KR20160054126A - Apparatus and method for providing foreign language learning service, recording medium for performing the method - Google Patents

Apparatus and method for providing foreign language learning service, recording medium for performing the method Download PDF

Info

Publication number
KR20160054126A
KR20160054126A KR1020140152933A KR20140152933A KR20160054126A KR 20160054126 A KR20160054126 A KR 20160054126A KR 1020140152933 A KR1020140152933 A KR 1020140152933A KR 20140152933 A KR20140152933 A KR 20140152933A KR 20160054126 A KR20160054126 A KR 20160054126A
Authority
KR
South Korea
Prior art keywords
sentence
learning
output
degree
difficulty
Prior art date
Application number
KR1020140152933A
Other languages
Korean (ko)
Inventor
강보영
김대원
조진혁
Original Assignee
경북대학교 산학협력단
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 경북대학교 산학협력단 filed Critical 경북대학교 산학협력단
Priority to KR1020140152933A priority Critical patent/KR20160054126A/en
Publication of KR20160054126A publication Critical patent/KR20160054126A/en

Links

Images

Classifications

    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
    • G09B19/00—Teaching not covered by other main groups of this subclass
    • G09B19/06—Foreign languages
    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
    • G09B5/00—Electrically-operated educational appliances
    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
    • G09B5/00—Electrically-operated educational appliances
    • G09B5/06—Electrically-operated educational appliances with both visual and audible presentation of the material to be studied

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Educational Administration (AREA)
  • Educational Technology (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Electrically Operated Instructional Devices (AREA)

Abstract

Disclosed are an apparatus and a method for providing a foreign language learning service, and a recording medium for performing the method. The apparatus for providing a foreign language learning service including steps of analyzing a difficulty degree and a type of a sentence which is difficult for a user through a result of communication by using a sentence selected at random during an initial class, extracting a sentence, which is to be output for the next class, according to the difficult degree and type of the analyzed sentence, extracting at least one learning sentence according to the difficulty degree and type of the analyzed sentence, and calculating a hierarchy of the at least one extracted learning sentences, and outputting a result during the next class after setting an output priority according to the calculated hierarchy. According to the present invention, a class may be performed according to a study level of the user.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention [0001] The present invention relates to a foreign language learning providing apparatus and a method thereof, and a recording medium for performing the same. BACKGROUND OF THE INVENTION [0002]

The present invention relates to a foreign language learning providing apparatus and method, and a recording medium for performing the same, and more particularly, to a foreign language learning providing apparatus and method, and a recording medium for performing the same.

In general, the most effective way of teaching foreign language learning is to have a natural conversation between a native speaker and a student on a one-to-one basis. However, this method is costly and has a drawback in that it is difficult for many students to actually benefit.

As a result, research and development of a device for assisting foreign language learning that can substitute native English teachers is actively under way.

However, since the existing method of providing foreign language learning only provides a learning process that meets the learning ability of each learner, it is necessary to provide learning contents suited to the learning ability of the learner, The learning contents that are related to the learning contents provided to learn the learning contents of the learner and the types of learning contents related to the learning ability of the learner are automatically acquired so as to facilitate the learning of the foreign language of the learner But it has a disadvantage that it can not provide learning contents of a higher level of difficulty.

Therefore, it is necessary to provide the learning contents that are in accordance with the learning ability of the learner and to provide the learning contents related to the learning contents provided in the previous class so that the learning contents related to the learning can be acquired at the next time. It is necessary to provide a method of providing foreign language learning that provides learning contents with higher level of difficulty automatically because it judges that the learning ability of the learner is improved by acquiring both the learning contents and the types of learning contents corresponding to the learner's learning ability to be.

Korea Patent Publication No. 2011-0062255 Korean Patent Publication No. 2014-0033902

According to one aspect of the present invention, there is provided a device for providing a foreign language learning, the method comprising: outputting a sentence out of a plurality of sentences stored in advance; analyzing a user's voice input from a user in response thereto; If it is determined that the communication is unsuccessful, the type and difficulty of the outputted sentence are analyzed and at least one learning sentence is searched based on the analyzed type and difficulty, and according to the relation of the searched learning sentence, And provides the foreign language learning providing apparatus.

The apparatus for providing foreign language learning according to an embodiment of the present invention includes an input unit for receiving a voice uttered by a user, at least one sentence among a plurality of sentences stored in advance, and analyzing the voice of the user inputted through the input unit, Determining whether the communication is successful with respect to the output sentence, analyzing the type and difficulty of the output sentence if the communication is determined to be unsuccessful, searching at least one learning sentence based on the analyzed type and the difficulty level A control unit for setting an output priority of the learning sentence, and an output unit for outputting the learning sentence according to the output priority.

The control unit may calculate a semantic top-down relationship of the learning sentence and set an output priority of the learning sentence based on the calculated semantic vertical relationship.

