KR20180061876A - An E-book Production System Using Automatic Placement Of Illustration And Text - Google Patents

Abstract

According to the present invention, an electronic book production system through automatic arrangement of illustrations and characters to which the system is assigned, comprises: a data input module for receiving multimedia data including image data and text data for producing an electronic book from a user, and storing the same in a database; a system analysis module for analyzing the text data and the multimedia data to separately identify a text keyword and an image keyword, and assigning a system level which is upper and lower classifications depending on the importance; a pattern setting module for setting a format and the number of pages of the electronic book, and configuring a template corresponding to the format; and an arrangement module for arranging the text data and the multimedia data to which a system level is assigned, in the template depending on the system level.

Description

[0001] The present invention relates to an electronic book production system using an automatic arrangement of a board and characters assigned to a system,

More particularly, the present invention relates to an electronic book production system by automatically arranging a system and an electronic book, and more particularly, The system can reproduce the readability and indexing functions of existing electronic books with minimal intervention by the editors so that the system can dramatically reduce the amount of work involved in the production of electronic books. And a book production system.

In general, an e-book is a publication that has processed and stored the contents of a book as digital information, and can be viewed through a specific program such as an electronic book viewer installed in a personal computer (PC) It is possible to browse through the installed Internet browser.

In addition, when the user is moving, an electronic book stored in a portable device or a predetermined portable memory means can be viewed through personal portable terminals such as a PDA (Personal Digital Assistants), an electronic book terminal, and a tablet computer owned by the user If there is no stored e-book, the e-book file can be downloaded after accessing a predetermined site providing an e-book by accessing the Internet via a PDA or an e-book dedicated terminal.

As such, e-books can be used to read multiple books through a specific terminal even if they do not have a bulky and heavy book, and the convenience of being able to easily retrieve and read a desired book or a specific part of the book, It is expected that the scope of its use will steadily grow and grow on behalf of books.

With the development of such e-books, the e-book publishing industry is also steadily developing, and many prior art related to e-book production and publishing have been disclosed.

As an example of this, Korean Patent No. 10-1212494 discloses a method and system for providing electronic book publishing services.

Wherein the electronic book publishing system includes an electronic book writing client, an electronic book distribution server, and an electronic book reading client, wherein the number and / or arrangement of advertisements of the electronic book template is predetermined according to an advertisement revenue ratio, The client may change at least a portion of the number of ads and / or the advertisement arrangement. The e-book writing client can generate the first e-book by selecting the e-book template. The e-book distribution server may provide the e-book template and generate a second e-book in which an advertisement is inserted based on the generated first e-book. And the e-book reading client can receive the generated second e-book. Therefore, the e-book publishing system can allow the consumer to download the e-book free of charge, allow the author to easily issue the e-book, and make the calculation of the charge for the author clear and convenient.

However, in the production of such an electronic book, the arrangement of the data is performed according to the importance of the letters of the respective boards in the overall plate type. At this time, the arrangement of the importance and the layout of the importance are reflected in the editor's subjective, It is a limitation that electronic books are made according to the decision structure.

In order to solve the above-mentioned problems, the present invention relates to an electronic book production system by automatic layout of a board and a character to which a system is assigned. In the electronic book production system, Is reproduced in the form of an algorithm to reproduce the readability and indexing functions of existing electronic books with minimizing the intervention of the editors, thereby automatically reducing the number of steps for electronic book production, It is necessary to develop an electronic book production system.

The present invention has been devised to overcome the problems of the above-described technology, and it is an object of the present invention to provide a method and apparatus for reproducing an electronic book, such as an arrangement of importance and placement according to importance, The present invention aims at providing an electronic book production system by automatically arranging a book and a character to which a system capable of reproducing the readability and the indexing function of the electronic book of the electronic book of the present invention can be dramatically reduced.

It is another object of the present invention to provide a system and method for generating an image keyword and a text keyword from image data and text data, will be.

It is a further object of the present invention to improve the readability and information transfer effect by adjusting data arrangement based on the linkage between the main keyword and the image keyword and the text keyword passing through the image keyword and the text keyword.

