KR102490769B1 - Method and device for evaluating ballet movements based on ai using musical elements - Google Patents

Abstract

The present invention relates to a method and apparatus for evaluating ballet movements based on artificial intelligence using musical elements, the method comprising: constructing an artificial intelligence model for generating ballet class music matched with ballet class movements; Reproducing a basic ballet accompaniment generated through the artificial intelligence model; photographing a user's movement through a camera during reproduction of the basic ballet accompaniment; determining a user ballet motion corresponding to the motion and generating a user ballet accompaniment matching the user ballet motion through the artificial intelligence model; and generating an evaluation result for the movement by comparing feature information of each of the basic ballet accompaniment and the user ballet accompaniment.

Description

Artificial intelligence-based ballet motion evaluation method and apparatus using musical elements

The present invention relates to an evaluation technique for ballet practice practice, and more particularly, in a ballet practice process, by generating and providing evaluation of ballet motion based on artificial intelligence, using musical elements that can improve the user's practice efficiency. It relates to an artificial intelligence-based ballet movement evaluation method and apparatus.

Recently, artificial intelligence (AI) technology has been attracting attention from society as a whole as it shows a state-of-the-art development. Artificial intelligence is “a computer brain in which a computer executes areas that human intelligence can do,” “the engineering and science of creating intelligent machines,” “a set of algorithmic systems designed to think, sense, and act like humans.” It refers to the ability of computers to perform human-specific intellectual abilities at a high level.

Since AlphaGo, a Go program, showed the potential of software, artificial intelligence is bringing great changes to society as a whole. Artificial intelligence is introduced to provide a highly integrated smart space by being used together with augmented reality, Internet of Things, edge computing, and digital twins, and is highlighted as a key new technology that will lead the era of the 4th industrial revolution. In addition, artificial intelligence is attracting attention as a next-generation growth engine that can evolve the industrial ecosystem beyond solving standardized problems. It is also being actively applied to the knowledge service industry, such as telecommunications.

In other words, artificial intelligence is preparing for a new era by combining all existing systems with artificial intelligence, not only industries for convenience or level improvement in real life, but also the general culture and arts of our society.

Even in artistic creation, which seemed to be unreasonable for artificial intelligence, various experiments such as composition, performance, and imitation are taking place in the field of music as new revolutionary results are launched. Artificial intelligence music, which started with classical music with the clearest structure, is currently producing complex music quickly and immediately through deep learning technology. However, since ballet class music has unique characteristics differentiated from music for appreciation, it is necessary to input additional information specific to ballet accompaniment, such as motion texture, speed, and energy. This has an absolute impact on the efficiency of ballet practice and is a more important part than musical artistry.

Korean Patent Registration No. 10-0658869 (2006.12.11)

An embodiment of the present invention is an artificial intelligence-based ballet motion evaluation method using musical elements capable of defining characteristics of ballet accompaniment, generating learning data, learning this, and constructing artificial intelligence that generates ballet accompaniment necessary for ballet class. and to provide a device.

An embodiment of the present invention is an artificial intelligence-based ballet motion evaluation method and apparatus using musical elements that can improve a user's practice efficiency by generating and providing an evaluation of ballet motion based on artificial intelligence in a ballet practice process. it's about

Among the embodiments, an artificial intelligence-based ballet motion evaluation method using musical elements includes the steps of constructing an artificial intelligence model for generating ballet class music that matches ballet class motion; Reproducing a basic ballet accompaniment generated through the artificial intelligence model; photographing a user's movement through a camera during reproduction of the basic ballet accompaniment; determining a user ballet motion corresponding to the motion and generating a user ballet accompaniment matching the user ballet motion through the artificial intelligence model; and generating an evaluation result for the movement by comparing feature information of each of the basic ballet accompaniment and the user ballet accompaniment.

The step of constructing the artificial intelligence model may include defining a plurality of genres of ballet music corresponding to a plurality of ballet class movements as first characteristic information of ballet class music; defining a plurality of characteristics of ballet music as second characteristic information of the ballet lesson music; and extracting the first and second feature information from a plurality of pieces of ballet music, respectively, to generate learning data about the ballet class music.

The step of defining the plurality of ballet music genres includes first music that is slow and elegant, second music that is comfortable at a normal tempo, third music that is elegant at a normal tempo, fourth music that is a bit fast and light, and fifth music that is a bit fast and has an accent. , defining the 6th music with a little speed and accent, the 7th music with a little speed and elegance and power, and the 8th music with speed and lightness as the plurality of ballet music genres.

The defining of the plurality of ballet music features may include defining form, phrase, beat, tempo, dynamic, velocity, accompaniment type, accent, and pedaling as the plurality of ballet music features.

Building the artificial intelligence model may include building a first artificial intelligence model for generating basic ballet class music matched with the plurality of ballet class movements; and constructing a second artificial intelligence model for generating ballet class applied music based on the ballet class basic music.

The reproducing of the basic ballet accompaniment may include converting and reproducing the basic ballet accompaniment into a performance of a single piano tone.

The generating of the user's ballet accompaniment may include determining motion characteristic information about beat, tempo, dynamics, and velocity from the user's ballet motion.

Generating the evaluation result may include generating the evaluation result by mutually comparing only characteristic information corresponding to the motion characteristic information among the characteristic information of the basic ballet accompaniment with the motion characteristic information.

Generating the evaluation result may include generating a first evaluation result related to the movement by comparing feature information corresponding to the motion feature information among the feature information of the basic ballet accompaniment with the motion feature information; And generating a second evaluation result related to the motion by comparing feature information that does not correspond to the motion characteristic information among the characteristic information of the basic ballet accompaniment with the characteristic information of the user ballet accompaniment.

Among the embodiments, an artificial intelligence-based ballet motion evaluation device using musical elements includes a model building unit for constructing an artificial intelligence model for generating ballet class music that matches ballet class motion; Ballet accompaniment reproducing unit for reproducing basic ballet accompaniment including characteristic information about musical elements of ballet class music; a motion photographing unit for photographing a user's movement through a camera during reproduction of the basic ballet accompaniment; a motion analyzer for determining a user ballet motion corresponding to the movement and generating a user ballet accompaniment matched to the user ballet motion through an artificial intelligence model; and an evaluation performer for generating an evaluation result for the movement by comparing feature information of each of the basic ballet accompaniment and the user ballet accompaniment.