The control unit may calculate the reliability associated with the semantic size of the learning sentence and calculate the semantic top-down relationship of the learning sentence according to the calculated reliability.

The control unit may set the output priority of the learning sentence to be higher as the reliability of the learning sentence becomes lower.

The control unit may generate the communication result data by storing the communication failure success result data for each sentence.

Wherein the control unit searches the number of users who have failed to communicate with the output sentence by using the communication result data, calculates the degree of support of the output sentence by using the number of the retrieved users, The degree of difficulty of the output sentence can be calculated according to the degree of support.

The control section can search the degree of difficulty corresponding to the calculated degree of support using the degree of difficulty data previously stored which matches the degree of difficulty with respect to the degree of support of the sentence.

Wherein the control unit extracts a plurality of sentences having the same degree of difficulty as the output sentence, calculates a similarity between the output sentence and the extracted plurality of sentences, You can search by learning sentence.

The control unit may output a learning sentence having a degree of difficulty greater than the difficulty of the previously output sentence if it is determined that the learning sentence has been successfully communicated with the user.

The control unit may detect the degree of difficulty of the output sentence and output a sentence having a degree of difficulty higher than the degree of difficulty of the output sentence if it is determined that the user has successfully communicated with the output sentence.

According to another embodiment of the present invention, there is provided a foreign language learning providing method comprising: outputting at least one sentence out of a plurality of sentences stored in advance; analyzing a user's voice input from the outside; Analyzing the type and difficulty of the outputted sentence, searching at least one learning sentence based on the analyzed type and degree of difficulty, and setting output priority of the learning sentence And outputs the learning sentence according to the output priority.

Setting the output priority of the learning sentence can calculate the semantic top-down relationship of the learning sentence and set the output priority based on the calculated semantic vertical relationship.

Setting the output priority of the learning sentence includes calculating a reliability indicating a semantic size of the learning sentence and calculating a semantic vertical relationship of the learning sentence in accordance with the calculated reliability, The output priority of the learning sentence can be set higher.

And generating communication result data by storing the communication failure success result data for each sentence.

Analyzing the degree of difficulty of the output sentence may include searching for the number of users who have failed to communicate with the output sentence using the communication result data, And the degree of difficulty of the output sentence can be calculated according to the calculated degree of support.

In calculating the degree of difficulty of the output sentence, it is possible to retrieve the degree of difficulty corresponding to the calculated degree of support by using previously stored degree of difficulty data matching the degree of difficulty with respect to the degree of support of the sentence.

The retrieving of the at least one learning sentence may include extracting a plurality of sentences having the same level of difficulty as the output sentence, calculating the similarity between the output sentence and the extracted plurality of sentences, A sentence with a degree of similarity higher than the reference similarity degree can be searched for in the learning sentence.

Wherein the outputting of the learning sentence according to the output priority outputs a learning sentence having the highest priority among the output priority of the learning sentence, and if it is determined that communication with the best- Can be output.

Wherein the outputting of the learning sentence according to the output priority outputs a learning sentence having the highest priority among the output priority of the learning sentence and, when it is determined that the communication with the best ranked learning sentence has failed, It is possible to re-output the learning sentence of the ranking.

Detecting a degree of difficulty of the output sentence and outputting a sentence having a degree of difficulty greater than the degree of difficulty of the output sentence if it is determined that the output of the sentence is successful.

And may be a computer-readable recording medium on which a computer program is recorded, for providing foreign language learning.

According to one aspect of the present invention, the difficulty and the type of the difficulty of the user are analyzed and the sentence to be output at the time of the next class is extracted according to the analysis result, , Extracting and outputting other sentences having a type similar to the type of the sentence that the user is difficult to provide, thereby providing a variety of sufficient contents of learning to the user, thereby enhancing the user's understanding and communicating with the user If it is judged, the user can improve the learning level effectively by adjusting the difficulty level.

FIG. 1 is a diagram showing an example in which a foreign language learning providing apparatus according to an embodiment of the present invention is actually applied.
2 is a block diagram of a foreign language learning providing apparatus according to an embodiment of the present invention.
FIG. 3 is a view showing difficulty data in which difficulty levels of sentences according to the support degrees are classified.
4 is a flowchart illustrating a method for providing foreign language learning according to another embodiment of the present invention.
5 is a flowchart illustrating a foreign language learning providing method according to another embodiment of the present invention.

The following detailed description of the invention refers to the accompanying drawings, which illustrate, by way of illustration, specific embodiments in which the invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the invention. It should be understood that the various embodiments of the present invention are different, but need not be mutually exclusive. For example, certain features, structures, and characteristics described herein may be implemented in other embodiments without departing from the spirit and scope of the invention in connection with an embodiment. It is also to be understood that the position or arrangement of the individual components within each disclosed embodiment may be varied without departing from the spirit and scope of the invention. The following detailed description is, therefore, not to be taken in a limiting sense, and the scope of the present invention is to be limited only by the appended claims, along with the full scope of equivalents to which such claims are entitled, if properly explained. In the drawings, like reference numerals refer to the same or similar functions throughout the several views.

