WO2017122872A1

WO2017122872A1 - Device and method for generating information on electronic publication

Info

Publication number: WO2017122872A1
Application number: PCT/KR2016/003347
Authority: WO
Inventors: 김승훈; 김기원; 김서희; 박태근; 안희정; 윤종률; 이원진; 이재동; 홍민하
Original assignee: 단국대학교 산학협력단
Priority date: 2016-01-15
Filing date: 2016-03-31
Publication date: 2017-07-20
Also published as: KR101781597B1; KR20170085736A

Abstract

According to one embodiment of the present invention, a device for generating information on an electronic publication comprises: an input unit for receiving an electronic publication; a storage unit for storing, for each of a plurality of verbs, feature information indicating features of verbs; a character figure identification unit including a sentence structure identification unit for extracting each of subjects and verbs from a plurality of sentences constituting the electronic publication, and a character identification unit for acquiring feature information on each of the extracted verbs from the storage unit and identifying the subject related to the verb corresponding to the acquired feature information, as a character figure in the electronic publication, on the basis of the acquired feature information; and an information generating unit for generating information on the identified character figure.

Description

Apparatus and method for generating information about an electronic publication

The present invention relates to an apparatus and method for generating information about an electronic publication. More specifically, the characters are identified by using the property information indicating the properties of the verbs from the sentences constituting the electronic publication, and the information about the characters identified in this way, for example, the main portion of the electronic publication with a high proportion of characters. An information generating apparatus and method for generating information on who a character is.

Recently, many contents provided by existing paper books have been provided as e-books, which are a kind of electronic publications. The e-book can be viewed through an e-book reader or viewer software in an e-book dedicated terminal such as a personal computer (PC), smart phone, notebook or tablet.

Ebooks take the form of digitized information. Therefore, in extracting information and building the extracted information into a database, an e-book is easier than a conventional paper book. The information on the e-book constructed as a database can be variously used, for example, in a public library, a university library, or a book information providing site that sells e-books.

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

In the case of novels in e-books, the content mainly develops around the characters. Therefore, information about the characters in the novel, and among them, who is the main character who plays a major role in the novel, is more important than the e-books of other genres. In addition, in the analysis of books of other genres as well as novels, information on characters can be used in various ways.

In order to extract information about the characters from the e-book, a process of extracting the characters from a plurality of sentences constituting the e-book should be performed. As a conventional technique for this purpose, Korean Patent No. 10-1255957 extracts a person using a person dictionary that stores the person's name. According to this, if the sentence constituting the e-book contains the same word as the name of the person listed in the person dictionary, it is recognized that the word refers to the person.

However, this conventional technique cannot recognize a new name that is not listed in the person dictionary as a person. Considering that the names of the characters can be arbitrarily chosen and that the names continue to change according to the times, who is the main character who plays a major role in information about the characters, among them, without being restricted in the dictionary of characters. A method of extracting information about cognition is required.

The problem to be solved by the present invention is to provide a technique for extracting information about the characters from the electronic publication, such as an e-book, for example, who is the main character who plays a major role in the electronic publication. .

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

An information generating apparatus for an electronic publication according to an embodiment of the present invention includes an input unit for receiving an electronic publication, a storage unit storing property information representing a property of a verb for each of a plurality of verbs, and configuring the electronic publication. A sentence structure grasping unit for extracting a subject and a verb from a plurality of sentences, and obtaining property information of each of the extracted verbs from the storage unit and related to a verb corresponding to the obtained property information based on the obtained property information And a person identification unit including a person identification unit for identifying a subject as a person in the electronic publication, and an information generation unit for generating information about the identified person.

In addition, the verbs having the same or similar meanings in the storage unit may have the same property information.

The person identifying unit may identify a subject related to a verb corresponding to the acquired property information as a person in the electronic publication, if the acquired property information is property information related to an action of a person.

In addition, the sentence structure determiner is a result of extracting a subject and a verb from each of the plurality of sentences, the subject and the verb is extracted at least one sentence, the person grasping portion is stored in the property information of the verb included in the selected sentence Based on the acquired property information, a subject related to a verb corresponding to the obtained property information may be identified as a person in the electronic publication.

