KR20170085736A - Apparatus and method for creating information on electronic publication - Google Patents

Abstract

According to an embodiment of the present invention, there is provided an apparatus for generating information about an electronic publication, the apparatus comprising: an input unit for inputting an electronic publication; a storage unit for storing property information indicating a property of the verb for each of a plurality of verbs; A sentence structure grasping unit for extracting a subject and a verb from a plurality of sentences respectively, and a verb structure acquiring unit for acquiring the property information of each of the extracted verbs from the storage unit and associating the verb corresponding to the acquired property information on the basis of the obtained property information A character recognition unit for recognizing a subject as a character in the electronic publication; and an information generation unit for generating information on the identified character.

Description

[0001] APPARATUS AND METHOD FOR CREATING INFORMATION ON ELECTRONIC PUBLICATION [0002]

The present invention relates to an apparatus and method for generating information about electronic publications. More specifically, it is possible to grasp the characters by using the property information indicating the properties of the verb from the sentences constituting the electronic publications, and to obtain information on the characters thus identified, for example, And an information generating apparatus and method for generating information on who the character is.

In recent years, many contents provided as existing paper books have been provided as electronic books (e-books), which are electronic publications. An e-book can be viewed on an e-book-only terminal such as a personal computer (PC), a smart phone, a notebook or a tablet, or through an e-book reader or viewer software.

Electronic books have the form of digitized information. Therefore, in extracting information and constructing extracted information as a database, electronic books are easier than existing paper books. Information on e-books constructed as databases can be used in various ways, for example, in public libraries, university libraries, and book information websites that sell e-books.

Information that can be extracted from an eBook includes, for example, information about the price, information about the author, information about book reviews written online by others, and information about the characters appearing in e-books. Among these, the information about the characters will be discussed in more detail.

In the case of novels among e-books, contents are mainly developed around characters. Therefore, information about the characters in novels, among them the key characters who play a major role in novels, is relatively more important than other genres of electronic books. In addition, in the analysis of books of different genres as well as novels, information on characters can be used in various ways.

In order to extract information on the character from the electronic book, a process of extracting characters from a plurality of texts constituting the electronic book must be performed. In the conventional technique for this purpose, Korean Patent No. 10-1255957 extracts a character using a person dictionary storing the name of a person. According to this, if the sentence constituting the electronic book includes the same word as the name of the person registered in the person dictionary, the word is recognized as referring to the character.

However, such a conventional technique can not recognize a new name that is not listed in the person dictionary as a character. Considering that the name of the character can be arbitrarily constructed and that the name changes continuously according to the age, it is not limited to the character dictionary, and information about the character is the main character It is required to extract information about recognition.

Korea registered patent, 10-1255957 (registered on Apr. 11, 2013)

A problem to be solved by the present invention is to provide a technique for extracting information on a character from electronic publications such as electronic books, for example, information on who is a main character who plays a major role in the electronic publication .

However, the problem to be solved by the present invention is not limited to this

According to an embodiment of the present invention, there is provided an apparatus for generating information about an electronic publication, the apparatus comprising: an input unit for inputting an electronic publication; a storage unit for storing property information indicating a property of the verb for each of a plurality of verbs; A sentence structure grasping unit for extracting a subject and a verb from a plurality of sentences respectively, and a verb structure acquiring unit for acquiring the property information of each of the extracted verbs from the storage unit and associating the verb corresponding to the acquired property information on the basis of the obtained property information A character recognition unit for recognizing a subject as a character in the electronic publication; and an information generation unit for generating information on the identified character.

Also, verbs having the same or similar meaning in the storage unit may have the same property information among each other.

In addition, if the acquired property information is property information related to a behavior of a person, the person identification unit can identify a subject related to the verb corresponding to the acquired property information as a character in the electronic publication.

Also, the sentence structure recognition unit may extract a subject and a verb from the plurality of sentences, respectively, and select a sentence in which at least one subject and a verb are extracted, and the person identification unit identifies the verb's property information included in the selected sentence, And a subject associated with the verb corresponding to the obtained property information is recognized as a character in the electronic publication based on the acquired property information.