In order to achieve the above object, an electronic book production system according to the present invention is an electronic book production system through automatic layout of a board and a character to which a system is assigned, A data input module for receiving multimedia data and text data including image data for book production and storing the text data in a database, analyzing the text data and the multimedia data to identify text keywords and image keywords, A systematic analysis module for assigning a system level as a subclass, a pattern setting module for setting a plate type and a page number of the electronic book, and configuring a template corresponding to the plate type; And a placement module for arranging the text data and the multimedia data to which the systematic level is assigned in the template according to the systematic level.

The system analysis module includes an image database for storing a plurality of reference images in which image keywords are set, an image keyword recognition unit for comparing the input image data with the reference image to determine an image keyword of the image data, An image classifying unit for classifying the image data according to the image keyword, and an image level assigning unit for assigning a system level to the classified image data.

The system analysis module may further include a vectorization processing unit for vectorizing a bitmap image of the image data and a scanning processing unit for storing image information obtained by scanning a closed curve of the vectorized image data and a color of each coordinate, The image keyword recognizing unit compares the image information with the reference image and recognizes the image keyword of the image data.

In addition, the systematic analysis module may further include a placement coordinate determination unit for determining placement coordinates of the closed curve within the vectorized image data, and the placement module sets a placement position of the image data according to the placement coordinates And a text position determining unit for determining an arrangement position of the text data according to the layout coordinates.

In addition, the image classification unit may include an image classification classification part for classifying the image keyword for the image data into image classification, and an image classification classification part for classifying the image keyword for the image classification into image classification, which is a sub- And a holding part.

The layout module may further include a template division unit that divides the template into at least two divided regions including an image region and a text region, an image arrangement unit that arranges the image data in the image region, And a text arrangement unit for arranging the text data.

In addition, the phylogenetic analysis module may include a text keyword recognition unit for recognizing a text keyword from a term included in the text data, a text level assigning unit for assigning a system level to the text data according to the recognized text keyword, And a text keyword selection unit for selecting the text keyword from among the text keywords according to a system level, wherein the arrangement module further comprises a field division unit for dividing the text region into a plurality of text fields, And the text data is arranged in the text field according to the system level.

In addition, the arrangement module may further include a highlight unit for discoloring the color of the text data arranged in the text field according to the system level.

In addition, the text keyword recognition unit classifies terms based on a sorting factor calculated by the following Equation (1) by clustering terms contained in the text data to identify text keywords: .

Equation 1,

는 용어 a에 대한 용어 b의 소팅 팩터,

는 용어 a와 인접한 용어 b에 대한 누적 합,

은 용어 a와 인접한 전체 용어에 대한 누적 합,

는 용어 a와 용어 b 상호간의 소팅 팩터)(here,

Is a sorting factor of the term b for the term a,

Is the cumulative sum of terms a and b,

Is a cumulative sum for the entire term adjacent to the term a,

Is a sorting factor between terms a and b)

The system analysis module may further include a text keyword list generation unit for generating a keyword list for the text keyword and an image keyword list generation unit for generating an image keyword list for the image keyword identified through the input image data, And a large keyword calculation unit for comparing the text keyword list and the image keyword list to calculate a large keyword for the text keyword and the image keyword.

In addition, the main keyword calculation unit may calculate the main keyword and the main keyword for the image keyword according to the level of the linkage level by calculating the linkage degree through the following Equation (2) using the minimum weighting method: .

Equation (2)

는 텍스트키워드리스트에 포함된 전체 텍스트키워드의 빈도수,

은 이미지키워드리스트에 포함된 전체 이미지키워드의 빈도수,

는 텍스트키워드리스트에 포함된 텍스트키워드 중 이미지키워드와 중복되는 중복키워드의 빈도수,

은 이미지키워드리스트에 포함된 이미지키워드 중 텍스트키워드와 중복되는 중복키워드의 빈도수)(here,

The frequency of the full text keyword included in the text keyword list,

The frequency of all image keywords included in the image keyword list,

The number of duplicate keywords duplicated with the image keyword among the text keywords included in the text keyword list,

Is a frequency of a duplicate keyword that overlaps with a text keyword among image keywords included in an image keyword list)

In addition, the arrangement module may further include a text distance adjustment unit for differentially controlling the distance between the text fields according to the degree of association calculated between the large keyword and the text keyword.

In addition, the text distance adjustment unit may control the distance between the text fields based on Equation (3).

