KR20210056668A - Method and system for providing related kewords with respect to keyword input by user for in order to deriving idea - Google Patents

Abstract

The present invention relates to a method for providing related keywords with respect to a keyword input by a user to extract idea, which can extract idea quickly and effectively, and a system thereof. According to the present invention, the method comprises: a step of receiving a first keyword input by a user; a step of determining a plurality of second keywords as keywords related to the first keyword; a step of displaying the second keywords by being mapped on a first table of a mandal-art map with respect to the first keyword; and a step of mapping other keywords to the empty space of the mandal-art map according to keyword input of the user to update and display the mandal-art map.

Description

In order to derive an idea, a method and system for providing related keywords for keywords entered from users {METHOD AND SYSTEM FOR PROVIDING RELATED KEWORDS WITH RESPECT TO KEYWORD INPUT BY USER FOR IN ORDER TO DERIVING IDEA}

The embodiments relate to a method and system for providing related keywords for a keyword input by a user. In particular, in order to derive an idea, related keywords for the input keyword are provided, but the related keywords are mapped to a map in the form of a mandala. It relates to a method and a system that allows it to be provided.

In order to derive creative thoughts or ideas, idea derivation techniques such as mind map analysis, TRIZ analysis, and mandala analysis are used. This idea-derived technique is to derive creative thoughts or ideas for key keywords by thinking of keywords related to the key keywords determined by the user and mapping them on a map or listing them. Users can expand ideas related to key keywords by deriving keywords related to key keywords while increasing the depth of related keywords.

However, it is not easy to expand ideas related to key keywords by deriving keywords related to key keywords only with the user's thoughts, and there are cases where the expansion of ideas is concentrated in a specific category, or the relevance and trends with key keywords are not properly reflected. many.

Therefore, in order to derive an idea, a method and system capable of providing related keywords in various categories for the input keyword and related keywords reflecting trends, and promoting the derivation of the user's ideas based on these are required. do.

Korean Patent Registration No. 10-1951179 (registration date February 18, 2019) is the step of obtaining one or more keywords corresponding to an idea by a computer, searching for content including the obtained one or more keywords, the search result It describes a method for deriving an idea, including the step of evaluating the idea based on and providing a feedback including the evaluation result.

The information described above is for illustrative purposes only, may include content that does not form part of the prior art, and may not include what the prior art may present to a person skilled in the art.

In one embodiment, as a method of providing a related keyword related to an input keyword, a first keyword input by a user is received, a plurality of second keywords are determined as keywords related to the first keyword, and the first keyword The second keywords are mapped and displayed on the first table of the mandala-art map, centering on, but the keyword is further mapped to the empty space of the mandala-shaped map according to the keyword input from the user. It is possible to provide a method of providing related keywords to update and display a map in the form of a stream.

In one aspect, a method of providing a related keyword performed by a computer system, comprising: receiving a first keyword input by a user, determining a plurality of second keywords as keywords related to the first keyword The step of mapping the second keywords to a first table of a mandala-art map based on the first keyword, and the mandala-type to which the first keyword and the second keywords are mapped. Displaying a map, providing a user interface that allows the user to input a third keyword for an empty space of the mandala-shaped map, and according to the input of the third keyword from the user, the Updating and displaying a map in the form of a mandala, wherein each of the second keywords is a keyword according to a relevance search for the first keyword, a keyword according to a trend search for the first keyword, and the first keyword Includes at least two of a keyword according to a search for opposition to and a keyword searched based on a keyword selection frequency related to the first keyword, and the mandala-type map is displayed with at least 2 depths, and the In a second table corresponding to depth 2 of the mandala-type map, a plurality of fourth keywords related to one of the second keywords and the third keyword are determined based on one of the second keywords and the third keyword. Mapped, and according to a degree of relevance to the first keyword, the transparency of at least a portion of the first table and the second table are set differently.

Contents corresponding to one of the keywords are displayed in the second table, and the displayed contents include an image according to an image search for the one keyword, a slide show of a plurality of images according to the image search, and the Includes a gif image based on a plurality of images or a video according to a video search for the one keyword, and in response to the user's interaction with the part of the content, focusing on the one keyword, the first The second table to which 4 keywords are mapped may be displayed.

