KR102581364B1 - Edutech system that helps you to have conversations in foreign languages without being silence using interactive artificial intelligence technology - Google Patents

Abstract

The present invention relates to an edutech system that helps people have silent foreign language conversations using interactive artificial intelligence technology. The present invention includes the steps of detecting a conversation in a foreign language, the step of notifying one or more question information to determine the cause of the silence when silence is detected for more than a set time, and helping to continue the flow of the foreign language conversation in response to the selected question information. It includes the step of informing hint information.

Description

An edutech system that uses interactive artificial intelligence technology to help you have silent foreign language conversations

The present invention relates to a foreign language teaching method.

In general, speaking in a foreign language is a conversation between people, so it presupposes emotional exchange. If either the speaker or the listener feels awkward or strange during a conversation, it becomes difficult to continue the conversation.

People who learn a foreign language mainly memorize words or sentences that need to be expressed in specific situations or places. These people often try to communicate by obsessing over the expressions they have learned, rather than communicating ideally by feeling the flow of the conversation in real conversations with foreigners.

If the conversationalist becomes tied down to a certain expression and is unable to think of a foreign language that corresponds to a specific expression, the flow of the foreign language conversation is interrupted. In particular, beginners who are not familiar with a foreign language often get stuck in specific expressions. In conversations with foreigners, when the interlocutor frequently encounters interruptions in conversation, the interlocutor often feels a strong aversion to the foreign language and gives up studying the foreign language.

Accordingly, the inventor of the present invention developed the present invention through a long period of research and trial and error in order to solve such problems, and finally completed the present invention with a desperate and earnest desire to enable all citizens to use foreign languages easily and comfortably.

In order to solve the above-described problems, the present invention provides an edutech system that eliminates silence that may occur during conversations with foreigners and allows natural conversations to be held without an awkward atmosphere.

In addition, the present invention provides an edtech system that provides confidence in a foreign language, especially to foreign language beginners, and completely removes psychological burden such as foreign language anxiety or phobia, allowing all citizens to feel comfortable and easy to use a foreign language as if it were their native language. .

In addition, the present invention provides an edutech system that encourages learners' active participation in foreign language conversation by having conversations with them, and helps learners improve their foreign language conversation skills by stimulating the learner's metacognition. The technical problems to be achieved in the present invention are not limited to the above technical problems, and other technical problems not mentioned will be clearly understood by those skilled in the art from the description below.

One aspect of the present invention to solve the above-described problem is an interactive server that helps prevent the flow of foreign language conversation from being interrupted,

(a) detecting a conversation taking place in a foreign language;

(b) when static is detected for more than a set time, notifying one or more question information to determine the cause of the static;

(c) It may include a step of informing hint information helpful in continuing the flow of foreign language conversation in response to the selected question information.

Also, step (b) is,

A step of asking whether the foreign language expression for the answer corresponding to the conversation is unknown and providing learning status confirmation information to check the status of the conversationalist;

A step of announcing thought confirmation information asking whether there is a thought suitable for the answer;

It includes at least one of the steps of providing expression method confirmation information by asking if you do not know how to communicate in a foreign language about an idea that came to mind,

Step (c) is,

When learning status confirmation information is selected, receiving a native language expression for the answer;

It may include a step of informing alternative language information that has a similar meaning to the input native language expression.

Additionally, step (c) is,

If thought confirmation information is selected, announcing small talk,

The steps to promote small talk are:

Identifying the topic of the ongoing conversation;

Extracting categories within the DB corresponding to the identified topics; and

It may include selecting and informing at least one topic among topics stored in the DB corresponding to the category.

In addition, the present invention,

A voice recognition unit that detects conversations in foreign languages;

a speaker unit that speaks in response to a detected voice;

A conversationalist status checker that outputs one or more question information to determine the cause of the silence when silence is detected for more than a set time;

a hint information provider that outputs hint information linked to the question information when question information is selected;

Hint information provision department,

At least in the first selection of question information, hint information that allows the interlocutor to think of the foreign language expression and speak it on his or her own can be output rather than directly outputting a foreign language expression suitable as an answer.