In addition, the storage unit stores an exclusion list having information on the subject to be excluded from the character, the person identifying unit checks whether the extracted subject is included in the exclusion list, and the extracted subject is excluded If it is included in the list, the extracted subject may be excluded when it is identified as the character.

In addition, whenever the subject is identified as a person, the information generator may add a predetermined value to a main degree corresponding to the subject, and select a subject having a relatively high main degree as the main character.

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

An information generating method according to an embodiment of the present invention comprises the steps of receiving an electronic publication, extracting a subject and a verb from a plurality of sentences constituting the electronic publication, and extracting property information of each of the extracted verbs, Acquiring from a storage for storing each of a plurality of verbs; identifying a subject associated with a verb corresponding to the acquired property information as a person in the electronic publication based on the obtained property information; And generating information on the identified person.

In the identifying as the person, when the acquired property information is property information related to a person's behavior, a subject related to a verb corresponding to the obtained property information may be recognized as a person in the electronic publication.

The acquiring of the property information, identifying the subject as a person in the electronic publication, and generating information about the identified person may include extracting the information from the plurality of sentences. Result of extracting subject and verb respectively It can be performed if at least one subject and verb is extracted.

In addition, the storage unit stores an exclusion list having information on a subject to be excluded from the character, and the step of identifying as the character includes 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 further include a step of excluding when identifying as the character.

The generating of the information may include adding a predetermined value to a main degree corresponding to the subject whenever the subject is identified as a character, and selecting a subject having a relatively high main degree as the main character. It may include a step.

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

According to another embodiment of the present invention, a computer program stored in a computer-readable recording medium may include receiving an electronic publication, extracting subjects and verbs from a plurality of sentences constituting the electronic publication, and extracting the extracted verbs. Obtaining each property information from a storage for storing each of the plurality of verbs, and based on the obtained property information, a subject related to the verb corresponding to the obtained property information in the electronic publication. And identifying the person and generating the information about the identified person.

According to another embodiment of the present invention, a computer-readable recording medium may include receiving an electronic publication, extracting subjects and verbs from a plurality of sentences constituting the electronic publication, and properties of each of the extracted verbs. Acquiring information from a storage for storing each of a plurality of verbs; and identifying a subject related to the verb corresponding to the acquired property information as a character in the electronic publication, based on the obtained property information. And a command for performing the step of generating information on the identified person.

According to an embodiment of the present invention, information about a person may be extracted from an electronic publication such as an e-book without using a person dictionary. Therefore, even when the electronic publication includes names of characters randomly written by the author, information on the characters can be accurately extracted. In addition, in extracting information on who is the main character who plays a major role in the electronic publication, the main character can be extracted in more detail by reflecting the number of subjects included in one sentence.

1A is a diagram illustrating the use of an information generating device according to an embodiment of the present invention.

FIG. 1B is a diagram exemplarily illustrating that an information generating apparatus according to an embodiment of the present invention provides a reader with information about a person who appears 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 illustrating that property information is allocated to a plurality of verbs in a storage unit.

4 is a diagram illustrating in detail the configuration of the person identification unit 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 diagram illustrating in detail a step of generating information on a person in FIG. 5.

Advantages and features of the present invention and methods for achieving them will be apparent with reference to the embodiments described below in detail with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but can be implemented in various different forms, and only the embodiments make the disclosure of the present invention complete, and the general knowledge in the art to which the present invention belongs. It is provided to fully inform the person having the scope of the invention, which is defined only by the scope of the claims.

Prior to describing an embodiment of the present invention, an electronic publication refers to an e-book or textual information (eg, an internet newspaper, an internet magazine, a blog, etc.) that can be viewed on the Internet. However, the present invention is not limited thereto. An electronic publication consists of at least one sentence.

1A is a diagram illustrating a user using an information generating apparatus according to an embodiment of the present invention.

Referring to FIG. 1A, the information generating apparatus 100 and the user terminal 300 used by the user 310 are connected through the network 200. However, since FIG. 1A is exemplary, the spirit of the present invention is not limited to the illustrated embodiment.