The storage unit may store an exclusion list having information on a subject that should be excluded from the character, and the person identification unit may check whether the extracted subject is included in the exclusion list, If it is included in the list, the extracted subject can be excluded when it is recognized as the character.

Further, the information generating unit may add a predetermined value to the main figure corresponding to the subject every time the subject is recognized as a character, and may select a subject having a relatively high main figure as a main character.

In addition, the numerical value added to the main diagram may have a relatively small value in a single sentence including a subject recognized as the character, as the number of subjects included in the single sentence increases.

According to another aspect of the present invention, there is provided a method of generating information, the method comprising: receiving an electronic publication; extracting a subject and a verb from a plurality of sentences constituting the electronic publication; The method comprising the steps of: acquiring, from a storage unit for storing a plurality of verbs, a subject associated with a verb corresponding to the acquired property information as a character in the electronic publication based on the acquired property information; , And generating information on the identified character.

Also, verbs having the same or similar meaning in the storage unit may have the same property information among each other.

Also, in the step of identifying as a character, if the acquired property information is property information related to a behavior of a person, the subject related to the verb corresponding to the acquired property information can be recognized as a character in the electronic publication.

In addition, the step of acquiring the property information, the step of recognizing the subject as a character in the electronic publication, and the step of generating information on the identified character are performed in the extracting step, The subject and verb can be extracted if at least one subject and verb are extracted.

The storage unit may store an exclusion list having information on a subject that should be excluded from the character, and the step of recognizing the character as the character may include checking whether the extracted subject is included in the exclusion list, If the extracted subject is included in the exclusion list, the extracted subject may be excluded when the subject is recognized as the character.

The step of generating the information may include the steps of adding a predetermined value to the main figure corresponding to the subject every time the subject is recognized as a character, and selecting the main subject as a main character Step < / RTI >

In addition, the step of adding a predetermined value to the main figure may include adding a numerical value having a relatively small value in a single sentence including a subject recognized as the character, as the number of subjects included in the one sentence increases have.

A computer program stored in a computer-readable recording medium according to another embodiment of the present invention includes the steps of receiving an electronic publication, extracting a subject and a verb from a plurality of sentences constituting the electronic publication, Acquiring from the storage unit for storing each piece of property information for each of a plurality of verbs; and based on the acquired property information, extracting a subject related to the verb corresponding to the acquired property information from the electronic publication Identifying the person as a character, and generating information on the identified character.

According to another aspect of the present invention, there is provided a computer-readable medium having the steps of receiving an electronic publication, extracting a subject and a verb from a plurality of sentences constituting the electronic publication, Acquiring information on a verb corresponding to the obtained property information from a storage unit for storing each of a plurality of verbs; and acquiring, based on the acquired property information, a subject related to the verb corresponding to the acquired property information as a character in the electronic publication , And a step of generating information on the identified character is recorded.

According to an embodiment of the present invention, information on a character can be extracted from an electronic publication such as an electronic book without using a character dictionary. Therefore, even when the electronic publication includes the name of the character arbitrarily created by the artist, the information on the character can be accurately extracted. Further, in extracting information on who is the main character who plays a major role in the electronic publications, the main characters can be extracted more finely by reflecting the number of subjects included in one sentence.

FIG. 1A is a diagram showing the use of an information generating apparatus according to an embodiment of the present invention.
FIG. 1B is a diagram illustrating an example in which the information generating apparatus according to the embodiment of the present invention provides information to a reader about a character appearing in an electronic publication.
2 is a diagram illustrating a configuration of an information generating apparatus according to an embodiment of the present invention
3A and 3B are diagrams showing that property information is allocated to a plurality of verbs in the storage unit.
FIG. 4 is a diagram showing in detail a configuration of a character figure-of-catcher according to an embodiment of the present invention.
5 is a diagram illustrating steps of an information generating method according to an embodiment of the present invention
FIG. 6 is a detailed view showing a step of generating information on a character in FIG.