In addition, the present invention,

It further includes a taste analysis unit that derives taste information of the conversationalist by analyzing the frequency of keywords used in the conversation and identifying the topic of the foreign language conversation being conducted,

Hint information provision department,

After announcing the replacement word, if no conversation is detected for a certain period of time, an expression on a topic related to the analyzed taste can be output.

In addition, the present invention,

A grouping unit that classifies substitute words by level based on a preset vocabulary difficulty value for substitute words that have a similar meaning to the answer to the conversation; and

It further includes a hint information provision unit that outputs a replacement word as a response to the detected conversation,

Hint information provision department,

After outputting a substitute word, if the answer to the conversation is not detected for a preset time, the substitute word is output in order of level at preset time intervals from the substitute word belonging to the highest level to the substitute word belonging to the lowest level until the answer is detected. can do.

Detecting a conversation taking place in a foreign language; and

It may include the step of announcing an alternative word with a similar meaning as the answer to the detected conversation.

Additionally, the present invention may further include a step of announcing another alternative word if no conversation is detected for a certain period of time after announcing the alternative word.

In addition, the present invention includes the steps of announcing substitute words in order of level from a substitute word belonging to the highest level group to a substitute word belonging to the lowest level group based on the vocabulary difficulty of the substitute word; and

After announcing the replacement word corresponding to the lowest level, if no conversation is detected for a certain period of time, a step of notifying the expression classified as small talk may be further included.

In addition, the present invention,

A voice recognition unit that detects conversations in foreign languages;

A grouping unit that classifies substitute words by level based on a preset vocabulary difficulty value for substitute words that have a similar meaning to the answer to the conversation; and

Includes a notification unit that outputs an alternative word in response to a detected conversation,

Notification department,

After outputting a substitute word, if the answer to the conversation is not detected for a preset time, the substitute word is output in order of level at preset time intervals from the substitute word belonging to the highest level to the substitute word belonging to the lowest level until the answer is detected. can do.

In addition, the present invention further includes a taste analysis unit that derives the conversationalist's taste information by analyzing the frequency of keywords used in the conversation and identifying the topic of the foreign language conversation being conducted,

Notification department,

After notifying the substitute word belonging to the lowest level, if no conversation is detected for a certain period of time, an expression for a topic related to the analyzed taste can be output.

In addition, the present invention further includes a conversation level analysis unit that calculates the conversation ability level of the conversationalist by analyzing the level of conversational ability of the conversationalist detected in the ongoing foreign language conversation, and classifies the conversationalist into level groups based on the calculated ability value,

Notification department,

The number of alternative words to be output can be determined in response to the level group of the conversationalist who utters the answer, or the level to which the substitute word belongs can be determined and the substitute word for that level can be output.

The present invention eliminates the habit of being overly obsessed with limited expressions due to cramming foreign language education, allowing interlocutors to converse naturally and comfortably with foreigners without feeling awkward or awkward.

The present invention can help interlocutors overcome communication difficulties resulting from cultural differences by teaching them how to use small talk, thereby making foreign language conversations more comfortable and confident.

Furthermore, the present invention improves the conversational skills of speaking using various expressions without being tied to one expression, and also teaches techniques such as small talk and closing comments that help conversationalists easily avoid awkward situations, so that they can improve their conversation skills not only in foreign language conversations but also with other people. It can also teach you how to have a social conversation.

In addition, the present invention provides an edutech server that freely communicates with learners, allowing learners to practice foreign language conversations alone, regardless of time and place.

In addition, when silence occurs during a foreign language conversation, the present invention can improve the learner's metacognition by encouraging the learner to create and speak the foreign language expression.

Meanwhile, it is to be added that even if the effects are not explicitly mentioned herein, the effects described in the following specification and their potential effects expected from the technical features of the present invention are treated as if described in the specification of the present invention.

