KR102340404B1 - Method and apparatus for managing movie recommended items using language units - Google Patents

Abstract

The method for managing a movie recommendation item using a language unit according to an embodiment of the present specification is connected to a terminal and the terminal through a communication network to provide numerical language units, meta language units, and language unit categories of each language unit. A method for managing a movie recommendation item using a language unit by a movie recommendation item management device using a language unit including an information providing device comprising: numerical language units, meta language units and each language unit by the information providing device obtaining a linguistic unit category; receiving type identification information indicating selection of a language unit type of either a numeric type or a meta type from the terminal; generating a first set of language units corresponding to the type identification information from among the language units acquired by the information providing device; providing, by the information providing device, selection interface page information including an interface for selecting some language units from the set of first language units to the terminal; selecting a preset number of objects based on the language unit selected through the interface by the information providing device; transmitting interface page information including an object list including the selected object by the information providing device to the terminal; storing the selected language unit and a corresponding degree of relevance by the information providing device as a recommendation item for a virtual context; and providing, to the terminal, the selection interface page information including the selected language unit included in the stored recommendation item and a corresponding degree of relevance, wherein the selection interface page information is a numerical value of the first set of language units. If the type is a set of language units, further comprising an interface capable of adjusting the context-language unit association for the selected language unit, and selecting a preset number of objects based on the language unit selected through the interface receives the identification information of the numerical language unit selected from the terminal and the corresponding context-language unit relevance pair, and based on the numerical language unit and the context-language unit relevance pair, a preset number of objects The step of selecting a preset number of objects based on the identification information of the numerical language unit and the context-language unit relevance pair comprises: the received identification information of the numerical language unit In the context-language unit association level corresponding to each numerical language unit corresponding to and setting such that the accumulated value for the values and the context-object relevance for the arbitrary object have a positive correlation.

Description

Method and apparatus for managing movie recommendation items using language units

At least some embodiments of the present specification relate to a method and apparatus for managing a movie recommendation item using a language unit.

According to the conventional search method, a user can search for and find a desired web document by inputting a search keyword into a search window. For example, the user may search for information about the movie "Rome" by entering the movie "Rome" into the search box. However, if the user does not remember the movie he is looking for, another method of providing information is required. For example, the user may try to search by entering a movie title about a movie to be found, an actor who appeared in the movie, a director, a producer, etc. of the movie as keywords. Travel information sites or travel review sites sometimes provide information about movies about that movie along with travel information, so if you're not lucky, users can search for the movie they want using keywords such as movie title, actor, director, producer, etc. it might be

However, furthermore, if information is provided based on an atypical language, for example, an emotional language, rather than the standardized information, the conventional search method cannot be used. For example, the response provided by the conventional search engines to a search term such as "romantic movie" or "fantastic movie" is the same as searching for documents written by someone including the keywords "romantic movie" or "fantastic movie". will be only However, atypical language requires a different approach from formal information such as summer movies and winter movies. Even if someone didn't write something with the keywords "romantic movie" or "fantastic movie", there may actually be movies that many people find "romantic" or "fantastic".

Furthermore, a movie using a language unit for “romantic movie” or “fantastic movie” by using attribute keywords based on the emotional language input by the user, that is, keywords such as “romantic movie” or “fantastic movie” You can manage recommended items.

In addition, for fields other than movies, a different approach may be required for a request for information provision using a non-standardized language.

1. Korean Patent Registration No. 10-0943962 "Method for providing emotional-based item search service, database construction method and search server" (Announcement date: 2010.02.26.)

An embodiment of the present specification aims to provide a method and apparatus for managing movie recommendation items using language units.

The method for managing a movie recommendation item using a language unit according to an embodiment of the present specification is connected to a terminal and the terminal through a communication network to provide numerical language units, meta language units, and language unit categories of each language unit. A method for managing a movie recommendation item using a language unit by a movie recommendation item management device using a language unit including an information providing device comprising: numerical language units, meta language units and each language unit by the information providing device obtaining a linguistic unit category; receiving type identification information indicating selection of a language unit type of either a numeric type or a meta type from the terminal; generating a first set of language units corresponding to the type identification information from among the language units acquired by the information providing device; providing, by the information providing device, selection interface page information including an interface for selecting some language units from the set of first language units to the terminal; selecting a preset number of objects based on the language unit selected through the interface by the information providing device; transmitting interface page information including an object list including the selected object by the information providing device to the terminal; storing the selected language unit and a corresponding degree of relevance by the information providing device as a recommendation item for a virtual context; and providing, to the terminal, the selection interface page information including the selected language unit included in the stored recommendation item and a corresponding degree of relevance, wherein the selection interface page information is a numerical value of the first set of language units. If the type is a set of language units, further comprising an interface capable of adjusting the context-language unit association for the selected language unit, and selecting a preset number of objects based on the language unit selected through the interface receives the identification information of the numerical language unit selected from the terminal and the corresponding context-language unit relevance pair, and based on the numerical language unit and the context-language unit relevance pair, a preset number of objects The step of selecting a preset number of objects based on the identification information of the numerical language unit and the context-language unit relevance pair comprises: the received identification information of the numerical language unit In the context-language unit association level corresponding to each numerical language unit corresponding to and setting such that the accumulated value for the values and the context-object relevance for the arbitrary object have a positive correlation.

The apparatus for managing a movie recommendation item using a language unit according to an embodiment of the present specification is connected to a terminal and the terminal through a communication network, and provides numerical language units, meta language units, and language unit categories of each language unit. An apparatus for managing a travel destination recommendation item using a language unit including an information providing apparatus that Receives type identification information instructing selection of a language unit type of either a numeric type or a meta type from Provides selection interface page information including an interface for selecting some language units from a set of units to the terminal, selects a preset number of objects based on the language unit selected through the interface, and selects the selected objects transmits interface page information including a list of objects including A preset number of objects are selected based on unit identification information and context-language unit relevance pair, wherein the selection interface information page includes a search interface for language unit search, and the received type identification information is If the type identification information corresponding to the numeric type, the selection interface page information further includes an interface capable of adjusting the context-language unit relevance of the selected language unit, each corresponding to the received identification information of the numeric language unit In the context-language unit association corresponding to the numerical language unit, a value reflecting the object-language unit association corresponding to the numerical language unit and an arbitrary object is accumulated for the received numerical language units A context-object for a value and any of the above objects. The degree of association is set to have a positive correlation.

According to an embodiment of the present specification, it is possible to provide a method and an apparatus for easily managing movie recommendation items based on language units.

1 is a network configuration diagram of an information providing system using attribute keywords according to an embodiment of the present specification.
2 is a block diagram of a terminal according to an embodiment of the present specification.
3 is a block diagram of an information providing apparatus according to an embodiment of the present specification.
4 is a flowchart of an information providing process through an information providing interface according to an embodiment of the present specification.
5 is a detailed flowchart of step 910 according to an embodiment of the present specification.
6 is a detailed flowchart of step 510 according to an embodiment of the present specification.
7 is a detailed flowchart of step 530 according to an embodiment of the present specification.
8 is a flowchart of an information providing process according to another embodiment of the present specification.
9 is a flowchart of a movie recommendation item management process according to an embodiment of the present specification.
10 is an example of a stored object-language unit association diagram according to an embodiment of the present specification.
11 is a detailed flowchart of an item category setting process according to an embodiment of the present specification.
12 is an example of an interface page according to an embodiment of the present specification.
13 is an example of an interface for selecting an item according to an embodiment of the present specification.
14 is an example of a part of an interface page for selecting a search word according to an embodiment of the present specification.
15 is an example of a part of an interface page including a meta-type language unit according to an embodiment of the present specification.
16 is an example of a part of an interface page including a search box according to an embodiment of the present specification.
17 is an example of a part of an interface page for storing keywords according to an embodiment of the present specification.
18 is an example of an interface page including a context-language unit relevance adjustment unit according to an embodiment of the present specification.
19 is an example of an interface including a result preview according to an embodiment of the present specification.
20 is an example of an interface page according to another embodiment of the present specification.
21 to 24 are an example of an interface for selecting an item according to another embodiment of the present specification.
25 is an example of an interface including a result preview according to another embodiment of the present specification.

Hereinafter, embodiments of the present specification will be described in detail with reference to the accompanying drawings.

In describing the embodiments, descriptions of technical contents that are well known in the technical field to which the present specification belongs and are not directly related to the present specification will be omitted. This is to more clearly convey the gist of the present specification without obscuring the gist of the present specification by omitting unnecessary description.

For the same reason, some components are exaggerated, omitted, or schematically illustrated in the accompanying drawings. In addition, the size of each component does not fully reflect the actual size. In each figure, the same or corresponding elements are assigned the same reference numerals.

Hereinafter, embodiments of the present specification will be described with reference to the drawings.

According to some embodiments of the present specification, a 'language unit' may mean a minimum string capable of expressing and defining characteristics, usage methods, properties, etc. of an object. The 'language unit' may be referred to as 'attribute keyword', 'keyword', or 'keytalk ^{TM '.} Keytalk means that it becomes the key of talk.

1 is a network configuration diagram of an information providing system using a language unit according to an embodiment of the present specification.

Referring to FIG. 1 , an information providing system according to an embodiment of the present specification may include a terminal 200 , an information providing apparatus 300 , and a communication network 150 .

The terminal 200 may be implemented as an electronic device or similar device capable of performing, for example, a smart phone, PDA, tablet PC, notebook computer, laptop computer, personal computer, other communication, receiving user input, and outputting a screen. can

The terminal 200 may be the manager terminal 200 - 1 or the customer terminal 200 - 2 .