First, the user terminal 300 receives information about the electronic publication from the information generating apparatus 100 through the network 200 and displays it. The information displayed on the user terminal 300 includes various information about the electronic publication, for example, information on prices, information on authors, information on book reviews written by others, information on characters, and the like. . FIG. 1B is a diagram exemplarily illustrating that information about a person who appears in an e-book is displayed on the user terminal 300 when the electronic publication is an e-book. The user terminal 300 is a device that can be connected to the Internet, and may be, for example, a personal computer, a smartphone, or a smart pad.

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

The information generating apparatus 100 transmits the information about the electronic publication 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 is an online library for providing book information, an online book sales / information system operated by a company that sells paper books, or an online e-book sales / operated by a company that sells e-books. Applicable to an information providing system. Hereinafter, the information generating apparatus 100 will be described in more detail.

Referring to FIG. 2, the information generating apparatus 100 includes an input unit 110, a storage unit 120, a character identifying unit 130, and an information generating unit 140. However, since the configuration of the information generating apparatus 100 is exemplary, at least one of the components may not be included or a configuration not shown here may be further included.

The input unit 110 receives an electronic publication. The input unit 110 receives (or transmits) an electronic publication, for example, is connected to a separate database (not shown) for storing the electronic publication and receives the electronic publication therefrom, such as a USB or an optical disk. A method of receiving an electronic publication stored in the storage medium connected to the storage medium or a method of directly receiving an electronic publication from an administrator of the information generating apparatus 100 may be used. The input unit 110 may be a communication port connected to a database, a serial port connected to a USB, or a reader (for example, a CD-ROM) that reads an optical disk.

The storage unit 120 stores in advance a plurality of verbs and property information indicating the properties 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.

Property information is information indicating the property of a verb based on the meaning of the verb. This property information is given for each verb in an institution that studies and manages the language of the country, for example, the National Institute of the Korean Language. Thus, in one embodiment, such an institution may obtain and store data in which the property information is assigned to the verb in the storage unit 120, but is not limited thereto. 3A is a diagram exemplarily illustrating property information for each verb. Referring to FIG. 3A, since the verb 'price' refers to an act of hitting a specific object, the property information is 'directional action verb', and the verb 'process' refers to an action of generating something. 'Creative act verbs'.

Among the verbs stored in the storage unit 120 are verbs having the same or similar meanings. For example, the verb 'to speak' and the verb 'to converse' have similar meanings, and the verb 'want', the verb 'to sea' and the verb 'to come' have similar meanings to one another. For the verbs having the same or similar meanings as described above, the storage 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 character. As will be described later, in one embodiment, in determining whether a subject extracted from a sentence is a character, reference is made to the property information of a verb, and a subject identical to a name stored in an exclusion list is not a character regardless of the property information of the verb. Is considered. Such an exclusion list may be created by an administrator or the like who manages the information generating apparatus 100, and names included therein may be added, modified, or deleted.

The character identifying unit 130 may identify the characters appearing in the electronic publication, and may be embodied by a memory for storing instructions programmed to perform such a function, and a microprocessor for performing the instructions.

4 is a view showing in more detail the configuration of such a character identification unit. Referring to FIG. 4, the character determiner 130 may include a preprocessor 131, a sentence structure determiner 133, and a person determiner 135. Each configuration may be implemented by a memory storing instructions programmed to perform a function to be described later, and a microprocessor performing such instructions.

The preprocessor 131 may separate a plurality of sentences constituting the electronic publication into one sentence. To this end, the preprocessor 131 may search the parentheses, and may remove the searched parentheses and the contents in the parentheses. In addition, the preprocessor 131 may recognize a period, a comma, an exclamation point, or a question mark, and then separate the plurality of sentences into one sentence based on these.

The sentence structure determining unit 133 extracts a subject and a verb from each sentence. To this end, the sentence structure determiner 133 may distinguish between a subject and a verb in a sentence using a morpheme analyzer. For example, the sentence structure grasping unit 133 may extract the sentence as a subject of a sentence associated with a search such as 'silver', 'silver', 'yi' or 'ga'. However, since the technique of analyzing the sentence in morpheme units and extracting the subject and the verb from the sentence is already known, a detailed description thereof will be omitted.