Equation 3,

는 텍스트필드 a와 텍스트필드 b 사이의 거리,

는 텍스트필드 사이의 기준거리,

는 텍스트필드 a에 배치된 텍스트자료에 해당하는 텍스트키워드와 대주제키워드 사이의 연계도,

는 텍스트필드 a에 배치된 텍스트자료와 같은 계통레벨인 전체 텍스트자료 중 텍스트필드 a에 포함된 텍스트자료에 해당하는 텍스트키워드의 연계도가중치,

는 텍스트필드 b에 배치된 텍스트자료에 해당하는 텍스트키워드와 대주제키워드 사이의 연계도,

는 텍스트필드 b에 배치된 텍스트자료와 같은 계통레벨인 전체 텍스트자료 중 텍스트필드 b에 포함된 텍스트자료에 해당하는 텍스트키워드의 연계도가중치,

는 텍스트필드 a에 배치된 텍스트자료와 같은 계통레벨인 전체 텍스트자료에 해당하는 텍스트키워드의 평균 연계도)(here,

Is the distance between the text field a and the text field b,

A reference distance between text fields,

A linkage between a text keyword corresponding to the text data arranged in the text field a and the main keyword,

A linkage weight weight of a text keyword corresponding to a text data included in a text field a among the whole text data, which is a system level such as a text data placed in a text field a,

A linkage between a text keyword corresponding to the text data arranged in the text field b and the basic keyword,

The linkage weight of the text keyword corresponding to the text data included in the text field b among the entire text data such as the system level such as the text data placed in the text field b,

Is the average linkage degree of the text keyword corresponding to the entire text data at the system level such as the text data placed in the text field a)

According to the present invention, there is provided an electronic book production system,

1) It reproduces decision-making structure such as placement according to importance and importance in the whole plate form of electronic book in the form of algorithm to reproduce the readability and index function of existing electronic book with minimizing the intervention of editor, It is possible to drastically reduce the number of times that a book can be produced,

2) An image keyword and a text keyword are calculated from an image data and a text data, respectively, and are used not only for systematic assignment but also for large-scale keywords that pass through image keywords and text keywords,

3) It improves the readability and information transmission effect by adjusting the data arrangement based on the linkage between the main keyword and the image keyword and the text keyword passing through the image keyword and the text keyword.

1 is a conceptual diagram showing a schematic configuration of a system of the present invention;
2 is a block diagram showing a basic configuration of a system according to the present invention;
3 is a block diagram showing a detailed configuration of a system of the present invention;
4 is a conceptual diagram of an electronic book page produced through the system of the present invention;

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. The accompanying drawings are not drawn to scale and wherein like reference numerals in the various drawings refer to like elements.

1 is a conceptual diagram showing a schematic configuration of a system 10 of the present invention.

1, an electronic book production system through automatic layout of a board and characters to which a system is applied according to the present invention includes a user 20 for inputting multimedia data and text data including image data to the system 10 And a system 10 for assigning a system to multimedia data and text data inputted by the user 20 and automatically arranging a grid and a grid to which a system is assigned to produce an electronic book.

In this paper, we propose an electronic book production system that automatically assigns a system and a grid to the system, and reproduces decision-making structures such as placement of importance and importance according to importance in an overall layout of an electronic book in an algorithm form, It is possible to reproduce the readability and the indexing function of the existing electronic book in a minimized manner, thereby drastically reducing the number of steps required for electronic book production.

2, an electronic book production system through automatic layout of a board and characters to which a system is assigned according to the present invention is an electronic book production system through automatic layout of a board and a character to which a system is assigned, A data input module 100 for inputting multimedia data and text data including image data for electronic book production from the multimedia data and storing the data in a database, and analyzing the text data and the multimedia data, A system analysis module 200 for grasping and assigning system levels, which are upper and lower classifications according to importance; And a pattern setting module (300) for setting a plate type and a page number of the electronic book, and configuring a template corresponding to the plate type, and a text setting module And a placement module (400) for placing the template in the template.

The data input module 100 receives multimedia data and text data including image data for electronic book production from the user 20 and stores the data in a database. In this case, the multimedia data refers to only the image data But also various multimedia contents that can be provided to users through electronic books such as video data and voice data.