The manager terminal 200 - 1 is, for example, a terminal used by a manager providing an information service.

The customer terminal 200 - 2 is a terminal used by a customer who is provided with an information service.

The information providing device 300 may be implemented as, for example, a workstation, a server, a general computer, other electronic devices capable of performing communication, or similar devices.

As shown in FIG. 1 , the terminal 200 and the information providing apparatus 300 are connected through a communication network 150 and may communicate with each other through the communication network 150 . Also, the manager terminal 200 - 1 may access the information providing apparatus 300 through an interface directly provided by the information providing apparatus 300 .

When the manager terminal 200 - 1 accesses the information providing device 300 through an interface directly provided by the information providing device 300 , the information providing device 300 includes the configuration of a web server or an application server. In this case, the configuration of the web server/application server included in the information providing device 300 may be referred to as an interface module. The interface module may serve as a web server/application server to be described later. The web server/application server may input information or transmit a request message to an accessed terminal through an interface, and may receive information and/or a request message transmitted by the accessed terminal.

The communication network 150 is, for example, Long Term Evolution (LTE), LTE-Advanced (LTE-A), WI-FI, Local Area Network (LAN), Wide Area Network (WAN), Code Division Multiple Access (CDMA), TDMA (Time Division Multiple Access), WiBro (Wireless Broadband), GSM (Global System for Mobile Communications) may be implemented using at least some of the communication methods developed in the past, present or available in the future. Hereinafter, for convenience, the communication network 150 is not mentioned and the terminal 200 and the information providing device 300 directly communicate with each other.

When the information providing device 300 provides interfaces for both the manager terminal 200-1 and the customer terminal 200-2, an interface for object recommendation and attribute keyword management when a pre-registered user (administrator) approaches and, when accessing other general users (customers), it is possible to provide an interface for inquiring limited information, such as searching and inquiring of one's own object.

The information providing apparatus 300 may perform a user authentication or terminal authentication procedure to provide such a differentiated interface. For example, the information providing apparatus 300 determines whether the connected terminal is a manager terminal or a customer terminal through a user authentication process with the connected terminal. Alternatively, the information providing apparatus 300 may register as an administrator terminal through terminal authentication of the connected terminal. Since the user authentication or terminal authentication procedure between the information providing apparatus 300 and the terminal 200 is a technology that has already been put to practical use, a detailed description thereof will be omitted.

Specific operations and configurations of the terminal 200 and the information providing apparatus 300 will be described later with reference to FIGS. 2 to 11 .

2 is a block diagram of a terminal 200 according to an embodiment of the present specification.

Referring to FIG. 2 , the terminal 200 according to an embodiment of the present specification may include an input unit 210 , a display unit 220 , a communication unit 230 , a storage unit 240 , and a control unit 250 .

The input unit 210 converts a user's input operation into an input signal and transmits it to the control unit 250 . The input unit 210 may be implemented as, for example, a keyboard, a mouse, a touch sensor on a touch screen, a touch pad, a keypad, a voice input, or other input processing devices that are possible in the present, past or future. The input unit 210 may receive, for example, a user's information provision request input and transmit it to the control unit 250 .

The display unit 220 outputs a screen under the control of the control unit 250 . The display unit 220 may be embodied as, for example, a liquid crystal display (LCD), a light emitting diode (LED), an organic light emitting diode (OLED), a projector, or other display devices capable of present, past or future. The display unit 220 may display, for example, an interface page for providing information or an information provision result page. According to an embodiment, a component that uses another method for transmitting information to a user such as voice output or vibration instead of screen output may be used instead of the display unit 220 .

The communication unit 230 exchanges data with the information providing device 300 and/or other external devices. The communication unit 230 transmits the data received from the information providing apparatus 300 to the control unit 250 . Also, the communication unit 230 transmits data to the information providing apparatus 300 under the control of the control unit 250 . The communication technology used by the communication unit 230 may vary depending on the type of the communication network 150 or other circumstances.

The storage unit 240 stores data under the control of the control unit 250 and transmits the requested data to the control unit 250 .

The controller 250 controls the overall operation of the terminal 200 and each component. In particular, the control unit 250 transmits an information provision request and other data to the information providing apparatus 300 according to information input from the input unit 210 as will be described later, and according to the page information received from the information providing apparatus 300 . A result page and/or an interface page is displayed through the display unit 220 .

An operation performed by the control unit 250 may be distributed and processed by several physically separated arithmetic units. It is also possible that some of the operations performed by the controller 250 are performed by the first server and other operations performed by the second server. In this case, the control unit 250 may be implemented as a sum of physically separated arithmetic devices.

The storage unit 240 may be implemented as a total of physically separated storage devices.

When the control unit 250 or the storage unit 240 is implemented as a sum total of several physically separated devices, communication between multiple devices may be required. Here, for the sake of simplification of description, it is assumed that the storage unit 240 or the control unit 250 is implemented as one object.

When the terminal 200 transmits/receives data, it may be expressed that the communication unit 230 transmits/receives data according to the control of the control unit 250 depending on the viewpoint, or that the control unit 250 controls the communication unit 230 to transmit/receive data. can also express

A detailed operation of each component of the terminal 200 will be described later with reference to FIGS. 4 to 8 .

3 is a block diagram of an information providing apparatus 300 according to an embodiment of the present specification.

Referring to FIG. 3 , the information providing apparatus 300 according to an embodiment of the present specification may include a communication unit 310 , a control unit 320 , and a storage unit 330 .

The communication unit 310 exchanges data with the terminal 200 and/or other external devices. The communication unit 310 transmits the data received from the terminal 200 to the control unit 320 . Also, the communication unit 310 transmits data to the terminal 200 under the control of the control unit 320 . The communication technology used by the communication unit 310 may vary depending on the type of communication network 150 or other circumstances.

The storage unit 330 stores data under the control of the control unit 320 and transmits the data requested from the control unit 320 to the control unit 320 .

The controller 320 controls the overall operation of the information providing apparatus 300 and each component. As will be described later, the control unit 320 also retrieves the necessary data from the storage unit 330 when the control unit 320 receives the interface page request, the information provision result page request, and other data through the communication unit 310 ( load) page information is generated and the page information is transmitted to the terminal 200 through the communication unit 310 .

In addition, the control unit 320 transmits the search result of the user's attribute keyword selection to the terminal 200 as will be described later.

When the information providing device 300 transmits/receives data, it may be expressed that the communication unit 310 transmits/receives data according to the control of the control unit 320 depending on the viewpoint, and the control unit 320 controls the communication unit 310 to transmit data. It can also be expressed as sending and receiving.

A detailed operation of each component of the information providing apparatus 300 will be described later with reference to FIGS. 4 to 11 .

According to another embodiment, instead of a page for visually providing information, data for providing information through voice or other methods may be transmitted and received.

4 is a flowchart of an information providing process through an information providing interface according to an embodiment of the present specification.

In step 410, the controller 320 of the information providing apparatus 300 generates interface page information. The interface page information is information necessary to create an interface page. The interface page is a page for inducing a user's input, receiving the user's input, and delivering it to the information providing apparatus 300 . For example, the interface page information may be in the form of an HTML document or other markup language document. In another embodiment, the terminal 200 has the format information of the interface page in advance, and only the information corresponding to the content may be transmitted from the information providing apparatus 300 to the terminal 200 . Hereinafter, for convenience, it is assumed that interface page information or other page information is transmitted in the form of an HTML document. However, the scope of the present specification is not limited thereto.

In step 420 , the communication unit 310 of the information providing apparatus 300 transmits interface page information to the terminal 200 .

In step 430, the controller 250 of the terminal 200 configures an interface page using the interface page information. For example, the controller 250 may configure the interface page in the form of a web page by driving a web browser to interpret the HTML document. A separate application may be used instead of the web browser.

In step 440 , the display unit 220 of the terminal 200 displays an interface page to the user 400 . The interface page may include, for example, an interface through which the user 400 can request information provision, input and/or select keywords for information provision, and set other information provision.

In step 450 , the input unit 210 of the terminal 200 receives the selection input of the user 400 input through the interface page and transmits it to the control unit 250 .

In step 460 , the communication unit 230 of the terminal 200 transmits input information for identifying the user's selection input to the information providing apparatus 300 under the control of the control unit 250 .

In step 470 , the controller 320 of the information providing apparatus 300 generates result page information by using a user's input (eg, keyword and/or other information provision setting). A preparation process for generating result page information and a process for generating result page information will be described later with reference to FIGS. 5 to 11 . The result page information may be configured in an HTML document format and/or an image format, for example.

In step 480 , the communication unit 310 of the information providing apparatus 300 transmits result page information to the terminal 200 .

In step 490 , the control unit 250 of the terminal 200 configures a result page using the result page information received by the communication unit 230 . For example, the controller 250 may configure the result page by interpreting the result page information in HTML format.

In step 495, the display unit 220 of the terminal 200 provides a result page to the user.

In the following description, the control unit 250 of the terminal 200 controls the display unit 220 to cause the display unit 220 to output contents, or controls the communication unit 230 to communicate with the item recommendation management device 300 or input unit. Controlling 210 to receive content or controlling and storing the storage unit 240 will be described as the operation of the terminal 200 . The display unit 220 of the terminal 200 may be integrally coupled with the input unit 210 to perform both the functions of the input unit 210 and the display unit 220 . Hereinafter, the function of the input unit 210 in the display unit 220 It is also described as performing.

