KR20180013777A - Apparatus and method for analyzing irregular data, a recording medium on which a program / application for implementing the same - Google Patents

Abstract

Disclosed are an unstructured data analyzing technology device, a method thereof, and a recording medium recorded with an application/program for implementing the same. The unstructured data analyzing technology device comprises: a database which stores a plurality of data matching paintings painted by infants or children over 36 months old (3 years old) with analysis texts; an analysis text output unit which analyzes paintings of the database to extract a random image depending on each theme, inputs a painting according to a theme set randomly, compares the input painting with the random image to classify the same into a normal group, an interest group and a risk group and outputs analysis texts corresponding to the classified group; an input unit which receives a painting painted by a painting tool for a theme; a format analysis unit which verifies a size or a location of the input painting by means of a coordinate value; a color analysis unit which analyzes colors used in the input painting; an analyzed content output unit which outputs an analyzed content based on the analysis result of the format analysis unit and the color analysis unit; and a reliability check unit which analyzes a correlation between the output analysis text and the output analyzed content and calculates a reliability. Accordingly, the present invention uses data matching paintings painted by infants or children over 36 months old (3 years old) with analysis texts to analyze the generated analysis data and the input painting, calculates a reliability between analyzed contents, and feedbacks the correlation between the analysis data and the analyzed contents to increase an analysis reliability.

Description

Technical Field [0001] The present invention relates to an apparatus and method for an unstructured data analysis technology, and a recording medium on which an application / program for implementing the same is recorded.

More particularly, the present invention relates to an apparatus and method for analyzing atypical data, and more particularly, to an apparatus and method for analyzing atypical data, The present invention relates to an apparatus and method for an unstructured data analysis technique for analyzing a picture and calculating reliability of the obtained analysis contents, and a recording medium on which an application / program for implementing the same is recorded.

There is an unstructured data analysis technology system that analyzes unstructured data of 3 to 5 year old infants. The unstructured data analysis technology system analyzes the children 's emotional psychology by analyzing the pictures inputted by the drawing tool on the subject.

The conventional unstructured data analysis technology system analyzes the input pictures according to expert judgment and provides analysis results. The conventional unstructured data analysis technology system, which is performed manually, is not based on a large number of clinical data, so the analysis reliability is not high.

Low analytical reliability can not be used for psychotherapy, and applying this analysis to infants may prevent unintentional medical accidents.

Registration number: 10-1202024, Picture diagnostic device and method Registration number: 10-1581801, 3-way communication based child psychological counseling system and method using character

It is an object of the present invention to solve the above problems and to provide an analysis text with improved analysis reliability and to provide a criterion for extracting an image through a size, position and color of a picture drawn by a child or a child, And a recording medium on which an application / program for implementing the apparatus and method is recorded. The present invention also provides an apparatus and method for an unstructured data analysis technology capable of classifying emotional state and psychological state of a child or a child by extracting a default value according to the extracted object.

According to an aspect of the present invention, there is provided a computer-readable recording medium storing a database storing a plurality of data matching an analysis text and a picture drawn by an infant or a child over 36 months old (3 years old) We analyze the pictures of the database, extract random images according to each subject, input pictures according to the set theme arbitrarily, compare the input pictures with random images and classify them as normal, interest, and risk groups. An analysis text output unit for outputting a corresponding analysis text; An input unit for inputting a picture drawn by a drawing tool on a subject; A formal analysis unit for verifying a coordinate value of the size or position of the input picture; A color analyzer for analyzing the colors used in the input picture; An analytical content output unit for outputting analytical results as a result of analysis by the formal analysis unit and the color analysis unit; And a reliability check unit for calculating a reliability by analyzing a correlation between the output text and the interpreted text.

A translation tool that translates the printed analysis text into a foreign language and saves it in a database and provides analytic text for pictures drawn by children or children from other countries; And a modified data input unit for displaying the analyzed text displayed and storing the text modified by the expert in a database. The formal analysis unit extracts a normal group for a recent 5-year average value, Verify the coordinate values of the picture.

Wherein the input unit receives a picture drawn by a drawing tool on a free subject, and the content analyzer receives a weighted value of a mapping value of the inputted picture with respect to the free topic, To map the input picture to the picture stored in the database, and the analysis text output unit outputs the analyzed text for the free subject.