The system analysis module 200 performs a function of analyzing the text data and the multimedia data to grasp the text keyword and the image keyword, respectively, and assigns a system level, which is an upper level and a lower level class, according to the degree of importance. Refers to the subject of the text data, and the image keyword refers to the keyword represented by the image, that is, the subject of the image. In addition, the system level is an upper and a lower classification according to importance. In other words, the level of the text data and the image data belongs to any upper or lower classification. In the case of text data, the main title, subtitle, The system level can be assigned to the main image, the sub image, and the other box image in the case of the image data.

The pattern setting module 300 sets a plate type and a page number of the electronic book and performs a function of forming a template corresponding to the plate type. The pattern setting module 300 is a plate type of an electronic book, for example, a magazine, a newspaper, It is to set a plate type according to various kinds of books such as general literary books and cartoons, to function as a function of the number of pages of electronic books to be published and a template corresponding to the plate type.

The layout module 400 has a function of arranging the text data and the multimedia data to which the system level is assigned in the template according to the system level. In the case of text data, the main title is placed in the main title position and the subtitle in the subtitle position. In the case of the image data, the main image is placed in the main image position, the sub image is placed in the sub image position Place. In this case, since various templates can be configured according to the publication layout, it is needless to say that the layout of the text data and the multimedia data according to the system level can be variously configured.

FIG. 3 is a block diagram illustrating a detailed configuration of the system 10 of the present invention, and FIG. 4 is a conceptual diagram of an electronic book page produced through the system 10 of the present invention.

Referring to FIG. 3, a detailed configuration and a further configuration of an electronic book production system by automatic layout of a board and a character to which the system of the present invention is applied will now be described. In addition, FIG. 4 shows an example of an electronic book page produced using the electronic book production system 10 through the automatic arrangement of the boards and characters to which the system of the present invention is assigned.

First, the system analysis module 200 includes an image database 210 for storing a plurality of reference images in which image keywords are set, an image database 210 for comparing the input image data with the reference image, An image classifier 230 for classifying the image data according to the image keyword, and an image level assigning unit 240 for assigning a system level to the classified image data. .

The image database 210 stores a plurality of reference images in which an image keyword is set. For example, an image keyword of food is set in an image of a plurality of foods, and the image keyword is stored as a reference image, And to classify image keywords into image data through processing.

The image keyword recognizing unit 220 performs a function of comparing the image data inputted thereto with the reference image to grasp the image keyword of the image data. By comparing the uploaded image data with the reference image, Is included.

The image classifier 230 functions to classify the image data according to the image keywords. In general, since one electronic book includes a plurality of image data, image data is classified and processed according to image keywords The arrangement by image keyword is possible in the arrangement by the arrangement module 400 described above.

The image level assigning unit 240 performs a function of assigning a grid level to the classified image data. The description of the grid level may be made by referring to the basic description of the grid analysis module 200 described above. Omit it.

In this arrangement, the image data uploaded by the user 20 can be analyzed and the system level can be assigned. In the arrangement module 400 for arranging the image data in the template on the basis of the system level, The image data is classified based on the keyword and placed in the template, so that the plurality of image data can be more efficiently managed and utilized. Also, since the image data classified in this manner can be stored in the image database 210, the data of the image database 210 is accumulated more and more with the repeated generation of electronic books, thereby increasing the efficiency of keyword analysis and grasp of image data Of course.

In addition, in order to more efficiently analyze image data when the image keyword recognition unit 220 grasps image keywords, the systematic analysis module 200 performs a vectorization process for vectorizing the bitmap image of the image data A processing unit 250, and a scanning processing unit 260 for storing image information obtained by scanning a closed curve of the vectorized image data and a color of each coordinate.

The vectorization processing unit 250 performs a function of vectorizing the bitmap image of the image data. In the case of a bitmap image, since it represents a scalar value, all bits in the image analysis must be analyzed. have. Therefore, the vectorization processing unit 250 can vectorize the bitmap image, thereby shortening the analysis time. At this time, in the method of the vectorization processing, a conventional illustration conversion program, for example, a method of Photoshop, Illustrator, or the like can be referred to, and a detailed description will be omitted.

The scanning processing unit 260 stores the image information obtained by scanning the closed curve of the image data subjected to the vectorization process and the color of each coordinate. The scanning processing unit 260 can recognize the shape of the image data through the scanning of the closed curve, Information on the color of the image can be stored.

In the configuration including the vectorization processing unit 250 and the scanning processing unit 260, the image keyword recognition unit 220 compares the image information with the reference image and grasps the image keyword of the image data The time required for image keyword analysis can be significantly shortened.