Although it is assumed in the embodiment of FIG. 4 that a page in a visual form is provided to the user, it is also possible to provide an interface or result information through voice. In this case, an audio output unit may be used instead of the display unit 220 . Instead of the visual/auditory method, another interface method that is currently possible or will be possible in the future may be used in the relationship with the user 400 . In this case, the information providing apparatus 300 may provide the terminal 200 with information converted in another method instead of page information to match the interface method.

In the embodiment shown in FIG. 5 and later, the user 400 wants to be provided with information about an object in a specific field of interest in which he or she is interested. However, the scope of the present specification is not limited thereto.

A field of interest (item of interest) can be, for example, a type of object. For example, if the field of interest is 'great person', objects corresponding to the field of interest may include 'King Sejong the Great', 'Sunshin Yi', and 'Imdang Sim'. For example, if the field of interest is 'movie', objects corresponding to the field of interest may include 'Men in**', 'Spider*', and 'Player**'. For example, if the field of interest is 'broadcast program', objects corresponding to the field of interest may include 'infinite**', '** of the jungle', '** of the throne', and the like.

In the following embodiments, documents are collected to evaluate relationships (relevance/weight, etc.) between keywords. All of the collected documents may be evaluated as having an equal value, or the newest document may be evaluated as having a higher value. That is, the correlation between the age of the evaluation time reference document and keywords appearing in the document may have a negative correlation.

Even in the process subsequent to FIG. 5, which will be described later, the value may be evaluated differently according to the freshness of the document. For example, a case in which two keywords appear together in a document 1 day after the evaluation time may be evaluated with a 10-fold higher relevance than a case in which the two keywords appear together in a document 10 days after the evaluation time. The age of the document may be evaluated, for example, in units of seconds/minutes/hours, or in units of days/months/years, etc. The control unit 320 divides the partial relevance value of the document evaluated before the age of the document is reflected by the age of the document to set the partial relevance in which the document age is reflected, and accumulates the partial relevance between the two keywords relationship can be set.

The creation time of a document to confirm the age of a document is determined using, for example, the publication time and/or metadata contained within the document, or through periodic crawling, when a document not found in the previous crawling is newly discovered. In this case, it may be determined that a new document was added at a new crawling time.

5 is a flowchart illustrating a method of storing object-language unit association as a preprocessing process for managing movie recommendation items according to an embodiment of the present specification.

Referring to FIG. 5 , in step 510 , the controller 320 determines a representative attribute keyword candidate set from the first set of documents. For example, the controller 320 may collect keywords frequently appearing in a document corresponding to an area of interest among the first set of documents as a representative attribute keyword candidate set.

6 is a detailed flowchart of step 510 according to an embodiment of the present specification.

The control unit 320 sets keywords appearing in the document, such as object keywords indicating objects belonging to a specific field, and keywords appearing in the document, such as field keywords, indicating a specific field to a first attribute keyword candidate set and a second attribute keyword candidate set. can be set to

For example, if the field of interest to which the information service is provided is a celebrity, the field keyword may include 'celebrity', 'celebrity', 'movie actor', 'star', 'celeb', 'celeb', and the like. The field keyword may be set by an administrator or recommended and set by the controller 320 . After acquiring some field keywords, the controller 320 may recommend/set similar keywords whose relevance with the field keywords is analyzed to be greater than or equal to a preset value as additional field keywords.

If the field of interest is a celebrity, the object keyword may be an individual person belonging to the field of interest. That is, each person corresponding to a celebrity in the field of interest may be an object keyword.

To describe the relationship between the field keyword and the object keyword, for example, the field keyword may correspond to an attribute or type of the object keyword. If the field keyword indicates a set, the object keyword may be an element that belongs to the set.

The object keyword may be set by an administrator or may be selected in a manner similar to the field keyword. According to another embodiment, the controller 320 may analyze the context of the collected documents and select keywords determined as elements belonging to the set indicated by the field keyword as the object keyword.

Popular object keywords and unpopular object keywords may be classified according to the amount of searches/collections of the corresponding object keywords. The controller 320 may search/collect documents including each object keyword, set object keywords with a collection amount equal to or greater than a specific threshold as popular object keywords, and set the remaining object keywords as unpopular object keywords.

A keyword in a popular field and a keyword in an unpopular field may be classified according to a search/collection amount of the keyword in the corresponding field. The controller 320 may search/collect documents including each field keyword, set field keywords with a collection amount equal to or greater than a specific threshold as popular field keywords, and set the remaining field keywords as unpopular field keywords. However, the threshold value for discriminating the popular object keyword and the unpopular object keyword and the threshold value for discriminating the popular field keyword-unpopular field keyword may be different values. Hereinafter, for convenience, the popular object keyword and the popular field keyword are collectively referred to as a popular field object keyword. Also, for convenience, unpopular object keywords and unpopular field keywords are collectively referred to as unpopular field object keywords.

In a modified embodiment, only the popular field keyword or the popular object keyword may be used instead of the popular field object keyword. In a modified embodiment, only the unpopular field keyword or the unpopular object keyword may be used instead of the unpopular field object keyword.

In step 610, the controller 320 sets keywords appearing together in the document, such as the popular field object keyword, as the first attribute keyword candidate set.

The controller 320 may search/collect documents including popular field object keywords, and set keywords included in the collected documents as the first attribute keyword candidate set. According to another embodiment, the controller 320 may exclude a field keyword and an object keyword among keywords included in the collected document from the first attribute keyword candidate set. In addition, the control unit 320 may exclude preset meaningless keywords, for example, search/article, etc. from the first attribute keyword candidate set. According to another embodiment, the controller 320 may include a keyword registered in a preset dictionary among keywords included in the collected document in the first attribute keyword candidate set.

According to another embodiment, the control unit 320 searches/collects documents including the popular field object keyword, and searches for keywords arranged within a preset distance from the popular field object keyword or a sentence including the popular field object keyword in the collected documents. It may be included in the first attribute keyword candidate set. According to another embodiment, the control unit 320 searches/collects documents including the popular field object keyword, analyzes the context, and selects keywords used for formulating/explaining the popular field object keyword as the first attribute keyword candidate It can also be included in a set.

The distance between keywords or the distance between keywords and sentences is, for example, the number of sentences located between two keywords or keywords and sentences, the number of words located between two keywords or keywords and sentences, and the distance between two keywords or keywords and sentences. It may be determined based on any one or more of the number of positioned word words, two keywords, or the number of characters between the keyword and the sentence.

The controller 320 may first perform morpheme analysis for keyword analysis.

In step 620, the control unit 320 sets keywords appearing together in the document, such as the unpopular field object keyword, as the second attribute keyword candidate set.

The controller 320 may search/collect documents including unpopular field object keywords, and set keywords included in the collected documents as the second attribute keyword candidate set. According to another embodiment, the controller 320 may exclude a field keyword and an object keyword among keywords included in the collected document from the second attribute keyword candidate set. In addition, the controller 320 may exclude preset meaningless keywords, for example, search/article, etc. from the second attribute keyword candidate set. According to another embodiment, the controller 320 may include a keyword registered in a preset dictionary among keywords included in the collected document in the second attribute keyword candidate set.

According to another embodiment, the control unit 320 searches for/collects documents including unpopular field object keywords, and searches for keywords arranged within a preset distance from the unpopular field object keywords or sentences including the unpopular field object keywords in the collected documents. It may be included in the second attribute keyword candidate set. According to another embodiment, the control unit 320 searches/collects documents including unpopular field object keywords, analyzes the context, and selects keywords used for formulating/explaining unpopular field object keywords as second attribute keyword candidates. It can also be included in a set.

The distance between keywords or the distance between keywords and sentences is, for example, the number of sentences located between two keywords or keywords and sentences, the number of words located between two keywords or keywords and sentences, and the distance between two keywords or keywords and sentences. It may be determined based on any one or more of the number of positioned word words, two keywords, or the number of characters between the keyword and the sentence.

The controller 320 may first perform morpheme analysis for keyword analysis.

In operation 630, the controller 320 may set keywords belonging to both the first attribute keyword candidate set and the second attribute keyword candidate set as the representative attribute keyword candidate set. That is, keywords used both as expressions for modifying popular field object keywords and as expressions for modifying unpopular field object keywords may be collected in the representative attribute keyword candidate set.

According to another embodiment, in step 510 , the controller 320 may include keywords appearing together with the object keyword and/or the field keyword in the representative attribute keyword candidate set regardless of whether it is popular or unpopular.

Returning to FIG. 5 , in step 520 , the controller 320 determines two or more sub-keywords associated with each representative attribute keyword included in the representative attribute keyword candidate set from the second set of documents.

The second set document used for extracting the subkeywords in step 520 and the first set document used for extracting the representative attribute keyword candidate set in step 510 may be different document sets or the same document set. For example, the first set document may be a set including all of the collectible documents, and the second set document may be a set including only documents in which a specific area of interest to provide an information providing service is used as a main keyword. . The control unit 320 may analyze the collectible documents and analyze whether each document is a document in which a specific area of interest for which an information providing service is to be provided is used as a main keyword based on frequently appearing keywords. According to another embodiment, both the first and second aggregate documents may be sets including all of the collectable related documents. According to another embodiment, the first set document may be a set including all collectable related documents, and the second set document may be a set including only documents related to a specific area of interest to which an information providing service is to be provided. According to another embodiment, the second set of documents may be a set including all collectable related documents, and the first set of documents may be a set including only documents related to a specific area of interest to which an information providing service is to be provided.