1 is a diagram showing a schematic concept of a first embodiment according to the present invention.
Figure 2 is a diagram showing the operational flow of the first embodiment.
Figure 3 is a diagram showing another type of operational flow that can be implemented by the first embodiment.
Figure 4 is a diagram showing the configuration of the first embodiment according to the present invention.
Figure 5 is a diagram showing a schematic concept of a second embodiment according to the present invention.
Figure 6 is a diagram showing a flow chart of a second embodiment according to the present invention.
Figure 7 is a diagram showing the configuration of a second embodiment according to the present invention.
※ The attached drawings are intended as reference for understanding the technical idea of the present invention, and are not intended to limit the scope of the present invention.

In describing the present invention, detailed descriptions of related known functions will be omitted if they are obvious to those skilled in the art and are judged to unnecessarily obscure the gist of the present invention. Hereinafter, embodiments according to the present invention will be described in detail with reference to the drawings attached hereto.

1 is a diagram showing a schematic concept of a first embodiment according to the present invention. Figure 2 is a diagram showing the operational flow of the first embodiment. As can be seen in Figures 1 and 2, the present invention conducts a foreign language conversation with a conversationalist through a conversational interface and helps prevent silence in the conversationalist's foreign language conversation.

The user terminal 120 according to the present invention is capable of conducting a foreign language conversation, and can also detect a conversation being conducted in a foreign language and utter an appropriate answer to the conversationalist.

When the server 110 detects silence for more than a set time, it notifies the user terminal 120 of one or more question information to determine the cause of the silence. Furthermore, the server 110 notifies the user terminal 120 of hint information helpful in continuing the flow of the foreign language conversation in response to the selected question information.

Specifically, the question information informs the interlocutor in order to analyze the cause of silence, and includes any one of learning status confirmation information, thought confirmation information, or expression method confirmation information.

Learning status confirmation information is information about asking the interlocutor whether he or she does not know the foreign language expression for the answer corresponding to the conversation. As can be seen in Figure 2, the learning status confirmation information is “1. This is about checking whether silence occurs due to a lack of information on foreign language expressions of the interlocutor, such as “Don’t you know English expressions?” Therefore, as shown in Figure 1, when the interlocutor does not know the English expression of 'superpower', the server 110 receives the native language expression 'superpower' from the interlocutor and hints alternative words (special ability, ability, magic). It informs the interlocutor as information. If silence continues after announcing the substitute words, the server 110 additionally announces foreign language expressions (special power, ability, magic, skill) for the substitute words to solve the problem of silence during the conversation .

Thought checking information is information about asking whether there are any appropriate thoughts for the ongoing conversation. As can be seen in Figure 2, the thought confirmation information is “2. It can appear as “I don’t know what to say?” In the first static situation shown in FIG. 1, if the conversationalist selects hint information about small talk through thought confirmation information, the server 110 indicates the conversation distance about small talk, which will be described later. Interlocutors get inspiration from 'asking where I'm going' as a conversational distance that can be used casually, and can continue a conversation in a foreign language without silence by asking 'are you going?'

If the interlocutor says “1. If you select the hint information “Speak according to the six-down principle,” the server 110 provides examples of content suitable for the flow of conversation according to the six-down principle. For example, in a conversation related to lunch, the server 110 guides information such as who ate what and where, and the conversationalist expresses the conversation related to lunch in a foreign language in specific and detailed terms. In other words, the interlocutor does not say short English words such as “I ate lunch,” so phenomena such as silence do not occur during conversation.

Expression method confirmation information is information about asking whether you do not know how to communicate in a foreign language about an idea that came to mind. As shown in Figure 2, the expression method confirmation information is in “3. It can appear like, “I have an idea, but I don’t know how to say it.” Hint information linked to expression method confirmation information indicates word order appropriate for the foreign language or omits unnecessary words.

For example, in the case of word order appropriate for a foreign language, the hint information as shown in Figure 2 is “Try to say the subject and verb first. You can provide guidance in the form of “Who did what?” Through this, the conversationalist in Figure 1 can organize his or her thoughts in the second silence by considering the word order appropriate for the foreign language. If the interlocutor wants to express, “My parents tell me not to use that superpower in front of people,” they can easily and concisely express it as “Her Parents say ‘Do not use the power’” according to the word order of the foreign language, which is subject followed by verb. . In addition, the interlocutor can omit the expression 'unconditionally' through information about omitting unnecessary words, making it easier to express in a foreign language.