Hereinafter, preferred embodiments of the present invention will be described in more detail with reference to the drawings.

FIG. 1 is a diagram showing an example in which a foreign language learning providing apparatus according to an embodiment of the present invention is actually applied.

The foreign language learning and providing apparatus 100 according to an embodiment of the present invention can use the foreign language learning providing apparatus 100 to provide a learning level of the user 200 using the result of communication with the user 200, And repeatedly outputs sentences matching the learning level of the user 200 so that the user 200 can repeatedly learn a sentence matching the learning level at the next class. When the user 200 It is possible to automatically extract the sentences having the next difficulty level and output the sentences when the next class is performed so that the learning contents corresponding to the learning level of the improved user 200 can be automatically provided.

Specifically, the foreign language learning providing apparatus 100 according to an exemplary embodiment of the present invention can select and output an arbitrary sentence among a plurality of sentences stored therein. At this time, the foreign language learning providing apparatus 100 grasps the learning level of the user 200 according to the result of communicating with the user 200 using the output sentence, and then determines the learning level of the user 200 The foreign language learning providing apparatus 100 selects a sentence having the lowest difficulty level when selecting one of the plurality of sentences stored in the internal language in order to accurately grasp the learning level of the user 200, When communication is made on the selected sentence, it is desirable to select sentences having a degree of difficulty higher than that in order. The user can proceed with the conversation with the user 200 using the sentence arbitrarily selected by the foreign language learning providing apparatus 100. [ The foreign language learning providing apparatus 100 can analyze the result of communicating with the user 200 through the dialog using the arbitrarily selected sentence and detect the success or failure of communication with the user using the sentence arbitrarily selected. The foreign language learning providing apparatus 100 arbitrarily selects a sentence to be used when the communication with the user 200 is successful, that is, when the user 200 outputs a sentence arbitrarily selected by the foreign language learning providing apparatus 100, A sentence having a degree of difficulty higher than the degree of difficulty of the sentence randomly selected at the time of the next class can be extracted and output so as to improve the learning level of the user 200 when an appropriate answer is given to the selected sentence. The foreign language learning providing apparatus 100 can extract and output one sentence out of sentences having a higher level of difficulty and detect whether or not the user 200 has been communicated. The foreign language learning providing apparatus 100 arbitrarily selects a sentence to be used when the communication fails when the user 200 talks to the user 200, that is, when the user 200 outputs a sentence arbitrarily selected by the user 200 If the user does not answer the selected sentence properly or the speech is not recognized within the predetermined time, the user 200 determines that the sentence is arbitrarily selected or difficult. It is possible to improve the comprehension of the user 200 with respect to the sentence arbitrarily selected by repeatedly outputting a plurality of other sentences having difficulty. At this time, the foreign language learning providing apparatus 100 can calculate the number of users 200 that are not properly communicated when outputting the same sentence as the sentence arbitrarily selected from the communication result data stored therein. At this time, the communication result data may be data obtained by collecting and storing the results of communication with a plurality of users 200 when a foreign language class is performed on a plurality of users 200. At this time, since a sentence having a large number of users 200 having communication failures is a sentence difficult for a user 200, a sentence with a large number of users 200 having failed to communicate can be regarded as having a high degree of difficulty, As the number of users 200 is smaller, the user 200 can not regard the difficulty as a less complicated sentence. When the same sentence as the selected sentence is output, the foreign language learning providing apparatus 100 calculates the degree of support indicating the probability of failure of communication with the sentence output as the ratio of the total number of users to the number of users 200 that failed to communicate can do. At this time, the degree of support may be related to the degree of difficulty of the sentence because it indicates the probability of failure of communication. The foreign language learning providing apparatus 100 can search the degree of difficulty of the sentence by using the calculated degree of support. The foreign language learning providing apparatus 100 can extract a plurality of sentences having the same degree of difficulty as the searched degree of difficulty. The foreign language learning providing apparatus 100 can calculate the degree of similarity with a randomly selected sentence among a plurality of extracted sentences. The foreign language learning providing apparatus 100 can extract at least one learning sentence having a degree of similarity equal to or greater than a predetermined reference degree of similarity by comparing the calculated degree of similarity with a predetermined reference degree of similarity. The foreign language learning providing apparatus 100 sets the output priority of at least one learning sentence extracted according to the analyzed upper and lower relationships of the extracted at least one learning sentence and analyzes at least one learning sentence extracted by the at least one Can be output. At this time, the foreign language learning providing apparatus 100 can calculate the reliability indicating the semantic size for each sentence in order to analyze the vertical relationship of the extracted at least one learning sentence. On the other hand, as the calculated reliability is lower, the meaning of the sentence is narrower, meaning that the meaning of the sentence is clear. Therefore, the user 200 can feel less sense of heterogeneity in the sentence with lower reliability. Accordingly, the foreign language learning providing apparatus 100 can set and output the output priority of at least one learning sentence extracted in order of low reliability so that the user 200 can feel less sense of heterogeneity in the sentence. The foreign language learning providing apparatus 100 may output at least one learning sentence extracted in accordance with the output order set when the next class is performed and communicate with the user 200. [ At this time, when the next class starts, the foreign language learning providing apparatus 100 outputs a learning sentence having the highest priority among the set output priorities, and proceeds with the communication process with the user 200. [ When the communication with the user 200 fails using the learning sentence having the highest ranking among the output priorities set in the foreign language learning providing apparatus 100, the foreign language learning providing apparatus 100 matches and stores the learning sentence having the highest priority among the set output priorities And outputs the learning sentence having the highest priority among the output priorities set at the start of the next class. The foreign language learning providing apparatus 100 can detect whether there is a learning sentence to be output in the next class if the communication with the user 200 is successful by using the learning sentence having the highest ranking among the set output priorities . The foreign language learning providing apparatus 100 can set the learning sentence set to the order of the set output priority order to be output in the next instruction when the learning sentence to be output in the next class remains. The foreign language learning providing apparatus 100 can set a sentence of a higher level of difficulty to be output when the next class is to be performed if there is no learning sentence to be output in the next class.