The ballet accompaniment reproducing unit may play a ballet accompaniment specified according to a user's selection received from a user terminal among pre-generated or stored ballet accompaniments as the basic ballet accompaniment.

The apparatus includes an evaluation providing unit providing the evaluation result to a user terminal; And a feedback receiving unit for receiving feedback on the evaluation result from the user terminal; may further include.

The feedback receiving unit updates the characteristic information to a corresponding numerical value when the feedback includes a numerical value related to the characteristic information of the basic ballet accompaniment, and transmits the updated characteristic information to the ballet accompaniment reproducing unit to perform the basic ballet accompaniment by the artificial intelligence model. You can update the creation behavior of

The disclosed technology may have the following effects. However, it does not mean that a specific embodiment must include all of the following effects or only the following effects, so it should not be understood that the scope of rights of the disclosed technology is limited thereby.

Artificial intelligence-based ballet motion evaluation method and apparatus using musical elements according to an embodiment of the present invention defines the characteristics of ballet accompaniment, generates learning data, and learns artificial intelligence to generate ballet accompaniment necessary for ballet class. can be built

The artificial intelligence-based ballet motion evaluation method and apparatus using musical elements according to an embodiment of the present invention can improve the user's practice efficiency by generating and providing evaluation of ballet motion based on artificial intelligence in a ballet practice process. there is.

1 is a diagram illustrating a ballet motion evaluation system according to the present invention.
FIG. 2 is a diagram explaining the system configuration of the ballet motion evaluation device of FIG. 1 .
FIG. 3 is a diagram explaining the functional configuration of the ballet motion evaluation device of FIG. 1 .
4 is a flowchart illustrating an artificial intelligence-based ballet motion evaluation method using musical elements according to the present invention.
5 is a diagram illustrating ballet class operations for each music genre according to the present invention.
6 is a diagram explaining the formal structure of ballet class music and the phrase composition by rhythm division of ballet class music.
7 is a diagram for explaining the characteristics of a ballet class operation according to the present invention.
8 is a diagram illustrating the velocity and sustain of a note at the end of a phrase of ballet class music.
9 is a diagram for explaining an embodiment of a ballet motion evaluation and feedback process according to the present invention.

Since the description of the present invention is only an embodiment for structural or functional description, the scope of the present invention should not be construed as being limited by the embodiments described in the text. That is, since the embodiment can be changed in various ways and can have various forms, it should be understood that the scope of the present invention includes equivalents capable of realizing the technical idea. In addition, since the object or effect presented in the present invention does not mean that a specific embodiment should include all of them or only such effects, the scope of the present invention should not be construed as being limited thereto.

Meanwhile, the meaning of terms described in this application should be understood as follows.

Terms such as "first" and "second" are used to distinguish one component from another, and the scope of rights should not be limited by these terms. For example, a first element may be termed a second element, and similarly, a second element may be termed a first element.

It should be understood that when an element is referred to as being “connected” to another element, it may be directly connected to the other element, but other elements may exist in the middle. On the other hand, when an element is referred to as being "directly connected" to another element, it should be understood that no intervening elements exist. Meanwhile, other expressions describing the relationship between components, such as “between” and “immediately between” or “adjacent to” and “directly adjacent to” should be interpreted similarly.

Expressions in the singular number should be understood to include plural expressions unless the context clearly dictates otherwise, and terms such as “comprise” or “having” refer to an embodied feature, number, step, operation, component, part, or these. It should be understood that it is intended to indicate that a combination exists, and does not preclude the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

In each step, the identification code (eg, a, b, c, etc.) is used for convenience of explanation, and the identification code does not describe the order of each step, and each step clearly follows a specific order in context. Unless otherwise specified, it may occur in a different order than specified. That is, each step may occur in the same order as specified, may be performed substantially simultaneously, or may be performed in the reverse order.

The present invention can be implemented as computer readable code on a computer readable recording medium, and the computer readable recording medium includes all types of recording devices storing data that can be read by a computer system. . Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disk, and optical data storage devices. In addition, the computer-readable recording medium may be distributed to computer systems connected through a network, so that computer-readable codes may be stored and executed in a distributed manner.

All terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs, unless defined otherwise. Terms defined in commonly used dictionaries should be interpreted as consistent with meanings in the context of the related art, and cannot be interpreted as having ideal or excessively formal meanings unless explicitly defined in the present application.

1 is a diagram illustrating a ballet motion evaluation system according to the present invention.

Referring to FIG. 1 , the ballet motion evaluation system 100 may include a user terminal 110 , a ballet motion evaluation device 130 and a database 150 .

The user terminal 110 may correspond to a computing device capable of requesting creation and reproduction of ballet accompaniments and checking evaluation results regarding ballet movements. The user terminal 110 may be implemented as a smart phone, laptop, or computer that is connected to and operable with the ballet motion evaluation device 130, is not necessarily limited thereto, and may be implemented with various devices such as a tablet PC. The user terminal 110 may be connected to the ballet motion evaluation device 130 through a wired or wireless network, and a plurality of user terminals 110 may be connected to the ballet motion evaluation device 130 at the same time.

The ballet motion evaluation device 130 corresponds to a computer or program capable of generating and reproducing artificial intelligence (AI)-based ballet accompaniment and evaluating ballet motion according to the degree of matching between the user's movement and the ballet accompaniment. It can be implemented as a server that The ballet motion evaluation device 130 may be connected to the user terminal 110 through a wireless network such as Bluetooth or WiFi, and may transmit/receive data with the user terminal 110 through the network. The ballet motion evaluation device 130 may automatically generate a ballet accompaniment suitable for the user's motion through artificial intelligence, directly reproduce the ballet accompaniment, or transfer the ballet accompaniment to the user terminal 110 to play it through the user terminal 110. may make it so.

In one embodiment, the ballet motion evaluation device 130 may be implemented to operate in conjunction with a separate external system (not shown in FIG. 1) to provide an additional function for transmitting or processing data. For example, the ballet motion evaluation device 130 may operate in conjunction with a music providing server that provides a variety of music, and may automatically generate and provide ballet accompaniments corresponding to specific music through this.

In addition, the ballet motion evaluation device 130 may be implemented by including a camera for recognizing a user's motion, and may operate in conjunction with a separate camera system or a motion detection system that provides a user motion recognition result.