For step 520, for example, the control unit 320 generates a set including only documents related to a specific field of interest to which an information providing service is to be provided, and/or documents including field keywords indicating the field of interest. Alternatively, a set including only documents related to a specific field of interest may be generated by collecting documents including object keywords belonging to a corresponding field of interest, and extracting documents in which the proportion of field keyword/object keyword is greater than or equal to a preset value. The weight of the field keyword/object keyword can be determined based on the frequency of appearance of the field keyword/object keyword, the appearance location, the context, and the like. For example, documents in which field keywords/object keywords frequently appear, field keywords/object keywords are used as the title of the corresponding document, or are displayed in large letters or fonts for emphasis may be classified as documents related to a specific field of interest.

In step 520, for example, the control unit 320 analyzes at least a portion of the second set of documents to extract a preset number of sub-keywords having the highest relevance to each representative attribute keyword by a preset number of two or more sub-keywords associated with each representative attribute keyword. Keywords can be extracted.

For example, the control unit 320 may set the degree of association between the representative attribute keyword and the sub-keyword in consideration of the frequency in which the sub-keyword appears in the same or similar context as the representative attribute keyword. For example, it can be seen that words appearing around the keyword A in a specific sentence may appear around the word related to the keyword A in other documents as well.

"I went on a trip with a big heart, but it was July and the weather was too hot, so I had a hard time."

"I went on a trip with a big heart, but it was July and the weather was too humid, so I had a hard time."

Looking at the two sentences above, the word "because it's hot" is replaced with the word "because it's wet" in the same context. The controller 320 may infer that “hot” and “wet” are related words.

"I went on a trip with a big heart, but it was July and the weather was too hot, so I had a hard time."

"I went on vacation with a lot of heart, but it was July and the weather was so hot that I had a hard time."

Similarly, the controller 320 may infer that “travel” and “vacation” are related words through the above two sentences.

"I went on a trip with a big heart, but it was July and the weather was too hot, so I had a hard time."

"I went on a trip with a lot of heart, but it was August and the weather was so hot that I had a hard time."

Similarly, the controller 320 may infer that "July" and "August" are related words through the above two sentences.

The controller 320 determines that “hot” and “wet” are related words, “July” and “August” are related words, and “travel” and “vacation” are related words through previously collected documents. It is possible to save It is assumed that the following sentences are collected later.

"I went on vacation with a big heart, but it was July and the weather was too humid, so I had a hard time."

“I went on a trip with a big heart, but it was difficult because it was August and the weather was too hot.”

If the two sentences are not in the same context, but know that "hot" and "wet" are related words, "July" and "August" are related words, and "travel" and "vacation" are related words, the control unit 320 ) from the above sentence, you can learn that "it was hard" and "it was hard" are also related words.

A keyword pair with high frequency appearing in the same/similar context may be determined to be highly correlated with each other. In addition, it can be determined that the higher the similarity of the context in which the two keywords appear, the higher the correlation between the two keywords. The control unit 320 sets the degree of relevance between keywords by learning using the collected documents, and sets the degree of relevance of keywords appearing in the corresponding sentence using the set relevance between keywords and the context of the sentence. It is possible to increase the accuracy of the interrelationship judgment.

As similar learning methods, NNLM (Neural Net Language Model), RNNLM (Recurrent Neural Net Language Model), word2vec, skipgram, and CBOW (Continuous Bag-of-Words) methods are known. In particular, when word2vec is used, word2vec learns from documents and matches each keyword to a vector, and the similarity between two keywords can be determined by calculating the cosine similarity of the two vectors.

In this way or a similar method, the controller 320 may analyze at least a portion of the second set of documents to extract a preset number of sub-keywords most highly related to each representative attribute keyword.

In step 530, the controller 320 may determine an association weight corresponding to each representative attribute keyword and sub-keyword pair in the representative attribute keyword candidate set from the second set of documents.

7 is a detailed flowchart of step 530 according to an embodiment of the present specification.

In operation 710, the controller 320 may analyze at least a portion of the second set of documents to set a degree of correlation between the sub-keywords. For example, it is assumed that 50 sub-keywords of _{B1 1} to B1 ₅₀ are collected as related sub-keywords for the representative attribute keyword A1. In this case, the controller 320 may set the degree of correlation between the two sub-keywords by using the frequency at which the two sub-keywords appear together in the same document for these 50 sub-keywords. B1 is also interconnected between the _first B1 and B1 ₂ and B1 is determined in accordance with the _first frequency to the _second appearing in the same document. According to another embodiment, B1 ₁ and B1 ₂ are In addition to the fact that frequency of occurrence in the same document affects correlation, if B1 ₁ and B1 ₂ appear in the same document, _{the distance between two keywords B1 1} and B1 ₂ (or the distance between sentences in which the two keywords appear) ), a higher degree of correlation can be recognized. A degree of correlation between sub-keywords may be set in a similar manner. The distance between keywords or the distance between keywords and sentences is, for example, the number of sentences located between two keywords or keywords and sentences, the number of words located between two keywords or keywords and sentences, and the distance between two keywords or keywords and sentences. It may be determined based on any one or more of the number of positioned words, two keywords, or the number of characters positioned between a keyword and a sentence.

In operation 720, the control unit 320 may set a correlation weight between each representative attribute keyword and the sub-keyword based on the degree of correlation between the sub-keywords. For example, with respect to a sub-keyword set corresponding to each representative attribute keyword, the control unit 320 may determine a degree of correlation between a specific sub-keyword in the sub-keyword set and other sub-keywords in the sub-keyword set, and the specific sub-keyword and the sub-keyword in the sub-keyword set. The association weight between the specific sub-keyword and the representative attribute keyword may be set so that the association weights between the representative attribute keywords have a positive correlation with each other.

_{For example, the higher the correlation between the sub-keyword B1 1} of the representative attribute keyword A1 and the other sub-keywords B1 ₂ to B1 ₅₀ of A1 is, the higher the _{correlation weight between A1 and B1 1} may be set. For example, the arithmetic mean (or sum) of the correlation between _{B1 1} and other sub-keywords of A1 ( B1 ₂ to B1 ₅₀ ) may be the correlation weight between _{B1 1 and A1.} A geometric mean/harmonic mean may be used instead of a simple arithmetic mean. A cutting average excluding the highest two (example) and lowest two (example) among the correlations between the _{subkeyword B1 1} and the other subkeywords of A1 (B1 ₂ to B1 _{50 ) may be used.} have. Instead of the arithmetic mean of the degree of correlation, the median may be used.

According to some embodiments, the "B1 B1 ₁ and ₂ are used to calculate the associated weight for the ₁ B1 for A1 Frequency of occurrence in the same document" simply means that B1 ₁ and B1 ₂ Rather than depending on the number of documents appearing together (or appearing in the same sentence, or appearing adjacent), B1 ₁ and B1 ₂ are The number of documents appearing together (or appearing in the same sentence, or appearing adjacently) can be obtained by dividing the number of documents in _{which B1 1} appears and/or _{the number of documents in which B1 2 appears.} In a similar way, "B1 ₁ and B1 ₂ The frequency of occurrences in the same document" means that B1 ₁ and B1 ₂ A positive correlation with the number of documents co-occurring (or appearing in or adjacent to) the number of documents in the same sentence and negative correlation with the number of documents in which B1 ₁ appears and/or the number of documents in which B1 ₂ appears It can be set to have a relationship. It is a kind of normalization for simply preventing a commonly used word from having a high association weight in the representative attribute keyword A1.

Returning to FIG. 5 , in step 540 , the controller 320 may set a sub-relationship between an object and a sub-keyword from the first set of documents.

Among the first set of documents, a document such as an object keyword (eg, “Taylor Swift”) indicating an object, or sub-keywords frequently appearing in the same sentence or a sentence adjacent to the object may be determined to be related to the corresponding object. The control unit 320 may collect documents in which the object keyword of the corresponding object appears, and set a sub-relationship between the sub-keyword and the object keyword according to the frequency of appearing together in the documents. In particular, when the sub-keyword appears in the same sentence as the object keyword, the controller 320 may set the relation between the sub-keyword and the object to be higher than when the sub-keyword appears in a sentence different from the object keyword.

The controller 320 may set the relation between the sub-keyword and the object of the object keyword to be higher as the sentence in which the sub-keyword appears is closer to the sentence in which the object keyword appears. The proximity of two sentences is, for example, the number of sentences positioned between two sentences, the number of words positioned between the two sentences, the number of words positioned between the two sentences, and the number of characters positioned between the two sentences. It may be determined based on one or more.

The controller 320 may set a higher degree of association between the sub-keyword and the object of the corresponding object keyword as the position where the sub-keyword appears is closer to the position where the object keyword appears. The proximity between the sub-keyword and the object keyword is, for example, the number of sentences positioned between the sub-keyword and the object keyword, the number of words positioned between the sub-keyword and the object keyword, and the number of words positioned between the sub-keyword and the object keyword. It may be determined based on any one or more of the number and the number of characters positioned between the sub-keyword and the object keyword.

In operation 550 , the controller 320 may set the object-keyword association between the object and each of the representative attribute keywords by using the lower association degree of step 540 and the association weight of step 530 .

For example, the object-keyword relevance between object C and the representative attribute keyword A1 is determined using the sub-keywords of C and A1 (eg, B1 ₁ to B1 ₅₀ ) and the weight of each sub-keyword. can be set. For example, the object-keyword relevance between the object C and the representative attribute keyword A1 may be set higher as the sub-relationship between the _{objects C and B1 1} to B1 _{50 increases.}

In addition, in the relationship with A1, if the sub-keyword with a higher association weight has a high sub-relationship with object C, the relationship between object C and the representative attribute keyword A1 is higher than when the sub-keyword with a lower association weight has a high sub-relationship. may be set to have a higher object-keyword relevance. For example, in the case of Table ₁ , the sub-relationship of the side with a higher association weight (B1 1 ) is higher than in the case of Table 2, so the case of Table 1 is higher than the case of Table 2, the object between object C and the representative attribute keyword A1 The keyword relevance may be set to be high.