The foreign language learning providing apparatus 100 according to an embodiment of the present invention can use at least one learning sentence extracted and output in accordance with an output order in which at least one extracted sentence is extracted, If the user 200 succeeds, the user 200 determines that the learning level is improved, and when the next class is performed, the level of difficulty of the selected sentence is higher than that of the selected sentence A sentence having a difficulty level can be extracted and output.

The apparatus 100 for providing a foreign language learning according to an embodiment of the present invention is a device for giving a feeling of being conversant with a native speaker, The robot 100 may be manufactured as a humanoid robot as shown in FIG. 1, or may be manufactured in various other forms.

FIG. 2 is a block diagram of a foreign language learning and providing apparatus according to an embodiment of the present invention, and FIG. 3 is a diagram showing difficulty data in which difficulty levels of sentences classified by support levels are classified.

Referring to FIG. 2, the apparatus 100 for providing foreign language learning according to an embodiment of the present invention may include an input unit 110, a control unit 120, an output unit 130, and a memory unit 140.

The input unit 110 may receive a voice for a sentence uttered by the user 200 in response to a sentence output through the output unit 130. [

Specifically, when the foreign language class is started and a sentence arbitrarily selected by the control unit 120 is outputted through the output unit 130, the input unit 110 outputs the sentence to the user 200 in response to the sentence output through the output unit 130. [ Can be input using the microphone (111). The input unit 110 may transmit the voice of the user 200 to the control unit 120.

An input unit 110 according to another embodiment of the present invention may be configured to input a sentence to be used in a foreign language class from the user 200 through a keyboard (not shown) or a touch screen display (not shown) Difficulty information can be input.

The control unit 120 can control the overall operation of the foreign language learning providing apparatus 100. [ The control unit 120 includes a sentence extraction unit 121, a speech recognition processing unit 122, a communication determination unit 123, a difficulty calculation unit 124, a sentence extraction unit 125, . ≪ / RTI >

The sentence extracting unit 121 can arbitrarily extract one of a plurality of sentences stored in the memory unit 140 and output it through the output unit 130 when the foreign language learning class is started for the first time.

On the other hand, the foreign language learning providing apparatus 100 determines the learning level of the user 200 according to the result of communicating with the user 200 using a sentence arbitrarily extracted from a plurality of sentences stored in the memory unit 140 The degree of difficulty and type of the difficulty of the user 200), and then proceeds to the lesson by utilizing the learning level of the user 200 determined at the time of the instruction. Accordingly, the sentence extracting unit 121 extracts a sentence having a low degree of difficulty from a plurality of sentences stored in the memory unit 140 in order to accurately detect that the user 200 does not communicate with a sentence of a difficulty level It is possible to sequentially extract and output.

The speech recognition processor 122 receives the user's speech data input through the microphone 111 of the input unit 110 and converts the received speech data of the user into text to transmit the communication determination unit 123 .

The communication determination unit 123 analyzes the input voice data of the user in response to the sentence output through the output unit 130 and inputs the answer corresponding to the sentence output through the output unit 130, It can be judged whether or not it has been properly done.