As a result of extracting the subject and the verb, the sentence structure determining unit 133 selects a sentence including at least one of the subject and the verb from a plurality of sentences. In one embodiment, the person identifying unit 135 determines whether the subject included in the sentence corresponds to a person in the electronic publication, based on a sentence including at least one subject and a verb each.

The person grasping unit 135 obtains, from the storage 120, property information of a verb included in a sentence selected by the sentence structure grasping unit 133. In addition, the person grasping unit 135 determines whether the verb is an action verb given to a person based on the acquired property information. As a subject, an action verb means a verb whose subject is a person. 3B exemplarily shows an action verb based on a person.

Here, the person grasping unit 135 may determine whether the verb is an action verb 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 predetermined property information, such a verb can be discriminated as an action verb with a human subject. For example, a verb having the property information of 'result behavior verb', 'directional behavior verb' or 'creation behavior verb' may be designated as an action verb whose subject is the subject. Therefore, if the property information of the verb corresponds to any one of the above, the verb may be determined as an action verb with a subject. However, this is merely an example, and the inventive concept is not limited to this method. For example, the person grasping unit 135 may determine whether a verb is an action verb to which a person is given using a stem, among stems and endings constituting a verb.

On the other hand, the person grasping unit 135 checks whether the subject extracted by the sentence structure grasping 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 identifying whether the subject is a character (referring to the above-described verb property information) is not performed on the extracted subject, and is immediately excluded from the character. do. Through this, a process of determining whether a character is present for only some subjects but not all subjects may be performed. Thus, resources and time required to identify the characters can be saved.

If it is determined that the verb is an action verb with a subject, the person grasping unit 135 identifies the subject associated with the verb as a character in the electronic publication.

On the basis of this, in one embodiment, it is possible to determine whether a subject is a character in an electronic publication by using verbal property information without using a person dictionary. Therefore, even when the name of the person is arbitrarily named by the artist, information on the person can be accurately extracted.

The information generating unit 140 generates information on the person identified by the person identifying unit 135. The information on the generated characters may be, for example, information on who are the main characters who occupy a relatively large proportion of the characters. The information generating unit 140 may be implemented by a memory for storing instructions programmed to perform such a function and a microprocessor that executes the instructions.

In more detail, in order to select the main characters, the information generating unit 140 determines the number of times that the subject is identified as the characters, and calculates the main degree based on the number of times. For example, suppose that A, B, C, and D are identified as characters 3, 8, 7, and 6 in any electronic publication, respectively. In this case, the main degree of the characters from A to D is calculated by adding a predetermined value each time each is identified as a character. According to this, the main maps from A to D may be 3, 8, 7, and 6 as a result of adding 1, which is a predetermined value each time each is identified as a character.

At this time, the information generation unit 140 may calculate the principal degree by multiplying the weight added to each added value ('1' in the above) each time it is identified as a character, and then adding the multiplied value. The weight has a smaller value as the number of subjects included in one sentence increases. For example, in the sentence "Gap eats rice", the number of subjects is 1 because the number of subjects is 1, and in the sentence "Gap and Eul eats", the weight of the subject is 2, so the weight is 2, In the sentence 'Eating rice', the number of subjects is three, so the weight is 1, and in 'A, B, and B, the class eats', the number of subjects is four, so the weight may be zero.

Typically, the main character has many actions alone, while the secondary character has many actions with others. Reflecting this, in one embodiment, when the number of times the person (the former) acting alone is determined to be the same as the number of times the person (the latter) acting together with others is determined to be the same, the main figure of the former In order to calculate the higher than the latter main degree, the weight is reflected according to the number of subjects as above. However, since the method of reflecting the weight is exemplary, the spirit of the present invention is not limited thereto, but various methods for distinguishing the main character and the incidental character may be applied, although not disclosed herein.

As described above, according to an embodiment, whether or not the subject is a character may be determined using property information of a verb. Thus, it is possible to more accurately identify a person from an electronic publication without referring to fixed criteria such as a person dictionary.

In addition, by considering the number of subjects included in one sentence, the weight and the corresponding main road are calculated, and based on the main road, information about who the main person is from the characters is generated, and the character is simply. It is possible to select the main characters more accurately than to select the main characters only 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 illustrated in FIG. 5 may be performed by the information generating apparatus 100 illustrated in FIG. 2.