Association weight with A1 Sub-relationship with C B1 ₁ 0.5 0.5 B1 ₂ 0.2 0.2

Association weight with A1 Sub-relationship with C B1 ₁ 0.2 0.5 B1 ₂ 0.5 0.2

According to an embodiment, the object-keyword association (object-language unit) between object C and the representative attribute keyword A1 as the sum of values obtained by multiplying the association weight corresponding to each sub-keyword and the lower association degree (or using this total) It can also be used in conjunction with the degree of relevance). In the case of Table 1, 0.5×0.5+0.2×0.2=0.29, and in the case of Table 2, 0.2×0.5+0.5×0.2=0.20. Therefore, the case of Table 1 is between the object C and the representative attribute keyword A1 more than the case of Table 2 may be set to have high object-keyword relevance. The above-described object-keyword relevance calculation method is merely exemplary, and if the sub-relationship with C in step 540 and the association weight with A1 in step 530 are positively correlated with the object-keyword relevance between C and A1 Any other method may be used. Thereafter, when the communication unit 310 receives a request to provide information related to a specific representative attribute keyword, the control unit 320 may provide a result object through the communication unit 310 based on the object-keyword association degree extracted in step 550 . For example, when receiving a request for providing information including any one representative attribute keyword, the control unit 320 may provide information about the object in the order of the highest object-keyword relevance in the relation with the corresponding representative attribute keyword. . In another embodiment, when receiving an information provision request including two or more representative attribute keywords and weights corresponding thereto, the controller 320 for each object is an object-keyword association with representative attribute keywords included in the information provision request. The information about the object may be provided in the order in which the sum (or average) of values multiplied by weight (or similarly weighted) is highest.

8 is a flowchart of an information providing process according to another embodiment of the present specification.

The embodiment of FIG. 8 further includes two steps 523 and 526 between steps 520 and 530 in addition to the same processes as those of the embodiment of FIG. 5 . Here, redundant descriptions are avoided and only steps 523 and 526 are described.

In step 523, the controller 320 determines whether each of the sub-keywords extracted in step 520 corresponds to an emotional language (emotional language). To this end, the storage unit 330 or an external server may hold an emotional dictionary (dictionary). The sentiment dictionary is a tool for determining whether a certain word (keyword) is an emotional word, and may hold, for example, a list of sentiment words. Keywords included in the appraised word list may be regarded as appraised words, and keywords not included in the appraised word list may be determined not to be appraised words. However, these judgments are based on dictionary meanings and may not reflect the changing use of words by the public over time. Accordingly, the control unit 320 does not determine whether the representative attribute keyword itself is an appraisal word, but determines whether to use the representative attribute keyword based on whether sub-keywords related to the representative attribute keyword are an appraisal word.

In another embodiment, the controller 320 may add another word learned as having a high degree of relevance (more than a preset value) with a preset number or more of words registered as emotional words in the emotional dictionary.

In step 526, the controller 320 may leave only a preset number of representative attribute keywords in the representative attribute keyword candidate set in the order of increasing the emotional language ratio (or number) of the related sub-keywords, and remove the rest. Through this process, keywords that are far from emotional language can be prevented from being treated as emotional language.

9 is a flowchart for explaining a method for managing movie recommendation items according to an embodiment of the present specification, FIG. 10 is an example of a stored object-language unit association diagram according to an embodiment of the present specification, and FIG. 11 is this specification is a detailed flowchart of an item category setting process according to an embodiment.

In step 910 , the controller 320 stores the object-language unit association degree corresponding to the object and the representative attribute keyword (language unit) pair in the storage unit 330 .

In the embodiment of FIG. 10 , there are all m objects (i ₁ to i _m ) and there are all n representative attribute keywords (k ₁ to k _n ).

For example, the object-language unit association of the _{object i 5} and the representative attribute keyword k _{3 is w 5,3} .

The process of step 910 may be performed according to some of the above-described embodiments of FIGS. 5 to 8 , a process similar thereto, or a process corresponding thereto. According to another embodiment, the process of step 910 may be performed as an input of an administrator or may be performed by receiving an object-language unit relevance determined in an external system through a network or a storage medium.

In step 920 , the controller 320 acquires the numerical language units, the meta language units, and the language unit categories of each language unit and stores them in the storage unit 330 .

The process of step 920 may be performed by input from an administrator or by receiving numerical language units, meta language units, and language unit categories of each language unit determined in an external system through a network or a storage medium. Here, The numerical language unit is a language unit that can have a difference in the degree of, for example, 'cool' for each user with respect to an arbitrary object, and the degree of difference can be expressed as a context-language unit association between 0 and 1. For example, the context for the numerical language unit of 'cool' in the object 'A' - the language unit association is '0.1', and the context for the numerical language unit 'cool' in the object 'B' - When the language unit relevance is '0.9', it means that the object 'B' is more related to the keyword 'cool' than the object 'A'.

Next, the meta-type language unit has a preset association weight, for example, an association weight of 0 or 1. For example, the meta-type language unit may include 'Din*', 'Park*Rae', 'Park Myung*, 'Baekjong*', 'Chief*', 'Sungsi*', 'Songeun*', and the like. That is, the meta-type language unit means a language unit capable of answering 'it is related (relationship 1)) or 'not related (relationship level 0)' to an arbitrary object. For example, if the object is an arbitrary broadcast program, the associated weights of the actors 'Dean*', 'Park*Rae', 'Park Myung*, 'Baekjong*', and 'Chief*' are 1,1,0,0, In the case of 1, 'Dean*', 'Park*Rae', and 'Chief*' mean appearing on a broadcast program, and 'Park Myung* and 'Baekjong*' mean not appearing on a broadcast program.

In the present specification, it is assumed that the values indicating the context-language unit relevance and other relevance are values that are more closely related as the values are larger. In another embodiment, when some relevance values have a smaller relevance value, the closer the relevance is, and for other relevance values, the larger the relevance value, the tighter the relevance. may be used instead.

In addition, the language unit category may be, for example, any one selected from the group consisting of 'user response', 'atmosphere', 'performer', and 'genre characteristic'.

Steps 910 and 920 are preprocessing steps for recommending an object according to a context desired by a user.

In a next step 930, type identification information instructing selection of a type of a language unit of either a numeric type or a meta type is received from the terminal through the communication unit 310.

To this end, the controller 320 may provide the terminal 200 with an interface for selecting any one keyword type among a numerical language unit and a meta language unit. The user selects any one of the numerical language unit and the meta language unit displayed on the terminal 200 through the interface. According to this selection, the terminal transmits type identification information for the type selected by the user, and the control unit 320 receives the type identification information.

In step 940, the controller 320 generates a first set of language units corresponding to the received type identification information. That is, the controller 320 checks whether the language unit selected by the user is a numeric type or a meta type based on the received type identification information, and generates a first set of language units including language units of the selected type.

In step 950, the control unit 930 provides selection interface page information including an interface for selecting a part of the first set of language units to the terminal. Hereinafter, information transfer through the interface page between the terminal 200 and the information providing apparatus 300 follows the method described with reference to FIG. 4 .

The selection interface page information further includes an interface capable of adjusting the context-language unit relevance for the selected language unit when the type identification information corresponds to a numeric type, when the first set of language units is a set of language units in a numeric type include

That is, when the type identification information received in step 940 corresponds to the metatype, the first language unit set includes metatype language units, and the selection interface page information is included in the first language unit set consisting of metatype language units It includes an interface that allows you to select some of the linguistic units.

When the type identification information received in step 950 corresponds to a numeric type, the first set of language units includes numeric language units, and the selection interface page information includes a language included in the first set of language units composed of numeric language units. It includes an interface for selecting some of the units and an interface for adjusting the context-language unit association for the selected language unit.

In operation 960, the controller 930 selects a preset number of objects based on the language unit selected through the selection interface page information.

The control unit 930 receives identification information for some language units among the set of first language units from the terminal through the selection interface page information, and identifies a language unit corresponding to the received identification information.

When the confirmed type of language unit is a numeric type, a context-language unit association degree is received from the terminal to the numeric language unit.

In the context-language unit association degree corresponding to each numerical language unit corresponding to the received identification information of the numerical language unit, the object-language unit association degree corresponding to the numerical language unit and an arbitrary object is reflected A value is set so that the value accumulated for the received numerical language units and the context-object association for the arbitrary object have a positive correlation.

For example, for each numerical language unit, the corresponding context-language unit association is multiplied by the numerical language unit and the object-language unit association corresponding to an arbitrary object (or weighted similarly) By calculating an accumulated value for the numerical language units that have received a value, the context-object association may be obtained. In another embodiment, instead of multiplying the context-language unit relevance by the object-language unit relevance, the control unit 320 selects another operation/use method so that the context-language unit and the object-language unit relevance have a positive correlation. The context-object association can also be obtained by using the applied function. In addition, a value obtained by multiplying the context-language unit relevance corresponding to each numerical language unit by the numerical language unit and the object-language unit relevance corresponding to an arbitrary object (or similarly weighted) is received Any method of applying a correction based on other factors to the accumulated values of the numerical language units and utilizing them as a context-object relationship may be used.

For example, when the selected language unit type is the meta type, a preset number of objects are selected based on the object-language unit association degree corresponding to the selected meta type language units.