Specifically, when a sentence is output through the output unit 130, the communication determination unit 123 can detect whether or not the user's voice is input through the input unit 110 within a predetermined time. The communication determination unit 123 can determine that communication has not been performed unless the user's voice is input within a predetermined time. When the voice of the user is input through the input unit 110 within a predetermined time, the communication determination unit 123 analyzes the voice data of the input user and determines whether an appropriate answer corresponding to the output sentence is input, ) Can be detected. At this time, the communication determination unit 123 may determine that the communication has failed if the inputted voice data of the user is the same as the previously stored sentence (for example, I do not know, I can not understand, etc.) . The communication determination unit 123 can analyze the morpheme of the input user's voice data and extract words included in the inputted user's voice data. The communication determination unit 123 may determine that proper communication has failed if the overlapping rate with the word included in the sentence in which the extracted word is output is less than the reference overlapping ratio. The communication determination unit 123 can determine that the communication is successful if the voice data of the user inputted within a predetermined time is not stored in advance and the reference overlap ratio is higher than the reference overlap ratio. If it is determined that the communication is successful, the communication determination unit 123 may extract one of the sentences having a higher level of difficulty through the sentence extraction unit 121 at the start of the next class and output it. If the communication determination unit 123 determines that the communication has failed, the communication determination unit 123 can transmit the sentence information output to the difficulty level calculation unit 124.

The difficulty level calculating unit 124 can receive a sentence determined to have failed communication by the communication determining unit 123, and can detect the difficulty level of the received sentence.

Specifically, the difficulty level calculating unit 124 can receive the output sentence. The difficulty level calculating unit 124 may calculate a degree of support indicating a total communication failure probability for the sentence output using the communication result data stored in the memory unit 140. [ On the other hand, the communication result data is communication result data collected when a plurality of users 200 and foreign language learning classes are conducted, and whether or not communication is performed for a plurality of sentences for a plurality of users 200 is stored And can receive and update communication result data with a plurality of other users 200 through a communication unit (not shown) provided in the foreign language learning providing apparatus 100. [ At this time, the difficulty level calculating unit 124 may detect the number of users 200 that have failed to communicate using the same sentence as the sentence out of the plurality of users 200. The difficulty level calculating unit 124 can calculate the degree of support by calculating the ratio of the total number of users 200 to the number of detected users 200. [ The difficulty calculator 124 can detect the difficulty corresponding to the degree of support calculated by comparing the difficulty data and the calculated support. In this case, the difficulty level data may be data classified into difficulty levels according to the support level sections divided by a predetermined unit as shown in FIG. 3. The difficulty level calculating section 124 detects a section to which the calculated support degree belongs, The degree of difficulty to which the sentence belongs can be detected.

The learning sentence extracting unit 125 may extract a plurality of sentences having the same degree of difficulty as the detected sentence difficulty and extract at least one sentence having a type similar to the output sentence out of the extracted plurality of sentences .

Specifically, the learning sentence extracting unit 125 can detect the difficulty of each of the plurality of sentences stored in the memory unit 140, and extract the sentences having the same degree of difficulty as the difficulty. The learning sentence extracting unit 125 may calculate the similarity between a plurality of extracted sentences and an output sentence by analyzing the morpheme of the extracted sentence. At this time, the degree of similarity between the extracted plural sentences and the output sentence can be calculated using the following formula (1).

Figure pat00001

here,

Figure pat00002
Is the output sentence,
Figure pat00003
A plurality of extracted sentences,
Figure pat00004
Is the i-th element of the sentence,
Figure pat00005
I < th > element of a plurality of extracted sentences,
Figure pat00006
Is the similarity function for the ith element,
Figure pat00007
The
Figure pat00008
. At this time, it is possible to calculate the keyword according to part-of-speech as one element.

At least one learning sentence having a degree of similarity equal to or greater than the reference similarity among the plurality of sentences extracted from the learning sentence extracting unit 125 can be extracted.

The vertical relationship calculating unit 126 can calculate the vertical relationship between at least one learning sentence extracted through the learning sentence extracting unit 125. [

Specifically, the vertical relation calculating unit 126 can detect a noun, a verb, an adjective, an adverb, a preposition, a conjunction, and the like included in the learning sentence by analyzing the morpheme of the learning sentence. The vertical relation calculating unit 126 can detect the number of parts of speech included in the learning sentence such as nouns, verbs, adjectives, adverbs, prepositions, conjunctions, and the like. The upper / lower relationship calculation unit 126 calculates a ratio of a predetermined number (a predetermined number - the number of parts of speech included in the learning sentence) / a predetermined number * 100% to the number obtained by subtracting the number of parts of speech included in the learning sentence from a predetermined number. ) Can be calculated to calculate the reliability indicating the degree of semantic size. For example, if the first learning sentence is " how old are you? &Quot; and the second learning sentence is " how about you? &Quot;, the four parts of speech constituting the first learning sentence, Are three. If the predetermined number is 10, the reliability of the first learning sentence is 60% and the reliability of the second learning sentence can be calculated to be 70%. In this case, the predetermined number may mean a number greater than the total number of parts of speech included in the learning sentence including the most part of the learning sentence.