The database 150 may correspond to a storage device for storing various pieces of information necessary for the operation of the ballet motion evaluation device 130 . For example, the database 150 may store information about musical characteristics of ballet accompaniments, and may store information about learning data, learning algorithms, and learning models associated with building artificial intelligence for ballet accompaniment generation, and must be It is not limited thereto, and the ballet motion evaluation device 130 may store information collected or processed in various forms in the process of executing the AI-based ballet motion evaluation method using musical elements.

Meanwhile, in FIG. 1, the database 150 is shown as a device independent of the ballet motion evaluation device 130, but is not necessarily limited thereto, and is a ballet motion evaluation device as a logical storage device of the ballet motion evaluation device 130. Of course, it can be implemented by being included in (130). In addition, the user terminal 110 is also shown as a device independent of the ballet motion evaluation device 130, but is not necessarily limited thereto, and the user terminal 110 and the ballet motion evaluation device 130 are integrated as needed. It can be implemented as, and a detailed description thereof will be omitted.

FIG. 2 is a diagram explaining the system configuration of the ballet motion evaluation device of FIG. 1 .

Referring to FIG. 2 , the ballet motion evaluation apparatus 130 may be implemented by including a processor 210, a memory 230, a user input/output unit 250, and a network input/output unit 270.

The processor 210 may execute a procedure for processing each step in the process of the ballet motion evaluation device 130 operating, and manage the memory 230 read or written throughout the process, and the memory ( Synchronization time between the volatile memory and the non-volatile memory in 230) can be scheduled. The processor 210 may control the overall operation of the ballet motion evaluation device 130, and is electrically connected to the memory 230, the user input/output unit 250, and the network input/output unit 270 to control data flow between them. can do. The processor 210 may be implemented as a CPU (Central Processing Unit) of the ballet motion evaluation device 130 .

The memory 230 is implemented as a non-volatile memory such as a solid state drive (SSD) or a hard disk drive (HDD) and may include an auxiliary memory device used to store all data necessary for the ballet motion evaluation device 130, , may include a main memory implemented as a volatile memory such as RAM (Random Access Memory).

The user input/output unit 250 may include an environment for receiving user input and an environment for outputting specific information to the user. For example, the user input/output unit 250 may include an input device including an adapter such as a touch pad, a touch screen, an on-screen keyboard, or a pointing device, and an output device including an adapter such as a monitor or touch screen. In one embodiment, the user input/output unit 250 may correspond to a computing device connected through a remote connection, and in such a case, the ballet motion evaluation device 130 may be performed as an independent server.

The network input/output unit 270 includes an environment for connecting to an external device or system through a network, and includes, for example, a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), and a VAN ( An adapter for communication such as Value Added Network) may be included.

3 is a diagram explaining the functional configuration of the ballet motion evaluation device of FIG. 1, FIG. 5 is a diagram explaining ballet class motion for each music genre according to the present invention, and FIG. 6 is a formal structure of ballet class music and ballet class Figure 7 is a diagram explaining the composition of a phrase by rhythm division of music, Figure 7 is a diagram explaining the characteristics of ballet class operation according to the present invention, Figure 8 is a diagram explaining the velocity and sustain of the end note of the phrase of ballet class music it is a drawing

Hereinafter, configuration and operation according to the present invention will be described in detail with reference to FIGS. 3 and 5 to 8 .

Referring to FIG. 3A , the ballet motion evaluation device 130 includes a model construction unit 310, a ballet accompaniment playback unit 320, a motion capture unit 330, a motion analysis unit 340, an evaluation execution unit 350, It may include an evaluation provider 360, a feedback receiver 370, and a controller 380.

The model building unit 310 may build an artificial intelligence model that generates ballet class music that matches ballet class motions. The model builder 310 may build an artificial intelligence model by defining the unique musical elements of the anti-leptic accompaniment as feature information. Here, the artificial intelligence model may receive information about ballet class motions as input data and generate ballet class music corresponding to the corresponding ballet class motions as output data.

For example, a ballet accompaniment output by an artificial intelligence model may be expressed as a set of sounds that progress over time. In particular, artificial intelligence music can easily express music that requires a high level of skill beyond the limits of a pianist who has to play all the notes alone with 10 fingers. That is, in that notes of a wide range can be played simultaneously and fast scales and arpeggios can be accurately implemented, the ballet accompaniment output by the artificial intelligence model can be created in a very diverse and free form.

Meanwhile, the model building unit 310 may be implemented by including a plurality of modules that independently perform each operation of the model building process.

More specifically, referring to FIG. 3B , the model building unit 310 includes a genre classification module 311, a feature extraction module 312, a learning data generation module 313, and a model building module 314 to be implemented. can

The genre classification module 311 may define a plurality of ballet music genres corresponding to a plurality of ballet class movements as first characteristic information of ballet class music. A ballet class can consist of a variety of movements, from slow and flexible movements to fast and powerful movements. In ballet class, all movements are repeated in each direction, left and right, so the phrases are concise and clear, and can have a unique sensibility that matches the goal of performance.

For example, dance songs with clear phrases and independent rhythms such as pavane, galliard, minuet, allemande, sarabande, waltz, tarantella, and tango can be good examples for learning ballet music. Songs with unique characteristics, such as serenades, ballads, and nocturnes, are also effective in expressing the emotions of ballet, and vocal pieces such as opera arias, chansons, canzones, and littes are similar to ballet in terms of breathing, so they can be highly utilized.

Ballet class movements can have linguistic nuances such as 'flexible', 'elegant', 'moderate', 'agile', 'light', 'powerful', 'strong', and 'big'. This is a very important concept for expressing the texture of motion, and the connection with music genres with these nuances can be a very important factor in building an artificial intelligence model. Accordingly, the genre classification module 311 may classify musical genres effective for ballet accompaniment into a total of 8 categories according to speed and character, and may be expressed as shown in FIG. 5 .

More specifically, the first music is slow and elegant music, that is, nocturnes, ballads, fantasias, slow preludes, slow interludes mainly composed by Chopin and F. in the romantic era, and slow movements of symphonies, concertos, and sonatas popular in the classical era. , flexible arias among vocal music, songs with elegance, these songs can effectively express the atmosphere of ballet classes such as plie, batman develope, stretch, adagio, and slow waltz.

The secondary music is relaxed music of moderate tempo and may include pavannes, allemandes, minuets, gavottes, 18th-century peasant dances rentlers, habaneras, and relaxed Afro-Cuban jazz danced at court by aristocrats. These pieces of music can be used for batman tandue, batman fondue, long de jean en lare, etc., which combine flexibility and moderation during ballet movements.