When the displayed content is selected by the user, a keyword related to the content may be further determined and displayed.

The second keywords are selected by the user from among a plurality of keywords presented according to a search based on the first keyword, and an empty space of the mandala-type map is at least one of the first table and the second table. It is an empty space of a table, and according to a command from the user, keywords related to a keyword at the center of the at least one table may be determined and mapped to the empty space.

In response to the user's interaction with the first table, an idea keyword in which at least two of the keywords mapped to the first table are combined is determined, and the first table is converted into a card form to display the idea keyword. Or, in response to the user's interaction with the second table, an idea keyword in which at least two of the keywords mapped to the second table are combined is determined, and the second table is converted into a card form, so that the idea keyword is Can be displayed.

According to the embodiment, in relation to the input keyword, ideas can be quickly and effectively derived by dividing the idea of an idea in stages and providing a tailored tool for each stage.

In addition, through the embodiment, in relation to the input keyword, a tool for deriving ideas having a universality capable of efficiently deriving an idea may be provided.

In addition, through the embodiment, ideas can be effectively expanded through keyword search related to the input keyword.

In addition, through the embodiment, it is possible to shorten the time required for deriving an idea.

1 illustrates a method of providing keywords related to a keyword input to a user according to an exemplary embodiment.
2 is a flowchart illustrating a method of providing keywords related to a keyword input to a user according to an exemplary embodiment.
3 illustrates a method of mapping keywords related to a keyword input to a user to a map in the form of a mandal-art, according to an example.
4 and 5 illustrate a map in the form of a mandal-art in which related keywords for keywords input to a user are mapped, according to an example.
6 illustrates a method of determining a keyword related to a keyword input by a user, according to an example.

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. The same reference numerals shown in each drawing indicate the same members.

1 illustrates a method of providing keywords related to a keyword input to a user according to an exemplary embodiment.

In FIG. 1, a computer system 100 that receives a keyword from a user and determines and displays related keywords for the input keyword in order to help the user derive an idea for the input keyword is illustrated.

As illustrated, the computer system 100 may receive a keyword (eg,'job') from a user and determine related keywords related to the input keyword through communication with the search engine 130. The keyword input from the user may correspond to a "core keyword (or central keyword)" as a starting keyword for which the user intends to derive an idea.

The computer system 100 may be a server or other computing device for performing the above tasks. The computer system 100 may be a device that determines related keywords for a keyword input by the user's user terminal and provides the determined related keywords to the user terminal. That is, the computer system 100 may be a device that communicates with a user terminal and determines a related keyword for a keyword input through the user terminal and displays it on the user terminal.

Alternatively, the computer system 100 may be a user terminal through which a user inputs a keyword. In this case, the user terminal may determine related keywords for the keyword input by the user through communication with the search engine 130 and may display the determined related keywords. In this case, the user terminal is, for example, a smart phone, a personal computer (PC), a laptop computer, a laptop computer, a tablet, an Internet of Things device, or a wearable computer. computer), etc. may be a terminal used by a user.

The computer system 100 may include a communication unit 110 and a processor 120.

The communication unit 110 may be a device for the computer system 100 to communicate with other servers or devices. In other words, the communication unit 110 transmits/receives data and/or information to/from other servers or devices, such as a network interface card, a network interface chip, and a networking interface port of the computer system 100 or a network device driver ( driver) or a software module such as a networking program.

The processor 120 may manage components of the computer system 100 and may execute programs or applications used by the computer system 100. For example, the processor 120 may execute a program or application used to determine related keywords related to a keyword input by a user and map the determined related keywords to the map 140 in the form of a mandala, and the Operations required for execution of programs or applications and processing of data can be processed. The processor 120 may be at least one processor 120 of the computer system 100 or at least one core within the processor 120.

In the detailed description to be described later, for convenience of explanation, an operation performed by the processor 120 or its components may be described as being performed by the computer system 100. In addition, operations and functions of the computer system 100 to be described later may be implemented as one or more software modules and/or hardware modules as components of the processor 120.