In addition, when the vectorization processing unit 250 and the scanning processing unit 260 are included, the position where the closed curve is located in the entire image data, that is, the composition of the image can be more easily grasped, It is possible to arrange the text and the image according to it.

Therefore, in order to implement the above-described configuration, the systematic analysis module 200 may further include a layout coordinate determination unit 270 that grasps the layout coordinates of the closed lines in the image data processed by the vectorization process , The arrangement module 400 includes an image positioning unit 410 for setting the arrangement position of the image data according to the arrangement coordinates and a text positioning unit 410 for setting the arrangement position of the text data according to the arrangement coordinates, (420).

The placement coordinate acquiring unit 270 grasps placement coordinates of the closed curve in the vectorized image data, and grasps the coordinates of the closed curve to grasp the composition of the image data.

The image position determination unit 410 and the text position determination unit 420 respectively set the placement positions of the image data and the text data according to the layout coordinates, The layout position of the image data and the text data of the image data can be set to provide a more stable layout.

In the above-described configuration, the image classifying unit 230 classifies the image data according to the image keyword. For more detailed classification of the image data, the image classifying unit 230 may include an image classification classification part 231 for classifying the image keyword for the image data into image classification, And an image sub-category identification part 232 for classifying the image keyword into image sub-categories that are sub-components of the image sub-category.

The image major classification grasp part 231 functions to classify the image keyword for the image data into image major classes. The image major classification may be used to classify images such as people, objects, food, It becomes a standard for large classification.

The image sub-category identification part 232 functions to sort the image keyword for the image data into image sub-categories that are sub-constituents of the image sub-category. In this case, the image sub- Or a different sorting method such as dividing by age group of infant / youth / young man / old man / old man, or various occupational groups.

Therefore, the image keyword can be grasped as a more detailed keyword through the image classification classification part 231 and the image classification classification part 232, and it is also possible to recognize the image classification data as described above in the image database 210 Even if the data is stored, it is possible to store more detailed data for each keyword.

In the above description of the basic configuration, the arrangement module 400 performs the function of arranging the text data and the multimedia data to which the system level is assigned in the template according to the system level. In this case, the template refers to a basic layout configuration corresponding to the plate type. In this case, the template can be variously modified. In order to improve the efficiency of automatic placement of image data and text data, It is good to assign locations.

To this end, the layout module 400 includes a template division unit 430 for dividing the template into at least two divided regions including an image region and a text region, A layout unit 440, and a text arrangement unit 450 for arranging the text data in the text area.

In the template division unit 430, the placement module 400 divides the template into at least two divided regions including an image region and a text region. The template module 400 divides the template into separate image data or audio data , And when the advertisement data is inserted, it is also possible to divide it into an image area, a voice data insertion area, and an advertisement insertion area.

The image arranging unit 440 and the text arranging unit 450 function to arrange the image data in the image area and the text data in the text area, This configuration can work more efficiently.

In addition, the phylogenetic analysis module 200 includes a text keyword recognition unit 280 for recognizing a text keyword from a term included in the text data, and a text-level recognition unit 280 for assigning a system level to the text data according to the recognized text keyword. And a text keyword selection unit 291 for selecting the text keyword from among the text keywords according to the system level. In addition, the arrangement module 400 may further include a field dividing unit 460 dividing the text area into a plurality of text fields. In this case, the text arranging unit 450 may divide the text area into a plurality of text fields, The text data is arranged in the text field.

The text keyword recognition unit 280 functions to grasp a text keyword from a term included in the text data. Here, the text keyword refers to a keyword having a high frequency of the keywords included in the text data, Keyword.

The text level assigning unit 290 functions to assign a systematic level to the text data according to the recognized text keyword. Since the system level of the text data may be changed depending on which text keyword is included, will be.

The text keyword selector 291 performs a function of selecting the text keyword from among the text keywords according to the system level. In this case, the text keyword may be a text keyword that is typically a subject of a representative title.

In this way, it is possible not only to more efficiently grasp the text keyword from the text data, but also to automatically derive the text keyword from the text keyword.

In addition, the field dividing unit 460 divides the text area into a plurality of text fields, and divides the text area into a text field in which the main title is arranged, a text field in which the subtitle is arranged, a text field in which the main text is arranged, The text arrangement unit 450 arranges the text data in the text field in accordance with the system level so that the text data corresponding to the system level is assigned to the text field having the systematic level, A title, a subtitle, a text title, and the like in an appropriate text field.