Storing a plurality of data in a database matching images and analysis text drawn by an infant or child over 36 months old; Analyzing a picture of the database and extracting an arbitrary image according to each subject; Inputting a picture according to a randomly set subject; Comparing the input image with the arbitrary image, classifying the input image as a normal group, an interest group, and a risk group, and outputting analysis text corresponding to the classified group; Receiving a picture drawn by a picture tool on a subject; A formal analysis step of verifying the coordinate value of the size or position of the inputted picture; A color analysis step of analyzing the color used in the inputted picture; An analysis content output step of outputting analysis content as a result of the analysis of the formal analysis step and the color analysis step; And a reliability check step of calculating the reliability by analyzing a correlation between the output text and the output text.

According to another aspect of the present invention, there is provided an apparatus for analyzing atypical data, comprising: a database storing a plurality of data matching a picture drawn by a child or a child and analysis text; An input image generating unit for receiving an image drawn by the infant or child and generating an input image; A matching unit for matching an input image generated by the input image generating unit with a picture stored in the database and an analysis test for the picture; An analysis text output unit for analyzing the image of the database with respect to the matching image in the matching unit, classifying the input image into a normal group, an interest group, and a risk group, and outputting analysis text corresponding to the classified group; A picture size analyzer for analyzing a picture size of the input image generated by the input image generator; A picture position analyzer for analyzing a picture position of an input image generated by the input picture generator; A picture color analyzer for analyzing picture colors of an input image generated by the input image generator; An outline extracting unit for extracting an outline of a picture of the input image generated by the input image generating unit; And an analysis result outputting the analysis result of the picture size analyzing unit, the picture position analyzing unit, the picture color analyzing unit and the outline extracting unit and the output result of the emotional state or psychological state of the infant or the child and the behavior characteristics of the infant or the child And a control unit.

According to another aspect of the present invention, there is provided a method for analyzing atypical data, the method comprising: storing a plurality of data matching an analysis text with a picture drawn by a child or a child; An input image is input to an input image generating unit with respect to a picture drawn by the infant or child, and an input image is generated; Analyzing picture colors in a size analyzer, a picture position analyzer and a picture color analyzer for an input image generated by the input image generator, and extracting an outline of an input image in an outline extractor; Outputting an emotional state and a psychological state of a child or a child and a behavior characteristic of a child or a child according to the size, position, color, and outline of the child; And outputting the analysis text by matching a plurality of pictures and text data of the database with the size, position, color, and input image extracted by the outline, in the matching unit.

Here, the analysis contents for classifying behavior characteristics of infants and children according to the emotional state or psychological state of the child or infant are classified into normal group, interest group, and risk group, and the reliability of the output analysis text and interpretation contents is checked And further comprising:

An apparatus and method for an unstructured data analysis technology according to the present invention and a recording medium on which an application / program for implementing the same are recorded can be used as follows.

First, the reliability of the analysis data obtained by analyzing the input data and the analysis data generated by using a large number of data matched with the pictures drawn by the infants or children over 36 months (3 years old) is calculated, The reliability of analysis can be improved by feeding back the correlation between interpretations.

Second, we classify the emotional and psychological states of infants and children by assigning criteria for extracting images through the size, position, and color of pictures drawn by infants or children and extracting the default values according to the given criteria as objects , And behavioral characteristics of infants.

Thirdly, extracting the outline of the extracted object can know the emotional state and psychological state of the infant or the child, and it is easy to preliminarily check the emotional state and psychological state of the infant or child, It can facilitate early detection and prevention of infants / children who may experience abuse, emotional or psychological problems.

Fourth, emotional state, psychological state, and behavioral characteristics of infants and children can be derived by computer or smart device using web or application.

1 is a block diagram showing a configuration of an atypical data analysis technology apparatus according to the first embodiment of the present invention.
FIG. 2 is an exemplary diagram illustrating an input picture and analysis contents according to the first embodiment of the present invention.
3 is a flowchart illustrating an operation of the atypical data analysis technique according to the first embodiment of the present invention.
4 is a block diagram showing a configuration of an atypical data analysis technology device according to the second embodiment of the present invention.
5 is a flowchart illustrating an operation of the atypical data analysis technique according to the second embodiment of the present invention.
FIG. 6 is a diagram for explaining an example of size analysis for calculating the area (size) of a picture in the atypical data analysis technique according to the second embodiment of the present invention.
FIG. 7 is a view for explaining an example of interpreting the positions of pictures in the atypical data analysis technique according to the second embodiment of the present invention.
FIG. 8 is a view for explaining an example of measuring the casting color of a picture in the atypical data analysis technique according to the second embodiment of the present invention.
9 to 12 are views for explaining an example of a method of extracting an outline of a picture in the atypical data analysis technique according to the second embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings.