Additionally, in Korean, the subject is easily omitted, such as “when I ate tteokbokki.” In the process of translating Korean into a foreign language in the mind, the interlocutor sometimes has difficulty expressing in the foreign language due to the obsession with translating the exact form with the subject omitted. In preparation for this case, the server 110 says, “Try to say the subject and verb first. If guidance is given in the form of “Who did what?”, the interlocutor will be able to easily express in a foreign language, such as “When I ate tteokbokki.”

Alternatively, hint information linked to expression method confirmation information makes foreign language conversation easier by omitting unnecessary words, such as “If it is not a word that is absolutely necessary, boldly omit it.” For example, if the interlocutor has difficulty expressing a foreign language by using the expression 'brightly' in 'smile brightly', the server 110 uses hint information to make the interlocutor feel the need to omit the expression 'brightly'. Accordingly, the present invention helps the conversationalist to easily express things like 'smile' and continue the foreign language conversation without silence.

When thought confirmation information is selected, the server 110 notifies the user terminal 120 of small talk so that the conversation can be continued lightly and easily. The server 110 identifies the topic of the ongoing conversation and extracts a category in the DB corresponding to the identified topic. The server 110 selects and announces at least one topic among the topics stored in the DB corresponding to the category. For example, in a situation where a conversation about well-being is exchanged before the first silence in FIG. 1, the server 110 sets the topic of the detected conversation to 'checking on my well-being'. The DB of the server 110 includes various categories, one of which is 'confirmation of safety'. The ‘check your well-being’ category in the DB includes information on ‘meals’, ‘places you go to’, and ‘health status’. The server 110 matches the topic and category identified in the detected conversation and notifies the contents included in the 'Confirmation of Safety' category in the DB. The conversationalist can check the category contents, select one of them, and express “where are you going?” as shown in Figure 1, allowing the conversation to continue smoothly in the foreign language.

Additionally, the server 110 may continuously inform the user terminal 120 of reaction expression instructions to the conversationalist so that the foreign language conversation can continue naturally. Reaction expressions are expressions shown in bold in Figure 1 and serve as a lubricant for conversation. If the server 110 does not detect a reaction expression in the conversationalist's foreign language conversation, it displays a reaction expression instruction notification .

In addition, the server 110 may display analysis results of the conversationalist's foreign language conversation. The server 110 can record and display incorrect grammatical expressions in the conversationalist's foreign language conversation, and can also display the results of organizing the grammar parts that are mainly incorrect. In addition, the server 110 may analyze the static causes of foreign language conversation and display the results of the conversation, such as whether the conversationalist is too obsessed with one expression and has difficulty in foreign language conversation, along with a solution.

Figure 3 is a diagram showing another type of operational flow that can be implemented by the first embodiment. As can be seen in FIG. 3, when the server 110 detects silence for more than a set time, it notifies the user terminal 120 of question information in a form different from that of FIG. 2. Since the question information is intended to check the status of the interlocutor, the form of the question is diverse. In FIG. 3, the server 110 informs the user terminal 120 whether he has something to say, whether he did not hear or understand the conversation, whether he needs more time, and whether he wants to end the conversation. When the interlocutor selects question information, the server 110 notifies the user terminal 120 of other types of question information or hint information in connection with the question information.

For example, when a conversationalist says '1' on the user terminal 120. If you select 'Is there anything you want to say?', the server 110 notifies the user terminal 120 of hint information helpful for speaking a foreign language at length. Or, the interlocutor says '2.' on the user terminal 120. If you select 'I have something I want to say, but don't know how to say it?', the server 110 notifies the user terminal 120 of additional question information related to it in order to check the status of the conversationalist in more detail. The linked additional question information is about checking whether you are unable to converse because you do not know English expressions, or because you cannot organize sentences to say in your head. The interlocutor says '1. If you select 'Do you think you won't be able to come up with an English expression even if given time?', the server 110 goes through a search process as shown in FIG. 2 and notifies you of a replacement word. The interlocutor says '2. If you select ‘Do you think you can come up with an English expression if given time?’, the server 110 provides a search box for alternative words after the set time.