The arrangement module 400 may further include a highlight section 470 for discoloring the color of the text data arranged in the text field according to the system level, Of course, it is also possible to provide a highlight effect by discoloring text data which is more conspicuous to the user.

In addition, the text keyword recognition unit 280 performs a function of grasping text keywords from terms included in the text data. In this case, since an electronic book includes a vast amount of text data, It may be difficult to identify and perform the automatic layout.

Accordingly, in order to increase the efficiency of text keyword recognition and increase the speed of text keyword recognition, the text keyword recognition unit 280 classifies terms included in the text data to grasp a text keyword, 1, the clustering of terms is performed based on a sorting factor, thereby increasing the efficiency of text keyword grasping and increasing the speed of grasping text keywords.

Equation 1,

는 용어 a에 대한 용어 b의 소팅 팩터,

는 용어 a와 인접한 용어 b에 대한 누적 합,

은 용어 a와 인접한 전체 용어에 대한 누적 합,

는 용어 a와 용어 b 상호간의 소팅 팩터를 의미한다.)(here,

Is a sorting factor of the term b for the term a,

Is the cumulative sum of terms a and b,

Is a cumulative sum for the entire term adjacent to the term a,

Means a sorting factor between terms a and b.)

By clustering the terms contained in the text data through the clustering using the sorting factors thus calculated, it is possible to extract the text keywords more effectively by grasping the frequency and the relation of the terms in which the terms appear, Of course, in the calculation of the sorting factor, since the relation between the specific term and the adjacent term is used, more effective clustering is possible by calculating the sorting factor based on the relation between the terms.

In addition to the text keywords and the text keywords, an image keyword is calculated from the image data through the above-described configurations. In addition, the entire topic that passes through the text keyword and the image keyword, that is, the main keyword exists in the electronic book .

The system analysis module 200 includes a text keyword list generation unit 292 for generating a keyword list for the text keyword, and a text keyword list generation unit 292 for generating the image keyword An image keyword list generation unit 293 for generating an image keyword list for the text keyword list and the image keyword list by comparing the text keyword list and the image keyword list to generate a large keyword for the text keyword and the image keyword 294). ≪ / RTI >

The text keyword list generating unit 292 generates a keyword list for the text keyword. In the case of an electronic book, the text keyword list generating unit 292 generates a text keyword from an enormous amount of text data, , It is possible to generate a keyword list for comparison processing and to classify between lists.

The image keyword list generation unit 293 has a function and purpose similar to those of the text keyword list generation unit 292. The image keyword list generation unit 293 generates an image keyword list for the image keywords identified through the input image data, Therefore, a detailed description thereof will be omitted.

The large keyword calculation unit 294 performs a function of comparing the text keyword list with the image keyword list to calculate a large keyword for the text keyword and the image keyword. In this case, Method may be used, but it is preferable to calculate the linkage degree through the following equation (2) using the minimum weighting method, and then calculate the text keyword and the main keyword for the image keyword according to the level of the linkage degree .

Equation (2)

는 텍스트키워드리스트에 포함된 전체 텍스트키워드의 빈도수,

은 이미지키워드리스트에 포함된 전체 이미지키워드의 빈도수,

는 텍스트키워드리스트에 포함된 텍스트키워드 중 이미지키워드와 중복되는 중복키워드의 빈도수,

은 이미지키워드리스트에 포함된 이미지키워드 중 텍스트키워드와 중복되는 중복키워드의 빈도수를 의미한다.)(here,

The frequency of the full text keyword included in the text keyword list,

The frequency of all image keywords included in the image keyword list,

The number of duplicate keywords duplicated with the image keyword among the text keywords included in the text keyword list,

Denotes the frequency of duplicate keywords overlapping with the text keyword among the image keywords included in the image keyword list.)

In this case, since the minimum weighting method is applied in Equation (2) and the value is represented by taking log, it is possible to prevent an excessively large correlation value calculated due to a large number of text keywords and a high frequency due to image keyword analysis And the frequency of the duplicate keyword is obtained relative to the frequency of the full-text keyword and the image keyword, respectively, so that the accuracy of the linkage calculation can be further improved.

