KR102261548B1 - Apparatus of transforming art work into multimedia based on emotion - Google Patents

Abstract

The present invention comprises: a work input unit (100) for receiving text or voice, text and voice works from an artist or a system; a character input unit (200) that receives character information according to time information including a character name, age, gender, personality type, intimacy between the characters, and a relationship index between the characters from the writer or the system; a background information input unit (300) for receiving background information including historical information, spatial information, political information, and socio-cultural information according to time information from the writer or the system; a first emotion setting unit (400) for automatically setting and providing a first emotion, which is an initial value of emotion contained in the work, based on the information input from the character input unit and the background information input unit; and a first multimedia transforming unit (500) for automatically expressing the work audiovisually based on the basis of the first emotion. The present invention is to provide an apparatus for receiving text or voice, text and voice work from an artist or a system, analyzing the emotion of the work, and automatically converting the work into audiovisual, that is, multimedia, based on the emotion.

Description

A multimedia transformation device for works based on emotion {APPARATUS OF TRANSFORMING ART WORK INTO MULTIMEDIA BASED ON EMOTION}

The present invention relates to a multimedia conversion device for a work based on emotion, and more particularly, receives a text or voice, text and voice work from an artist or a system, analyzes the emotion of the work, and analyzes the emotion of the work. It relates to a multimedia conversion apparatus of a work based on emotion, which automatically converts the work audiovisually, that is, multimedia based.

Dutch cultural historian J. Heusinger has a view of humanity that grasps the essence of human beings in terms of play. Our human culture has developed through play, that is, entertainment. Today, we spend our time looking for entertainment through various video and audio content, especially online content such as YouTube. In the past, in the content market, there was only a market for paper books, but today's content is enjoying various contents such as e-books, audiobooks, and YouTube through eyes and ears.

Let's look at two aspects in this regard. The first aspect is that, in consideration of today's work activity that is different from the conventional one, instead of writing novels or essays by typing only text, modern writers consider other input methods such as voice and not only text, while , a device for receiving text input and automatically converting text into multimedia based on emotion has not been disclosed.

In the second aspect, all information and data, which is said to be the culmination of human intelligence, are written and in the form of books. Although mass-producing various other issues, Google is trying to digitize millions of books, but until now, a device that automatically converts texts and the like into multimedia based on emotions by receiving vast amounts of text information that existed in the past has been disclosed. there is no bar

As a related conventional patent document, Korean Patent Laid-Open Patent Publication No. 10-2009-0126862 (Applicant: NHN Diequest, Title of Invention: Sentiment information analysis system and method using natural language processing, emotional information analysis method using natural language processing in a computer In the recording medium storing the program for execution {SYSTEM AND METHOD FOR ANALYZING EMOTIONAL INFORMATION FROM NATURAL LANGUAGE SENTENCE, AND MEDIUM FOR STORAGING PROGRAM FOR THE SAME}), "The present invention provides an emotional information analysis system using natural language processing. In such a system, the analysis target document storage means maintains a plurality of natural language sentences that contain the speaker's emotions toward the evaluation target, and the sentiment information analysis server includes a morpheme analyzer that analyzes the natural language sentences in units of morphemes, and the analysis A semantic extractor that extracts a semantic tag representing the meaning of the morpheme from the morpheme and generates an abstract sentence composed of a combination of the morpheme and the semantic tag, and corresponds to the abstract sentence among a plurality of maintained pattern rules (LSP) A technical configuration including a rule processor that selects at least one pattern rule to be selected and calculates emotion information representing a speaker's emotion for an evaluation target contained in the abstract sentence with reference to the selected pattern rule" is disclosed.

As described above, although there are some technologies for natural language processing of text and analysis of morpheme units to find the speaker's emotions, there is an existing device or existing that receives text input and automatically converts text into multimedia based on emotion. A device for automatically converting books or texts into multimedia based on emotions by receiving vast amounts of book or text information has not been disclosed at all.

Korean Patent Laid-Open Patent No. 10-2009-0126862 (Applicant: NHN Die Quest, Title of Invention: System and method for analyzing emotional information using natural language processing, a record storing a program for executing a method for analyzing emotional information using natural language processing on a computer MEDIUM {SYSTEM AND METHOD FOR ANALYZING EMOTIONAL INFORMATION FROM NATURAL LANGUAGE SENTENCE, AND MEDIUM FOR STORAGING PROGRAM FOR THE SAME}

The present invention was created to solve the above problems, and an object of the present invention is to receive text or voice, text and voice works from an artist or a system, analyze the sensibility of the work, and based on the sensibility Therefore, it is to provide a multimedia conversion device for works based on emotion, which automatically converts the work audiovisually, that is, multimedia.