The vertical relation calculating unit 126 according to another embodiment of the present invention can calculate the vertical relationship between the learning sentences by analyzing the morpheme of the learning sentence. The vertical relation calculating unit 126 can analyze the morpheme of the learning sentence and detect words included in the learning sentence. The upper / lower relationship calculating unit 126 compares the words included in the learning sentence with the word data stored in the memory unit 140, in which reliability indicating the degree of semantic coverage for each word is matched and stored, Can be detected. In this case, since the reliability indicates the extent of the semantic range of the word, that is, the degree to which the word can semantically include various meanings, the reliability number itself can mean the semantic size of the sentence.

The vertical relation calculating unit 126 according to the embodiment of the present invention can set the output priority of the learning sentence according to the reliability of each learning sentence. The vertical relation calculating unit 126 can set the output priority of the learning sentence in the order of higher reliability. The vertical relation calculating unit 126 can control the output of the learning sentence according to the ranking set at the start of the next class.

The control unit 120 determines that the learning level of the user 200 is improved by one step if the communication with the user 200 is successful by using the extracted learning sentence, It is possible to control so that a sentence having a higher level of difficulty can be outputted. If the communication with the user 200 is successful by using the extracted learning sentence, the control unit 120 can extract a plurality of sentences having a higher level of difficulty and repeat the above-described process.

The output unit 130 may output the sentence extracted by the control unit 120. [ The output unit 130 may include an audio output unit 131 and a display unit 132. The output unit 130 can output a sentence extracted by the control unit 120 through the sound output unit 131 and outputs the sentence extracted by the control unit 120 as an image through the display unit 132 Can be output.

The memory unit 140 may store a program for processing and controlling the controller 120, and may perform a function for temporarily storing input / output data. In particular, the memory unit 140 according to an embodiment of the present invention may store a plurality of sentence data used in a foreign language learning lesson, and may store communication result data including a result of communicating with a plurality of users 200 And can store difficulty data indicating the degree of difficulty according to the degree of support of each stored sentence.

Hereinafter, a method of providing foreign language learning according to another embodiment of the present invention will be described with reference to FIG.

First, when a foreign language learning class starts (310), a sentence of arbitrary one of a plurality of sentences stored in the memory unit 140 is selected and outputted (315).

In response to the output sentence, an appropriate answer is entered from the user 200 to detect whether the communication is successful (320).

At this time, if the randomly selected sentence is communicated to the user 200 in response to the output, the difficulty of the randomly selected sentence is detected (325), and a plurality of sentences having the difficulty level one level higher than the detected difficulty level are extracted 330).

In addition, if an arbitrary selected sentence is not output from the user 200 in response to the output, that is, if communication with the user 200 fails, the difficulty of the randomly selected sentence is detected 335.

At this time, the detection of the difficulty level of the arbitrarily selected sentence is performed by using a sentence randomly selected by using the communication result data of all the users 200 stored in the memory unit 140, 200), calculates a degree of support at a ratio of the total number of users 200 to the number of users 200 who fail to communicate using an arbitrarily selected sentence, and detects a degree of difficulty corresponding to the calculated degree of support, The degree of difficulty of the selected sentence can be detected.

The difficulty level of the arbitrarily selected sentence is detected (335), and a plurality of sentences having the same degree of difficulty as the arbitrarily selected sentence are extracted (340).

In this case, extracting a plurality of sentences having the same degree of difficulty as the arbitrarily selected sentence is performed by detecting the difficulty of each of a plurality of sentences stored in the memory unit 140, and by using a plurality of sentences having the same degree of difficulty as the randomly selected sentence Can be extracted.

At least one learning sentence having a type similar to a randomly selected sentence among the plurality of extracted sentences is extracted (345).

At this time, extracting at least one learning sentence having a type similar to a randomly selected sentence can calculate the similarity between a randomly selected sentence and a plurality of extracted sentences, and extract a sentence having a degree of similarity equal to or greater than the reference similarity .

The upper / lower relationship between the extracted at least one learning sentences is calculated (350), and the order in which at least one learning sentence is output is set in accordance with the calculated dependency (355).

Hereinafter, a description will be given of a method for providing the foreign language learning when the foreign language learning and providing apparatus completes the initial class and proceeds to the next class through FIG.

First, when the next foreign language learning class starts (410), the first set learning sentence is output according to the set output order (420).

In this case, the learning sentence set first according to the set output order may be a sentence having difficulty and type similar to the sentence in which communication at the previous class failed.

In operation 430, whether the communication with the user 200 is successful is detected using the learning sentence set first according to the set output order.

At this time, if an appropriate answer is not inputted from the user 200 in response to the learning sentence set first according to the set output order, that is, if the communication fails, the first matching learning sentence is matched to the learning sentence set according to the set output order And outputs the stored commentary information (440).

Also, if an appropriate answer is input from the user 200 in response to the learning sentence set first according to the set output order, that is, if communication is successful, it is detected whether or not a learning sentence to be output remains in accordance with the set output order (450).

At this time, if there is a learning sentence to be output according to the set output order, the learning sentence set in the next order is set in the first order (460) in accordance with the set output order so as to be output when the next class starts.