BRIEF DESCRIPTION OF THE DRAWINGS The advantages and features of the present invention and the manner of achieving them will become apparent with reference to the embodiments described in detail below with reference to the accompanying drawings. The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art. To fully disclose the scope of the invention to those skilled in the art, and the invention is only defined by the scope of the claims.

Before describing an embodiment of the present invention, an electronic publication refers to an electronic book (e-book) or information in a form of text that can be browsed on the Internet (for example, an Internet newspaper, an Internet magazine, a blog, , But is not limited thereto. The electronic publication is composed of at least one sentence.

FIG. 1A is a diagram illustrating a user's use of an information generating apparatus according to an embodiment of the present invention.

Referring to FIG. 1A, a user terminal 300 used by an information generating apparatus 100 and a user 310 is connected through a network 200. It should be understood, however, that the concept of the present invention is not construed as being limited by the above description,

First, the user terminal 300 receives information about the electronic publications from the information generating apparatus 100 via the network 200 and displays the information. The information displayed on the user terminal 300 includes various pieces of information about the electronic publication, for example, information on prices, information on the author, information on book reviews created by others, information on characters, and the like . FIG. 1B is a diagram exemplarily showing information on a character appearing in an electronic book displayed on the user terminal 300 when the electronic publication is an e-book. Such a user terminal 300 is an apparatus connectable to the Internet, for example, a personal computer, a smart phone, a smart pad, or the like.

The network 200 connects the user terminal 300 and the information generating apparatus 100 and may be implemented by a method such as LAN, 3G, LTE, LTE-A, Wi-Fi or Bluetooth.

The information generating apparatus 100 transmits information about electronic publications to the user terminal 300 through the network 200. [ To this end, the information generating apparatus 100 receives at least one electronic publication and extracts various information from the received electronic publication. The information generating apparatus 100 may be implemented in a server, a personal computer (PC) or the like. In addition, the information generating apparatus 100 may include an online library for providing book information, an online book selling / information providing system operated by a company that sells paper books, an online book selling / information providing system operated by a company that sells electronic books, Information providing system, and the like. Hereinafter, the information generating apparatus 100 will be described in more detail.

2 is a diagram showing a configuration of an information generating apparatus according to an embodiment of the present invention.

2, the information generating apparatus 100 includes an input unit 110, a storage unit 120, a character recognizing unit 130, and an information generating unit 140. As shown in FIG. However, this configuration of the information generating apparatus 100 is for illustrative purposes, so that at least one of the configurations of the information generating apparatus 100 is not included or may not be shown here.

The input unit 110 receives electronic publications. Examples of the way in which the input unit 110 receives (or delivers) electronic publications include a method of receiving electronic publications from a separate database (not shown) storing electronic publications and receiving electronic publications therefrom, A method of receiving an electronic publication stored in the storage medium, or a method of directly receiving an electronic publication from an administrator of the information generating apparatus 100, but the present invention is not limited thereto. The input unit 110 may be a communication port connected to the database, a serial port connected to the USB, or a reader (e.g., CD-ROM) for reading the optical disc.

The storage unit 120 previously stores a plurality of verbs and property information indicating the property of each of the plurality of verbs. The storage unit 120 may be implemented as a memory for storing data. Hereinafter, the property information will be described in more detail.

The property information is information indicating the nature of the verb based on the meaning represented by the verb. Such property information is given to each verb in an institution that researches and manages the language of the country, for example, the National Language Institute. Accordingly, in one embodiment, data obtained by assigning property information to a verb in such an institution may be obtained and stored in the storage unit 120, but the present invention is not limited thereto. 3A is a diagram exemplarily showing property information for each verb. Referring to FIG. 3A, since the verb 'prune' indicates an act of striking a specific object, the property information is a 'directional action verb', and the verb 'generates' something to produce. It is a 'creation act verb'.

Among the verbs stored in the storage unit 120, there are verbs having the same or similar meaning. For example, the verb 'to talk' and the verb 'to communicate' have a similar meaning, and the verb 'wants', 'verb' and 'originate' have similar meanings. For such verbs having the same or similar meaning, the storage unit 120 may be configured to have the same property information.

