KR102368418B1 - Apparatus and Method for Creating Rap Lyrics included Punch Lines - Google Patents

Abstract

A method for generating rap lyrics performed by an apparatus according to the present invention, comprising the steps of: obtaining a homonym for the rap lyrics; Calculating a sentence, displaying a list including the plurality of sentences, a first sentence including the first meaning of the homonym in the list, and a second meaning different from the first meaning of the homonym generating a third sentence in which at least one first character in the first sentence, at least one second character in the second sentence, and the homonym are combined when the second sentence to be there is.

Description

Apparatus and Method for Creating Rap Lyrics included Punch Lines

The present invention relates to automatically generating rap lyrics, and more particularly, to an apparatus and method for generating rap lyrics including punch lines.

Recently, due to the development of media such as the Internet and YouTube, popular music has become so huge that even the United States, the world's largest music market, cannot afford it. Popular music became very popular not only in the United States, but also in other countries.

Among popular music in Korea, idol music and rap are gaining a lot of popularity. In the case of rap, from the early rap called old school hip-hop to the present, rap has developed tremendously and its popularity is also increasing. Here, rap consists of the components of message, rhyme, and flow, and rappers use these components to induce a response from the audience. Here, a message may be a subject (theme), a rhyme may be a word with a similar sound, and a flow may be read aloud according to the beat. And in particular, rap includes the punch line, which rappers research and use the most.

With the advent of several survival music programs related to rap, many people became interested in rap, and even academies that specialize in rap appeared.

As interest in rap among popular music has increased, more and more people are learning to professionally learn rap lyrics and skills to rap, or write and practice rap lyrics themselves. However, there are many cases where it is burdensome to attend an academy that specializes in rap, and there are many difficulties in learning rap professionally or writing rap lyrics outside of the academy. Also, although the general public often tries to create rap lyrics and punchlines on their own, it is not easy to know how to approach them to create fun punchlines.

Therefore, each individual can learn the rules and skills to write rap lyrics, and there is a need for a way to create lyrics according to one's own style. Specifically, there is a need for a method to automatically generate a punchline that can give a strong impression among rap lyrics and provide it to users who do not have the ability to write the lyrics directly.

Republic of Korea Patent Publication No. 10-2007-0081368

An object of the present invention for solving the above problems is to provide words or sentences of rap lyrics suitable for users through a deep learning model by accumulating various information for each user.

Another object of the present invention is to provide a sentence including a homonym for the rap lyrics and a word that is meaningful even if read backwards when providing the user with a word or sentence of the rap lyrics.

The problems to be solved by the present invention are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the following description.

In a method for generating rap lyrics performed by an apparatus according to the present invention for solving the above-mentioned problems, the steps of obtaining a homonym for the rap lyrics include the steps of: Calculating a plurality of sentences each having different meanings, displaying a list including the plurality of sentences, and a first sentence including a first meaning of the homonym in the list and the first of the homonyms When a second sentence including a second meaning different from the meaning is selected, a third sentence in which at least one first character in the first sentence, at least one second character in the second sentence, and the homonym are combined may include the step of creating

In addition, the step of acquiring the homonym may include a word or sentence input from a user, a location, date, time, event or accident that occurred on the date, and a past date same as the date when the user inputted the word or sentence It may be acquired based on an event or accident that occurred in the , and the user's bio-signals.

In addition, periodically acquiring information related to at least one of user information for each user, a word or sentence, a time or place at which the word or sentence was inputted, an event or an accident related to the time or place, for a preset time, and the group The method may further include accumulating and storing the information periodically acquired for a set time for each user. Here, the first model may be machine-learned based on the information accumulated and stored for each user and a plurality of sentences related to the accumulated and stored information.

In addition, the calculating of the plurality of sentences may include calculating the plurality of sentences associated with the homonym based on the learned first model.