If the interlocutor says '3. If you select 'Can't you organize the sentence you want to say in your head?', the server 110 receives information about the Korean sentence you want to say from the interlocutor. Afterwards, the server 110 notifies the user terminal 120 of hint information to distinguish between the subject and the verb. Nevertheless, if silence continues, the server 110 notifies the user terminal 120 of additional question information. If the conversation cannot be maintained due to difficult expressions, the server 110 provides a replacement word search process through a selection process. Additionally, the server 110 informs the user terminal 120 of hint information to 'omit' unnecessary expressions, thereby helping the conversationalist speak more easily.

The operational flow in Figure 3 confirms the status of the interlocutor in more detail. The server 110 can check the conversational understanding level of the conversationalist and provide time in consideration of the conversationalist's tendency or state. Additionally, the server 110 provides question information asking for a closing comment at every quiet moment if there is nothing more to say. For example, when the conversationalist selects '3 Did you not understand?' from the initial screen information of the user terminal 120, the server 110 provides hint information such as 'Sorry, I did not understand. Can you say it again?' announce. The interlocutor looks at the hint information and says 'Sorry, I didn't get it.' You can say things in a foreign language, such as 'Can you say that again please?' If the silence is maintained even though the server 110 announces hint information in Korean, the server 110 provides hint information in English so that the conversationalist can directly see and read it. In a similar principle, the interlocutor says '4. Do you need time?’ or ‘5. When 'Do you want to end the conversation?' is selected, the server 110 provides hint information corresponding to the selected question information. Similar to the process of checking conversation understanding, the server 110 first provides hint information in the native language and then provides hint information in the foreign language depending on whether it is static.

Figure 4 is a diagram showing the configuration of the first embodiment according to the present invention. As can be seen in Figure 4, the server 110 includes a voice recognition unit 111, a speaker unit 112, a conversationalist status check unit 113, a grouping unit 114, a hint information provision unit 115, and a taste analysis unit. Includes (116).

The voice recognition unit 111 detects a conversation in a foreign language, and the speaker unit 112 utters the foreign language in response to the detected voice. When the interlocutor status checker 113 detects silence for more than a set time, it outputs one or more question information to determine the cause of the silence. When question information is selected, the hint information provider 115 outputs hint information linked to the question information. The hint information provider 115 does not directly output a foreign language expression suitable as an answer, at least in the first selection of question information, but outputs hint information that allows the interlocutor to think of the foreign language expression and speak it. In other words, the server 110 encourages the interlocutor to actively participate in foreign language expressions and improves the interlocutor's foreign language conversation agility so that he can communicate without awkwardness or shyness in actual conversation with foreigners.

The server 110 may further include a taste analysis unit 116 that derives taste information of the conversationalist by analyzing the frequency of keywords used in the conversation and identifying the topic of the foreign language conversation being conducted. The hint information provider 115 announces a substitute word and, if no conversation is detected for a certain period of time, outputs an expression on a topic related to the analyzed taste. This will be described in detail in the second embodiment.

Additionally, the server 110 may further include a grouping unit 114 that classifies alternative words by level based on a preset vocabulary difficulty value for alternative words that have a similar meaning to the answer to the conversation. The server 110 may further include a hint information provider 115 that outputs a replacement word as a response to the detected conversation. After outputting the substitute word, if the answer to the conversation is not detected for a preset time, the hint information provider 115 sets a preset time interval from the substitute word belonging to the highest level to the substitute word belonging to the lowest level until the answer is detected. Outputs alternative words in level order. This will be described in detail in the second embodiment.

The server 110 may be implemented with artificial intelligence to ensure high accuracy of results. To this end, the interlocutor status check unit 113, grouping unit 114, hint information provision unit 115, and taste analysis unit 116 may be included in the artificial intelligence determination unit. The artificial intelligence judgment unit can use a variety of neural networks, and can accurately implement conversations appropriate to the situation through learning from big data.