The computer system 100 may determine a plurality of related keywords related to the input keyword for a keyword (eg,'job') input by the user, and mandala the plurality of related keywords based on the input keyword. -art) can be mapped to the table of the map 140. The computer system 100 may cause the user terminal to display the map 140 in the form of such a mandala. As an example, as in the table of the illustrated mantarat-shaped map 140, based on the input keyword "job", "House Price", "Unemployment Rate", "Social Enterprise", "N Four Generations" and "Deep Learning" Related keywords such as "may be mapped. The table of the map 140 in the form of a mantarat may include at least one empty space (blank), and a user may directly input a keyword related to the keyword “job” input for the empty space.

The map 140 in the form of a mantarat may have a depth of 2 or more. That is, secondary related keywords related to each of the input keyword "job" and the primary related keywords "home price", "unemployment rate", "social enterprise", "Npo generation" and "deep learning" are manta. The first related keyword may be mapped to the table of depth 2 of the map 140 in the form of a latt.

With reference to FIGS. 2 to 6 to be described later, an operation of the computer system 100 and a method of providing related keywords for a keyword input from a user accordingly will be described in more detail.

2 is a flowchart illustrating a method of providing keywords related to a keyword input to a user according to an exemplary embodiment.

In step 210, the computer system 100 may receive a first keyword input by the user. The first keyword may be a core keyword (or a central keyword) from which the user intends to derive an idea. The first keyword may be directly inputted into the computer system 100 or inputted through a user terminal of the user and received by the computer system 100.

In step 220, the computer system 100 may determine a plurality of second keywords as keywords related to the inputted first keyword. The second keywords are keywords related to the first keyword, and may be keywords obtained through a search through at least one of a search engine 130, an SNS associated with a user, and a user's profile. In addition, the second keywords are keywords related to the first keyword and may be determined according to a search using a predetermined related keyword extraction algorithm (eg, Word2Vec algorithm, LDA algorithm, LSA algorithm, and a combination of at least two thereof).

The determined second keywords may be selected by a user from among a plurality of keywords presented according to a search based on the first keyword. That is to say, the computer system 100 may present a plurality of keywords as related keywords for the first keyword, and among them, only keywords selected by the user may be determined as the second keywords.

Each of the second keywords is based on a keyword according to a relevance search for a first keyword, a keyword according to a trend search for a first keyword, a keyword according to an opposite search for a first keyword, and a keyword selection frequency related to the first keyword. It may include at least two of the keywords searched based on it.

The keyword according to the relevance search for the first keyword may be a relevance keyword that is determined to have a relevance to the first keyword and retrieved. The association keyword may include, for example, a keyword determined as a keyword associated with the first keyword using the Word2Vec algorithm (or a combination of the Word2Vec algorithm and the LSA algorithm). In addition, the correlation keyword may include a keyword exposed as a related keyword when the search engine 130 searches using the first keyword. Also, the correlation keyword may include a keyword belonging to the same category as the predetermined category determined for the first keyword.

The keyword according to the trend search for the first keyword may be a trend keyword that is determined and searched as a keyword related to the first keyword by reflecting a trend at a time when the first keyword is input. The trend keyword may include, for example, a keyword exposed in a trend search by the search engine 130 using the first keyword. The related keyword extraction algorithm of the computer system 100 may determine a trend keyword searched for the inputted first keyword by reflecting the trend at the time when the keyword is input as the second keyword. For example, for the first keyword "job", keywords such as "N Four Generation", "Knit Group" and "Silver" may be determined as trend keywords as reflecting current trends.

The keyword according to the oppositeness search for the first keyword may include, for example, an antonym of the first keyword, a keyword corresponding to the first keyword, or a keyword opposite to the first keyword.

Keywords searched based on the frequency of keyword selection related to the first keyword may be, for example, a keyword with a high frequency of selection by users in a search in the search engine 130 using the first keyword or a keyword associated with content with a high frequency of selection by users It may include. This may include, for example, a popular search word (keyword) associated with the first keyword.

6 illustrates a method of determining a keyword related to a keyword input by a user, according to an example. In FIG. 6, a method of determining second keywords for a first keyword (job) is illustrated.