In addition, if the linkage is calculated in such a manner, it is also possible to modify the layout scheme in the template based on the topic passing through the text keyword and the image keyword, that is, the linkage to the main keyword and each text data do. In order to implement this, the arrangement module 400 further includes a text distance adjustment unit 480 for controlling the distance between the text fields according to the degree of association calculated between the large keyword and the text keyword At this time, the text distance adjustment unit 480 controls the distance between the text fields based on Equation (3).

Equation 3,

는 텍스트필드 a와 텍스트필드 b 사이의 거리,

는 텍스트필드 사이의 기준거리,

는 텍스트필드 a에 배치된 텍스트자료에 해당하는 텍스트키워드와 대주제키워드 사이의 연계도,

는 텍스트필드 a에 배치된 텍스트자료와 같은 계통레벨인 전체 텍스트자료 중 텍스트필드 a에 포함된 텍스트자료에 해당하는 텍스트키워드의 연계도가중치,

는 텍스트필드 b에 배치된 텍스트자료에 해당하는 텍스트키워드와 대주제키워드 사이의 연계도,

는 텍스트필드 b에 배치된 텍스트자료와 같은 계통레벨인 전체 텍스트자료 중 텍스트필드 b에 포함된 텍스트자료에 해당하는 텍스트키워드의 연계도가중치,

는 텍스트필드 a에 배치된 텍스트자료와 같은 계통레벨인 전체 텍스트자료에 해당하는 텍스트키워드의 평균 연계도를 의미한다.)(here,

Is the distance between the text field a and the text field b,

A reference distance between text fields,

A linkage between a text keyword corresponding to the text data arranged in the text field a and the main keyword,

A linkage weight weight of a text keyword corresponding to a text data included in a text field a among the whole text data, which is a system level such as a text data placed in a text field a,

A linkage between a text keyword corresponding to the text data arranged in the text field b and the basic keyword,

The linkage weight of the text keyword corresponding to the text data included in the text field b among the entire text data such as the system level such as the text data placed in the text field b,

Means an average linkage degree of a text keyword corresponding to a whole text data which is a system level such as text data arranged in a text field a.

In Equation (3), the linkage weight between the text keyword and the image major classification corresponding to the text data included in the text field, as well as the linkage weight among the whole text data, such as the text data included in the text field, It is a matter of course that standardized and objectified distance calculation is possible because it reflects the average connection degree together.

As described above, the configuration and operation of the electronic book production system 10 through the automatic arrangement of the system and the electronic book production system according to the present invention are described in the above description and drawings. However, It will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit of the invention.

10: System 20: User
100: data input module 200: grid analysis module
210: image database 220: image keyword recognition unit
230: Image classification section 231: Image classification classification part
232: Understanding image classification part 240: Image level control
250: Vectorization processor 260: Scanning processor
270: Position coordinate detection unit 280: Text keyword detection unit
290: Whether the text level is added or not 291:
292: Text keyword list generation unit 293: Image keyword list generation unit
294: Major word calculation unit 300: Pattern setting module
400: Batch module 410: Image positioning unit
420: text position determination unit 430: template division unit
440: image arrangement unit 450: text arrangement unit
460: field division part 470: highlight part
480: Text distance adjustment section

Claims (13)