[Second Embodiment]

Figure 5 is a diagram showing a schematic concept of a second embodiment according to the present invention. As shown in Figure 5, the present invention provides alternative words related to emotions, thoughts, or facts that are difficult for the interlocutor to express in a foreign language. Here, the foreign language is not necessarily limited to English, and may include various languages such as Japanese or Chinese. Additionally, substitute words include words, idioms, sentences, etc., and may be in one's native language or a foreign language.

Figure 5 assumes easy expressions in everyday life to easily explain the concept of the present invention. Figure 5 assumes a case in which the English expression for the expression 'flutter' does not come to mind among various situations related to foreign language conversation.

As can be seen in Figure 5, the foreigner asks the interlocutor how he feels about backpacking, and the interlocutor thinks of an English expression for his current feeling of excitement. However, the interlocutor does not know the English expression for excitement. In this case, the server 210 according to the present invention communicates with the user terminal 220, and the user terminal 220 speaks to the other party in English, such as 'interesting' or 'can't wait' as an alternative to excitement. Provides easy expressions. A conversationalist who does not know the English expression for 'excited' can say 'I can't wait', which he or she can express in English. Accordingly, the interlocutor can easily and comfortably conduct a foreign language conversation with a foreigner without interruption.

Hereinafter, a second embodiment according to the present invention will be described in detail with reference to FIGS. 6 and 7.

Figure 6 is a diagram showing a flow chart of a second embodiment according to the present invention. As can be seen in FIG. 6, the server 210 receives detected English conversation information (S210) and transmits alternative language information with a similar meaning as the answer to the detected conversation to the user terminal 220 (S210). S220). The server 210 further includes a step of transmitting other alternative word information to the user terminal 220 if conversation information is not received for a certain period of time after announcing the substitute word. Accordingly, even if the conversationalist cannot express English using the substitute language provided by the server 210, the conversationalist can continue the foreign language conversation using another substitute language.

Specifically, the server 210 transmits substitute word information to the user terminal 220 in order of level, from substitute word information belonging to the highest level group to substitute word information belonging to the lowest level group, based on the vocabulary difficulty for the substitute word. Includes steps. That is, the server 210 sequentially transmits alternative words that the conversationalist can easily express in English to the user terminal 220, so that the present invention realizes the conversationalist's uninterrupted English conversation. Nevertheless, if the conversationalist finds it difficult to speak English expressions, the server 210 transmits alternative word information corresponding to the lowest level, and then, if conversation information is not received for a certain period of time, outputs an expression classified as small talk (S230) ) includes. A detailed explanation of small talk will be provided later.

Figure 7 is a diagram showing the configuration of a second embodiment according to the present invention. As can be seen in Figure 7, the server 210 according to the present invention includes a voice recognition unit 211, an answer derivation unit 212, an alternative word derivation unit 213, a grouping unit 214, a notification unit 215, It includes a taste analysis unit 216 and a conversation level analysis unit 217.

The voice recognition unit 211 receives foreign language conversation information detected by the user terminal 220 and analyzes the topic of the foreign language conversation content. The voice recognition unit 211 calculates the frequency of keywords used in foreign language conversations and analyzes the topic using keywords with the highest frequency. This is to generate a reference value for the substitute word to be derived, and details about this will be explained together with the substitute word derivation unit 213, which will be described later.

The answer derivation unit 212 derives an answer appropriate for the detected conversation based on the analyzed topic. That is, the answer derivation unit 212 may hold pre-stored answers that are frequently used in the analyzed topic. Alternatively, the answer derivation unit 212 may derive answers frequently used in the analyzed topic through deep learning learning. For example, when the voice recognition unit 211 receives conversation information related to emotional expression, the voice recognition unit 211 generates emotional expression topic information through topic analysis. The answer derivation unit 212 derives an answer suitable for emotional expression topic information through big data and deep learning learning, and derives answer information such as 'excited' or 'disappointed' as an expression representing the current mood state.