In addition, obtaining a fourth sentence and a fifth sentence that do not contain the homonym, recognizing the meaning of each sentence based on the first model with respect to the fourth sentence and the fifth sentence, the Calculating the homonym matching the fourth sentence and the fifth sentence based on a second model for the meaning of the sentence, the fourth sentence and the fifth sentence, and the fourth sentence, the fifth sentence, and the homonym The method may further include generating a sixth sentence including the opposite word.

In addition, in an apparatus for performing a method for generating rap lyrics according to the present invention for solving the above-described problem, a homonym for the rap lyrics is obtained from a memory and a homonym for the homonym based on a first model Calculating a plurality of sentences in which the homonym has different meanings, displaying a list including the plurality of sentences, and a first sentence including the first meaning of the homonym in the list and the homonym When a second sentence including a second meaning different from the first meaning is selected, a second sentence obtained by combining at least one first character in the first sentence, at least one second character in the second sentence, and the homonym It may include a processor for generating 3 sentences.

In addition, the processor, the word or sentence input by the user, the location, date, time, event or accident that occurred on the date when the user input the word or sentence, and the same as the date in the past It can be acquired based on an event or accident and the user's bio-signals.

In addition, the processor periodically obtains information related to at least one of user information for each user, a word or sentence, a time or place at which the word or sentence is input, and an event or accident related to the time or place for a preset time period, and , the information acquired periodically for the preset time may be accumulated and stored for each user. Here, the first model may be machine-learned based on the information accumulated and stored for each user and a plurality of sentences related to the accumulated and stored information.

Also, the processor may calculate the plurality of sentences associated with the homonym based on the learned first model.

In addition, the processor acquires a fourth sentence and a fifth sentence that do not contain the homonym, and recognizes the meaning of the sentence for each of the fourth sentence and the fifth sentence based on the first model, and , calculates the homonym matching the fourth sentence and the fifth sentence based on the second model for the meaning of the sentence, the fourth sentence and the fifth sentence, and the fourth sentence, the fifth sentence, and the A sixth sentence including homonyms may be generated.

In addition to this, another method for implementing the present invention, another system, and a computer-readable recording medium for recording a computer program for executing the method may be further provided.

According to the present invention as described above, by accumulating various information for each user and providing words or sentences of rap lyrics suitable for the user through a deep learning model, there is an effect that the time required for the user to make rap lyrics can be reduced.

In addition, according to the present invention, when providing a word or sentence of rap lyrics to a user, a punchline of rap lyrics is generated by providing a sentence including a homophone for the rap lyrics and a word that is meaningful even if read backwards, thereby generating a punchline of the rap lyrics. It has the effect of improving the quality of

Effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

1 is a schematic diagram of an apparatus for generating rap lyrics according to the present invention;
2 is an exemplary diagram illustrating a process in which the processor of the apparatus according to the present invention generates a third sentence.
3 is an exemplary diagram illustrating a process in which the processor of the apparatus according to the present invention generates a third sentence when A is a verb.
4 is an exemplary diagram illustrating a process in which the processor of the apparatus according to the present invention generates a third sentence when A is a noun.
5 is an exemplary diagram illustrating a process in which the processor of the apparatus according to the present invention generates a third sentence when A is a letter, a clause, or the like.

Advantages and features of the present invention and methods of achieving them will become apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only those of ordinary skill in the art to which the present invention pertains, to complete the disclosure of the present invention. It is provided to fully understand the scope of the present invention, and the present invention is only defined by the scope of the claims.

The terminology used herein is for the purpose of describing the embodiments and is not intended to limit the present invention. In this specification, the singular also includes the plural unless specifically stated otherwise in the phrase. As used herein, “comprises” and/or “comprising” does not exclude the presence or addition of one or more other components in addition to the stated components. Like reference numerals refer to like elements throughout, and "and/or" includes each and every combination of one or more of the recited elements. Although "first", "second", etc. are used to describe various elements, these elements are not limited by these terms, of course. These terms are only used to distinguish one component from another. Accordingly, it goes without saying that the first component mentioned below may be the second component within the spirit of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used herein will have the meaning commonly understood by those of ordinary skill in the art to which this invention belongs. In addition, terms defined in a commonly used dictionary are not to be interpreted ideally or excessively unless specifically defined explicitly.