In operation 970 , the controller 320 may provide an object list including an object selected based on the context-object association to the terminal 200 through the interface. For example, if _{the context-object relationship corresponding to the selected language unit C 2} is as shown in Table 3 below, the controller 320 may provide the object as an interface in the order of Table 4 .

object item Context-object association i ₁ 0.23 i ₂ 0.33 i ₃ 0.99 i ₄ 0.84

order object item Context-object association One i ₃ 0.99 2 i ₄ 0.84 3 i ₂ 0.33 4 i ₁ 0.23

That is, the controller 320 may select a preset number of objects in the order of highest context-object relevance for the selected language unit, and may provide an object list including the selected objects through the interface. The terminal 200 receiving the object list may provide the user with related information stored in advance on the _{object i 3 through the display unit 220 .} The terminal 200 may also provide pre-stored related information about other objects in the lower order, if necessary. The terminal 200 may provide information on the _{object i 3} to the user by voice instead of the display unit 220 through a speaker.

In another variation, steps 930 to 950 may be repeatedly performed by the user. That is, in step 930, a numerical language unit is selected to generate a first set of language units, which is a set of numerical language units, and in step 940, one or more numerical language units are selected from among the first set of language units consisting of numerical language units. After selection, the context-language unit association degree of the numerical language unit selected in step 950 is set and temporarily stored. After that, the process returns to step 940 again to select a metatype language unit to generate a first set of language units that is a metatype keyword set, and in step 950, one or more metatype language units from among the first set of language units consisting of metatype keywords can be selected.

In this case, in step 960, the context-language unit association is reflected in the object-language unit association, the context-object association is calculated, and objects associated with the selected meta-type language unit are filtered, and then the context-object association Objects can be selected in ascending order.

In step 980, upon receiving an instruction for storing the selected language unit and the corresponding relevance degree from the terminal through the interface, the control unit stores the selected language unit and the corresponding context-language unit relevance degree as an arbitrary virtual context. store in wealth

In step 990, according to the stored virtual context search request, the stored selected language unit and the corresponding context-language unit association degree are provided to the user as a movie recommendation item. A movie recommendation item will be described later with reference to FIG. 25 .

In another variant, as a pre-processing process, a process of classifying an item category may be added. When an item category is classified, a movie recommendation item may be managed with respect to the classified item category.

Item category classification and item category setting will be described with reference to FIG. 11 .

In an embodiment of the present specification, the controller 320 may provide a list of item categories classified according to the type of object (item category).

To this end, in step 911, the controller 320 classifies a plurality of objects into a plurality of items. It may be classified based on the steps described in FIG. 5 or may be classified by an administrator.

In operation 912, a plurality of objects of the specific item category related to the respective language units are matched based on documents related to the specific item category.

To this end, numerical language units and meta language units may be obtained from the terminal through the communication unit. If the numerical language units and meta-language units are acquired in operation 912 , acquiring the numerical language units and meta-language units in operation 920 may be omitted.

In step 913, a language unit associated with a plurality of objects corresponding to each item category is set as a language unit corresponding to the item category.

In step 914, the list of item categories is provided to the terminal through the item category selection interface.

In step 915, one of the item categories is selected from the terminal through the item category selection interface.

In step 916, a set of language units including language units corresponding to the item category selected is generated.

Thereafter, step 920 of FIG. 9 may be performed. Provided to the terminal The control unit 320 provides the list of item categories to the terminal through the interface, selects one item from the list of item categories, and generates a set of basic language units corresponding to the selected item.

The step of FIG. 9 is performed only for language units included in the generated basic language unit set.

As such, the object-language unit relevance set by document-based analysis related to the type of object (item category) is set differently according to the item category. As can be seen with reference to FIG. 5 above, since different aggregate documents are collected according to the type of object (item category), the degree of similarity of language units and the degree of object-language unit relevance based on the frequency of language units is the object type. It will be different depending on the (item category).

Only for language units included in the basic language unit set corresponding to the selected item category, the first language unit set is generated through steps 920 and 930.

For example, if the item category is 'Comic', the language unit categories of the language units included in the basic language unit set are 'Shadows', 'Character', 'Story', 'Social Reaction', 'Review', 'Material', It may be 'autumn', 'adult', 'popular', 'popular', etc., and when the item category is 'broadcast', the linguistic unit category of the linguistic units included in the basic language unit set is 'genre characteristic', 'performer' ', 'user response', 'producer', etc.

12 is an example of an interface page according to an embodiment of the present specification, FIG. 13 is an example of an interface for item selection according to an embodiment of the present specification, and FIG. 14 is an example of an interface page according to an embodiment of the present specification This is an example of a part of the selection interface page.

The interface page is displayed on the terminal 300 according to the information provided by the information providing device 300 . When a button or tab displayed on the interface page is selected, the terminal 200 may transmit input information converted from a user's input to the information providing apparatus 300 .

Referring to FIG. 12 , the interface page (I-100) for managing movie recommendation items includes an item selection unit (I-110), a language unit search unit (I-120), a language unit selection unit (I-130), and a snap. It may include a shot unit I-140 and a result preview unit I-150.

12 and 13 , the item selection unit I-110 displays a list of categories of searchable or recommendable objects. As an example, the item selection unit I-110 may display a list of item categories, such as comics, movies, novels, dramas, and entertainment shows.

An administrator or a user may select one category from among a plurality of item categories through the item selection unit I-100 of the interface page displayed on the terminal.

The language unit search unit I-120 includes a search window I-121, and the user inputs all or a part of a desired key talk into the search window I-121 to find a language unit matching the virtual context. You can search easily.

12 and 14 , the language unit selection unit I-130 includes the language unit type selection tabs I-131 and I-132, the language unit category display unit I-135, and the language unit set display unit I -133). The user selects keywords and keyword relevance corresponding to the virtual context through the language unit type selection tabs (I-131, I-132), the language unit category display unit (I-135), and the language unit set display unit (I-133). can be easily selected.

The language unit type selection tabs I-131 and I-132 include a numeric type tab I-131 and a meta type tab I-132. When the user selects a numerical language unit through the numerical tab (I-131) of the interface page displayed on the terminal, the first language unit set consisting of a plurality of numerical language units is displayed on the language unit set display unit I-133, , when the user selects a meta-type language unit through the meta-type tab I-132, it is displayed on the first language unit set display unit I-133 composed of a plurality of meta-type language units.

The language unit category display unit I-135 displays a language unit category corresponding to the first set of language units.

A language unit category displayed in the language unit category, for example, a first set of language units classified as a 'genre characteristic' is displayed.

The language unit set display unit I-133 displays a plurality of language units included in the first language unit set. When some language units are selected among the plurality of language units displayed on the language unit set display unit I-133, the selected language units are displayed on the snapshot unit I-140 to be described later.

In addition, the language unit set display unit I-133 may include a previous page button and/or a next page button for page movement in case all keywords included in the first language unit set cannot be displayed on one page. . The previous page button and/or the next page button may be selectively provided according to the number of actual keywords and the current page position. In addition, an interface that is expanded through scrolling instead of the previous page button and/or the next page button may be provided.

15 is an example of a part of an interface page including a meta-type language unit according to an embodiment of the present specification.

Referring to FIG. 15 , the language unit category display unit I-135 displays a meta-type language unit, for example, a word unit whose category is 'appearance'. The linguistic unit of the 'appearance' category is, for example, the linguistic unit of whether a particular celebrity appeared on a given broadcast.

The language unit set display unit I-133 may display numerical language units and meta language units differently.

For example, the language unit set display unit I-133 of FIG. 14 displays the numerical language unit with a long oval border, while the meta-type language unit of FIG. 15 is displayed with a rectangular border.

As another example, the language unit set display unit I-133 may display the numerical language unit and the meta type language unit differently by changing the character color, border color, background color, etc. of each keyword.

15 is an example of a part of an interface page including a meta-type language unit according to an embodiment of the present specification.

Referring to FIG. 15 , the language unit category display unit I-135 displays a meta-type language unit, for example, a word unit whose category is 'appearance'. The linguistic unit of the 'appearance' category is, for example, the linguistic unit of whether a particular celebrity appeared on a given broadcast.

The language unit set display unit I-133 may display numerical language units and meta language units differently.

For example, the language unit set display unit I-133 of FIG. 14 displays the numerical language unit with a long oval border, while the meta-type language unit of FIG. 15 is displayed with a rectangular border.

As another example, the language unit set display unit I-133 may display the numerical language unit and the meta type language unit differently by changing the character color, border color, background color, etc. of each keyword.

16 is an example of a part of an interface page including a search box according to an embodiment of the present specification.

14 and 16 , the language unit set display unit I-133 may display a second language unit set, which is a set of language units including a search word input in the search window I-121.

For example, when 'a' is input in the search box I-121, the second set of language units whose language unit category is 'genre characteristics' is 'various', 'providing various information,' ', and the second set of linguistic units whose language unit category is 'user response' may include 'unusual', 'cider-like', 'awaited', 'worried about waiting', 'laughing and crying', etc. can

The language unit set display unit I-133 may display the word inputted in the search box from among the language units included in the second language unit set differently from the rest. For example, when 'da' is input into the search box I-121 and 'various' is displayed in the second set of language units, 'da' and 'yanghan' in 'various' are displayed in different colors or different sizes can be

In another modified example, the language unit set display unit I-133 may further display a language unit that does not include the search word, and display a language unit including the search word and a language unit not including the search word differently. Alternatively, the language unit including the search term may be displayed first, and the language unit not including the search term may be displayed later.