The third music may include a 19th century Viennese waltz with syncopation added as graceful music at a normal tempo performed in a wide range. This music can be effectively used for long de jean à ter and waltz, which deal with elegance and flow of energy in ballet class.

The 4th music is music with a slightly faster and lighter atmosphere, that is, music with a fast passage among the galant music of the pre-classical era, divertimento, serenade, casaccione, notturno, and Italian folk dance songs depicting light entertainment in the classical era. As tarantella, foxtrot in the early 20th century, bossa nova, etc., these music can be connected with light movements such as batmang tandu jeute and petit batmang in ballet class.

The fifth music is music that is slightly faster and includes an accent, and may include folk dance pieces such as Mannheim music school in the early 18th century, gallop, trepak, tango, and the second half of Tzardash. These pieces of music can be usefully used for batman frappé and tours that require agility and accent in ballet class.

The sixth music is music that is a little faster and contains stronger energy, and may include mazurkas, polonaises, polo, marches, and powerful finale movements. These pieces of music can be effectively used in ballet classes such as Grand Bateman, Medium Allegro, and Tour en Lère, which require great and strong energy.

The seventh music may include a big waltz containing an elegant and powerful atmosphere at a slightly faster tempo. Waltz is the most versatile dance song in ballet, with various types ranging from slow waltz to fast and splendid waltz. A powerful big waltz can be usefully used for grand allegro in ballet class.

Finally, the eighth music is music of fast and light energy, and may include bright and fast etude, light polka, ragtime, Charleston, and Dixieland jazz. These pieces of music can be effectively used for petit allegro such as soté, assemblé, and jeote that are performed agilely and lightly.

The feature extraction module 312 may define a plurality of features of ballet music as second feature information of ballet lesson music. For example, the plurality of ballet music characteristics may include form, phrase, beat, tempo, dynamic, velocity, accompaniment, accent, and pedaling. Here, a plurality of ballet music features defined by the feature extraction module 312 will be described in detail.

1) Count, form, phrase

Unlike general music, ballet class music may use the concept of 'count' rather than the concept of 'beat'. Although the ballet accompaniment score is marked with various beats, complex beats, mixed beats, etc. can give confusion, so each time a bass sound appears, it can be converted into 1 count and counted. In order to clearly match the movement of ballet music, 4 beats can be minimized to 2 beats and 6 beats to 3 beats, and the phrase can be performed in units of 2 counts. That is, 8 bars of 4 nights can be calculated as 16 counts of 2 nights. However, the fast 6 beats can be counted as 2 beats by grouping 3 beats together as in normal music.

In addition, a ballet class may be composed of a two-part form or a three-part form, and may be composed of a prelude. The two-part format can consist of 32 counts performing 16 counts from the forward direction immediately followed by 16 counts from the backward direction, or a length of 64 counts doubled. The three-part form may correspond to a structure in which a sideward motion is added after performing the forward and backward directions. In addition, the intro may include three types of '3 notes', '2 counts', and '4 counts', and may also include a case of adding a sound as a role of other signals. Endnotes can include four types of lengths of '1 note', '2 notes', '4 counts', and '8 counts' if necessary for the finishing action (see Figure 6 (a)).

A phrase may be formed by gathering counts. Phrases in units of 1 count, 2 count, 4 count, and 8 count can form 16 counts, that is, 1 set, in various combinations. A phrase can be formed the moment it passes or arrives at an important point. The 4 counts constituting the basic skeleton can be composed of six combinations of 1+1+1+1, 1+1+2, 1+2+1, 2+1+1, 2+2, and 4. In ballet, phrases are related to breathing, so the smallest phrase can correspond to a very important concept. It doesn't matter which form of 4 counts is configured for music for appreciation, but in ballet class music, 2+2 and 1+1+2 can mean completely different motion configurations even with the same 4 counts.

The minimum unit of phrase may be associated with rhythm division. When the same count continues, it is most effective to use the same rhythm type repeatedly. For example, a combination of 1+1+2 can be expressed by repeating a 1-count rhythm type twice and adding a 2-count rhythm type (see Figure 6 (b)).

2) beat, tempo, dynamic

Unlike listening music, all ballet class music can be input by minimizing it to 2 nights or 3 nights. After unifying the calculation unit as 2 or 3 beats per 1 count, you can input the BPM value suitable for the speed of each movement. Since the tempo of music directly affects the performance of accurate ballet movements, BPM numerical input suitable for the characteristics of each movement can be very important. 7 may correspond to what is defined by analyzing beats and tempos for each ballet class motion.

Dynamic may correspond to an element that expresses the scale, energy, and liveliness of motion, and may be divided into six levels from pianissimo to fortissimo. For example, plié, batman tandu, batman tandue cheute, batman fondue, ronde jean en lère, and petit allegro are dynamics between mezzopiano and mezzoforte, and batman de velope, adagio, and waltz are mezzopiano. It can be played in a wide range from to forte. Ron de Jean à Terre, Bateman Frappe, Petit Bateman, and Tour are dynamic from mezzo-forte to forte to express vibrancy, and Grand Bateman, Medium Allegro, and Grand Allegro are mezzo-forte to express splendor and intense energy. It can be played by extending the range of dynamics from forte to fortissimo.

Meanwhile, the dynamics may be converted into a velocity value and inputted in the computing device. At this time, the velocity is subdivided into 127 steps, so piano is 55 (±5), mezzopiano is 70 (±5), mesoforte is 85 (±5), forte is 100 (±5), and fortissimo is 115 ( It can be defined as ±5), and specific values can be adjusted according to the characteristics of each operation. For example, the dynamic range of plié, batman tandu, and batman tandu cheute is the same from mezzo piano to mezzo forte, but when converted to velocity, plié is 65-80, batman tandu is 70-85, and more The breezy atmosphere of batmang tandu jeute can be adjusted from 75 to 90, so the nuance of the song can be delicately expressed (see Fig. 7).

3) accompaniment, accent, pedaling

Performance can be very important in increasing the effectiveness of ballet classes. There are various playing methods that can express the nuances of movement, such as fast scales, trills, ornamental notes, octaves, chords, various accompaniment patterns, and pedaling. It can correspond to 'accent' as a sense of space and 'pedaling' related to flow.