An electronic book production system by automatic layout of a board and a character to which a system is assigned,
A data input module for receiving multimedia data and text data including image data for producing electronic books from a user and storing the data in a database;
A system analysis module for analyzing the text data and the multimedia data to grasp a text keyword and an image keyword, respectively, and assigning a system level;
A pattern setting module for setting a plate form and a page number of the electronic book, and configuring a template corresponding to the plate form;
And a layout module for arranging the text data and the multimedia data to which the systematic level is assigned in the template according to the systematic level. system. The method according to claim 1,
The system analysis module includes:
An image database for storing a plurality of reference images in which image keywords are set;
An image keyword recognition unit for comparing the input image data with the reference image to determine an image keyword of the image data;
An image classifier for classifying the image data according to the image keyword,
Further comprising an image level assigning unit for assigning a systematic level to the classified image data. 3. The method of claim 2,
The system analysis module includes:
A vectorization processing unit for vectorizing a bitmap image of the image data;
Further comprising a scanning processor for storing image information obtained by scanning a closed curve of the vectorized image data and a color of each coordinate,
The image keyword recognizing unit,
Wherein the electronic book production system comprises: an electronic book production system for automatically arranging graphics and a systematic drawing board, wherein an image keyword of the image data is recognized by comparing the image information with the reference image The method of claim 3,
The system analysis module includes:
Further comprising a placement coordinate acquiring unit for acquiring placement coordinates of the closed curve in the vectorized image data,
Wherein the arrangement module comprises:
An image positioning unit for setting an arrangement position of the image data according to the arrangement coordinates;
Further comprising a text position determining unit for determining an arrangement position of the text data in accordance with the layout coordinates. 3. The method of claim 2,
Wherein the image classifier comprises:
An image major classification grasp part for classifying the image keyword for the image data into image major classes,
Further comprising an image subclass grasping part for classifying the image keyword for the image data into image subclasses that are subcomponents of the image subclass. . The method according to claim 1,
Wherein the arrangement module comprises:
A template dividing unit dividing the template into at least two divided regions including an image region and a text region;
An image arrangement unit for arranging the image data in the image area,
Further comprising a text arrangement unit for arranging the text data in the text area, wherein the text arrangement unit arranges the text data in the text area. The method according to claim 6,
The system analysis module includes:
A text keyword recognition unit for recognizing a text keyword from a term included in the text data;
A text level assigning step of assigning a grid level to the text data according to the identified text keyword,
Further comprising a text keyword selector for selecting the text keyword from the text keywords according to the system level,
Wherein the arrangement module comprises:
Further comprising a field dividing unit dividing the text area into a plurality of text fields,
The text arrangement unit includes:
And arranging the text data in the text field according to the system level, wherein the text data is arranged in the text field according to the system level. 8. The method of claim 7,
Wherein the arrangement module comprises:
Further comprising a highlight section for discoloring the color of the text data arranged in the text field according to the system level. 8. The method of claim 7,
The text keyword recognizing unit,
The method comprising the steps of: clustering terms contained in the text data to identify text keywords,
Wherein the grouping of terms is performed on the basis of a sorting factor calculated by the following equation (1).
Equation 1,

(here,

Is a sorting factor of the term b for the term a,

Is the cumulative sum of terms a and b,

Is a cumulative sum for the entire term adjacent to the term a,

Is a sorting factor between terms a and b) 8. The method of claim 7,
The system analysis module includes:
A text keyword list generation unit for generating a keyword list for the text keyword,
An image keyword list generating unit for generating an image keyword list for the image keyword that is grasped through the input image data;
Further comprising a main keyword calculation unit operable to compare the text keyword list with the image keyword list to calculate a main keyword for the text keyword and the image keyword, Electronic book production system. 11. The method of claim 10,
Wherein the main keyword calculation unit comprises:
Calculating a linkage degree by using the following formula (2) to which a minimum weighting method is applied, and then calculating a keyword keyword for the text keyword and a keyword for the image keyword according to the degree of the linkage degree, And electronic book production system by automatic arrangement of characters.
Equation (2)

(here,

The frequency of the full text keyword included in the text keyword list,

The frequency of all image keywords included in the image keyword list,

The number of duplicate keywords duplicated with the image keyword among the text keywords included in the text keyword list,

Is a frequency of a duplicate keyword that overlaps with a text keyword among image keywords included in an image keyword list) 11. The method of claim 10,
Wherein the arrangement module comprises:
Further comprising a text distance adjusting unit for controlling the distance between the text fields according to the degree of association calculated between the large keyword and the text keyword. Electronic book production system. 13. The method of claim 12,
Wherein the text distance adjusting unit comprises:
Wherein the distance between the text fields is controlled differently based on Equation (3). ≪ RTI ID = 0.0 > 11. < / RTI >
Equation 3,

(here,

Is the distance between the text field a and the text field b,

A reference distance between text fields,

A linkage between a text keyword corresponding to the text data arranged in the text field a and the main keyword,

A linkage weight weight of a text keyword corresponding to a text data included in a text field a among the whole text data, which is a system level such as a text data placed in a text field a,

A linkage between a text keyword corresponding to the text data arranged in the text field b and the basic keyword,

The linkage weight of the text keyword corresponding to the text data included in the text field b among the entire text data such as the system level such as the text data placed in the text field b,

Is the average linkage degree of the text keyword corresponding to the entire text data at the system level such as the text data placed in the text field a)

Images