If there is no learning sentence to be output in accordance with the set output order, the user 200 learns all of the learning contents related to the sentence output in the foreign language class, judges that the learning level is improved, Step 470 is set to output a sentence having a high degree of difficulty.

Such a technique for providing effective foreign language learning using a foreign language learning providing device can be implemented in an application or can be implemented in the form of program instructions that can be executed through various computer components and recorded in a computer-readable recording medium. The computer-readable recording medium may include program commands, data files, data structures, and the like, alone or in combination.

The program instructions recorded on the computer-readable recording medium may be ones that are specially designed and configured for the present invention and are known and available to those skilled in the art of computer software.

Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tape, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, media, and hardware devices specifically configured to store and execute program instructions such as ROM, RAM, flash memory, and the like.

Examples of program instructions include machine language code such as those generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter or the like. The hardware device may be configured to operate as one or more software modules for performing the processing according to the present invention, and vice versa.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it will be understood by those skilled in the art that various changes and modifications may be made therein without departing from the spirit and scope of the invention as defined in the appended claims. It will be possible.

100: Foreign language learning device
200: User

Claims (21)

An input unit for receiving a voice uttered by the user;
And outputting at least one sentence out of a plurality of sentences stored in advance, analyzing a voice of a user input through the input unit to determine whether or not communication with the output sentence is successful, A controller for analyzing the type and difficulty of the outputted sentence, searching at least one learning sentence based on the analyzed type and the difficulty level, and setting an output priority of the learning sentence; And
And outputting the learning sentence according to the output priority. The method according to claim 1,
Wherein,
A semantic hierarchical relationship of the learning sentence is calculated, and an output priority of the learning sentence is set based on the calculated semantic hierarchical relationship. 3. The method of claim 2,
Wherein,
A reliability associated with the semantic size of the learning sentence is calculated, and a semantic top-down relationship of the learning sentence is calculated according to the calculated reliability. The method of claim 3,
Wherein,
And sets the output priority of the learning sentence to be higher as the reliability of the learning sentence becomes lower. The method according to claim 1,
Wherein,
And the communication result data is generated by storing the result data of the communication failure success by sentence. 6. The method of claim 5,
Wherein,
Retrieving the number of users who have failed to communicate with the output sentence by using the communication result data, calculating a degree of support of the output sentence by using the number of retrieved users, And calculates the degree of difficulty of the outputted sentence. The method according to claim 6,
Wherein,
And searches the degree of difficulty corresponding to the calculated degree of support using the degree of difficulty data previously matched with the degree of difficulty with respect to the degree of support of the sentence. The method according to claim 1,
Wherein,
Extracting a plurality of sentences having the same degree of difficulty as the output sentence, calculating a degree of similarity between the output sentence and the extracted plurality of sentences, and searching the sentence having the calculated degree of similarity equal to or higher than the standard similarity degree into the learning sentence A foreign language learning providing device. The method according to claim 1,
Wherein,
And outputs a learning sentence having a degree of difficulty greater than the difficulty level of the previously output sentence if it is determined that the communication with the user is successful for the learning sentence. The method according to claim 1,
Wherein,
Detecting a degree of difficulty of the output sentence and outputting a sentence having a degree of difficulty higher than a degree of difficulty of the output sentence if it is determined that the output sentence is successfully communicated with the user. Outputting at least one sentence out of a plurality of sentences stored in advance,
Analyzing the voice of the user inputted from the outside, judging whether or not communication of the outputted sentence is successful,
Analyzing the type and difficulty of the output sentence if the communication is determined to be unsuccessful,
Searching at least one learning sentence based on the analyzed type and degree of difficulty,
And setting the output priority of the learning sentence and outputting the learning sentence according to the output priority. 12. The method of claim 11,
The setting of the output priority of the learning sentence,
A semantic top-down relationship of the learning sentence is calculated, and the output priority is set based on the calculated semantic top-down relationship. 13. The method of claim 12,
The setting of the output priority of the learning sentence,
A reliability indicating a semantic size of the learning sentence is calculated,
Calculating a semantic vertical relationship of the learning sentence according to the calculated reliability,
And sets the output priority of the learning sentence to be higher as the reliability of the learning sentence becomes lower. 12. The method of claim 11,
And generating communication result data by storing the communication failure success result data for each sentence. 15. The method of claim 14,
The analyzing of the degree of difficulty of the output sentence,
Retrieving the number of users who have failed to communicate with the output sentence using the communication result data,
Calculating a degree of support of the output sentence by using the number of the retrieved users,
And calculating the degree of difficulty of the output sentence according to the calculated degree of support. 16. The method of claim 15,
Calculating the degree of difficulty of the output sentence,
And searching the degree of difficulty corresponding to the calculated degree of support using the degree of difficulty data previously stored, which matches the degree of difficulty with respect to the degree of support of the sentence. 12. The method of claim 11,
Searching for the at least one learning sentence,
Extracting a plurality of sentences having the same degree of difficulty as the output sentence,
Calculating a similarity between the output sentence and the extracted plurality of sentences,
And searches the sentence having the calculated degree of similarity equal to or greater than the reference degree of similarity in the learning sentence. 12. The method of claim 11,
And outputting the learning sentence in accordance with the output priority,
Outputting a learning sentence having the highest ranking among the output priority of the learning sentence and outputting a learning sentence having the lowest ranking when it is determined that communication with the best ranked learning sentence is successful. 12. The method of claim 11,
And outputting the learning sentence in accordance with the output priority,
Outputting a learning sentence having the highest priority among the output priority of the learning sentence and outputting the outputting the best ranked learning sentence if it is determined that communication with the best ranked learning sentence fails. 12. The method of claim 11,
Further comprising detecting a degree of difficulty of the output sentence and outputting a sentence having a degree of difficulty higher than the degree of difficulty of the output sentence if it is determined that communication has been successfully performed on the output sentence. 20. A computer-readable recording medium on which a computer program is recorded for providing foreign language learning according to any one of claims 11 to 20.
KR1020140152933A 2014-11-05 2014-11-05 Apparatus and method for providing foreign language learning service, recording medium for performing the method KR20160054126A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020140152933A KR20160054126A (en) 2014-11-05 2014-11-05 Apparatus and method for providing foreign language learning service, recording medium for performing the method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020140152933A KR20160054126A (en) 2014-11-05 2014-11-05 Apparatus and method for providing foreign language learning service, recording medium for performing the method