The accompaniment types commonly used in ballet classes are 'waltz type' composed of bass and chords, 'polka type', 'arpeggio type' used to express soft passages in nocturnes or ballads, and 'marching music' for expressing restrained movements. It can include 'type', 'habanera type' that induces inner energy, and 'tango type'. The 'waltz' and 'polka' accompaniment types can be used for most movements. For example, it can be usefully used for batman tandue, batmant tandue cheute, long de jean a terre, batman fondue, long de jean en ler, and allegro. That is, since the bass note informs the start of the count and the code guides the beat, the efficiency of practice can be increased. Soft and flexible movements such as plie, batman develope, stretch, and adagio can prevent sound from breaking by using the 'arpeggio' accompaniment. The accompaniment type is a technique of distributing chords like glissando of a harp and playing them like flowing water, which can have a positive effect on muscle extension. The 'March' accompaniment type can give a strong feeling by proceeding with a chord every beat. This is due to the fact that percussion instruments and brass instruments continue to play the beat for an orderly march. Even in ballet class, the 'marching form' can be used when vigorous and moderate movements are required, such as Battman Flape and Grand Battman.

'Habanera' and 'Tango' can be characterized by syncopation rhythms that can raise inner energy. The music is composed of the same rhythm, but there may be differences in the flow and accent of the song. 'Habanera' accompaniment type can be used for Battman Fondue to continue the energy, and 'Tango' accompaniment type with strong accent can be used for Battman Tandu, Battman Flappe, and Grand Battman.

Also, the accent may correspond to a preparation signal notifying the ballerina that a new phrase starts. That is, it has the meaning of 'emphasis' and can highlight a specific part by 'lengthening' or 'strengthening' the sound.

Accents appear when 'emphasizing an important note' or 'when emotions are heightened'. In general, it is customary to play strongly on the first beat of a regular phrase or where the direction of a melody changes without an accent mark. However, in ballet class, an accent may be used as a signal to induce preparation of a new phrase immediately before a phrase begins. For example, in a short prelude, the last note is extended and emphasized, and in a regular phrase, the last beat is strongly played to convey the meaning as a preparatory beat.

On the other hand, when performing an accent, the effect can be increased by stepping on the pedal together. A pedal is a device that gives resonance to a specific part and can give a rich sense of space. For example, it can be used to help emphasize accents or to give softness to a song by naturally connecting notes. The pedal may be input after being converted into sustain in the computing device. In FIG. 8, an example of appropriate use of accents and pedals in a 4-count song is shown. Specifically, it can be seen that the phrase in units of 2 counts is repeated twice, and the velocity value is increased at the end of the phrase, and sustain is also input at the same time.

In ballet class, the pedal is regularly used because the accompaniment pattern is repeated, but if there is a special progression in the melody line, the flow of the melody can be reflected preferentially. That is, while sustain is regularly input, the sustain start point may be changed, added, or deleted according to the flow of the melody.

The learning data generating module 313 may extract first and second feature information from a plurality of pieces of ballet music, respectively, and generate learning data about ballet class music. The learning data generation module 313 may extract first and second feature information from each ballet music for a learning population composed of various ballet music pieces. For example, a music genre may be assigned to one ballet music, and a ballet class operation corresponding to the corresponding music genre may be assigned.

In addition, characteristic values for form, phrase, beat, tempo, dynamic, velocity, accompaniment type, accent, and pedaling may be assigned according to the composition of the corresponding ballet music. The learning data generation module 313 may generate learning data for building an artificial intelligence model based on a plurality of feature information assigned to each ballet class music. At this time, the learning data may consist of only the first characteristic information or the second characteristic information about ballet music, may consist of only some of each characteristic information, and the first and second characteristic information may be configured in an integrated form. may be

The model building module 314 may build an artificial intelligence model that generates ballet class music matched with a plurality of ballet class movements as a result of learning the learning data. The model building module 314 may repeatedly perform learning on the artificial intelligence model until a predetermined matching accuracy is reached based on the learning data generated from the learning population. The model building module 314 may basically perform an operation of building one artificial intelligence model, but is not necessarily limited thereto, and may independently build one or more artificial intelligence models as needed.

In one embodiment, the model building module 314 is a first artificial intelligence model for generating basic ballet class music matched with a plurality of ballet class movements, and a second artificial intelligence model for generating ballet class application music based on ballet class basic music. AI models can be built independently. Each of the first and second artificial intelligence models may be used to determine ballet class music that is matched with ballet class motions as a result by operating in connection with each other. That is, the basic ballet class music output by the first artificial intelligence model may be provided as an input to the second artificial intelligence model, and the ballet class application music output by the second artificial intelligence model corresponds to the ballet class motion. It can be used as class music. At this time, the basic music for ballet class may correspond to the basic accompaniment type of ballet accompaniment, and the applied music for ballet class may correspond to the applied accompaniment type of ballet accompaniment.

On the other hand, the model building module 314 may use data on the genre of ballet music as learning data as first feature information of ballet class music to build a first artificial intelligence model, and to build a second artificial intelligence model. As the second characteristic information of ballet class music, data on characteristics of ballet music may be used as learning data.

The ballet accompaniment reproducing unit 320 may reproduce a basic ballet accompaniment generated through an artificial intelligence model. Here, the basic ballet accompaniment is ballet class music used for ballet movement practice and may be used as reference information for evaluating the user's ballet movement. The ballet accompaniment reproducing unit 320 may reproduce basic ballet accompaniment through a speaker, and reproduce actual sound by playing the ballet accompaniment with a single instrument or a plurality of instruments. The ballet accompaniment reproducing unit 320 may select instruments corresponding to the characteristic information of the ballet accompaniment among a plurality of musical instruments, and reproduce the ballet accompaniment by playing the ballet accompaniment based on the sound of the corresponding instruments.

In one embodiment, the ballet accompaniment reproducing unit 320 may convert and reproduce the ballet accompaniment into a performance of a single piano tone. In the case of ballet class music, since most of them are performed with a single piano tone, the ballet accompaniment reproducing unit 320 can realistically reproduce the ballet accompaniment in the same form as the actual ballet class music.

In one embodiment, the ballet accompaniment player 320 may automatically adjust the volume of the speaker according to the number of users identified when a plurality of users are detected within the photographing area of the camera. The motion photographing unit 330 may perform a counting operation by identifying users existing within a photographing area of the camera while photographing the motion of the user through the camera. When a plurality of users are identified by the motion recording unit 330, the ballet accompaniment reproducing unit 320 may automatically adjust the volume of the speaker according to the number of users.