In addition, although the term used in the present invention is selected as a general term that is widely used at present, there are some terms selected arbitrarily by the applicant in a specific case. In this case, since the meaning is described in detail in the description of the relevant invention, It is to be understood that the present invention should be grasped as a meaning of a term that is not a name of the present invention. Further, in describing the embodiments, descriptions of technical contents which are well known in the technical field to which the present invention belongs and which are not directly related to the present invention will be omitted. This is for the sake of clarity of the present invention without omitting the unnecessary explanation.

An unstructured data analysis technology device may be produced in the form of an application that performs analytical text output, output of analytical content, or reliability check between analytical text and analytical content. The application is executed in a computer terminal including a portable computer and a smart phone. The unstructured data analysis technology device can generate an index that increases the correlation and data reliability between the two data by performing a reliability check between the analysis text and the analysis content. Further, the present invention may include a recording medium on which an application / program for implementing the application is recorded. Such a recording medium becomes readable by a computer or a smart device.

1 is a block diagram showing a configuration of an atypical data analysis technology apparatus according to the first embodiment of the present invention.

A database 110 for storing a plurality of data matching images and analytical texts drawn by infants or children over 36 months (3 years old); The image of the database 110 is analyzed to extract an arbitrary image according to each subject, a picture according to a set subject is arbitrarily inputted, and the input picture and the arbitrary image are compared to classify it as a normal group, an interest group, An analysis text output unit 160 for outputting an analysis text corresponding to the group to which the analysis text is input; An input unit 120 for inputting a picture drawn by a drawing tool on a subject; A formal analysis unit 130 for verifying the coordinate value of the size or position of the inputted picture; A color analyzer 150 for analyzing the color used in the input picture; An analysis content output unit 170 for outputting analysis content as a result of analysis by the formal analysis unit and the color analysis unit; And a reliability check unit 180 for analyzing the correlation between the output text and the analyzed text to calculate the reliability. A configuration that enables the operation of such an unstructured data analysis technology apparatus will be described.

The database 110 stores a large number of data that matches the pictures and analysis texts drawn by infants or children over 36 months (three years old). The database 110 has hundreds to millions of pieces of data and is a big database.

The analysis text output unit 160 analyzes a picture of the database 110, extracts an arbitrary image according to each subject, inputs a picture according to an arbitrarily set subject, compares the inputted picture with an arbitrary image, Interest group, and risk group, and output the analysis text corresponding to the classified group.

An arbitrary image is a representative image obtained by analyzing the images accumulated in the database 110 and obtained according to each subject. The figure contains various objects, and the random image is the representative image obtained by the analyzed object. Random images can be classified into normal, interest, and risk groups in terms of the quality of the images.

Input images are compared with random images and classified into normal, interest, and risk groups. And the analysis text output unit 160 can output the analysis text corresponding to the classified group.

The input unit 120 receives the picture drawn by the drawing tool with respect to the subject. The drawing tools are provided with standardized paper and colored pencils. The infant or child draws the picture with the drawing tool, and the input unit 120 receives the drawing drawn by the drawing tool.

The input unit 120 may be a computer terminal. The computer terminal displays an input area corresponding to a standardized paper, provides a touch pen for each color, and receives a picture in a corresponding color when using a touch pen classified by color. The input unit 120 may be a scanner. The scanner scans images drawn on paper by infants or children and receives them.

The formal analysis unit 130 verifies the coordinate value of the size or position of the inputted picture. The formal analysis unit 130 analyzes the size of the inputted picture and verifies the coordinates of the position of the inputted picture.

The color analyzer 150 analyzes the colors used in the input image. The color analyzer 150 analyzes what color is used in the input picture. The color analyzer 150 performs color analysis on the used color.

The analysis content output unit 170 outputs the analysis content as a result of analysis by the formal analysis unit 130 and the color analysis unit 150. [ The analysis content output unit 170 outputs the analysis contents according to the formal analysis and the analysis contents according to the color analysis. An example of the interpretation content output unit 170 will be described with reference to FIG.