A multimedia conversion apparatus for a work based on emotion according to the present invention for achieving the above object, a work input unit 100 for receiving a work of text or voice, text and voice from an artist or a system; and a multimedia conversion unit that analyzes the emotion of the work and automatically expresses the work audiovisually based on the emotion.

In addition, the multimedia conversion apparatus for a work based on emotion according to the present invention includes: a work input unit 100 for receiving a work of text or voice, text and voice from an artist or a system; a character input unit 200 that receives character information according to time information including a character name, age, gender, personality type, intimacy between the characters, and a relationship index between the characters from the writer or the system; a background information input unit 300 for receiving background information including historical information, spatial information, political information, and socio-cultural information according to time information from the author or the system; a first emotion setting unit 400 for automatically setting and providing a first emotion, which is an initial value of emotion contained in the work, based on the information input from the character input unit and the background information input unit; and a first multimedia conversion unit 500 that automatically expresses the work audiovisually based on the first emotion.

In addition, a second emotion setting unit that receives information for correcting the first emotion of the work set by the first emotion setting unit from the artist or the system and sets a second emotion adjusted with the first emotion ( 450); it is preferable to further include.

In addition, the multimedia conversion unit, based on the audiovisual expression of the work that is the result of the first multimedia conversion unit 500, the first emotion through the second emotion setting unit 450 from the author or the system and a second multimedia conversion unit 550 for receiving the second emotion adjusted by , and automatically expressing the work audiovisually.

In addition, it is preferable that the work is one of genre novels including science fiction novels, martial arts novels, fantasy novels, mystery novels, horror novels, and romance novels.

In addition, the time information is set according to the event development information of the genre novel, and the character information includes the character name, age, gender, personality type, intimacy between the characters, and the character information according to the event development information of the genre novel. It includes a relationship index between characters, and the background information preferably includes epochal information, spatial information and political information, and socio-cultural information according to the event development information of the genre novel.

In addition, when the first emotion setting unit 400 automatically sets the first emotion, which is the initial value of the emotion contained in the work, the natural language processing unit processes the text as natural language, and the morpheme analysis unit analyzes the text in units of morphemes. , based on the emotion dictionary, the emotion analysis unit analyzes the emotion of the text to automatically express the work audiovisually, but if there is an emoticon included in the text from the author or the system, the emoticon takes precedence It is preferable to automatically express the work audiovisually by analyzing the emotion of the text.

In addition, when there is no input of the personality type from the writer or the system, the character of the genre novel may be profiled and set as one of the pre-stored typical personality types.

In addition, it is preferable that the sentiment dictionary is an expandable variable dictionary in which a machine-learned sentiment word is added in a data processing process to an initially set sentiment dictionary indicating emotion.

In addition, when the first emotion setting unit 400 automatically sets the first emotion, which is the initial value of the emotion contained in the work, the artist's biosignal sensor, which operates in conjunction with the work input unit 100, Based on the audio sensor and the camera sensor, based on the sensing result value of the biosignal sensor, the sensing result value of the audio sensor, and the sensing result value obtained through image processing obtained from the camera, the first emotion can be set.

In addition, the visual expression in the first multimedia conversion unit and the second multimedia conversion unit is to type each Hangul character in the form of typing the text so as to induce the reader's gaze, but by adjusting the speed of the typing, Adjusting the font size of the text, adjusting the font color of the text, applying an emotional effect to the characters of the text, or visually expressing a specific object appearing in the text on a layer, the second multimedia The auditory expression in the conversion unit and the second multimedia conversion unit may change the speaker who reads the text or adjust the reading speed of the speaker, adjust the volume of the speaker's reading voice, or in the reading of the speaker. It is preferable to apply an emotional effect or to output a specific object appearing in the reading over the layer of the speaker's reading voice.

According to the multimedia conversion apparatus of the work based on the emotion according to the present invention,

First, receiving a text or voice, text and voice work from the artist or from the system, analyzing the emotion of the work, and automatically converting the work into audiovisual, that is, multimedia, based on the emotion It is possible.