Meanwhile, the storage unit 120 stores the exclusion list. The exclusion list has at least one name that should be excluded from the characters. As will be described later, in one embodiment, the fact that the subject extracted from the sentence is a character is referred to, and the same subject as the name stored in the exclusion list is not a character regardless of the property information of the verb . Such an exclusion list may be created by an administrator or the like who manages the information generating apparatus 100, and the names included therein may be added, modified or deleted.

The character identification unit 130 can be embodied by a microprocessor for recognizing a character appearing in an electronic publication, a memory for storing a command programmed to perform such a function, and a microprocessor for executing such a command.

Fig. 4 is a diagram showing in more detail the configuration of the character character recognition unit. 4, the character character recognition unit 130 may include a preprocessor 131, a sentence structure recognition unit 133, and a character recognition unit 135. [ Each configuration may be implemented by a memory that stores instructions programmed to perform the functions described below, and a microprocessor that executes such instructions.

The preprocessing unit 131 may separate a plurality of sentences constituting the electronic publication into one sentence. To this end, the preprocessing unit 131 may search for parentheses and remove the searched parentheses and the content within these parentheses. In addition, the preprocessing unit 131 may recognize a period, a comma, an exclamation point, a question mark, or the like, and divide a plurality of sentences into one sentence on the basis of these.

The sentence structure grasping unit 133 extracts subject and verb from each sentence. For this, the sentence structure grasping unit 133 can distinguish a subject from a verb in a sentence using a morpheme analyzer. For example, a sentence structure grasping unit 133 can extract a word combined with an investigation such as 'E', 'E', 'E', or 'G' as a subject of a sentence. However, the technique of analyzing a sentence by morpheme unit and extracting a subject and a verb from the sentence is already known, so a detailed description thereof will be omitted.

The sentence structure grasping unit 133 selects a sentence including at least one subject and a verb among a plurality of sentences as a result of extracting subject and verb. In one embodiment, the person identification unit 135 determines whether the subject included in the sentence corresponds to a character in the corresponding electronic publication, with respect to a sentence including at least one subject and verbs respectively.

The person identification unit 135 acquires the property information of the verb contained in the sentence selected by the sentence structure identification unit 133 from the storage unit 120. [ In addition, the person identification unit 135 determines whether the verb is an action verb based on a person, based on the acquired property information. The act verb, given to a person, means a verb whose subject is a person. FIG. 3B is an exemplary representation of an action verb based on a person.

Here, the person identification unit 135 can determine whether the verb is an action verb based on the person, based on the property information, by using the following method. For example, if the property information of the verb belongs to any one of the pre-specified property information, it can be determined that the verb is an action verb based on a person. For example, a verb with property information of 'result action verb', 'directional verb' or 'creation verb' may be predefined as an action verb based on a person. Therefore, if the property information of the verb corresponds to any one of them, the verb can be judged as an action verb based on the person. However, the present invention is not limited to the above-described method. For example, the person identification unit 135 can determine whether the verb is an action verb based on a person, using the stem between the stem and the mother of the verb.

On the other hand, the person identification unit 135 checks whether or not the subject extracted by the sentence structure recognition unit 133 is included in the exclusion list stored in the storage unit 120. [ As a result of the check, if the extracted subject is included in the exclusion list, the process of determining whether the subject is a character (the process of referring to the property information of the verb mentioned above) is not performed with respect to the extracted subject, do. Through this process, it is possible to perform a process of determining whether a character is a character only for a part of subjects, not all subjects. Therefore, resources and time required to identify characters can be saved.

If the verb determination unit 135 determines that the verb is an action verb that takes a person as a subject, the subject recognition unit 135 identifies the subject related to the verb as a character in the electronic publication.

On the basis of this, in one embodiment, it is possible to know whether or not a subject is a character in an electronic publication by using the property information of the verb without using a person dictionary. Therefore, even when the name of the character is arbitrarily set by the artist, the information on the character can be accurately extracted.