Referring to FIG. 5, an operation S100 of receiving an electronic publication is performed. The method of receiving (or transmitting) an electronic publication may include, for example, connecting to a separate database (not shown) for storing the electronic publication and receiving the electronic publication therefrom, or to a storage medium such as a USB or an optical disk. There may be a method of receiving the electronic publication stored therein or a method of directly inputting any electronic publication from an administrator of the information generating apparatus 100, but is not limited thereto.

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

Next, with respect to the sentences selected in step S200, step S300 of obtaining property information of verbs included in such sentences is performed. Since the property information is previously stored in the storage unit 120 illustrated in FIG. 2, the property information may be obtained from the storage unit 120. Subsequently, it is determined whether the verb is an action verb based on the acquired property information. The action verb which has a human subject means the verb whose subject is a person as the above-mentioned.

At this time, it is checked whether the extracted subject in the step S200 is included in the exclusion list stored in the storage unit 120, and if the extracted subject is included in the exclusion list, the person identification unit 135 extracts the extracted subject. Is excluded from the character without performing the process of identifying whether or not it is a character (referring to the above-described verbal property information). Through this, the person grasping unit 135 may perform a process of identifying whether the person is a character for only some of the subjects instead of all subjects. Therefore, it is possible to save the resources and time required to identify the characters.

Subsequently, if it is determined that the verb is an action verb based on a person, a step (S400) of identifying a subject related to the verb as a character in the electronic publication is performed.

Based on this, in one embodiment, information on the characters of an electronic publication may be extracted using property information of a verb without using a person dictionary. Therefore, the names of the characters randomly created by the artist can be extracted as the names of the characters.

Next, an operation (S500) of generating information on the person is performed. For example, the information on the characters indicates the main characters who occupy a relatively large portion of the characters, as described above.

Looking in more detail with reference to Figure 6, in order to select the main character, the main figure is calculated for each subject based on the number of times the subject is identified as the character (S510). At this time, the information generating unit 140 may multiply the added value every time it is identified as a character, and then calculate the main degree by adding the multiplied weight value, wherein the weight is included in one sentence. As the number of subjects becomes larger, the smaller is as described above.

Subsequently, a main character is selected from the characters based on the main degree (S520).

On the other hand, the information generating method 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 instructions for performing each step included in the method. It may be implemented as a recorded computer readable recording medium.

Combinations of each block of the block diagrams and respective steps of the flowcharts attached to the present invention may be performed by computer program instructions. These computer program instructions may be mounted on a processor of a general purpose computer, special purpose computer, or other programmable data processing equipment such that instructions executed through the processor of the computer or other programmable data processing equipment may not be included in each block or flowchart of the block diagram. It will create means for performing the functions described in each step. These computer program instructions may be stored in a computer usable or computer readable memory that can be directed to a computer or other programmable data processing equipment to implement functionality in a particular manner, and thus the computer usable or computer readable memory. It is also possible for the instructions stored in to produce an article of manufacture containing instruction means for performing the functions described in each block or flowchart of each step of the block diagram. Computer program instructions may also be mounted on a computer or other programmable data processing equipment, such that a series of operating steps may be performed on the computer or other programmable data processing equipment to create a computer-implemented process to create a computer or other programmable data. Instructions that perform processing equipment may also provide steps for performing the functions described in each block of the block diagram and in each step of the flowchart.

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

The above description is merely illustrative of the technical idea of the present invention, and those skilled in the art to which the present invention pertains may make various modifications and changes without departing from the essential quality of the present invention. Therefore, the embodiments disclosed in the present invention are not intended to limit the technical idea of the present invention but to describe 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 interpreted by the following claims, and all technical ideas that fall within the scope of equivalents should be construed as being included in the scope of the present invention.