Second, through the character input unit 200, it is possible to receive character information according to time information including a character name, age, gender, personality type, intimacy between characters, and a relationship index between characters from a writer or system, It is possible to increase the effectiveness of setting the initial value of emotion setting or emotion derivation. As a result, it is possible to reduce the waste of time or effort of the writer.

Third, through the background information input unit 300, it is possible to receive background information, including historical information, spatial information, political information, and socio-cultural information according to time information, from an artist or system, so that it is possible to set emotions or derive emotions. The validity of the initial value setting can be increased. As a result, it is possible to reduce the waste of time or effort of the writer.

Fourth, through the second multimedia conversion unit 550, the artist verifies the audiovisual data of the work temporarily created by the first multimedia conversion unit 500, it is possible to set the second emotion to adjust the first emotion Do.

Fifth, if there is an emoticon included in the text from the author or the system, it is possible to apply the emoticon first, analyze the emotion of the text, and automatically express the work audiovisually.

Sixth, if there is no personality type input from the writer or the system, or if supplementation is needed, the character of the genre novel is profiled using the profiling technique used in OBA (online behavior advertisement), etc., and stored in advance. By setting it as one of the typical personality types that exist, it is possible to increase the effectiveness of setting the initial value of emotion setting or emotion elicitation. As a result, it is possible to reduce the waste of time or effort of the writer.

Seventh, considering the case of a new word that has never appeared before or the author's destructive word selection, the emotional dictionary uses the emotional dictionary set at the beginning to express emotions, and the emotional words that are machine-learned (deep learning, etc.) in the data processing process. It is possible to improve the validity of setting the initial value of emotion setting or emotion derivation by including an expandable variable dictionary that adds .

Eighth, when the first emotion setting unit 400 automatically sets the first emotion, which is the initial value of the emotion contained in the work, a biosignal sensor (eg, ECG, EEG, blood pressure sensor, heart rate sensor, etc.), audio sensor (eg, microphone, audio frequency analysis or spectrum analyzer, etc.), and the camera sensor, the sensing result of the biosignal sensor, the sensing result of the audio sensor, and the camera Thus, it is possible to set the first emotion based on the sensing result value derived through image processing, thereby improving the accuracy of emotion setting or emotion derivation.

Ninth, through the visual expression and auditory effect in the first multimedia conversion unit and the second multimedia conversion unit, it is possible to induce a higher degree of concentration than the reader's interest in the text, the reader's gaze, and to deliver emotions it is possible

1 is a block diagram schematically showing an apparatus for converting a multimedia work based on emotion according to a preferred embodiment of the present invention.
2 is a diagram illustrating character information input to the character input unit 200 of the multimedia conversion apparatus for a work based on emotion according to a preferred embodiment of the present invention.
3 is a diagram illustrating character information input according to time information, for example, event development information, with respect to the character input unit 200 of the multimedia conversion apparatus for a work based on emotion according to a preferred embodiment of the present invention.
4 is a diagram illustrating background information input to the background information input unit 300 of the apparatus for converting a multimedia work based on emotion according to a preferred embodiment of the present invention.
5 is a diagram illustrating input of background information according to time information, for example, event development information, to the background information input unit 300 of the apparatus for converting a multimedia work based on emotion according to a preferred embodiment of the present invention.
6 is a diagram illustrating natural part processing, morpheme analysis, emotion dictionary unit, and emotion analysis unit of the multimedia conversion device for works based on emotion according to a preferred embodiment of the present invention.
7 is a view showing Korean morphemes and Korean morpheme codes used by the morpheme analysis unit of the multimedia conversion device for works based on emotion according to a preferred embodiment of the present invention.

Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Prior to this, the terms or words used in the present specification and claims should not be construed as being limited to conventional or dictionary meanings, and the inventor should properly understand the concept of the term in order to best describe his invention. Based on the principle that can be defined, it should be interpreted as meaning and concept consistent with the technical idea of the present invention.

Accordingly, the configuration shown in the embodiments and drawings described in the present specification is only the most preferred embodiment of the present invention and does not represent all the technical spirit of the present invention, so at the time of the present application, various It should be understood that there may be equivalents and variations.

(A multimedia conversion device for works based on emotions)

1 is a block diagram schematically showing an apparatus for converting a multimedia work based on emotion according to a preferred embodiment of the present invention.

As shown in FIG. 1 , the multimedia conversion apparatus for a work based on emotion according to the present invention includes a work input unit 100 , a character input unit 200 , a background information input unit 300 , a first emotion setting unit 400 and It includes a first multimedia conversion unit (500).