For example, the ballet accompaniment reproducing unit 320 may increase the speaker volume when there are many users. On the other hand, the ballet accompaniment reproducing unit 320 may calculate the amount of change in the volume of the speaker according to the number of users based on the size information of the recording area and the speaker output information input in advance, and determine the volume of the speaker based on the amount of change. can be adjusted

In one embodiment, when the ballet accompaniment is reproduced for the purpose of ballet movement evaluation, the ballet accompaniment reproducing unit 320 may reproduce the ballet accompaniment with a preset speaker volume. That is, in order to accurately evaluate ballet movements, the accompaniment provided to the user needs to be reproduced under the same conditions, and the ballet accompaniment playback unit 320 reproduces the ballet accompaniment with the user's setting or input for the purpose of evaluating ballet movements. When it is specified, it may operate to reproduce ballet accompaniment according to a preset speaker volume.

In one embodiment, the ballet accompaniment reproducing unit 320 may basically reproduce the ballet accompaniment generated by the artificial intelligence model, but is not necessarily limited thereto, and is received from the user terminal 110 among pre-generated or stored ballet accompaniments. The ballet accompaniment specified according to the user's selection may be reproduced as the basic ballet accompaniment. To this end, the ballet accompaniment reproducing unit 320 may utilize the ballet accompaniment stored in the database 150, and may receive ballet accompaniment from an external system that works with the ballet motion evaluation device 130 as needed.

The motion photographing unit 330 may capture the user's motion through a camera during reproduction of the basic ballet accompaniment. The ballet motion evaluation device 130 may capture the user's movement while the ballet accompaniment is played in order to evaluate the user's ballet motion. To this end, the camera that captures the motion of the user may have a fixed capturing area, and may operate in a state in which a capturing direction, a capturing resolution, a capturing magnification, and the like are specified for fair evaluation as well as the capturing area.

In addition, the motion photographing unit 330 may be implemented by including a camera that captures the user's motion or may operate in conjunction with an independent camera device. The motion photographing unit 330 may capture an image of a user's motion through a camera connected by wire or wirelessly.

In one embodiment, the motion capture unit 330 may capture the user's motion through a plurality of cameras. The motion photographing unit 330 may receive images or photos taken by the camera and store them in the database 150, and may include a motion analysis unit 340 that analyzes user movements or an evaluation performer 350 that evaluates ballet movements. ) can be passed directly to

In an embodiment, the motion photographing unit 330 may identify each of the plurality of users when a plurality of users are detected within the photographing area of the camera, and may generate and store an image related to motion for each user. Basically, evaluation of ballet motions may be performed for individual users, and evaluation of group ballet motions performed by two or more users may be performed as needed. The motion photographing unit 330 may identify each user present in the photographing area from the photographed image in the case of evaluation of a group ballet motion, and may extract an independent motion image for each user.

The motion analyzer 340 may determine a user ballet motion corresponding to the movement and generate a user ballet accompaniment matching the user ballet motion through an artificial intelligence model. That is, the user's ballet motion may correspond to a ballet motion corresponding to the user's motion, and may be determined according to the analysis result of the motion analyzer 340 . In addition, the motion analysis unit 340 may generate a user ballet accompaniment corresponding to the identified user ballet motion, and the user ballet accompaniment may be used as evaluation data for evaluating the user's ballet motion. For example, the ballet motion evaluation device 130 may perform a specific evaluation according to a result of comparing the user ballet accompaniment corresponding to the user's ballet motion and generated by the artificial intelligence model with the actually reproduced basic ballet accompaniment.

The motion analyzer 340 may determine a user's ballet motion from a video or image related to the user's motion by using a video analysis or image analysis algorithm. To this end, the motion analyzer 340 may utilize data about ballet motions defined in advance. That is, based on the information on the ballet movements stored in the database 150, a ballet movement most similar to the user's movement may be determined as the user's ballet movement.

In one embodiment, the motion analyzer 340 may determine the beat, tempo, dynamics, and velocity of the user's ballet motion, respectively. The motion analyzer 340 may determine a user ballet motion corresponding to the user's motion and express data on beat, tempo, dynamics, and velocity as specific numerical values as characteristic information on the user's ballet motion.

In one embodiment, the motion analyzer 340 may determine the beat, tempo, dynamics, and velocity of the user's ballet motion, respectively, based on a characteristic table defined for a plurality of ballet class motions. For example, the motion analyzer 340 may determine each beat, tempo, dynamics, and velocity corresponding to the user's ballet motion based on a predefined characteristic table as shown in FIG. 7 . That is, the characteristic table may correspond to a matching table specifically defining characteristics related to beat, tempo, dynamic range, and velocity for each ballet class motion. The characteristic table may be created in advance by the ballet motion evaluation device 130 and stored in the database 150 .

In one embodiment, the motion analyzer 340 may independently determine a user ballet motion corresponding to each user's motion when evaluation of a group ballet motion of a plurality of users is performed. In addition, the motion analyzer 340 may analyze a correlation between user ballet movements of each user. For example, the motion analysis unit 340 may calculate a similarity between user ballet movements, and the similarity information may then be transmitted to the evaluation performer 350 and used for evaluation of group ballet movements.

The evaluation performing unit 350 may generate an evaluation result for motion by comparing feature information of each of the basic ballet accompaniment and the user ballet accompaniment. The feature information defined for the musical elements of the ballet accompaniment may include count, form, phrase, beat, tempo, dynamic, etc., and the evaluation performer 350 individually analyzes the correlation between the feature information to obtain an evaluation result can create In addition, the evaluation performer 350 may calculate the similarity between the basic ballet accompaniment and the user ballet accompaniment as a result of integrating the results of individually analyzing the feature information, and based on this, the evaluation result for the user's movement can also create

In addition, the evaluation performer 350 may express the evaluation result as a specific numerical value. For example, the evaluation performer 350 may express the integrated evaluation result of the user's motion as a total evaluation score. The evaluation unit 350 may generate detailed evaluation scores for each item as an evaluation result, along with overall evaluation scores. The evaluation unit 350 may apply standardization, weighting, synthesis, grading, and the like in the process of generating a comprehensive evaluation result based on the evaluation result for each item.