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

Before the description, the meaning of the terms used in this specification will be briefly described. However, it should be noted that the descriptions of terms are for the purpose of helping the understanding of the present specification, and are not used in the meaning of limiting the technical spirit of the present invention unless explicitly described as limiting the present invention.

1 is a schematic representation of a device 10 for generating rap lyrics according to the present invention.

The device 10 may have the effect of reducing the time the user spends making rap lyrics by accumulating various information for each user and providing words or sentences of rap lyrics suitable for the user through the deep learning model.

In addition, when the device 10 provides a word or sentence of rap lyrics to the user, the device 10 provides a sentence including a homonym and an inversion word for the rap lyrics, thereby generating a punchline of the rap lyrics to increase the quality of the rap lyrics. may have a possible effect.

Here, the homonym may mean a word used in a completely different meaning only with the same sound. As an example, there may be 'ship' as a homonym, and 'ship' is a boat that rides in a river or sea, a boat that eats, and a boat that people eat, and the meaning is not related at all.

Also, a word that is meaningful even when read backwards may mean a word that can be a meaningful word even if the order of the words is changed with respect to a word composed of at least two words. That is, a word that is meaningful even when read backwards may be a word that has meaning even when effects such as reverse effect, inversion, reflection, etc. are applied. For example, words that have meaning even if read backwards are kiss - ski / mosquito - raised / army - army / ants - uncivilized / city - city / city / clock - revelation / shoes - outgoing / temple - whole body / eccentricity - impotence / railroad tracks - Directions (pronunciation) / Korea - There may be localization, etc. Hereinafter, words that are meaningful even when read backwards are described as "inverted words".

Here, the device 10 is a mobile phone, a smart phone, a personal digital assistant (PDA), a portable multimedia player (PMP), a tablet PC, etc. all kinds of handheld (Handheld) based that can be connected to the web server through the network. It may include a wireless communication device, and among digital devices equipped with memory means and equipped with a microprocessor, such as personal computers (eg, desktop computers, notebook computers, etc.), workstations, PDA's, web pads, etc. It could be one.

In addition, the device 10 according to the present invention may be a server that receives a request from a client and performs information processing. In this case, the server may include the same components as in FIG. 1 , and all operations described below server can do the same.

In addition, the device 10 according to the present invention may be the computer described above, and in this case, the computer may include the same components as those of FIG. 1 , and the computer may perform all operations described below in the same manner. .

In addition, the device 10 according to the present invention may be the mobile terminal (smartphone) described above. In this case, the mobile terminal may include the same components as those of FIG. 1 , and all operations described below may be performed by the mobile terminal. can be performed in the same way.

On the other hand, mobile terminals include mobile phones, smart phones, laptop computers, digital broadcasting terminals, personal digital assistants (PDA), portable multimedia players (PMPs), navigation systems, slate PCs, and tablet PCs. (tablet PC), ultrabook (ultrabook), wearable device (wearable device, for example, a watch-type terminal (smartwatch), glass-type terminal (smart glass), HMD (head mounted display), etc. may be included.

Referring to FIG. 1 , the device 10 may include a communication unit 110 , a display unit 120 , a memory 130 , and a processor 140 , but is not necessarily limited thereto and may include fewer or more components. may include

The communication unit 110 may include one or more modules that enable wireless communication between the device 10 and a wireless communication system or between the device 10 and an external device (not shown). In addition, the communication unit 110 may include one or more modules for connecting the device 10 to one or more networks.

The display unit 120 may implement a touch screen by forming a layer structure with the touch sensor or being formed integrally with the touch sensor. Such a touch screen may provide an input interface between the device 10 and a user and, at the same time, provide an output interface between the device 10 and a user.

The display 120 may display various information generated by the processor 140 and provide it to the user, and at the same time receive various information from the user.