The language unit set display unit I-133 receives one or more language units selected by the user from among a plurality of displayed language units and transmits the selected language units to the control unit 320 . The controller 320 causes the selected language unit to be displayed on the snapshot unit I-140.

17 is an example of a part of an interface page including a snapshot unit I-140 according to an embodiment of the present specification, and FIG. 18 is an association control unit I-149 according to an embodiment of the present specification. is an example of a part of an interface page that includes

12, 17 and 18, the snapshot unit I-140 includes a relevance setting button I-147, a keyword deletion button I-148, and a keyword setting storage button I-146. include

When the relevance setting button I-147 is selected by the user through the interface page displayed on the terminal, each of the numerical language units selected through the language unit search unit I-120 and the language unit selection unit I-130 A relevance adjustment unit I-149 that can be adjusted by the user for setting the context-language unit relevance for .

The user inputs the context-language unit relevance of the selected numerical language unit through the relevance adjusting unit I-149. The association level adjusting unit I-149 may be displayed in the form of a slide bar. One end of the slide bar may correspond to the lowest relevance and the other end may correspond to the maximum relevance. The degree of relevance may be, for example, from 0 to 1 or from 0.1 to 5. This relevance range is only an example, and is not limited thereto.

The language unit deletion button I-148 is displayed to match each of the selected language units, and when the language unit deletion button I-148 is selected, the matched keyword can be deleted.

When the language unit deletion button I-148 is selected by the user, the terminal 200 provides input information to the information providing device 300 , and the controller 320 of the information providing device 300 controls the matching language unit. can be deleted. Deleting a language unit means canceling the language unit selection by the user.

The language unit setting save button (I-146) is a meta-language unit and numeric language unit selected through the language unit selection unit (I-130), and the context of the numeric language unit selected through the snapshot unit (I-140)- The language unit relevance may be stored by a user's selection.

When the language unit setting storage button I-146 is selected, the controller 320 stores the language unit and context-language unit relevance related settings together with log information through the snapshot unit I-140. By storing the language unit and context-language unit relevance together with the log information, it is possible to immediately set the stored language unit and context-language unit relevance when searching for log information later.

Instead of the buttons I-148 and I-146, other interfaces similar to buttons or other interfaces capable of replacing the functions of the buttons may be utilized.

12 and 19 , as shown in FIG. 19 , the result preview unit I-150 provides a result preview unit I-150 based on the selected language unit and context-language unit association. Provides information about one or more retrieved objects. To this end, the control unit 320 provides the result preview unit I-150 with object information searched according to the user's selection through the language unit selection unit I-130 and the snapshot unit I-140.

In addition, when the result view according to the virtual context (selected language unit and context-language unit association) stored by the controller is selected, the result preview unit I-150 provides object information according to the virtual context.

The result preview unit I-150 may display an image of the searched object and an individual item name (eg, a broadcast program/book) based on the selected language unit. If there are a plurality of searched objects, the objects may be displayed in the order of the highest degree of relevance.

When the searched object is, for example, programs, a main image and title of the program may be displayed.

When an arbitrary object from among a plurality of objects is selected, detailed information about the corresponding object may be provided.

When a searched object is, for example, programs, when an arbitrary program is selected, the program's organization, highest viewership, genre, performers, production team, official website address, etc. may be displayed in detail.

Through the result preview, the user can check the searched object item in advance. Accordingly, when an object that is not suitable for the virtual context is included in the result, the user can search again, so that it is possible to provide a result suitable for the virtual context that the user thinks.

20 is an example of an interface page according to another embodiment of the present specification, FIGS. 21 to 24 are an example of an interface for selecting an item according to another embodiment of the present specification, and FIG. 25 is an embodiment of the present specification An example of a portion of an interface page that includes search results according to the example.

The interface page is displayed on the terminal 300 according to the information provided by the information providing device 300 .

Referring to FIG. 20 , the interface page II-100 for managing movie recommendation items may include an item selection unit II-110, a keyword selection unit II-120, and a result preview unit II-130. can

20 and 21 , the item selection unit I-110 displays a list of categories of searchable or recommendable objects. As an example, the item selection unit I-110 may display a list of item categories, such as movies, broadcasts, stars, webtoons, wine, clothes, art, and beer.

An administrator or a user may select one category from a list of a plurality of item categories displayed on the item selection unit I-100.

20 and 22 , the keyword selection unit II-120 includes a category selection tab II-121 and a language unit set unit II-122.

The category selection tab II-121 displays a list of a plurality of language unit categories. The plurality of language unit categories may include any one from the group consisting of picture type, character, story, social reaction, review, material, autumn, right, floating, and popularity.

The category selection tab II-121 includes a matching checkbox II-123 for each displayed language unit category. The category selection tab II-121 displays the first language unit set corresponding to the selected language unit category on the language unit set unit II-122 when a check box is selected.

The user selects one or more language unit categories from the list of language unit categories through the category selection tab II-121 that meet the pre-established situation.

The category selection tab II-121 may include a meta-type language unit tab II-221 and a numeric language unit tab II-321.

20 and 23 , the meta-type language unit tab II-221 displays one or more meta-language unit categories included in the category list of one or more meta-type language units.

As shown in FIG. 23 , the meta-type language unit tab II-221 displays a category of the meta-type language unit, for example, 'serialization day'. The first set of language units included in the category of meta-type language units is displayed in the language unit set unit II-122. The user may select one or more meta-type language units displayed in the language unit set unit II-122, for example, one or more meta-type language units among Mon, Tue, Wed, Thu, Fri, Sat, and Sun.

20 and 24 , the numerical language unit tab II-321 displays the numerical language unit category. If a plurality of numerical language units are included in the numerical language unit tab II-321, a check box II-323 matching each numerical language unit may be included. The user selects the checkbox (II-323) displayed in the numerical language unit tab (II-321) and selects a plurality of numerical language units, such as figure, character, story, novel reaction, review, material, autumn, right, floating You can select one or more numeric language units from among , popularity, and the like.

The first set of language units included in the numeric language unit selected in the numeric language unit tab II-321 is displayed on the language unit set unit II-322. The user can use the numerical language units displayed in the language unit set unit II-322, for example, dreamy, excited, attractive, novel, cramped, heavy, sticky, informative, warm, growing, sweet, empathetic. You can select one or more numerical language units from among thin, cheerful, scary, new, exciting, funny, brutal, raunchy, sensational, solid storyline, heartwarming, didactic.

Each language unit displayed in the language unit set unit II-322 may be displayed to be classified according to a language unit category.

As can be seen with reference to FIGS. 23 and 24 , the numerical language unit and the metatype language unit may be displayed differently. For example, the numerical language unit of FIG. 24 is indicated by a long oval border, while the metatype language unit of FIG. 23 is indicated by a rectangular border.

As another example, the numerical language unit and the meta type language unit may be displayed differently by changing the text color, border color, background color, etc. of each keyword.

20 and 25 , the curation unit II-130 provides context for the language unit (keyword) selected in the language unit set unit II-122 and/or the language unit set unit II-322 - Provides information on one or more objects found based on the object relevance.

The curation unit (II-130) previews the object information searched according to the user's selection through the curation storage tab (II-131), the selected language unit display unit (II-132), and the result preview (II-133). It is provided through the auxiliary part II-133.

The selected keyword display unit II-132 displays one or more keywords selected by the keyword selection unit II-120. One or more language units may be arranged side by side in a selected order. The selected keyword may be displayed differently depending on the type of keyword. When the selected keyword includes, for example, 'beneficial', 'number', and 'complete', the numeric linguistic unit 'beneficial' is indicated by a long oval, and the meta-language unit 'number' and 'final' are indicated by a rectangle. is displayed

The curation storage tab II-131 stores the language unit displayed on the selected keyword display unit II-132 as a recommended item in the storage unit.

If there is a pre-stored recommendation item, the recommendation item may be displayed together when the interface page II-100 for managing the movie recommendation item is provided. That is, when there is a recommendation item stored in advance by the administrator or the user, the selected language unit included in the recommendation item is displayed without the user selecting the language unit type or language unit. In addition, the selected object may be displayed on the result preview unit II-133 based on the selected language unit included in the recommendation item and the context-language unit relation of the selected language unit. The object selection method is the same as in step 960 of FIG. 9 .

The result preview unit II-133 displays an object list including one or more objects selected based on the selected keyword. The result preview unit II-133 may display an image for the searched object and an individual item name (eg, a cartoon). If there are a plurality of searched objects, the objects may be displayed in the order of the highest degree of relevance.

The result preview unit II-133, for example, is serialized on 'Wednesday' and displays the objects in the order of 'beneficial' and high relevance among 'completed' objects.

When the searched object is, for example, programs, a main image and title of the program may be displayed.

Also, the result preview unit II-133 may include a previous page button and/or a next page button for page movement in case all objects included in the object list cannot be displayed on one page. The previous page button and/or the next page button may be selectively provided according to the number of objects and the current page position. In addition, an interface that is expanded through scrolling instead of the previous page button and/or the next page button may be provided.

When any one of the plurality of objects is selected, detailed information about the corresponding object may be provided.

When the searched object is, for example, a cartoon, the author of the corresponding cartoon, other works of the corresponding author, and the author's website address may be displayed in detail.

Through the result preview, the user can check the searched object item in advance. Accordingly, when an object item that is not suitable for the virtual context is found, it is possible to search again, so that it is possible to provide a result suitable for the virtual context considered by the user.

A movie recommendation item to be provided to a real customer/buyer in the future may be determined according to the virtual situation set above. However, although the virtual context is fixed, as external learning data is added, the recommended movie items according to the virtual context will gradually change. Therefore, the manager can effectively create dynamically changing recommendation items.