The information generation unit 140 generates information on the characters identified by the character identification unit 135. [ The information on the character to be generated may be, for example, information on who is the main character that occupies a relatively large portion of the characters. The information generation unit 140 may be implemented by a memory that stores instructions programmed to perform such functions and a microprocessor that executes such instructions.

More specifically, in order to select a major character, the information generation unit 140 determines the number of times a subject is recognized as a character, and calculates a main figure based on the number of times. For example, assume that A, B, C, and D are identified as characters 3, 8, 7, and 6, respectively, in an electronic publication. In this case, the main figures of characters from A to D are calculated by adding predetermined numerical values each time they are identified as characters. According to this, the main diagrams A to D can be 3, 8, 7, and 6, respectively, as a result of adding a predetermined value of 1 each time it is identified as a character.

At this time, the information generating unit 140 may calculate the main figure by multiplying the added value ('1' in the above) by a weight, and adding the multiplied value to the added value every time the character is recognized as a character. The weights are smaller as the number of subjects included in one sentence is larger. For example, in the sentence "Eat a meal", the number of subjects is 1, so the weight is 10, and in the sentence "Eat and eat rice", the number of subjects is 2, so the weight is 2, In the sentence "eat this rice", the weight is 1, since the number of subject is 3, and the number of subject is 4 in '

Typically, a major character has many actions in isolation, while an incidental character has many behaviors with others. In other words, if the number of times the character (electronic) acting as a sole person is judged as the subject and the number of times the character (latter) acting as the subject is judged as the subject is the same in the embodiment, In order to estimate higher than the latter, the weight is reflected according to the number of subjects. However, the method of reflecting the weight is exemplary, and thus the idea of the present invention is not limited thereto. Various methods for distinguishing the main characters from the auxiliary characters, which are not disclosed here, can be applied.

As described above, according to one embodiment, it can be determined whether or not a subject is a character by using the property information of the verb. Thus, characters can be grasped more precisely from electronic publications without reference to fixed criteria such as person dictionary.

In addition, by calculating the weights and the major figures according to the number of subjects included in one sentence, and by generating information on the major characters from the characters based on the main figure, Can be selected more precisely than the main characters by the number of appearances.

5 is a diagram illustrating steps of an information generating method according to an embodiment of the present invention. The information generating method shown in FIG. 5 can be performed by the information generating apparatus 100 shown in FIG.

Referring to FIG. 5, step S100 of receiving an electronic publication is performed. A method of receiving (or transmitting) electronic publications includes, for example, a method of receiving electronic publications from a separate database (not shown) for storing electronic publications, a method of receiving electronic publications therefrom, a method of connecting to a storage medium such as a USB or an optical disk A method of receiving electronic publications stored therein, or a method of directly receiving an electronic publication from an administrator of the information generating apparatus 100, but the present invention is not limited thereto.

Next, a step S200 of extracting a subject and a verb from a plurality of sentences constituting the electronic publication is performed. In this step S200, a plurality of sentences constituting the electronic publications are separated into respective sentences. Then, subject and verb are extracted from each separated sentence. In this case, the subject and the verb can be distinguished in the sentence using the morpheme analyzer as described above. Then, sentences containing at least one subject and verb are selected from a plurality of sentences. That is, in one embodiment, a sentence including at least one subject and verb is determined, and it is determined whether the subject included in the sentence corresponds to a character in the corresponding electronic publication.

Next, with respect to the sentence selected in step S200, step S300 of obtaining the property information of the verb included in the sentence is performed. Since the property information is stored in advance in the storage unit 120 shown in FIG. 2, it can be acquired from the storage unit 120. FIG. Then, based on the acquired property information, it is determined whether the verb is an action verb that takes a person as a subject. An act that takes a person as a verb means the verb that the subject of the act is a person, as described above.