The memory 130 may store information supporting various functions of the device 10 . The memory 130 may store a plurality of application programs (or applications) running in the device 10 , data for operation of the device 10 , and commands. At least some of these application programs may be downloaded from an external server (not shown) through wireless communication. In addition, at least some of these application programs may exist for a basic function of the device 10 . Meanwhile, the application program may be stored in the memory 130 , installed on the device 10 , and driven by the processor 140 to perform an operation (or function) of the device 10 .

The memory 130 may store a first model, a second model, and an application for generating rap lyrics. Here, the first model may be modeled based on at least one technique of semantics and ontology. The semantics can understand the meaning of input information and perform logical reasoning, and the ontology expresses concepts, characteristics, and relationships of words used in a certain range, so that general knowledge about words is explicitly expressed. It is revealed, and the meaning of the sentence can be grasped by defining the relationship between words. Since each of the semantics and ontology is a known technology, a detailed description thereof will be omitted. The rap lyrics generation application may be an application that generates and provides rap lyrics including a punchline for each user according to a user's request.

The second model may be configured as an algorithm for detecting each word in a plurality of sentences and extracting a homonym for the word.

The rap lyrics generation application is for generating and providing rap lyrics to a user, and may be downloaded through an external device or downloaded through a web server.

The memory 130 may store a thesaurus, and the thesaurus includes part-of-speech information, semantic information, homonym information, nuclear vocabulary information, etc. for each vocabulary at a certain word scale (eg, 500,000 words). As such, such information may be integrated and built in the memory 130 . Here, nuclear vocabulary is the most basic word constituting a sentence, and may be the easiest and most basic word in terms of vocabulary difficulty. As an example, the nuclear vocabulary may include 'have', 'give', 'go', 'not', and the like.

In addition to the operation related to the application program, the processor 140 may generally control the overall operation of the device 10 . The processor 140 may provide or process appropriate information or functions to the user by processing signals, data, information, etc. input or output through the above-described components or by driving an application program stored in the memory 130 .

The processor 140 may control at least some of the components discussed with reference to FIG. 1 in order to drive an application program stored in the memory 130 . Furthermore, in order to drive the application program, the processor 140 may operate at least two or more of the components included in the device 10 in combination with each other.

The processor 140 may obtain a homonym or an inversion word for the rap lyrics from the user. In addition, the processor 140 may obtain a plurality of sentences including the homonym or inversion word from the user.

The processor 140 determines the word or sentence input by the user, the location, date, time, event or accident that occurred on the date when the user inputted the word or sentence, and an event that occurred on the same past date as the date. Alternatively, at least one homonym or inverted word may be acquired based on at least one of an accident and the user's biometric information, or a plurality of sentences including the homonym or inverted word may be acquired.

That is, whenever the user inputs a word or sentence, the processor 140 is configured to perform at least one of the word or sentence input by the user and the time, location, date, and user biometric information for the time when the user inputs the word or sentence. By inputting one as a training dataset to the first model, the first model may be machine-learned.

In this case, as an example, the processor 140 determines the current location through the GPS module (not shown) of the device 10 according to the user's command for obtaining a place-based homophone or inversion word, and the first The at least one homonym or inversion word may be obtained from the word or sentence input by the user at the identified position in the past through the model.

As another example, the processor 140 determines the current location through the GPS module (not shown) of the device 10 according to the user's instruction for obtaining a place-based homophone or inversion word, and the first model or The at least one homonym or inversion word may be obtained from information related to a place representing the current location through a web browser search.

As another example, the processor 140, according to the user's instruction for obtaining a time (or date or day)-based homonym or inversion word, through the first model, the current time (or date or day of the week) and the same past The at least one homonym or inversion word may be obtained from the word or sentence input by the user at time.

