KR20180094738A - Apparatus and method for digitizing sentiment and predicting climax using the same - Google Patents

Abstract

Disclosed are an apparatus for digitizing emotion and predicting a climax using the same and a method thereof. The apparatus for digitizing emotion and predicting a climax using the same comprises: a memory for storing at least one text related to an emotional state and a database in which positive or negative emotion strength of the at least one text is digitized; an emotional state digitizing unit for dividing a scenario or script into a plurality of scenes and extracting a text related to an emotional state included in each scene to search for the database of the memory and to calculate a sum of emotion values corresponding to the extracted text related to the emotional state; a window application unit for calculating an average of the emotion values by grouping the scenes into a window including a set number of scenes, and calculating an average of the emotion values by sequentially moving the window by one scene with respect to the scenes; a graphic generation unit for displaying, as a graph, an average of emotion values of each of the set number of scenes to which the window calculated in the window application unit is applied; and a climax prediction unit for predicting a climax by using the graph displayed in the graphic generation unit. According to the present invention, it is possible to digitize an emotional state of a text to objectively display the same and to accurately predict a climax by using a curve of an objectified emotional state.

Description

[0001] APPARATUS AND METHOD FOR DIGITIZING SENTIMENT AND PREDICTING CLIMAX USING THE SAME [0002]

The present invention relates to an empirical quantification method for predicting a climax of a movie using emotion information of a text included in a scenario, and a climax prediction apparatus and method using the same.

Video culture contents consist of value chain of various industry and distribution organization. In other words, it is considered to be a technology environment in which contents are naturally converged in the process of communication between networks because network technology enables mutual organic combination between all devices.

In addition, a complex academic process is required through each of various devices, and a standardization work is also required. This complex value chain improves the added value when interfacing with Web platform technology.

The field of computer graphics technology, which is related to video culture contents, is a field that has a large ripple effect on all industries such as games, animation, and e-Learning. It is a leading core technology.

Especially, the base of the video culture contents is a scenario, a literature, a script having a narrative structure, and a scenario, a literature, a script etc. have a narrative structure. Conventionally, in order to analyze the movie culture contents, the flow of the movie or the climax is searched based on the short-list data of the movie, or the flow of the movie based on the sound, Respectively.

However, in order to understand the flow of movie culture contents, it is necessary to study methods for analyzing the narrative structure itself such as scenarios, literatures, scripts, etc.

In order to solve the above-mentioned problems and other problems, it is an object of the present invention to detect a climax of a movie by analyzing texts included in a scenario, a literature, and a script as a basis of movie culture contents.

According to an aspect of the present invention there is provided a computer program product comprising a memory, a scenario, or a scenario for storing a database of at least one text associated with an emotional state, the emotional intensity of the at least one text being affirmative or negative, An emotion state quantization unit for dividing the scene into a plurality of scenes, extracting text related to the emotion state included in each scene, searching the database of the memory, and calculating a sum of emotion values corresponding to the text related to the extracted emotion state, Calculating an average of the emotion values by grouping the plurality of scenes into a window including a set number of scenes, sequentially moving the windows one by one for the plurality of scenes, and calculating an average of the emotion values A window application unit, a window application unit, And a climax predictor for predicting the climax using the graph shown in the graphic generator, and a climax prediction unit using the empirical quantification and the climax prediction unit, Lt; / RTI >

Here, the climax prediction unit may predict a scene corresponding to a period in which the slope of the graph fluctuates by more than a reference value, with a climax.

When a plurality of intervals in which the slope of the graph fluctuates by more than a reference value are detected, the climax prediction unit determines a scene corresponding to the interval having the largest slope among the plurality of intervals as a climax, You can decide by climax.

The emotion quantification according to the present invention and the effect of the climax prediction apparatus using the same will be described as follows.

According to at least one of the embodiments of the present invention, the emotion state of the text can be numerically displayed and displayed objectively, and the climax can be accurately predicted by using the objectized emotional state curve.

Further scope of applicability of the present invention will become apparent from the following detailed description. It should be understood, however, that the detailed description and specific examples, such as the preferred embodiments of the invention, are given by way of illustration only, since various changes and modifications within the spirit and scope of the invention will become apparent to those skilled in the art.

FIG. 1 is a block diagram of an empirical quantification and a climax prediction apparatus using the same according to an embodiment of the present invention.
FIG. 2 is a flowchart of emotion quantification and a climax prediction method using the emotion quantification according to an embodiment of the present invention.
FIGS. 3 to 5 are diagrams for explaining emotion quantification and a climax prediction method using the emotion quantification according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings, wherein like reference numerals are used to designate identical or similar elements, and redundant description thereof will be omitted. The suffix "module" and " part "for the components used in the following description are given or mixed in consideration of ease of specification, and do not have their own meaning or role. In the following description of the embodiments of the present invention, a detailed description of related arts will be omitted when it is determined that the gist of the embodiments disclosed herein may be blurred. It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory and are intended to provide further explanation of the invention as claimed. , ≪ / RTI > equivalents, and alternatives.