At this time, it is checked whether or not the subject extracted in step S200 is included in the exclusion list stored in the storage unit 120. If the extracted subject is included in the exclusion list, the person identification unit 135 extracts the subject Is excluded from the character without performing the process of determining whether the character is a character (the process of referring to the property information of the verb mentioned above). Through this, the person identification unit 135 can perform a process of determining whether or not the subject is only the subject of some subject but not all subjects. Therefore, it is possible to save resources and time required to identify characters.

Thereafter, if the verb is judged to be an action verb with a person as a subject, a step (S400) of recognizing the subject related to the verb as a character in the electronic publication is performed.

On the basis of this, in one embodiment, it is possible to extract information about the character of the electronic publication using the property information of the verb without using the character dictionary. Therefore, the name of the character arbitrarily created by the artist can be extracted as the character's name.

Next, a step S500 of generating information on the characters is performed. The information about the character is, for example, a major character that occupies a relatively large portion of the characters.

6, in order to select a major character, a main figure is calculated for each subject based on the number of times a subject is recognized as a character (S510). At this time, the information generating unit 140 may multiply the added value every time it is recognized as a character, multiply the weighted value, and add the value multiplied by the weighted value to calculate the main figure. The weighted value is included in one sentence The larger the number of subjects is, the smaller the number of subjects is.

Then, a main character is selected from the characters based on the main figure (S520).

As described above, according to one embodiment, it can be determined whether or not a subject is a character by using the property information of the verb. Thus, characters can be grasped more precisely from electronic publications without reference to fixed criteria such as person dictionary.

In addition, by calculating the weights and the major figures according to the number of subjects included in one sentence, and by generating information on the major characters from the characters based on the main figure, Can be selected more precisely than the main characters by the number of appearances.

Meanwhile, a method of generating information according to an embodiment of the present invention includes a computer program stored in a computer recording medium programmed to perform each step included in the method, or a program including an instruction to perform each step included in the method And may be embodied as a computer-readable recording medium recorded thereon.

Combinations of each step of the flowchart and each block of the block diagrams appended to the present invention may be performed by computer program instructions. These computer program instructions may be loaded into a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus so that the instructions, which may be executed by a processor of a computer or other programmable data processing apparatus, And means for performing the functions described in each step are created. These computer program instructions may also be stored in a computer usable or computer readable memory capable of directing a computer or other programmable data processing apparatus to implement the functionality in a particular manner so that the computer usable or computer readable memory It is also possible for the instructions stored in the block diagram to produce a manufacturing item containing instruction means for performing the functions described in each block or flowchart of the block diagram. Computer program instructions may also be stored on a computer or other programmable data processing equipment so that a series of operating steps may be performed on a computer or other programmable data processing equipment to create a computer- It is also possible that the instructions that perform the processing equipment provide the steps for executing the functions described in each block of the block diagram and at each step of the flowchart.

Also, each block or each step may represent a module, segment, or portion of code that includes one or more executable instructions for executing the specified logical function (s). It should also be noted that in some alternative embodiments, the functions mentioned in the blocks or steps may occur out of order. For example, two blocks or steps shown in succession may in fact be performed substantially concurrently, or the blocks or steps may sometimes be performed in reverse order according to the corresponding function.

The above description is merely illustrative of the technical idea of the present invention, and various modifications and changes may be made by those skilled in the art without departing from the essential characteristics of the present invention. Therefore, the embodiments disclosed in the present invention are intended to illustrate rather than limit the scope of the present invention, and the scope of the technical idea of the present invention is not limited by these embodiments. 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 thereof should be construed as falling within the scope of the present invention.

100: Information generating device
110: input unit 120: storage unit
130: Charactor identification unit 140:

Claims (16)