As another example, the processor 140 generates on the same past date as the current date through the search of the first model or web browser according to a command for obtaining a homonym or inversion word based on a past event or accident from the user The at least one homonym or inversion word may be obtained from information related to the representative event/accident. In this case, the representative event/accident may be included in at least one of article information on the front page of at least one newspaper, first news of a news broadcast program of a public broadcasting station, and disaster text.

On the other hand, the user's biometric information is the wearer's biometric information measured through a wearable device interworking with the device 10 through the communication unit 110, and includes the wearer's heart rate, blood flow and It may include at least one of the stress index.

Then, the processor 140 acquires the wearer's biometric information through the wearable device according to a command for obtaining a biometric information-based homophone or inverted word from the user, and learns the biometric information through the first model The at least one homonym or inversion word may be obtained from the obtained word or sentence.

In addition, the processor 140 may acquire the homonym based on a consonant rhyme, a vowel rhyme, a next verse rhyme, etc. from pre-stored rap lyrics that read or utter a text with a rhyme aloud according to the beat.

The processor 140 may calculate a plurality of sentences in which the homonyms have different meanings based on the first model for the homonym, and display a list including the plurality of sentences.

When a first sentence including a first meaning of the homonym and a second sentence including a second meaning different from the first meaning of the homonym from the list are selected by the user, the processor 140 is configured to A third sentence may be generated by combining at least one first character in the first sentence, at least one second character in the second sentence, and the homonym.

Here, the processor 140 may select the first sentence and the second sentence from the list, respectively, according to a specific criterion, without being selected by the user for the first sentence and the second sentence. The processor 140 may select the first sentence and the second sentence from the list, respectively, based on the shape of the homonym as one of the specific criteria. For example, the processor 140 may select the first sentence and the second sentence in which the form of the homonym is included in the order of noun > verb > phrase/clause from the list, respectively.

For example, the processor 140 is configured to 'write lyrics today', which is a first sentence including the first meaning of 'seo', which is a homophone, and a second sentence, '' It is possible to create a punchline 'write the lyrics like a medicine that is good for the body', which is the third sentence combining 'a drug that is good for the body'.

Here, the first character or the second character may be a word or a part of the character. Also, the first sentence and the second sentence may be plural, and the third sentence in which the first sentence and the second sentence including the homonym are combined may also be plural. Accordingly, the plurality of third sentences may be a part of rap lyrics. For example, the four third sentences may be composed of parts in which a sentence composed of 4 bars has a form of 4 lines.

In addition, the third sentence may be a punch line in the rap lyrics, and the punch line composed of homonyms is, for example, 'The stage is a burdensome gaze like heavy snow', 'Don't exaggerate even though it's not an office', 'Min-sang Yoo. The ship came out like a port' and so on.

The processor 140 may periodically store the third sentence in the memory 130 and input the third sentence into the first model to learn. In addition, the processor 140 may additionally write a third sentence to a part of the rap lyrics previously written by the user.

The processor 140 provides information related to at least one of user information, words or sentences, time or place at which the word or sentence is inputted, an event or accident related to the time or place, and biometric information of the user for each user for a preset time. It can be obtained periodically. The processor 140 may sort pre-stored information for each user based on a location tab, an event/accident tab, a biosignal tab, etc. on the driving screen of the rap lyrics generation application, or display information received from the user.

Here, the user information may be information such as age, gender, place of residence, place of birth, current occupation, etc. for each user who downloads and uses the rap lyrics generation application. The time or place at which the word or sentence is input may be a time when the user inputs the word or sentence, for example, PM10:00, and a place, for example, a park. The event or accident related to time or place may be an event or accident corresponding to the time and place when the user inputs the word or sentence, or may be a past event or accident that occurred on the same date.

The processor 140 may accumulate the information periodically acquired for the preset time for each user and store it in the memory 130 .

Here, the processor 140 may perform machine learning with respect to the first model stored in the memory 130 based on the information accumulated and stored for each user and a plurality of sentences related to the accumulated and stored information. Thereafter, the processor 140 may calculate the plurality of sentences associated with the homonym or inversion word based on the learned first model.

