S205).

Here, the input voice signal may be text-converted, or may be transmitted to the learning service providing apparatus 100 to be text-converted.

Then, the learning service providing apparatus 100 performs primary pronunciation score matching and differential evaluation for each conversion unit (S207).

Thereafter, the learning service providing apparatus 100 provides a differential evaluation interface image for each pronunciation time section on the learning text (S209).

Then, the learning service providing apparatus 100 obtains final evaluation result information and outputs a result interface corresponding to the evaluation result information (S211).

More specifically, FIG. 6 shows a learning text output screen of a pronunciation learning interface according to an embodiment of the present invention.

Referring to FIG. 6 , the pronunciation learning interface provided to the terminal 200 through the apparatus 100 for providing a learning service according to an embodiment of the present invention may include a learning text including a pronunciation time period, and the learning text may be output in a form in which pronunciation sections are sequentially emphasized according to the passage of time.

And, referring to FIG. 7, FIG. 7 shows a screen of the terminal 200 in which the differential evaluation interface image for each pronunciation time period is provided on the learning text. The terminal 200 according to an embodiment of the present invention receives the evaluation result information of the service providing unit 190 according to the processing of the pronunciation score matching unit 170 and the differential evaluation processing unit 180 as described above, and the evaluation Language evaluation information for each pronunciation time period according to the result information may be output as a color image corresponding to the time period of the training text. Here, the color image is an example of a differential evaluation interface image for each pronunciation time period, and other types of images or evaluation grade display output may be possible.

As shown in FIG. 7 , the user can check the pronunciation evaluation result that is fed back in real time while he or she pronounces the pronunciation. The differential evaluation interface image for each pronunciation time section may be displayed in color for each text time section, and may indicate a relatively low score when displayed in red color and a high score when displayed in blue color.

8 is a diagram for explaining an evaluation result interface based on differential evaluation.

As shown in (A) to (C) of FIG. 8 , in the evaluation result interface according to an embodiment of the present invention, the differential evaluation interface image according to the differential evaluation for each converted word can be displayed in real time as well as , as the evaluation results described below, pronunciation evaluation of the entire sentence may also be performed.

In addition, for example, as shown in FIG. 8 (C), the learning service providing apparatus 100 provides an interface for inducing re-pronunciation through the terminal 200 when the evaluation result is less than or equal to a certain evaluation grade score. may be

The method according to the present invention described above may be produced as a program to be executed on a computer and stored in a computer-readable recording medium. Examples of the computer-readable recording medium include ROM, RAM, CD-ROM, magnetic tape. , floppy disks, and optical data storage devices.

The computer-readable recording medium is distributed in a network-connected computer system, so that the computer-readable code can be stored and executed in a distributed manner. In addition, functional programs, codes, and code segments for implementing the method can be easily inferred by programmers in the art to which the present invention pertains.

In addition, although preferred embodiments of the present invention have been illustrated and described above, the present invention is not limited to the specific embodiments described above, and the technical field to which the present invention belongs without departing from the gist of the present invention as claimed in the claims Various modifications may be made by those of ordinary skill in the art, and these modifications should not be individually understood from the technical spirit or perspective of the present invention.

Claims (7)

A program for executing on a computer an operating method of a terminal for receiving and outputting language learning content from a language learning service providing apparatus, the program comprising:
a function of outputting a pronunciation learning interface corresponding to the learning content;
a function of outputting a learning text including a pronunciation time period through the pronunciation learning interface;
a function of receiving a user voice signal corresponding to the training text;
a function of generating a differential evaluation interface image for each time period of the converted word processed by text conversion of the user's voice signal; and
including a function of outputting the differential evaluation interface image on the training text
A program to provide an interface for language evaluation of pronunciation keywords. According to claim 1,
The differential evaluation interface image includes a color image corresponding to the time period of the training text
A program to provide an interface for language evaluation of pronunciation keywords. 3. The method of claim 2,
The differential evaluation interface image is,
characterized in that it is determined according to a differential evaluation result obtained by differentially evaluating the converted word converted from the user's voice signal into text by the apparatus for providing the language learning service as a pronunciation score for the evaluation target keyword
A program to provide an interface for language evaluation of pronunciation keywords. 4. The method of claim 3,
The differential evaluation interface image is,
In response to the user's input of the voice signal, a differential evaluation interface image according to the differential evaluation for each converted word corresponding to the pronunciation time period is variably output in real time
A program to provide an interface for language evaluation of pronunciation keywords. According to claim 1,
The differential evaluation interface image is,
The apparatus for providing the language learning service compares the conversion word with the evaluation target keyword for each keyword unit, matches the primary pronunciation score, and uses the matching information of the primary pronunciation score and the differential evaluation table to obtain the evaluation target keyword. generated according to the evaluation result information determined by performing differential evaluation processing on
A program to provide an interface for language evaluation of pronunciation keywords. 6. The method of claim 5,
The differential evaluation table is
including a score weight table for each converted word preset for differential level determination according to the possibility of native speaker recognition of the text-converted converted word
A program to provide an interface for language evaluation of pronunciation keywords. 6. The method of claim 5,
The differential evaluation table is
including a keyword weight table for each keyword in a sentence preset according to the language recognition possibility of the entire sentence including the text-converted converted word
A program to provide an interface for language evaluation of pronunciation keywords.

Images