The reliability check unit 180 calculates the reliability by analyzing the correlation between the output text and the output text. The higher the confidence, the higher the correlation between the analytical text output from the database accumulation results and the analytical content output by the image analysis module. The reliability check unit 180 analyzes the correlation between the analysis text and the analysis contents through emotional word comparison analysis.

In another embodiment, the translation tool translates the analysis text output from the analysis text output unit 160 into a foreign language, stores it in the database 110, and provides analysis texts for pictures drawn by children or children of other countries. The translation tool translates the analysis text into other languages to enhance the utilization of the database 110. Translation tools can improve the reliability of analysis of infants / children in other countries and their children / children. The translation tool can include analysis content in addition to analysis text.

The correction data input unit displays the output analysis text and stores the corrected text in the database 110. The revised data entry part can be analyzed by the experts by referring to the patterns that the infant or the child lives in the kindergarten and the house and modify the text of the analysis.

In another embodiment, the formal analysis unit 130 extracts the normal group for the recent 5-year average value, and verifies the coordinate values of the inputted picture based on the extracted normal group. The formal analysis unit 130 can increase the analytical reliability by setting the normal group sample using the recent average value and verifying the coordinate value of the inputted picture based on the extracted normal group.

In another embodiment, the content analysis unit maps the input image to the image stored in the database 110. The content analysis unit maps the picture drawn by the infant or child and the picture already drawn by another infant or child stored in the database 110. The content analysis department conducts a content analysis of pictures drawn by infants or children through picture mapping.

The input unit 120 receives a picture drawn by the drawing tool with respect to a free subject, and the content analysis unit weights the mapping value of the picture inputted to the free subject to match the input picture with the picture stored in the database 110 , The analysis text output unit 160 outputs the analyzed text for the free subject. For example, the mapping value between the image input by the content analysis unit and the image stored in the database 110 may be 0.5, 0.3, or 0.2. The content analysis unit can assign three stored pictures to the input picture with the mapping value weight. The analysis text output unit 160 may output a weighted value to the analyzed text corresponding to the three stored pictures and output the combined weight.

The content analyzer can map the input image to the image stored in the database 110 by assigning a weight to the mapping value for the corresponding degree by associating the image stored in the database 110 with the input image. The analysis text output unit 160 synthesizes the analysis text corresponding to the mapping value weight and outputs the analyzed text.

FIG. 2 is an exemplary diagram illustrating an input picture and analysis contents according to the first embodiment of the present invention.

Table 1 shows measurement indices for analyzing the size of the inputted picture.

Table 2 shows measurement indices for analyzing the position of the input image.

Table 3 shows measurement indices for analyzing the colors of the inputted pictures.

For the input picture, interpretation contents are provided according to size, position and color.

When the measurement is performed according to the size, position and color of the input picture, the analysis contents are derived from the size C-2, position A-2, and color A-1.

The text corresponding to the interpretation contents is as follows.

It is assumed that the interpretation contents tend to be confidently or aggressively responding to the needs of the environment for the size C-2, and it seems to have a feeling of uncertainty and tension on the self at position A-2, Adaptive and self-centered tendency, has a mental dissatisfaction with color A-1, has some possibility of aggressive behavior depending on the situation, is sympathetic to others, relies on other people's affection, , And it is assumed that it is cooperative and adaptable.

3 is a flowchart illustrating an operation of the atypical data analysis technique according to the third embodiment of the present invention.

Describes how to analyze unstructured data.

An unstructured data analysis technology device includes a program memory for storing a program, a data memory for storing data, and a processor for executing the program.

Storing (310) a plurality of data in the database matching a picture drawn by the infant or child over 36 months (3 years old) and the analysis text; Analyzing a picture of the database and extracting (320) an arbitrary image according to each subject; A step (330) of inputting a picture according to a randomly set subject; Comparing the input image with the random image, classifying the input image as a normal group, an interest group, and a risk group, and outputting an analysis text corresponding to the classified group (340); A step (350) of inputting a picture drawn with a picture tool on a subject; A formal analysis step (360) of verifying the coordinate value of the size or position of the input picture; A color analysis step 370 for analyzing the color used in the input picture; An analysis content output step (380) for outputting analysis content as a result of the analysis of the formal analysis step and the color analysis step; And a reliability check step 390 for calculating the reliability by analyzing the correlation between the outputted analysis text and the outputted analysis content.

An unstructured data analysis technology device executes a program stored in a program memory by a processor, and the operation will be described as follows.

* Describe the procedures executed in the unstructured data analysis technology device in time series.