Terms including ordinals, such as first, second, etc., may be used to describe various elements, but the elements are not limited to these terms. The terms are used only for the purpose of distinguishing one component from another.

It is to be understood that when an element is referred to as being "connected" or "connected" to another element, it may be directly connected or connected to the other element, . On the other hand, when an element is referred to as being "directly connected" or "directly connected" to another element, it should be understood that there are no other elements in between.

The singular expressions include plural expressions unless the context clearly dictates otherwise.

In the present application, the terms "comprises", "having", and the like are used to specify that a feature, a number, a step, an operation, an element, a component, But do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, or combinations thereof.

The climax prediction apparatus described in this specification includes a mobile phone, a smart phone, a digital broadcasting terminal, a personal digital assistant (PDA), a portable multimedia player (PMP), a tablet PC, an ultrabook, Devices (wearable devices, e.g., smartwatches, smart glasses, head mounted displays (HMDs)), and the like.

FIG. 1 is a block diagram of an empirical quantification and a climax prediction apparatus using the same according to an embodiment of the present invention.

Referring to FIG. 1, an empirical quantification and climax prediction apparatus 100 according to an embodiment of the present invention includes a memory 110, emotion state values and units 120, a window application unit 130, (140), and a climax prediction unit (150).

The memory 110 may store a database that numerically quantifies the affirmative or negative emotional intensity of at least one text, at least one text, associated with the emotional state. For example, a neutral word such as 'shame' related to the emotional state has an emotional score of '0', a negative word like 'sadness' has an emotional score of '-1' Quot; 1 " to be stored in the database. In addition to the words exemplified above, a plurality of words can be stored in the database, and can be databaseized so that the same emotion score is matched according to the type change of the word, for example, a change in the form of a predicate, a noun, an adjective,

The emotion state quantization unit 120 may divide a scenario or a script into a plurality of scenes and extract text related to the emotion state included in each scene. The emotion state quantization unit 120 may search the database of the memory 110 and calculate the sum of the emotion values corresponding to the text related to the extracted emotion state. For example, among the texts included in the 1st scene, the text stored in the database is 100 words, and the sum total of the emotion values of 100 words can be added. If the scenario or the script is composed of 16 scenes, the sum of emotion values of each of 16 scenes can be calculated.

The window application unit 130 may group a plurality of scenes into windows including a predetermined number of scenes to calculate an average of emotion values. The window application unit 130 may calculate the average of the emotion values by sequentially moving the windows one by one for a plurality of scenes. Specifically, when the scenario or scenario is composed of 16 scenes and the size of the window is set to include 4 scenes, the window application unit 130 applies the window to the first scene to the fourth scene, The average of the emotion values of the fourth scene can be calculated. Next, the window application unit 130 moves the window to set the second to fifth scenes to be included, calculates the average of the emotion values, and sequentially shifts the images to include the 13th to 16th scenes After the window is moved to calculate the average of the emotion values, the execution can be completed. In this case, the average of the emotion values is the sum of the emotion values of the four scenes included in the window divided by four.

The graph generating unit 140 may graphically represent an average of the emotion values of the predetermined number of scenes to which the window calculated by the window applying unit 130 is applied.

The climax prediction unit 150 can predict the climax using the graph shown in the graphic generator 140. [ Specifically, the climax prediction unit 150 can predict a scene corresponding to a section where the slope of the graph fluctuates by more than the reference value, by using the climax. In addition, when a plurality of intervals where the slope of the graph fluctuates more than the reference value are detected, the climax prediction unit 150 determines a scene corresponding to the interval having the largest slope among a plurality of intervals as a climax, Can be determined as the subclimax.

FIG. 2 is a flowchart of emotion quantification and a climax prediction method using the emotion quantification according to an embodiment of the present invention.

Referring to FIG. 2, emotional quantification and climax prediction method related to an embodiment of the present invention quantifies text extracted from each scene of a scenario or a scenario using an emotion state database, processes numerical scores, Can be predicted.

Specifically, the emotional quantification and the climax prediction method using the same may store the emotion state database (S210), and calculate the emotion value of the text included in each scene of the scenario or the script (S220).

The process of storing the emotional state database may store and store a plurality of words in a database by matching emotional values according to the representative type, the change type, the affirmation or the unjustness of the words related to the emotional state. In addition, the emotion value can be set to various values such as 0, +1, +2, +3, -1, -2, -3 depending on the degree of affirmation or negation of each word. The above emotion value can be changed by the user, and a new word can be stored.