That is, whenever the user inputs a word or sentence, the processor 140 is configured to perform at least one of the word or sentence input by the user and the time, location, date, and user biometric information for the time when the user inputs the word or sentence. By inputting one as a training dataset to the first model, the first model may be machine-learned.

In this case, as an example, the processor 140 determines the current location through the GPS module (not shown) of the device 10 according to the user's command for obtaining a place-based homophone or inversion word, and the first The at least one homonym or inversion word may be obtained from the word or sentence input by the user at the identified position in the past through the model.

As another example, the processor 140 determines the current location through the GPS module (not shown) of the device 10 according to the user's instruction for obtaining a place-based homophone or inversion word, and the first model or The at least one homonym or inversion word may be obtained from information related to a place representing the current location through a web browser search.

As another example, the processor 140, according to the user's instruction for obtaining a time (or date or day)-based homonym or inversion word, through the first model, the current time (or date or day of the week) and the same past The at least one homonym or inversion word may be obtained from the word or sentence input by the user at time.

As another example, the processor 140 generates on the same past date as the current date through the search of the first model or web browser according to a command for obtaining a homonym or inversion word based on a past event or accident from the user The at least one homonym or inversion word may be obtained from information related to the representative event/accident. In this case, the representative event/accident may be included in at least one of article information on the front page of at least one newspaper, first news of a news broadcast program of a public broadcasting station, and disaster text.

On the other hand, the user's biometric information is the wearer's biometric information measured through a wearable device interworking with the device 10 through the communication unit 110, and includes the wearer's heart rate, blood flow and It may include at least one of the stress index.

Then, the processor 140 acquires the wearer's biometric information through the wearable device according to a command for obtaining a biometric information-based homophone or inverted word from the user, and learns the biometric information through the first model The at least one homonym or inversion word may be obtained from the obtained word or sentence.

In addition, the processor 140 may calculate a plurality of clauses, phrases, or sentences according to the content determined by the user as the subject (theme) of the lyrics through the model, and a rhyme is inserted according to the note rate in consideration of the number of measures. can be calculated.

The processor 140 may obtain a fourth sentence and a fifth sentence that do not include a homonym or an inversion word. Here, the homonym or inversion word may be the same as or different from the homonym.

The processor 140 may input the fourth sentence and the fifth sentence into the first model to recognize the meaning of each sentence.

The processor 140 may calculate the homonym matching the fourth sentence and the fifth sentence based on the meaning of the sentence and the second model for the fourth sentence and the fifth sentence. Here, the second model may be configured as an algorithm that detects each word within a plurality of sentences and extracts a homonym for the word.

The processor 140 may generate a sixth sentence including the fourth sentence, the fifth sentence, and a homonym. Here, the processor 140 may periodically store the sixth sentence in the memory 130, input the sixth sentence into the first model to learn, and use the sixth sentence as part of the rap lyrics previously written by the user. You can also enter

The processor 140 may generate a voice file based on a preset rhythm for each of the third sentence and the sixth sentence, and output the voice file to the user through an output unit (not shown) to provide it. Here, the user may have the effect of being able to easily practice the third sentence and the sixth sentence, which are punchlines, through the voice provided through the output unit.

2 is an exemplary diagram illustrating a process of generating a third sentence by the processor 140 of the device 10 according to the present invention.

3 is an exemplary diagram illustrating a process in which the processor 140 of the device 10 according to the present invention generates a third sentence when A is a verb.

4 is an exemplary diagram illustrating a process in which the processor 140 of the device 10 according to the present invention generates a third sentence when A is a noun.

5 is an exemplary diagram illustrating a process in which the processor 140 of the device 10 according to the present invention generates a third sentence when A is a letter, a clause, or the like.

Hereinafter, the operation of the processor 140 of the device 10 according to the present invention will be described with reference to FIGS. 2 to 5 .

Referring to FIG. 2 , the processor 140 may obtain A, which is a word, sentence, or clause from the user. Here, A may be a homonym even if it is a word or a sentence.