First, the work input unit 100 receives text or voice, text and voice works from an artist or a system. Here, writers include genre novelists including science fiction novels, martial arts novels, fantasy novels, mystery novels, horror novels, and romance novels, as well as other essays, general novels, screenplays, and plays. Likewise, it is desirable that the work be one of genre novels including science fiction, martial arts novels, fantasy novels, mystery novels, horror novels, and romance novels, but of course it may be other literary works.

Here, receiving works from the system automatically converts novels that existed in the form of vast texts back to modern multimedia, taking into account the character's sensibility, context or fingerprint sensibility, sociocultural sensibility or situational sensibility, and the atmosphere of the times. It refers to the input for converting into multimedia combined with emotion.

(character input section)

2 is a view showing character information input to the character input unit 200 of the multimedia conversion device for a work based on emotion according to a preferred embodiment of the present invention, and FIG. 3 is an emotion-based work based on emotion according to a preferred embodiment of the present invention. It is a diagram illustrating input of character information according to time information, for example, event development information, to the character input unit 200 of the multimedia conversion device of the work.

As shown in FIGS. 2 and 3 , the character input unit 200 is, systematically from the author or system, the character's name (stage name, nickname, nickname, nickname, etc.), age, gender, personality type, and intimacy between the characters. , and character information according to time information including a relationship index between characters is received.

Here, the time information may represent the development of events or the flow of time of the work. More specifically, it may be set according to the event development information of the genre novel. That is, the character information includes a character name, age, gender, personality type, intimacy between the characters, and a relationship index between the characters according to the event development information of the genre novel. The form stored in the database is a three-dimensional form that considers the divergence, merging, or reverse flow of forms according to the sequence of time in consideration of omnibus event development or type slip type event development. and time order can be a mapping.

For example, in case 1, two college student men (C2, C3) who are close friends meet a beautiful mysterious woman (C1). You can express the feeling of youth, which is lovely and spring-like. Later, in case 4, two men (C2, C3) fall in love with C1, and the two men enter the composition in which they become enemies by expressing the intimacy between the characters or the relationship index between the characters, and based on this, the text is entered. When adding emotion, the first emotion is set based on the intimacy between the characters and/or the relationship index between the characters.

(background information input unit)

4 is a view showing the input of background information to the background information input unit 300 of the multimedia conversion apparatus for a work based on emotion according to a preferred embodiment of the present invention, and FIG. 5 is a view showing the emotion based on the emotion according to the preferred embodiment of the present invention. It is a diagram illustrating input of background information according to time information, for example, event development information, to the background information input unit 300 of the multimedia conversion apparatus for a work based on the work.

As shown in FIGS. 4 and 5 , the background information input unit 300 may receive an input from, for example, a writer of a genre novel or may receive an input from a system in a systematic manner. Background information including temporal information, spatial information, political information, and socio-cultural information according to temporal information is input.

Here, the background information preferably includes, for example, historical information, spatial information and political information, and socio-cultural information according to the event development information of the genre novel. I was living in Seoul. Light and lively emotions can be expressed in voice or text typing that describes the text of Event 1. However, due to an unknown reason, the time slip to Hanyang in 1395 in the early Joseon Dynasty can capture the appearance of the early Joseon sensibly in Case 2, and in Case 3 and 4, the appearance of the early Ming Dynasty in Nanjing and Beijing in China is spatially and It can be emotionally contained in accordance with the political, socio-cultural situation or background. However, this is to set the default value, and it can be used in the basic background explanation. That is, it goes without saying that dialogue between characters may be set differently in context or context.

(Multimedia converter)

Next, as shown in FIG. 1 , the first first emotion setting unit 400 is based on the information input from the above-described character input unit 200 and background information input unit 300 , the initial emotion contained in the work. The first emotion, which is a value, is automatically set and provided. By doing this, it is possible to increase the efficiency of the automatic multimedia conversion device containing emotion.

It can be quite inefficient if the artist sets all the emotions, but firstly, the first emotion, which is the initial value of the emotion contained in the work, is automatically set, and the first emotion is verified and corrected or supplemented as described later by the artist, If the first emotion is right for the artist to feel, it can be left as it is.

That is, the second emotion setting unit 450 is further included to receive information for correcting the first emotion of the work set by the above-described first emotion setting unit from the artist or the system and adjust the first emotion. 2 Set the emotion.