The alternative word derivation unit 213 derives alternative word information for the derived answer information. In other words, substitute words similar in meaning to the answer are derived. For this purpose, the alternative word derivation unit 213 stores and retains the input alternative word information to correspond to the answer information. For example, an alternative word with a similar meaning to the answer to 'excitement' could be 'I'm excited' or 'I can't wait.' As described above, based on the topic analyzed by the voice recognition unit 211, the alternative word derivation unit 213 generates a substitute word similar to the answer.

The grouping unit 214 classifies substitute words by level based on a preset vocabulary difficulty value for substitute words that have a similar meaning to the answer to the conversation. For example, as a substitute for 'excitement', the high-level substitute is 'I'm excited,' the middle-level substitute is 'can't wait,' and the low-level substitute is 'very good.' It can be

The notification unit 215 outputs a replacement word as a response to the detected conversation. After outputting the substitute word, if the answer to the conversation is not detected for a preset time, the notification unit 215 replaces the substitute word belonging to the highest level to the substitute word belonging to the lowest level at a preset time interval until the answer is detected. Outputs words in level order. If the server 210 does not detect the conversationalist's voice for a certain period of time, it outputs 'I am excited', and if it does not detect the conversationalist's voice again for a certain period of time, it outputs 'I cannot wait'. If the server 210 does not detect a conversation even when outputting a substitute word at a medium level, it outputs 'very good' corresponding to a low level.

The server 210 according to the present invention further includes a taste analysis unit 216 that derives taste information of the conversationalist by analyzing the frequency of keywords used in the conversation and identifying the topic of the foreign language conversation being conducted. The taste analysis unit 216 determines topics within a preset ranking among the identified topics to derive the conversationalist's taste information as the conversationalist's taste information .

The notification unit 215 notifies the substitute word belonging to the lowest level and, if no conversation is detected for a certain period of time, outputs an expression on a topic related to the analyzed taste. To prevent the conversationalist's English conversation from being interrupted, the notification unit 215 outputs expressions related to the conversationalist's favorite field to the conversationalist who finds English conversation difficult. Even if you are a beginner in English, you have a wealth of common sense and expression information about your favorite field, so the notification unit 215 outputs expressions related to the speaker's taste to make English speaking much easier.

Alternatively, the notification unit 215 may announce an alternative word corresponding to the lowest level and then output an expression classified as small talk if no conversation is detected for a certain period of time. Small talk is a light, everyday conversation that is essential for interpersonal communication. For example, when silence occurs because the interlocutor has difficulty speaking in English, the notification unit 215 may output a re-question such as 'How about you?' or 'And you?' Alternatively, the notification unit 150 outputs expressions such as 'Ah~ Really?', 'Ah-yeah?', 'Oh~Okay', etc. as an expression to make a gesture to sympathize with the other person's words. In addition, the notification unit 215 may output a follow-up question or an expression such as “Find something in common and difference” to find a topic of conversation that is easy to sympathize with by finding commonalities or differences with the other person.

The server 210 according to the present invention includes a conversation level analysis unit 217 that calculates the conversational ability level by analyzing the level of conversational ability of the conversationalist detected in the ongoing foreign language conversation, and classifies the conversationalist into level groups based on the calculated ability value. It further includes.

The conversation level analysis unit 217 extracts information about expressions related to words and idioms used in detected foreign language conversations, and calculates a difficulty level matched with the expression information . The conversation level analysis unit 217 calculates the conversationalist's ability level by deriving an average value of the calculated difficulty values. The conversation level analysis unit 217 uses the calculated ability values to assign level groups classified by level to the conversationalist information .

The notification unit 215 determines the number of alternative words to be output corresponding to the level group of the interlocutor who utters the answer, or determines the level to which the substitute word belongs and outputs the substitute word for that level. Accordingly, the present invention can provide more and easier alternative words to speakers who find English conversation quite difficult, helping them maintain quiet conversations regardless of the speakers' English level.

The server 210 may be implemented with artificial intelligence as described above in the first embodiment. To this end, the alternative word derivation unit 213, grouping unit 214, notification unit 215, taste analysis unit 216, and conversation level analysis unit 217 may be included in the artificial intelligence judgment unit. The artificial intelligence judgment unit can use a variety of neural networks, and can accurately implement conversations appropriate to the situation through learning from big data.