When A is a word, the processor 140 may distinguish whether it is a verb or a noun. Thereafter, the processor 140 may generate various sentences based on A as shown in FIGS. 3 to 5 . Here, the generated various sentences may be configured such that A is positioned last.

First, referring to FIG. 3 , when A is both a word and a verb, the processor 140 may generate a first sentence A1 of a + A including the noun a based on the A, which is a homonym. Also, when A is both a word and a verb, the processor 140 may generate a second sentence A2 of b + A including the noun b based on the A. Thereafter, the processor 140 generates a third, which is a + b + A, which is a combination of at least one first character in the first sentence A1, at least one second character in the second sentence A2, and A, which is a homonym. You can create sentences.

If the homonym A is, for example, 'write' or 'write', the first sentence of 'write lyrics (a) (A)', which is A1 today, and 'medicine good for the body (b)' as A2 ) can create the second sentence 'Written in the mouth (A)'. The processor 140 may generate a third sentence, 'Write lyrics (a) like a medicine (b) that is good for the body (A)', which is A3 that is a combination of a in A1 and b in A2.

Referring to FIG. 4 , when A is both a word and a noun, the processor 140 may generate a first sentence A1 of a + A including the noun a based on the A, which is a homophone. Also, when A is both a word and a verb, the processor 140 may generate a second sentence A2 of b + A including the noun b based on the A. Thereafter, the processor 140 generates a third, which is a + b + A, which is a combination of at least one first character in the first sentence A1, at least one second character in the second sentence A2, and A, which is a homonym. You can create sentences. Alternatively, the processor 140 may generate a combination of a new word, phrase, or sentence c, at least one second letter in the second sentence A2, and a homonym A included in the first sentence and the second sentence c + b + A third sentence can be created. Here, c may be used to expand the content to be expressed.

For example, if the homophone A is 'snow', the first sentence of 'eye (A) towards the stage (a)' which is A1, 'heavy snow (b) fell (burden) snow ( A)' can be generated as a second sentence. Here, the processor 140 may generate the third sentence, 'The stage (a) is a heavy snow (A) like heavy snow (b)', which is A3 that is a combination of a in A1 and b in A2. In addition, when the new phrase c is 'her eyes', the processor 140 says that 'her eyes (c) are burdensome eyes (A) like heavy snow (b)', which is A4 combining c, b and A. You can create a third sentence.

If the homonym A is, for example, 'eyes', the first sentence of A1 not doing homework (a) (A)', A2 being 'the king (b) bee (A) met in the mountains' )' can be generated. The processor 140 may generate the third sentence, 'I'm not doing my homework (a), then, like the king (b) bee (A) I met on a picnic~!', which is A3 that is a combination of A1 and A2. In addition, the processor 140, when the new old c is 'dis', 'my diss (c), which is A4 combining c, b and A, is surprised like a king (b) bee (A) that I met by chance in the mountain~! A third sentence of ' can be generated.

Referring to FIG. 5 , when A is a sentence or clause, the processor 140 may generate a first sentence A1 of a + A including the noun a based on the A including the homonym. Also, when A is a sentence or clause, the processor 140 may generate a second sentence A2 of b + A including the noun b based on the A. Thereafter, the processor 140 generates a third, which is a + b + A, which is a combination of at least one first character in the first sentence A1, at least one second character in the second sentence A2, and A, which is a homonym. You can create sentences. Alternatively, the processor 140 may generate a combination of a new word, phrase, or sentence c, at least one second letter in the second sentence A2, and a homonym A included in the first sentence and the second sentence c + b + A third sentence can be created.

For example, if the homonym A is 'a boat is out', the first sentence of A1, Min-sang Yu (a), is a boat (A)', A2 is 'a boat came out of the port (b) (A) ' can be generated as a second sentence. Here, the processor 140 may generate the third sentence 'Yoo Min-sang (a) is out of the boat (A) like a port (b)', which is A3 that is a combination of a in A1 and b in A2. In addition, the processor 140, when the new word c is 'sweat', A4, which is a combination of c, b and A You can create the third sentence, 'I came in (A*) and ate a hundred times like a staple in my life'. Here, A* may be expanded and created with a new meaning of the content desired to be expressed through c.