At this time, the first multimedia conversion unit 500 automatically expresses the work audiovisually based on the first emotion as described above. The artist verifies the audiovisual material of the work temporarily created by the first multimedia conversion unit 500, and it is possible to set the second emotion to adjust the first emotion.

Thereafter, the multimedia converter may further include a second multimedia converter 550 . That is, based on the audiovisual expression of the work, which is the result of the first multimedia conversion unit 500 , the second emotion adjusted through the second emotion setting unit 450 is received from the artist or the system. , based on the result value, it is possible to automatically express the work audiovisually.

Visual expression in the multimedia conversion unit is, for example, typing each Hangul character in the form of typing to induce the reader's gaze on the text, but adjusting the typing speed, adjusting the font size of the text, or Adjusting the color of the text, emotional effects on the letters of the text (e.g. the letters are shaking in cold weather, the letters are shaking to represent that the character is shaking because of the object of fear, or the letters are sweating in hot weather) Or, to express that the character is sweating in a difficult situation, the character is sweating, or the character is unconscious and the character collapses) is possible. In addition, if a seagull appears on the beach, the seagull object may be overlaid on the image layer and displayed.

In addition, the auditory expression in the multimedia conversion unit, for example, adjusts the speed of the speaker reading the text, adjusts the speaker's voice volume, or the emotional effect of the speaker (a happy voice if happy, sad voice if sad) expressed as ), it is possible to In addition, if a seagull appears at the beach, it can be output by overlaying the previously stored seagull voice on the speaker's reading voice layer.

(character profiling)

If there is no input of a personality type from the writer or the system, the character of the genre novel may be profiled and set as one of the pre-stored typical personality types.

The typical personality type is entered by organizing and entering the most typical personality type among the protagonists of various genre novels that are generally published. For example, the Don Quiote personality type, etc. Through such character profiling, by identifying which personality type group the corresponding character belongs to, it is used as basic information when setting the first emotion based on the typical personality type.

On the other hand, even if there is a personality type input, it is possible to provide an adjustment value to the reader if it does not fit the character profiling analysis result.

(Emotional Dictionary)

In addition, it is preferable that the sentiment dictionary be an expandable variable dictionary in which emotional words that are machine-learned (deep learning, etc.) are added in the data processing process to the sentiment dictionary that is initially set for expressing emotions. By systematically analyzing previously accumulated data, it is possible to expand the emotional dictionary. This can be effective in the case of a new word that has never appeared before or the author's destructive word choice. It is also possible to set the emotional dictionary differently for each author, period, or country.

(Technology for improving the accuracy of emotional derivation)

6 is a view showing the natural part processing, morpheme analysis, emotion dictionary unit, and emotion analysis unit of the multimedia conversion device for works based on emotion according to a preferred embodiment of the present invention, and FIG. 7 is a view showing emotion analysis according to a preferred embodiment of the present invention. It shows Korean morphemes and Korean morpheme codes used by the morpheme analysis unit of the multimedia conversion device of the based work.

6 and 7, when the first emotion setting unit 400 automatically sets the first emotion, which is the initial value of the emotion contained in the work, the natural language processing unit 510 processes the text in natural language, The morpheme analyzer 520 analyzes the morpheme unit, and the emotion analyzer 540 analyzes the emotion of the text based on the emotion dictionary 530 and automatically expresses the work audiovisually. Here, the sentiment analysis of the text is set for each word, each sentence, each paragraph, and each event.

At this time, if there is an emoticon included in the text from the author or the system, it is preferable to apply the emoticon first, analyze the emotion of the text, and automatically express the work audiovisually. For example, if there is a heart emoticon of love, it is expressed visually (expressed in pink, etc.) and aurally (selected as a speaker in a lovely voice, etc.) as a lovely atmosphere.

In addition, when the first emotion setting unit 400 automatically sets the first emotion, which is the initial value of the emotion contained in the work, the work input unit 100, for example, the artist's voice when the work is performed with voice. A biosignal sensor (e.g., ECG, EEG, blood pressure sensor, heart rate sensor), an audio sensor (eg, a microphone, an audio frequency analysis or spectrum analyzer, etc.), and a camera sensor, the sensing result value of the biosignal sensor, the sensing result value of the audio sensor, the It is possible to set the first emotion based on the sensing result value obtained through image processing obtained from the camera to improve the accuracy of emotion setting or emotion derivation.