It is obvious to those skilled in the art that the present invention can be embodied in other specific forms without departing from the characteristics of the present invention. Accordingly, the above detailed description should not be construed as restrictive in all respects and should be considered illustrative. The scope of the present invention should be determined by reasonable interpretation of the appended claims, and all changes within the equivalent scope of the present invention are included in the scope of the present invention.

Claims (6)

An interactive server that helps prevent the flow of foreign language conversation from being interrupted.
(a) detecting a conversation taking place in a foreign language;
(b) when static is detected for more than a set time, notifying one or more question information to determine the cause of the static; and
(c) Including a step of informing hint information helpful in continuing the flow of foreign language conversation in response to the selected question information,
Step (b) is,
A step of asking whether the foreign language expression for the answer corresponding to the conversation is unknown and providing learning status confirmation information to check the status of the conversationalist;
A step of announcing thought confirmation information asking whether there is a thought suitable for the answer; and
It includes at least one of the steps of informing information about the method of expression by asking if you do not know how to communicate in a foreign language about the idea that came to mind,
Step (c) is,
When learning status confirmation information is selected, receiving a native language expression for the answer and notifying alternative language information having a similar meaning to the input native language expression;
When thought confirmation information is selected, the topic of the ongoing conversation is identified, the category in the DB corresponding to the identified topic is extracted, and at least one topic among the topics stored in the DB is selected corresponding to the extracted category. Informing Small Talk Notification Step; and
When expression method confirmation information is selected, including the step of informing hint information related to word order appropriate for the foreign language and omission of unnecessary words,
A method to help you have a silent foreign language conversation using conversational artificial intelligence technology.
delete delete A voice recognition unit that detects conversations in foreign languages;
a speaker unit that speaks in response to a detected voice;
A conversationalist status checker that outputs one or more question information to determine the cause of the silence when silence is detected for more than a set time; and
When question information is selected, it includes a hint information providing unit that outputs hint information linked to the question information,
Talker status check section
Learning status check information to check the status of the conversationalist by asking whether he or she does not know the foreign language expression for the answer corresponding to the conversation,
Thought checking information that asks if any thoughts fit the answer and
Outputs at least one question information among the expression method confirmation information that asks if you do not know how to communicate in a foreign language about an idea that came to mind,
Hint information provision department,
Instead of directly outputting an appropriate foreign language expression as an answer according to the first choice for the output question information, hint information that allows the speaker to think of the foreign language expression and speak it on his or her own is output,
When learning status confirmation information is selected, the native language expression for the answer is input, and alternative language information with a similar meaning to the input native language expression is output.
When thought confirmation information is selected, the topic of the ongoing conversation is identified, the category in the DB corresponding to the identified topic is extracted, and at least one topic among the topics stored in the DB is selected corresponding to the extracted category. Print it out,
When expression method confirmation information is selected, hint information related to word order appropriate for the foreign language and omission of unnecessary words is output.
An edutech server that helps you have silent foreign language conversations using interactive artificial intelligence technology.
According to paragraph 4,
It further includes a taste analysis unit that derives taste information of the conversationalist by analyzing the frequency of keywords used in the conversation and identifying the topic of the foreign language conversation being conducted,
Hint information provision department,
After announcing the replacement word, if no conversation is detected for a certain period of time, an expression on a topic related to the analyzed taste is output .
An edutech server that helps you have silent foreign language conversations using interactive artificial intelligence technology. According to paragraph 4,
A grouping unit that classifies substitute words by level based on a preset vocabulary difficulty value for substitute words that have a similar meaning to the answer to the conversation; and
It further includes a hint information provision unit that outputs a replacement word as a response to the detected conversation,
Hint information provision department,
After outputting a substitute word, if the answer to the conversation is not detected for a preset time , the substitute word is output in order of level at preset time intervals from the substitute word belonging to the highest level to the substitute word belonging to the lowest level until the answer is detected. doing,
An edutech server that helps you have silent foreign language conversations using interactive artificial intelligence technology.