An input unit for receiving electronic publications,
A storage unit for storing property information indicating a property of a verb for each of a plurality of verbs;
A sentence structure recognition unit for extracting a subject and a verb from a plurality of sentences constituting the electronic publication, a feature extraction unit for extracting the feature information of each extracted verb from the storage unit, A character recognition unit for recognizing a subject associated with a verb corresponding to the electronic publication as a character in the electronic publication;
And an information generating unit for generating information on the identified character
Information generating device for electronic publications.
The method according to claim 1,
In the storage section,
Verbs with the same or similar meaning have the same property information
Information generating device for electronic publications.
The method according to claim 1,
The person-
If the obtained property information is property information related to a behavior of a person, a subject related to the verb corresponding to the acquired property information is identified as a character in the electronic publication
Information generating device for electronic publications.
The method according to claim 1,
The sentence structure determination unit selects a sentence in which at least one subject and verb are extracted from the plurality of sentences,
The person-
Acquiring property information of the verb included in the selected sentence from the storage unit and identifying a subject related to the verb corresponding to the acquired property information as a character in the electronic publication based on the acquired property information
Information generating device for electronic publications.
The method according to claim 1,
The storage unit stores an exclusion list having information on a subject that should be excluded from the character,
The person-
Checking whether the extracted subject is included in the exclusion list, and if the extracted subject is included in the exclusion list, extracting the extracted subject from the character
Information generating device for electronic publications.
The method according to claim 1,
Wherein the information generating unit comprises:
Each time a subject is recognized as a character, a predetermined value is added to a main figure corresponding to the subject, a main subject having a higher degree is selected as a main character in the character, Information on the character is generated as information on the character
Information generating device for electronic publications.
The method according to claim 6,
The numerical value added to the above-
In a single sentence including a subject recognized as the character, the larger the number of subjects included in the one sentence, the smaller the value
Information generating device for electronic publications.
Receiving an electronic publication,
Extracting a subject and a verb from a plurality of sentences constituting the electronic publication,
Acquiring property information of each of the extracted verbs from a storage unit that stores property information for each of a plurality of verbs;
Identifying a subject associated with the verb corresponding to the obtained property information as a character in the electronic publication based on the acquired property information;
And generating information on the identified character
A method for generating information about electronic publications.
9. The method of claim 8,
In the storage section,
Verbs with the same or similar meaning have the same property information
A method for generating information about electronic publications.
9. The method of claim 8,
The step of recognizing the character as the character comprises:
If the obtained property information is property information related to a behavior of a person, a subject related to the verb corresponding to the acquired property information is identified as a character in the electronic publication
A method for generating information about electronic publications.
9. The method of claim 8,
The method comprising: acquiring the property information; identifying the subject as a character in the electronic publication; and generating information on the identified character,
In the extracting step, a subject and a verb are extracted from the plurality of sentences, respectively, and at least one subject and a verb are extracted and extracted
A method for generating information about electronic publications.
9. The method of claim 8,
The storage unit stores an exclusion list having information on a subject that should be excluded from the character,
The step of recognizing the character as the character comprises:
Checking whether the extracted subject is included in the exclusion list,
And if the extracted subject is included in the exclusion list, excluding the extracted subject from the character
A method for generating information about electronic publications.
9. The method of claim 8,
Wherein the step of generating the information comprises:
Adding a predetermined value to the main figure corresponding to the subject each time the subject is recognized as a character;
Selecting a main subject having a relatively high main figure as a main character and generating information on the selected main character as information on the identified character
A method for generating information about electronic publications.
14. The method of claim 13,
Wherein the step of adding a predetermined value to the main figure comprises:
In one sentence including a subject recognized as the character, a value having a relatively small value is added to the number of subjects included in the one sentence
A method for generating information about electronic publications.
Receiving an electronic publication,
Extracting a subject and a verb from a plurality of sentences constituting the electronic publication,
Acquiring property information of each of the extracted verbs from a storage unit that stores property information for each of a plurality of verbs;
Identifying a subject associated with the verb corresponding to the obtained property information as a character in the electronic publication based on the acquired property information;
And generating information about the identified character
A computer program stored on a computer readable recording medium.
Receiving an electronic publication,
Extracting a subject and a verb from a plurality of sentences constituting the electronic publication,
Acquiring property information of each of the extracted verbs from a storage unit that stores property information for each of a plurality of verbs;
Identifying a subject associated with the verb corresponding to the obtained property information as a character in the electronic publication based on the acquired property information;
And a step of generating information on the identified character by executing the step of:
Computer readable recording medium.

Images