The evaluation provider 360 may provide evaluation results to the user terminal 110 . The evaluation providing unit 360 may provide the evaluation results generated by the evaluation performing unit 350 through various graphic user interfaces (GUIs). The user terminal 110 may provide a dedicated interface for this, and various expression methods such as statistical tables and graphs may be applied. For example, the user terminal 110 visualizes a bar graph for expressing digitized evaluation scores, a line graph for comparison with previous evaluations, and a graph for visualizing structural characteristics such as the frequency and distribution of evaluation scores for each item. Evaluation results can be expressed effectively by using elements.

In one embodiment, the evaluation providing unit 360 may provide a recommendation of a ballet accompaniment suitable for the user's level together with the evaluation result of the user's movement. For example, when it is determined that a specific item is lower than the average as a result of the user's evaluation, the evaluation providing unit 360 may recommend usable ballet accompaniments to the user to supplement the corresponding item. In another embodiment, instead of recommending a ballet accompaniment suitable for the user's level, the evaluation providing unit 360 may express characteristic information of the corresponding ballet accompaniment as a specific numerical value and provide it to the user. The user may change the numerical value of a desired item based on the corresponding numerical value and input feedback therefor.

The feedback receiving unit 370 may receive feedback on the evaluation result from the user terminal 110 . In this case, the feedback may include a user input for changing a specific numerical value for a specific item after the user confirms the evaluation result. That is, the feedback receiving unit 370 may receive a specific numerical value for a specific item (musical element) among the evaluation items as feedback from the user, and the corresponding feedback is provided to the ballet accompaniment reproducing unit 320 to produce a basic ballet accompaniment. can be updated Through this, the user can increase the effect of practice by adjusting the level of difficulty of the ballet accompaniment through analysis of the evaluation result.

In one embodiment, the feedback receiving unit 370 may detect a change in the numerical value of a specific item among the numerical values for each item of the recommended ballet accompaniment provided to the user by the evaluation providing unit 360 and receive it as the user's feedback. there is. The evaluation providing unit 360 may recommend a predetermined ballet accompaniment together with the evaluation result, and may provide specific numerical values for each item as characteristic information of the recommended ballet accompaniment. When some of the numerical values for each item provided to the user are detected, the feedback receiving unit 370 may receive corresponding change information as feedback, and pass it to the ballet accompaniment reproducing unit 320 to update the basic ballet accompaniment provided to the user. can That is, as a result of the feedback information transmitted to the ballet accompaniment reproducing unit 320 being provided as an input of the artificial intelligence model, the basic ballet accompaniment generated by the artificial intelligence model may be updated.

The control unit 380 controls the overall operation of the ballet motion evaluation device 130, and the model building unit 310, the ballet accompaniment reproducing unit 320, the motion capturing unit 330, the motion analyzing unit 340, and evaluation are performed. A control flow or data flow between the unit 350, the evaluation providing unit 360, and the feedback receiving unit 370 may be managed.

4 is a flowchart illustrating an artificial intelligence-based ballet motion evaluation method using musical elements according to the present invention.

Referring to FIG. 4 , the ballet motion evaluation device 130 may build an artificial intelligence model for generating ballet class music matching the ballet class motion through the model building unit 310 (step S410). The artificial intelligence model may be generated as a result of defining feature information about musical elements of ballet class music and learning feature information about ballet music of a learning population.

The ballet motion evaluation device 130 may generate a basic ballet accompaniment using the artificial intelligence model previously built through the ballet accompaniment reproducing unit 320 and then play it through a speaker (step S430). The artificial intelligence model can generate ballet class music corresponding to a specific ballet class motion, and the ballet accompaniment reproducing unit 320 provides characteristic information about the ballet class motion to the artificial intelligence model as input data to generate a basic ballet accompaniment. can do. In one embodiment, the ballet accompaniment reproducing unit 320 may automatically reproduce a ballet accompaniment corresponding to the movement by analyzing the motion of the user photographed through the camera.

The ballet motion evaluation device 130 may capture the motion of the user through a camera during reproduction of the basic ballet accompaniment through the motion capture unit 330, and determine the user ballet motion corresponding to the motion through the motion analyzer 340. And it is possible to generate a user ballet accompaniment matching the user ballet motion through the artificial intelligence model (step S450).

The ballet motion evaluation device 130 may generate an evaluation result for motion by comparing feature information of each of the basic ballet accompaniment and the user ballet accompaniment through the evaluation unit 350 (step S470). In addition, the ballet motion evaluation device 130 may provide evaluation results to the user terminal 110 through the evaluation providing unit 360 .

9 is a diagram for explaining an embodiment of a ballet motion evaluation and feedback process according to the present invention.

Referring to FIG. 9 , the ballet motion evaluation device 130 may capture a user's motion through a camera in the process of reproducing a basic ballet accompaniment. The ballet motion evaluation device 130 analyzes the video captured by the camera to generate an evaluation result according to the degree to which the user's movement matches the basic ballet accompaniment, and provides it to the user through the user terminal 110. .

Through this, the user can check the evaluation of his/her own ballet movements, and can clearly recognize what he or she lacks through specific numerical values for each item. In addition, the user may input feedback on the evaluation result provided by the ballet motion evaluation device 130 .

For example, the user may input feedback for changing the numerical value of the corresponding item to compensate for the evaluation item lacking, and the ballet motion evaluation apparatus 130 receives the corresponding feedback and based on the variation of the numerical value. Renewal of ballet accompaniment may be performed (S930). If the user does not input separate feedback or if there is no change in specific numerical values even if the user inputs feedback, the ballet motion evaluation device 130 evaluates the user's motion while continuing to reproduce the existing basic ballet accompaniment. may be repeatedly performed (S910).

The ballet motion evaluation method and apparatus according to the present invention analyzes and defines the characteristics of ballet class music as basic data of a data set for implementing artificial intelligence ballet accompaniment, and learns the characteristic information derived from ballet music of a learning data population. An artificial intelligence model that generates ballet accompaniment can be built. In addition, the ballet motion evaluation and apparatus according to the present invention recognizes the user's motion and provides ballet accompaniment suitable for the user's ballet motion in real time to support the efficient progress of ballet classes and to maximize participation and efficiency of ballet classes. there is.

In addition, the ballet motion evaluation method and apparatus according to the present invention can evaluate the user's motion corresponding to the ballet accompaniment and provide the result. That is, the degree of matching between the ballet accompaniment and the user's ballet motion may be expressed as a specific numerical value and provided, and evaluation results subdivided for each musical element, which is characteristic information of the ballet accompaniment, may be provided. Through this, the user can check the musicality by himself during the ballet movement practice process, and the efficiency of the practice can be increased by practicing the ballet movement according to the ballet accompaniment suitable for the user's level.