The unstructured data analysis technology device stores a large number of data in the database that matches the analysis text with pictures drawn by infants or children over 36 months (3 years old). Unstructured data analysis technology devices have hundreds to millions of data sets in a database and manage big databases.

The unstructured data analysis technology device analyzes the images of the database, extracts arbitrary images according to each subject, inputs pictures based on arbitrarily set subjects, compares the input images with random images, And outputs the analysis text corresponding to the classified group. An arbitrary image is a representative image obtained by analyzing the images accumulated in the database and obtained according to each subject. The figure contains various objects, and the random image is the representative image obtained by the analyzed object. Objects can be trees, houses, people. Random images can be classified into normal, interest, and risk groups in terms of the quality of the images. Input images are compared with random images and classified into normal, interest, and risk groups. There is an analytical text matched to the figure, and an unstructured data analysis technology device can output analytical text corresponding to the classified group.

The unstructured data analysis technology device receives the picture drawn by the drawing tool on the subject. The drawing tools are provided with standardized paper and colored pencils. Infants and children draw pictures with drawing tools, and atypical data analysis technology devices draw pictures drawn with drawing tools. The atypical data analysis technology device may be a computer terminal. The computer terminal displays an input area corresponding to a standardized paper, provides a touch pen for each color, and receives a picture in a corresponding color when using a touch pen classified by color. The atypical data analysis technology device may be a scanner. The scanner scans images drawn on paper by infants or children and receives them.

The unstructured data analysis technology device verifies the coordinate value of the size or position of the inputted picture. The atypical data analysis technology device analyzes the size of the input image and verifies the coordinates of the position of the input image.

The unstructured data analysis technology device analyzes the colors used in the input picture. The unstructured data analysis technology device analyzes what color is used in the input picture. Atypical data analysis technology devices perform color analysis on the colors used.

The unstructured data analysis technology device outputs analysis contents as a result of analysis of formal analysis and color analysis. The unstructured data analysis technology device outputs the analysis contents according to the formal analysis and the analysis contents according to the color analysis.

The unstructured data analysis technology device calculates the reliability by analyzing the correlation between the output text and the interpreted text. The correlation between the analysis text outputted from the database accumulation result and the interpretation contents output by the image analysis module becomes higher. Atypical data analysis technology device analyzes the correlation between analysis text and interpretation contents through emotional word comparison analysis.

In another embodiment, the atypical data analysis technology device extracts the normal group for the recent 5-year average value and verifies the coordinate value of the input image based on the extracted normal group. Unstructured data analysis technology device can increase the analytical reliability by setting the normal group sample using the recent average value and verifying the coordinate value of the inputted picture based on the extracted normal group.

In another embodiment, the atypical data analysis technology apparatus receives a picture drawn by a drawing tool on a free subject, assigns a weight to the mapping value of the picture inputted to the free subject, matches the inputted picture with the picture stored in the database, Outputs analyzed text for free topic.

The unstructured data analysis technology device can map the input picture and the picture stored in the database by assigning a weight to the mapping value of the correspondence degree by associating the picture stored in the database with the inputted picture. The unstructured data analysis technology device synthesizes the analysis text corresponding to the mapping value weight and outputs the analyzed text.

4 is a block diagram showing a configuration of an atypical data analysis technology device according to the second embodiment of the present invention.

As shown in FIG. 2, the atypical data analysis technology device according to the second embodiment of the present invention includes a database 110 (FIG. 2) for storing a plurality of data matching an analysis text with a picture drawn by an infant or a child over 36 months An input image generating unit 300 for inputting a picture drawn by a child or a child and generating an input image, an input image generated by the input image generating unit 300, an image stored in the database and an analysis test A matching unit 400 for matching the input image with the matching unit 400 and analyzing the image of the database 110 with respect to the matching image in the matching unit 400 to classify the input image into normal group, An analysis text output unit 160 for outputting an analysis text, a picture size analyzer 210 for analyzing a picture size of an input image generated by the input image generation unit 300, A picture position analyzer 220 for analyzing picture positions of an input image generated by the image generator 300, a picture color analyzer 220 for analyzing picture colors of an input picture generated by the input picture generator 300, An outline extractor 240 for extracting an outline of a picture of the input image generated by the input image generator 300 and a picture size analyzer 210 and a picture position analyzer 220, An analysis content output unit 170 for outputting (deriving) the emotional state and the psychological state of the infant or the child and the infant behavior characteristic according to the analysis result of the color analysis unit 230 and the outline extractor 240, And a reliability check unit 180 for analyzing the correlation between the analysis text output unit 160 and the analysis content output unit 170 and calculating the reliability. A configuration that enables the operation of such an unstructured data analysis technology apparatus will be described.