As described above, although the present invention has been described with reference to limited embodiments and drawings, the present invention is not limited thereto, and the technical spirit of the present invention and the following by those of ordinary skill in the art to which the present invention pertains. It goes without saying that various modifications and variations are possible within the scope of equivalents of the claims to be described.

(Explanation of symbols)

100...Artwork input

200...character input

300...Background information input

400... 1st emotion setting unit

450...Second emotional setting unit

500... first multimedia conversion unit

510...Natural Language Processing Unit

520... morpheme analysis unit

530...Emotional Dictionary

540...Sentiment Analysis Department

550...Second multimedia conversion unit

Claims (11)

a work input unit 100 for receiving text or voice, text and voice works from an artist or a system; and a multimedia conversion unit that analyzes the emotion of the work and automatically expresses the work audiovisually based on the emotion.
a character input unit 200 that receives character information according to time information including a character name, age, gender, personality type, intimacy between the characters, and a relationship index between the characters from the writer or the system; and
a background information input unit 300 for receiving background information including historical information, spatial information, political information, and socio-cultural information according to time information from the author or the system;
a first emotion setting unit 400 for automatically setting and providing a first emotion, which is an initial value of emotion contained in the work, based on the information input from the character input unit and the background information input unit; and
Based on the first emotion, the first multimedia conversion unit 500 for automatically expressing the work audiovisually; further comprising,
A second emotion setting unit 450 that receives information for correcting the first emotion of the work set by the first emotion setting unit from the artist or the system and sets a second emotion adjusted with the first emotion further including;
The multimedia conversion unit,
Based on the audiovisual expression of the work, which is the result of the first multimedia conversion unit 500, the second emotion adjusted by the author or the system through the second emotion setting unit 450 and a second multimedia conversion unit 550 for receiving the input and automatically expressing the work audiovisually;
The above work is one of the genre novels including science fiction novels, martial arts novels, fantasy novels, mystery novels, horror novels, and romance novels,
The time information is set according to the event development information of the genre novel,
The character information includes the character name, age, gender, personality type, intimacy between the characters, and a relationship index between the characters according to the event development information of the genre novel,
The background information, characterized in that it includes historical information, spatial information and political information, and socio-cultural information according to the event development information of the genre novel,
Multimedia conversion device for works based on emotion
delete delete delete delete delete The method of claim 1,
When the first emotion setting unit 400 automatically sets the first emotion, which is the initial value of the emotion contained in the work, the natural language processing unit processes the text in natural language, the morpheme analysis unit analyzes the text in units of morphemes, and the emotion On the basis of the dictionary, the emotion analysis unit analyzes the emotion of the text to automatically express the work audiovisually, but if there is an emoticon included in the text from the author or the system, the emoticon takes precedence over the text. Characterized in automatically expressing the work audiovisually by analyzing the emotion,
A multimedia conversion device for works based on emotion.
8. The method of claim 7,
Characterized in that when there is no input of the personality type from the writer or the system, the character of the genre novel is profiled and set as one of the pre-stored typical personality types,
A multimedia conversion device for works based on emotion.
9. The method of claim 8,
The sentiment dictionary is an expandable variable dictionary that adds machine-learned sentiment words in a data processing process to an initially set sentiment dictionary indicating emotions,
A multimedia conversion device for works based on emotion.
10. The method of claim 9,
When the first emotion setting unit 400 automatically sets the first emotion, which is the initial value of the emotion contained in the work, the artist's biosignal sensor and audio sensor that operate in conjunction with the work input unit 100 , and based on the camera sensor, based on the sensing result value of the biosignal sensor, the sensing result value of the audio sensor, and the sensing result value obtained through image processing obtained from the camera, setting the first emotion characterized in that
A multimedia conversion device for works based on emotion.
11. The method of claim 10,
The visual expression in the first multimedia conversion unit and the second multimedia conversion unit is to type each Hangul character in the form of typing the text so as to induce a reader's gaze, but by adjusting the speed of the typing, or by adjusting the speed of the text Adjusts the font size of the text, adjusts the text color of the text, applies an emotional effect to the text text, or visually expresses a specific object appearing in the text layer over the layer,
The auditory expression in the second multimedia conversion unit and the second multimedia conversion unit may change a speaker who reads the text or adjust the reading speed of the speaker, adjust the volume of the speaker's reading voice, or the Characterized in that an emotional effect is applied to the speaker's reading, or a specific object appearing in the reading is overlaid on the speaker's reading voice layer and output.
A multimedia conversion device for works based on emotion.

Images