Claims

An input unit for receiving an electronic publication,

A storage unit for storing property information representing a property of a 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 constituting the electronic publication, and property information of each of the extracted verbs is obtained from the storage unit, and the acquired property information is based on the obtained property information. A character grasping unit comprising a character grasping unit which grasps a subject related to a verb corresponding to the character as the character in the electronic publication;

An information generator for generating information about the identified person,

Device for generating information about electronic publications.
The method of claim 1,

In the storage unit,

Verbs that have the same or similar meanings have the same property information

Device for generating information about electronic publications.
The method of claim 1,

The person grasping unit,

If the acquired property information is property information related to a person's behavior, identifying a subject related to a verb corresponding to the obtained property information as a character in the electronic publication.

Device for generating information about electronic publications.
The method of claim 1,

The sentence structure determiner selects at least one sentence from which a subject and a verb are extracted from the plurality of sentences,

The person grasping unit,

Acquiring property information of a verb included in the selected sentence from the storage unit, and recognizing a subject related to the verb corresponding to the acquired property information as a person in the electronic publication based on the acquired property information;

Device for generating information about electronic publications.
The method of claim 1,

The storage unit stores an exclusion list having information on a subject to be excluded from the character,

The person grasping unit,

Check whether the extracted subject is included in the exclusion list, and if the extracted subject is included in the exclusion list, exclude the extracted subject from the character

Device for generating information about electronic publications.
The method of claim 1,

The information generation unit,

Whenever the subject is identified as a character, a predetermined value is added to the main degree corresponding to the subject, a subject having a relatively high main degree is selected as the main main character among the characters, and the selected main Generating information on the character as information on the identified character

Device for generating information about electronic publications.
The method of claim 6,

The numerical value added to the said main figure,

In one sentence including the subject identified as the character, the more the number of subjects included in the one sentence has a relatively smaller value

Device for generating information about electronic publications.
Receiving an electronic publication;

Extracting a subject and a verb from each of a plurality of sentences constituting the electronic publication;

Obtaining property information of each of the extracted verbs from a storage for storing a plurality of verbs;

Identifying a subject associated with a verb corresponding to the acquired property information as a person in the electronic publication based on the obtained property information;

Generating information about the identified person;

How to generate information about electronic publications.
The method of claim 8,

In the storage unit,

Verbs that have the same or similar meanings have the same property information

How to generate information about electronic publications.
The method of claim 8,

The step of identifying as the character,

If the acquired property information is property information related to a person's behavior, identifying a subject related to a verb corresponding to the obtained property information as a character in the electronic publication.

How to generate information about electronic publications.
The method of claim 8,

Acquiring the property information, identifying the subject as a person in the electronic publication, and generating information about the identified person,

In the extracting step, a result of extracting a subject and a verb from each of the plurality of sentences is performed when at least one of the subject and the verb is extracted.

How to generate information about electronic publications.
The method of claim 8,

The storage unit stores an exclusion list having information on a subject to be excluded from the character,

The step of identifying as the character,

Checking whether the extracted subject is included in the exclusion list;

If the extracted subject is included in the exclusion list, further comprising: excluding the extracted subject from the character;

How to generate information about electronic publications.
The method of claim 8,

Generating the information,

Each time the subject is identified as a character, adding a predetermined value to a main degree corresponding to the subject;

Selecting a subject having a relatively high majority as a main character, and generating information on the selected main character as information on the identified character;

How to generate information about electronic publications.
The method of claim 13,

Adding a predetermined value to the main diagram,

In one sentence including the subject identified as the character, the larger the number of subjects included in the one sentence, the more numerical value having a relatively smaller value is added.

How to generate information about electronic publications.
Receiving an electronic publication;

Extracting a subject and a verb from each of a plurality of sentences constituting the electronic publication;

Obtaining property information of each of the extracted verbs from a storage for storing a plurality of verbs;

Identifying a subject associated with a verb corresponding to the acquired property information as a person in the electronic publication based on the obtained property information;

Programmed to perform the step of generating information about the identified person.

A computer program stored on a computer readable recording medium.
Receiving an electronic publication;

Extracting a subject and a verb from each of a plurality of sentences constituting the electronic publication;

Obtaining property information of each of the extracted verbs from a storage for storing a plurality of verbs;

Identifying a subject associated with a verb corresponding to the acquired property information as a person in the electronic publication based on the obtained property information;

A program is recorded that includes a command to perform the step of generating information about the identified person.

Computer-readable recording medium.