Although the above has been described with reference to preferred embodiments of the present invention, those skilled in the art will variously modify and change the present invention within the scope not departing from the spirit and scope of the present invention described in the claims below. You will understand that it can be done.

100: ballet movement evaluation system
110: user terminal 130: ballet motion evaluation device
150: database
210: processor 230: memory
250: user input/output unit 270: network input/output unit
310: model building unit
311: genre classification module 312: feature extraction module
313: learning data generation module 314: model building module
320: ballet accompaniment playback unit
330: motion capture unit 340: motion analysis unit
350: evaluation performing unit 360: evaluation providing unit
370: feedback receiver 380: controller

Claims (13)

Building an artificial intelligence model that generates ballet class music that matches ballet class movements;
Reproducing a basic ballet accompaniment generated through the artificial intelligence model;
photographing a user's movement through a camera during reproduction of the basic ballet accompaniment;
determining a user ballet motion corresponding to the motion and generating a user ballet accompaniment matching the user ballet motion through the artificial intelligence model; and
Comparing feature information of each of the basic ballet accompaniment and the user ballet accompaniment to generate an evaluation result for the movement; including,
The constructing of the artificial intelligence model may include defining a plurality of genres of ballet music corresponding to a plurality of ballet class movements as first characteristic information of ballet class music; defining a plurality of characteristics of ballet music as second characteristic information of the ballet lesson music; And extracting the first and second characteristic information from a plurality of ballet music pieces, respectively, to generate learning data about the ballet class music;
The step of defining the plurality of ballet music characteristics includes defining form, phrase, beat, tempo, dynamic, velocity, accompaniment type, accent, and pedaling as the plurality of ballet music characteristics,
The step of generating the user ballet accompaniment includes determining motion characteristic information about beat, tempo, dynamic and velocity from the user ballet motion,
The generating of the evaluation result comprises: generating a first evaluation result related to the movement by mutually comparing feature information corresponding to the motion feature information among the feature information of the basic ballet accompaniment with the motion feature information; And generating a second evaluation result related to the motion by comparing feature information that does not correspond to the motion characteristic information among the characteristic information of the basic ballet accompaniment with the characteristic information of the user ballet accompaniment. A method for evaluating ballet movements based on artificial intelligence using musical elements.
delete According to claim 1,
The step of defining the plurality of ballet music genres
Music 1 is slow and graceful, Music 2 is relaxed at a normal tempo, Music 3 is graceful at a normal tempo, Music 4 is a bit fast and light, Music 5 is a bit fast and has an accent, Music 6 is a bit fast and accented, An artificial intelligence-based ballet motion evaluation method using musical elements, comprising the step of defining a fast, elegant and powerful seventh music and a fast and light eighth music as the plurality of ballet music genres.
delete According to claim 1,
Building the artificial intelligence model
Building a first artificial intelligence model for generating basic ballet class music matched with the plurality of ballet class movements; and
An artificial intelligence-based ballet motion evaluation method comprising the steps of constructing a second artificial intelligence model for generating ballet class applied music based on the ballet class basic music.
According to claim 1,
The step of reproducing the basic ballet accompaniment
An artificial intelligence-based ballet motion evaluation method using musical elements, comprising the step of converting and reproducing the basic ballet accompaniment into a performance of a single piano tone.
delete According to claim 1,
The step of generating the evaluation result is
Artificial intelligence-based ballet using musical elements comprising the step of generating the evaluation result by comparing only the characteristic information corresponding to the motion characteristic information among the characteristic information of the basic ballet accompaniment with the motion characteristic information. Motion evaluation method.
delete A model construction unit for building an artificial intelligence model that generates ballet class music that matches ballet class motion;
Ballet accompaniment reproducing unit for reproducing basic ballet accompaniment including characteristic information about musical elements of ballet class music;
a motion photographing unit for photographing a user's movement through a camera during reproduction of the basic ballet accompaniment;
a motion analyzer for determining a user ballet motion corresponding to the movement and generating a user ballet accompaniment matched to the user ballet motion through an artificial intelligence model; and
An evaluation performer for generating an evaluation result for the movement by comparing feature information of each of the basic ballet accompaniment and the user ballet accompaniment;
The model construction unit includes a genre classification module defining a plurality of ballet music genres corresponding to a plurality of ballet class movements as first characteristic information of ballet class music; a feature extraction module defining a plurality of features of ballet music as second feature information of the ballet lesson music; And a learning data generation module for extracting the first and second characteristic information from a plurality of ballet music pieces, respectively, and generating learning data about the ballet class music;
The feature extraction module defines form, phrase, beat, tempo, dynamic, velocity, accompaniment type, accent, and pedaling as the plurality of ballet music features,
The motion analyzer determines motion characteristic information about beat, tempo, dynamics, and velocity from the user's ballet motion;
generating a first evaluation result related to the movement by the evaluation unit comparing feature information corresponding to the motion feature information among the feature information of the basic ballet accompaniment with the motion feature information; And generating a second evaluation result related to the movement by comparing feature information that does not correspond to the motion feature information among the feature information of the basic ballet accompaniment with the feature information of the user ballet accompaniment. An artificial intelligence-based ballet motion evaluation device using musical elements to perform.
The method of claim 10, wherein the ballet accompaniment reproducing unit
An artificial intelligence-based ballet motion evaluation device using musical elements, characterized in that for reproducing, as the basic ballet accompaniment, a ballet accompaniment specified according to a user's selection received from a user terminal from among pre-generated or stored ballet accompaniments.
According to claim 10,
an evaluation providing unit providing the evaluation result to a user terminal; and
Ballet motion evaluation device based on artificial intelligence using musical elements, characterized in that it further comprises a; feedback receiver for receiving feedback on the evaluation result from the user terminal.
The method of claim 12, wherein the feedback receiver
When the feedback includes a numerical value related to the characteristic information of the basic ballet accompaniment, the characteristic information is updated to a corresponding numerical value and transmitted to the ballet accompaniment reproducing unit, thereby performing an operation of generating the basic ballet accompaniment by the artificial intelligence model. Artificial intelligence-based ballet motion evaluation device using musical elements, characterized in that for updating.

Images