As mentioned above, although embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art to which the present invention pertains know that the present invention may be embodied in other specific forms without changing the technical spirit or essential features thereof. you will be able to understand Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive.

10: device
110: communication department
120: display unit
130: memory
140: processor

Claims (10)

A method for generating rap lyrics performed by a device, comprising:
obtaining a homonym for the rap lyrics;
The first model for the homonym
calculating a plurality of sentences in which the homonyms have different meanings based on each other;
displaying a list including the plurality of sentences; and
When a first sentence including a first meaning of the homonym and a second sentence including a second meaning different from the first meaning of the homonym are selected from the list, at least one first sentence in the first sentence generating a third sentence in which one character, at least one second character in the second sentence, and the homonym are combined;
A method comprising According to claim 1,
The step of obtaining a homonym for the rap lyrics is,
a word or sentence input by the user, the location, date, time, event or accident that occurred on the date when the user entered the word or sentence, an event or accident that occurred on the same past date as the date, and the user is obtained based on the biometric information of the method. According to claim 1,
periodically acquiring information related to at least one of user information for each user, a word or sentence, a time or place at which the word or sentence was input, and an event or an accident related to the time or place for a preset time; and
accumulating and storing the information periodically acquired for each user for the preset time; further comprising,
The first model is
Machine learning is performed based on the information accumulated and stored for each user and a plurality of sentences related to the accumulated and stored information. 4. The method of claim 3,
The step of calculating the plurality of sentences,
Calculating the plurality of sentences associated with the homonym based on the learned first model. According to claim 1,
obtaining a fourth sentence and a fifth sentence that do not include the homonym;
recognizing the meaning of each sentence based on the first model with respect to the fourth sentence and the fifth sentence;
calculating the homonym matching the fourth sentence and the fifth sentence based on a second model for the meaning of the sentence and the fourth and fifth sentences; and
The method further comprising; generating a sixth sentence including the fourth sentence, the fifth sentence, and the homonym. An apparatus for performing a method of generating rap lyrics, comprising:
Memory; and
Obtain a homonym for the rap lyrics,
Calculating a plurality of sentences in which the homonyms have different meanings based on the first model for the homonyms,
Display a list including the plurality of sentences,
When a first sentence including a first meaning of the homonym and a second sentence including a second meaning different from the first meaning of the homonym are selected from the list, at least one first sentence in the first sentence a processor for generating a third sentence by combining one character, at least one second character in the second sentence, and the homonym;
A device comprising a. 7. The method of claim 6,
The processor is
a word or sentence input by the user, the location, date, time, event or accident that occurred on the date when the user entered the word or sentence, an event or accident that occurred on the same past date as the date, and the user device, which is obtained based on the biometric information of 7. The method of claim 6,
The processor is
Periodically acquire information related to at least one of user information, words or sentences, time or place at which the word or sentence is inputted, an event or accident related to the time or place for each user for a preset time,
accumulating and storing the information acquired periodically for the preset time for each user,
The first model is
Machine learning is performed based on the information accumulated and stored for each user and a plurality of sentences related to the accumulated and stored information. 9. The method of claim 8,
The processor is
An apparatus for calculating the plurality of sentences associated with the disambiguation based on the learned first model. 7. The method of claim 6,
The processor is
Obtaining the fourth and fifth sentences that do not contain the homonym,
Recognizing the meaning of each sentence based on the first model for the fourth sentence and the fifth sentence,
Calculating the homonym matching the fourth sentence and the fifth sentence based on a second model for the meaning of the sentence and the fourth sentence and the fifth sentence,
An apparatus for generating a sixth sentence including the fourth sentence, the fifth sentence, and the homonym.

Images