The database 110 stores a large number of data that matches the pictures and analysis texts drawn by infants or children over 36 months (three years old). The database 110 has hundreds to millions of pieces of data and is a big database.

The analysis text output unit 160 analyzes the pictures of the database 110 and extracts images according to the respective topics. The analysis text output unit 160 extracts the images input by the infant or child generated by the input image generating unit 300, If the picture is matched in the matching unit 400, the picture is classified into normal group, interest group, and risk group, and the analysis text corresponding to the classified group is output.

The image is a representative image obtained by analyzing the images accumulated in the database 110 and obtained according to each subject. The picture contains various objects and each image is classified into normal group, interest group, and risk group.

The images generated by the input image generating unit 300 are compared with the images stored in the database 110 and classified into normal groups, interest groups, and risk groups, and matched in the matching unit 400. And the analysis text output unit 160 can output the analysis text corresponding to the classified group.

Here, the input image generating unit 300 receives the picture drawn by the drawing tool. The drawing tools may be provided with standardized paper and colored pencils. The infant or child draws a picture with a drawing tool, and the input image generating unit 300 receives a picture drawn by a child or a child.

The input image generating unit 300 may be a computer terminal. The computer terminal displays an input area corresponding to a standardized paper, provides a touch pen for each color, and receives a picture in a corresponding color when using a touch pen classified by color. The input image generating unit 300 may also be a scanner. The scanner scans images drawn on paper by infants or children and receives them.

The picture size analyzing unit 210 analyzes the picture size of the picture drawn on the drawing sheet of the preset standard, for example, as shown in Table 1, in the same manner as FIG. 6 in the image generated by the input image generating unit 300 .

For example, as shown in Table 2, the picture position analysis unit 220 analyzes the picture position in the same manner as in FIG. 7 in the image generated by the input image generation unit 300, do.

For example, as shown in Table 3, the picture color analysis unit 230 extracts a picture color (color) from the image generated by the input image generation unit 300, .

On the other hand, the outline extracting unit 240 extracts the outline (outline line) of the figure from the image generated by the input image generating unit 300 in the same manner as in FIGS. 9 to 12, And extracts an object to be analyzed.

The analysis content output unit 170 outputs analytical results of the size, position, and color of the image generated by the input image generating unit 300, and analysis results of the outline and the extracted results. An example of the analysis content output unit 170 is as described in FIG.

The reliability check unit 180 calculates the reliability by analyzing the correlation between the output text and the output text. The higher the confidence, the higher the correlation between the analytical text output from the database accumulation results and the analytical content output by the image analysis module. The reliability check unit 180 analyzes the correlation between the analysis text and the analysis contents through emotional word comparison analysis.

In addition, since the contents of the translation tool and the modification data input unit as described above are the same, a detailed description thereof will be omitted.

Meanwhile, the atypical data analysis technology apparatus according to the first and second embodiments of the present invention may be a recording medium on which an application or a program for realizing the application is recorded.

5 is a flowchart illustrating an operation of the atypical data analysis technique according to the second embodiment of the present invention.

The operation of the atypical data analysis technique according to the second embodiment of the present invention is similar to that of FIG. 5 except that a plurality of children (children) aged over 36 months Data is stored (S400). Of course, it may not be necessary to specifically limit the age of the infant or child. The database 110 has hundreds to millions of pieces of data and is a big database.

Then, an input image is input to the input image generating unit 300 (S410) and an input image is generated (S420).

The picture color is analyzed in the picture size analyzer 210, the picture position analyzer 220 and the picture color analyzer 230 in step S430 and the outline of the input image is extracted in the outline extractor 240 (S440).

In this case, an example of size analysis for calculating the area (size) of the picture in FIG. 6 will be described. In FIG. 6, a picture of a child or a child drawn on a drawing paper of a predetermined size is input to the input image generating unit 300, The size of the picture can be analyzed by calculating the area of the y coordinate value. At this time, a plurality of data matching the analytical text and the figure in which the area of the same standard predetermined in advance is calculated in the database 110 is also determined.