Related Child Applications (1)

Application Number Title Priority Date Filing Date
KR1020170006063A Division KR101837576B1 (en) 2017-01-13 2017-01-13 Apparatus and method for providing foreign language learning service, recording medium for performing the method

Publications (1)

Publication Number Publication Date
KR20160054126A true KR20160054126A (en) 2016-05-16

Family

ID=56108927

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020140152933A KR20160054126A (en) 2014-11-05 2014-11-05 Apparatus and method for providing foreign language learning service, recording medium for performing the method

Country Status (1)

Country Link
KR (1) KR20160054126A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102080323B1 (en) * 2018-08-17 2020-02-21 주식회사 아이포트폴리오 System of providing learning roadmap and its operating method
KR20220077726A (en) * 2020-12-02 2022-06-09 아주대학교산학협력단 Sysem and method for learning languages

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102080323B1 (en) * 2018-08-17 2020-02-21 주식회사 아이포트폴리오 System of providing learning roadmap and its operating method
KR20220077726A (en) * 2020-12-02 2022-06-09 아주대학교산학협력단 Sysem and method for learning languages

Similar Documents

Publication Publication Date Title
US11797763B2 (en) Allowing spelling of arbitrary words
Forbes-Riley et al. Benefits and challenges of real-time uncertainty detection and adaptation in a spoken dialogue computer tutor
US8515764B2 (en) Question and answer database expansion based on speech recognition using a specialized and a general language model
CN106297800B (en) Self-adaptive voice recognition method and equipment
KR101629415B1 (en) Method for detecting grammar error and apparatus thereof
US10679609B2 (en) Biasing voice correction suggestions
US11682381B2 (en) Acoustic model training using corrected terms
US8751226B2 (en) Learning a verification model for speech recognition based on extracted recognition and language feature information
KR20130128716A (en) Foreign language learning system and method thereof
US9652991B2 (en) Systems and methods for content scoring of spoken responses
US20160104478A1 (en) Voice recognition method using machine learning
US20100285435A1 (en) Method and apparatus for completion of keyboard entry
KR20180062003A (en) Method of correcting speech recognition errors
KR20130045547A (en) Example based error detection system and method for estimating writing automatically
Skantze Galatea: A discourse modeller supporting concept-level error handling in spoken dialogue systems
KR101837576B1 (en) Apparatus and method for providing foreign language learning service, recording medium for performing the method
KR20160054126A (en) Apparatus and method for providing foreign language learning service, recording medium for performing the method
Yoon et al. Off-Topic Spoken Response Detection with Word Embeddings.
US20180365224A1 (en) Natural language processing apparatus and a natural language processing method
CN111128181B (en) Recitation question evaluating method, recitation question evaluating device and recitation question evaluating equipment
Lee et al. Grammatical error detection for corrective feedback provision in oral conversations
CN117275319B (en) Device for training language emphasis ability
KR101089329B1 (en) System and method for performing learning challenges for foreign language learners
US20230116804A1 (en) User-centric conversion of natural language responses to potential multiple choice statements
KR20110024624A (en) System and method for evaluating foreign language pronunciation

Legal Events

Date Code Title Description
A201 Request for examination
E902 Notification of reason for refusal
AMND Amendment
E601 Decision to refuse application
AMND Amendment
A107 Divisional application of patent