The process of calculating the text included in each scene of the scenario or the scenario as the emotion value is performed by dividing the scenario or the script into a plurality of scenes according to the set conditions, dividing the sentences included in each scene into words, . ≪ / RTI > At this time, the corresponding item of the database can be searched by considering the form of each word.

Next, the emotion quantification and the climax prediction method using the emotion quantification may apply a window to a plurality of scenes of the scenario or the script (S230), and determine whether the final scene is included in the window (S240).

If it is determined that the last scene is included in the window, the movement of the window may be stopped and the average of the emotion value of each window may be calculated and displayed as a graph (S260).

On the other hand, if the window does not include the last scene, the window can be shifted sideways by one scene (S250), and the calculation of the emotion value average can be repeated. That is, when the size of the window is configured to include four scenes, when the window moves once, three scenes overlap and only one scene is newly incorporated so that the total sum of emotion values of each scene is compared with a graph It can be controlled to be relatively rough.

Finally, the process of predicting the climax (S270) can be predicted by the climax of the movie when the absolute value of the graph slope is greater than the reference value, that is, when the emotional state change is large. When a plurality of intervals in which the absolute value of the gradient of the graph is greater than or equal to the reference value are detected, all of the scenes corresponding to the plurality of intervals may be determined as the climax, or only the interval corresponding to the maximum slope may be determined as the climax. The criteria for determining the climax can be set differently.

FIGS. 3 to 5 are diagrams for explaining emotion quantification and a climax prediction method using the emotion quantification according to an embodiment of the present invention.

3 is a view for explaining a method of applying a window to a scenario or a scenario composed of N SCENEs.

Referring to FIG. 3, the climax prediction apparatus can set four SCENEs as one window W and calculate an average of the textual emotion values of SCENE included in the window W. FIG. After calculating the average of the text emotion values of 1-SCENE to 4-SCENE, the window W can be moved to calculate the average of the text sensation values of the following SCENEs, 2-SCENE to 5-SCENE.

In this way, the average of text emotion values can be calculated by moving the window W to be included in the window W up to N-SCENE.

FIGS. 4 to 5 are graphs showing emotion values of each SCENE.

If the average of the text emotion values included in each SCENE is directly plotted, the variation rate between the SCENEs is large and the climax prediction may be inaccurate (FIG. 4). On the other hand, when the window is applied and the average of the text emotion values included in each SCENE is shown in a graph, the graph can be roughly changed by the influence of the emotion value of adjacent SCENEs, and the accuracy of the climax prediction can be improved.

According to the present invention, the objectivity and accuracy of the climax prediction of a movie using a scenario or a script can be enhanced by using the emotion value of the text included in the scenario or the script.

The present invention described above can be embodied as computer-readable codes on a medium on which a program is recorded. The computer readable medium includes all kinds of recording devices in which data that can be read by a computer system is stored. Examples of the computer readable medium include a hard disk drive (HDD), a solid state disk (SSD), a silicon disk drive (SDD), a ROM, a RAM, a CD-ROM, a magnetic tape, a floppy disk, , And may also be implemented in the form of a carrier wave (e.g., transmission over the Internet). Also, the computer may include a control unit 180 of the terminal. Accordingly, the above description should not be construed in a limiting sense in all respects and should be considered illustrative. The scope of the present invention should be determined by rational interpretation of the appended claims, and all changes within the scope of equivalents of the present invention are included in the scope of the present invention.

100: climax layer apparatus
110: memory 120: emotional state digitizing unit
130: window application unit 140: graphics generation unit
150: Climax prediction unit

Claims (3)

At least one text associated with an emotional state; a memory for storing a database of numerical values of an affirmative or negative emotional intensity of the at least one text;
An emotion that calculates the sum of the emotion values corresponding to the text related to the extracted emotion state by dividing the scenario or the scenario into a plurality of scenes, extracting texts related to the emotion states included in each scene, State quantization unit;
Calculating an average of the emotion values by grouping the plurality of scenes into a window including a set number of scenes, sequentially moving the windows one by one for the plurality of scenes, and calculating an average of the emotion values A window application unit;
A graphical generation unit for graphically representing an average of emotion values of each of the predetermined number of scenes to which the window is applied, calculated by the window application unit; And
A climax prediction unit for predicting the climax using the graph shown in the graphic generation unit;
And a climax prediction device using the same.
The method according to claim 1,
Wherein the climax prediction unit predicts a scene corresponding to an interval in which the slope of the graph fluctuates by at least a reference value, using a climax, and a climax prediction apparatus using the same.
3. The method of claim 2,
Wherein the climax prediction unit determines a scene corresponding to an interval in which the slope is the largest among the plurality of intervals as a climax when a plurality of intervals in which the slope of the graph fluctuates more than a reference value are detected, And the climax is determined as a climax.

Images