7 is a view for explaining an example of interpreting the position of a picture. In FIG. 7, a picture of a child or a child drawn on a drawing sheet of a predetermined standard is input to the input image generating unit 300, The position of the figure is interpreted through the measurement of the reference point. At this time, a plurality of data matching the analytical text and the figure of the position calculated through the measurement of the reference point of the coordinates are determined in advance in the image of the same standard predetermined in the database 110 as well.

FIG. 8 is a diagram for explaining an example of measuring the color of a picture. The color of the picture is divided into RGB color space, cylindrical color coordinate, HSV (Hue, Saturation, Value) color space, and HSL , Lightness) We use the color space method to determine the number of colors using the most weight. For reference, HSV or HSL is a conceptual color space that is different from the characteristic that human beings perceive the actual color, but it is a conceptual color space that can be used when searching for or referring to a certain color. It is often used, for example, to create color selection features such as the window's color palette. Therefore, the accuracy of color measurement in the present invention can be improved.

On the other hand, in the database 110, a plurality of data is determined by matching the color of the picture of the same standard predetermined with the color of the picture and the analysis text.

Accordingly, the size, position, and color of the picture drawn by the child or the child are matched with the data of the database 110 in the matching unit 400, and the analysis text output unit 160 outputs the emotion state and psychological state .

In addition, not only the method using R, G, B

9 to 12 are diagrams for explaining an example of a method of extracting an outline of a picture in the atypical data analysis technique according to the second embodiment of the present invention. The input image generating unit 300 removes noise from the image when the image is generated.

Then, a gradient value is detected as shown in FIG. In this case, for example, a process of finding an edge of a lane among edges is used in a method of finding a part where a pixel value of an image changes abruptly, and a process of finding the edge of a lane is used. And the pixel value is output as zero.

Then, non-maximum removal is performed in the same manner as in FIG. In other words, it is a process of expressing the detected edge more accurately. For example, it is possible to use a method of comparing pixel values of eight directions based on a center pixel, for example, if the center pixel is largest, and removing it if not.

Then, the threshold setting is performed. This threshold setting can be performed as shown in FIG. 11, which is an image enhancement process for removing an edge that is not an edge in the removal process of FIG. 10, It is a task to divide a certain value into a strong edge and a weak edge with a double thresholding.

Finally, edge tracking is performed to extract the outline. This method can use the method shown in FIG. 12, which is a process of re-creating a part that is an actual boundary line but is determined not to be an edge in the previous step, Edge determination is performed to determine whether the edge is an edge or not, similar to the non-maximum removal process described above, by comparing the lightness with the pixels in eight directions. In this case, if the edge is connected to the edge, the edge is judged as an actual edge. In this process, a portion of the edge determined to be connected is connected.

In this way, the size, position, and color of the picture and the outline of the picture are extracted to output the analysis contents for deriving the emotional state and psychological state of the infant or child and the behavior characteristics of the infant (S450).

At this time, the matching unit combines a plurality of data and the generated input image in the manner described above to output analysis text (S460).

The reliability of the outputted analysis text (S460) and interpretation content (S450) is checked by an expert or the like (S470).

On the other hand, the interpretation contents (S450) for classifying the emotional state and the psychological state of the infant or child, the analysis text (S460) matched in the matching unit (400) and the reliability check contents are stored again in the database (110) .

While the present invention has been described with reference to the exemplary embodiments, it is to be understood that the invention is not limited to the disclosed exemplary embodiments. Therefore, the examples disclosed in the present invention are not intended to limit the scope of the present invention and are not intended to limit the scope of the present invention. The scope of protection of the present invention should be construed according to the following claims, and all technical ideas within the scope of equivalents should be construed as falling within the scope of the present invention.

110: Database 120: Input
130: formal analysis unit 150: color analysis unit
160: Analysis text output unit 170: Analysis content output unit
180: reliability check unit 210: picture size analyzing unit
220: picture position analysis unit 230: picture color analysis unit
240: Outline extraction unit 300: Input image generation unit
400:

Claims (8)