According to the method for managing a movie recommendation item using a language unit of an information providing apparatus according to an embodiment of the present specification, it is possible to easily manage a movie recommendation item corresponding to a virtual situation considered by a user.

At this time, it will be understood that each block of the flowchart diagrams and combinations of the flowchart diagrams may be performed by computer program instructions. These computer program instructions may be embodied in a processor of a general purpose computer, special purpose computer, or other programmable data processing equipment, such that the instructions performed by the processor of the computer or other programmable data processing equipment are not described in the flowchart block(s). It creates a means to perform functions. These computer program instructions may also be stored in a computer-usable or computer-readable memory which may direct a computer or other programmable data processing equipment to implement a function in a particular manner, and thus the computer-usable or computer-readable memory. It is also possible that the instructions stored in the flow chart block(s) produce an article of manufacture containing instruction means for performing the function described in the flowchart block(s). The computer program instructions may also be mounted on a computer or other programmable data processing equipment, such that a series of operational steps are performed on the computer or other programmable data processing equipment to create a computer-executed process to create a computer or other programmable data processing equipment. It is also possible that instructions for performing the processing equipment provide steps for performing the functions described in the flowchart block(s).

Additionally, each block may represent a module, segment, or portion of code that includes one or more executable instructions for executing specified logical function(s). It should also be noted that in some alternative implementations it is also possible for the functions recited in blocks to occur out of order. For example, two blocks shown one after another may be performed substantially simultaneously, or the blocks may sometimes be performed in the reverse order according to a corresponding function.

At this time, the term '~ unit' used in this embodiment means software or hardware components such as FPGA or ASIC, and '~ unit' performs certain roles. However, '-part' is not limited to software or hardware. '~' may be configured to reside on an addressable storage medium or may be configured to refresh one or more processors. Accordingly, as an example, '~' indicates components such as software components, object-oriented software components, class components, and task components, and processes, functions, properties, and procedures. , subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables. The functions provided in the components and '~ units' may be combined into a smaller number of components and '~ units' or further separated into additional components and '~ units'. In addition, components and '~ units' may be implemented to play one or more CPUs in a device or secure multimedia card.

Those of ordinary skill in the art to which this specification belongs will be able to understand that the present specification may be embodied in other specific forms without changing the technical spirit or essential features thereof. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. The scope of the present specification is indicated by the claims described later rather than the detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts are included in the scope of the present specification. should be interpreted

On the other hand, in the present specification and drawings, preferred embodiments of the present specification have been disclosed, and although specific terms are used, these are only used in a general sense to easily explain the technical content of the present specification and help the understanding of the invention, It is not intended to limit the scope of the specification. It will be apparent to those of ordinary skill in the art to which this specification pertains that other modifications based on the technical spirit of the present specification may be implemented in addition to the embodiments disclosed herein.

Claims (17)

A movie recommendation item management device using a language unit including a terminal and an information providing device connected to the terminal and a communication network through a communication network to provide numerical language units, meta language units, and language unit categories of each language unit A method for managing movie recommendations using language units, the method comprising:
acquiring numerical language units, meta language units, and language unit categories of each language unit by the information providing device;
receiving type identification information indicating selection of a language unit type of either a numeric type or a meta type from the terminal;
generating a first set of language units corresponding to the type identification information from among the language units acquired by the information providing device;
providing, by the information providing device, selection interface page information including an interface for selecting some language units from the set of first language units to the terminal;
selecting a preset number of objects based on the language unit selected through the interface by the information providing device;
transmitting interface page information including an object list including the selected object by the information providing device to the terminal;
storing the selected language unit and a corresponding degree of relevance by the information providing device as a recommendation item for a virtual context; and
providing the selected interface page information including the selected language unit included in the stored recommendation item and a corresponding degree of relevance to the terminal;
When the first set of language units is a set of language units in a numeric form, the selection interface page information further includes an interface capable of adjusting the context-language unit association of the selected language unit;
The step of selecting a preset number of objects based on the language unit selected through the interface comprises:
Receive identification information of the numerical language unit selected from the terminal and a corresponding context-language unit relevance pair, and select a preset number of objects based on the numerical language unit and context-language unit relevance pair comprising the steps of
The step of selecting a preset number of objects based on the identification information of the numerical language unit and the context-language unit relevance pair comprises:
In the context-language unit association degree corresponding to each numerical language unit corresponding to the identification information of the received numerical language unit, the object-language unit association degree corresponding to the numerical language unit and an arbitrary object is reflected setting a value so that the value accumulated for the received numerical language units and the context-object relation of the arbitrary object have a positive correlation; management method. delete According to claim 1,
The selection interface information page includes a search interface for language unit search,
wherein the search interface includes an interface for selecting some language units from among a set of language units corresponding to a character string input in a search window of the search interface from among the set of first language units; . According to claim 1,
The interface for selecting some language units from the first set of language units displays each language unit of the first set of language units to be classified according to a language unit category. 4. The method of claim 3,
an interface for selecting some language units from among the first set of language units displays each language unit of the set of first language units to be classified according to a language unit category;
An interface for selecting some language units from among a set of language units corresponding to a character string input to the search window from among the set of first language units is a language unit corresponding to a character string input to the search window from among the set of first language units. A method for managing movie recommendations using a language unit that displays the listeners to be classified according to language categories. According to claim 1,
classifying a plurality of objects into a plurality of item categories;
matching a plurality of objects of the specific item category related to the language unit based on documents related to the specific item category;
setting a language unit associated with a plurality of objects corresponding to each item category as a language unit corresponding to the item category;
providing the list of item categories to the terminal through an item category selection interface;
receiving a selection of one item category from among a plurality of item categories through the item category selection interface from the terminal; and
Creating a basic language unit set including language units corresponding to the selected item category; Method for managing movie recommendation items using language units further comprising: 7. The method of claim 6,
The item category is a method for managing movie recommendation items using a language unit of an information providing device including any one or more of a comic book, a movie, a novel, a drama, and a variety show. According to claim 1,
Before the step of generating the first set of language units,
Storing the object-language unit relevance on the basis of the representative attribute keyword corresponding to the representative attribute keyword and the sub-keyword pair-sub-keyword relevance and the sub-keyword corresponding to the sub-keyword and the object pair-object relevance; A method of managing movie recommendations using the linguistic unit. A travel destination recommendation item management device using a language unit, which is connected to a terminal and the terminal and a communication network through a communication network, and includes an information providing device that provides numeric language units, meta language units, and language unit categories of each language unit,
The information providing device,
obtaining the numerical language units, meta language units, and language unit categories of each language unit;
Receives type identification information indicating selection of a language unit type of either a numeric type or a meta type from the terminal,
generating a first set of language units corresponding to the type identification information from among the acquired language units;
providing selection interface page information including an interface for selecting some language units from the first set of language units to the terminal;
Based on the language unit selected through the interface, a preset number of objects is selected,
Transmitting interface page information including an object list including the selected object to the terminal,
Storing the selected language unit and the corresponding degree of relevance as a recommendation item for the virtual context,
Selecting a preset number of objects based on the identification information of the numerical language unit and the context-language unit relevance pair received through the selection interface page,
The selection interface information page includes a search interface for language unit search,
If the received type identification information is type identification information corresponding to the numeric type, the selection interface page information further includes an interface capable of adjusting the context of the selected language unit-language unit relevance,
In the context-language unit association degree corresponding to each numerical language unit corresponding to the identification information of the received numerical language unit, the object-language unit association degree corresponding to the numerical language unit and an arbitrary object is reflected A movie recommendation item management apparatus using a language unit for setting a value so that a value accumulated for the received numerical language units and a context-object association for the arbitrary object have a positive correlation. delete 10. The method of claim 9,
The search interface may include an interface for selecting some language units from among a set of language units corresponding to a string input to a search box of the search interface from among the set of first language units, a movie recommendation item management device using a language unit . 10. The method of claim 9,
The interface for selecting some language units from the first set of language units displays each language unit of the first set of language units to be classified according to a language unit category. 12. The method of claim 11,
an interface for selecting some language units from among the first set of language units displays each language unit of the set of first language units to be classified according to a language unit category;
An interface for selecting some language units from among a set of language units corresponding to a character string input to the search window from among the set of first language units is a language unit corresponding to a character string input to the search window from among the set of first language units. A device for managing movie recommendation items using a language unit for displaying to be listened to to be classified according to a language category. 10. The method of claim 9,
The information providing apparatus classifies a plurality of objects into a plurality of item categories, matches a plurality of objects of the specific item category related to the language unit based on documents related to the specific item category, and a plurality of objects corresponding to each item category sets a language unit associated with an object of , as a language unit corresponding to the item category, selects one item category from among a plurality of item categories included in the list of item categories, and selects an item category corresponding to the selected item category A movie recommendation item management apparatus using a language unit for generating a set of basic language units including language units. 15. The method of claim 14,
The list of item categories is a movie recommendation item management device using a language unit including any one or more of a comic book, a movie, a novel, a drama, and a variety show. 10. The method of claim 9,
The information providing device stores the object-language unit relevance on the basis of the representative attribute keyword-sub-keyword relevance corresponding to the representative attribute keyword and the sub-keyword pair and the sub-keyword-object relevance corresponding to the sub-keyword and the object pair. A device for managing movie recommendations using language units stored in . 10. The method of claim 9,
The information providing apparatus is a movie recommendation item management apparatus using a language unit for providing the selection interface page information including the selected language unit included in the stored recommendation item and a corresponding degree of relevance to the terminal.

Images