A database that stores a large number of data that matches texts and analysis text drawn by infants and children over 36 months (3 years old);
The image of the database is analyzed to extract an arbitrary image according to each subject, a picture according to a set subject is arbitrarily inputted, and the inputted picture and the arbitrary image are compared with each other, and classified into normal group, An analysis text output unit outputting analysis text corresponding to the group;
An input unit for inputting a picture drawn by a drawing tool on a subject;
A formal analysis unit for verifying a coordinate value of the size or position of the input picture;
A color analyzer for analyzing colors used in the input picture;
An analytical content output unit for outputting analytical results as a result of the formal analysis unit and the color analysis unit; And
And a reliability check unit for calculating a reliability by analyzing a correlation between the output text and the output text.
The method according to claim 1,
A translation tool that translates the printed analysis text into a foreign language and saves it in a database and provides analytic text for pictures drawn by children or children from other countries; And
And a correction data input unit for displaying the analyzed text and storing the modified text by a specialist in a database,
The formal analysis unit
The normal group for the 5 - year average was extracted,
An unstructured data analysis technology device that verifies the coordinate values of the input image based on the extracted normal group.
The method according to claim 1,
Further comprising a content analyzer for mapping the input image and the image stored in the database,
Wherein the input unit comprises:
On the free topic, I received a picture drawn by the drawing tool,
Wherein the content analysis unit comprises:
Mapping the input picture to a picture stored in the database by weighting a mapping value of the picture inputted for the free topic,
The analysis text output unit outputs,
And outputting the analyzed text for the free subject.
Storing a plurality of data in a database matching images and analysis text drawn by an infant or child over 36 months old;
Analyzing a picture of the database and extracting an arbitrary image according to each subject;
Inputting a picture according to a randomly set subject;
Comparing the input image with the arbitrary image, classifying the input image as a normal group, an interest group, and a risk group, and outputting analysis text corresponding to the classified group;
Receiving a picture drawn by a picture tool on a subject;
A formal analysis step of verifying the coordinate value of the size or position of the inputted picture;
A color analysis step of analyzing colors used in the input picture;
An analysis content output step of outputting analysis content as a result of the formal analysis step and the color analysis step; And
And a reliability check step of calculating the reliability by analyzing a correlation between the output text and the output text.
A database that stores a large number of data that matches the pictures and analysis text drawn by infants or children over 36 years of age (3 years old);
An input image generating unit for receiving an image drawn by the infant or child and generating an input image;
A matching unit for matching an input image generated by the input image generating unit with a picture stored in the database and an analysis test for the picture;
An analysis text output unit for analyzing the image of the database with respect to the matching image in the matching unit, classifying the input image into a normal group, an interest group, and a risk group, and outputting analysis text corresponding to the classified group;
A picture size analyzer for analyzing a picture size of the input image generated by the input image generator;
A picture position analyzer for analyzing a picture position of an input image generated by the input picture generator;
A picture color analyzer for analyzing picture colors of an input image generated by the input image generator;
An outline extracting unit for extracting an outline of a picture of the input image generated by the input image generating unit; And
The analysis result and the extraction result of the picture size analyzing unit, picture position analyzing unit, picture color analyzing unit and outline extracting unit are used to output (extract) the behavior characteristics of the infant or the child according to the emotional state and psychological state of the infant or child And an output unit for outputting the at least one input data.
Storing a plurality of pieces of data matching a picture and analysis text drawn by a child or a child in the database;
An input image is input to an input image generating unit with respect to a picture drawn by the infant or child, and an input image is generated;
Analyzing picture colors in a size analyzer, a picture position analyzer and a picture color analyzer for an input image generated by the input image generator, and extracting an outline of an input image in an outline extractor;
Outputting the behavior characteristics of the infant or the child according to the emotional state and the psychological state of the infant or child by extracting the size, position, color, and outline of the infant or child; And
And outputting the analysis text by matching the plurality of pictures and text data of the database with the size, position, color, and input image extracted by the outline of the database in the matching unit.
The method according to claim 6,
The behavioral characteristics of infants and children according to their emotional and psychological states are classified into normal,
Further comprising the step of checking reliability of the analyzed text and interpreted contents (S470).
Storing a plurality of pieces of data matching a picture and analysis text drawn by a child or child over 36 months (3 years old) in the database;
An input image is input to an input image generating unit with respect to a picture drawn by the infant or child, and an input image is generated;
Analyzing picture colors in a size analyzer, a picture position analyzer and a picture color analyzer for an input image generated by the input image generator, and extracting an outline of an input image in an outline extractor;
Outputting an analysis content for extracting an infant behavior characteristic according to an emotion state and a psychological state of a child or a child by extracting the size, position, color, and outline of the infant; And
And outputting the analysis text by matching the plurality of pictures and text data of the database with the size, position, color, and input image extracted by the outline in the matching unit. A recording medium on which the application / program is recorded.

Images