As shown, the computer system 100 is related keywords related to the first keyword (job), “rental housing” and “housing price” in the living category, “non-regular workers”, “unemployment rate” and “youth unemployment” in the economic category. And “immigration”, “social enterprise” and “sharing economy” in the social category, “deep learning” and “autonomous driving” as popular keywords, and “N four generations”, “nits” and “silver” as trend keywords. Can be determined and presented. Keywords may be recommended for each topic according to their similarity ranking.

All of these presented keywords or keywords selected by the user may be determined as the second keywords. Alternatively, unlike shown, the keywords may be presented as a list, and second keywords may be selected by the user from the list.

Meanwhile, as illustrated in FIG. 6, when a user selects (eg, clicks or touches) suggested keywords, a search may be performed by combining the selected keyword and the first keyword.

In step 230, the computer system 100 may map the second keywords to the first table of the map 140 in the form of a mandala around the first keyword. The first table may be a table of depth 1 of the map 140 in the form of a mandala. A first keyword may be mapped at the center of the first table, and determined second keywords may be mapped around the first keyword.

In operation 240, the computer system 100 may display a map 140 in the form of a mandala to which the first and second keywords are mapped. The map 140 in the form of a mandala may be displayed through a user terminal.

The map 140 in the form of a mandala may include at least one empty space. For example, as illustrated in FIG. 1, the first table of the map 140 in the form of a mandala may include an empty space (empty space).

In step 250, the computer system 100 may provide a user interface that allows a user to input a third keyword for an empty space of the map 140 in the form of a mandala. The third keyword may be a keyword that the user collectively inputs as a related keyword in relation to the first keyword. For example, the user may select an empty space (an empty space of the first table) of the map 140 in the form of a mandala through a click or touch, and may directly input a third keyword for the selected empty space. The user can derive an appropriate third keyword by referring to the keywords mapped on the presented mandala-shaped map 140, and can fill the empty space of the mandala-shaped map 140 with the derived third keyword. .

In step 260, the computer system 100 may update and display the map 140 in the form of a mandala according to an input of the third keyword from the user. That is, as the empty space of the mandala-shaped map 140 is filled with the third keyword, the mandala-shaped map 140 may be updated.

The map 140 in the form of a mandala may be displayed in at least 2 depths. In the second table corresponding to depth 2 of the map 140 in the form of a mandala, a plurality of fourth keywords related to one of the second keywords and the third keyword are determined based on one of the second keywords and the third keyword. And can be mapped. That is, in the second table corresponding to depth 2 of the map 140 in the form of a mandala, each of the keywords primarily related to the first keyword (second keywords and third keywords) is mapped to the center, and Keywords related to the mapped keyword may be mapped around it. As for the method of determining the keywords mapped to the second table, a description of the method of determining the keywords mapped to the first table may be similarly applied, and thus a duplicate description will be omitted.

The map 140 in the form of a mandala may be displayed at 3 depths, for example. By displaying the map 140 in the form of a mandala having a plurality of depths as described above, it is possible to easily expand an idea related to the first keyword.

The empty space of the above-described mandala-shaped map 140 may be an empty space of the second table. In other words, the computer system may provide a user interface that allows a user to input a keyword in an empty space of the second table. For example, the user may select an empty space (an empty space of the second table) of the map 140 in the form of a mandala through a click or touch, and may directly input a related keyword for the selected empty space. The user may derive an appropriate related keyword by referring to keywords mapped on the presented mandala-shaped map 140, and may fill the empty space of the mandala-shaped map 140 with the derived related keywords.

Meanwhile, in the map 140 in the form of a mandala, the transparency of at least a portion of the first table and the second table may be set differently according to the degree of relevance to the first keyword. Through the display form of the map 140 in the form of mandala, the user can easily grasp the degree of relevance of the keyword mapped to the map 140 in the form of mandala with respect to the first keyword.

As described above, the empty space of the mandala-type map 140 may be an empty space of at least one of the first table and the second table of the mandala-type map 140. This empty space can be filled according to an instruction by the user. For example, keywords related to the keyword at the center of the at least one table may be determined and mapped in an empty space according to a user's command. As an example, when a keyword at the center of a table in which an empty space exists is selected twice, the empty space of the table may be filled with keywords related to the center keyword.

In addition, the computer system 100 may provide a user interface for collectively filling empty spaces of the map 140 in the form of a mandala.

In addition, the computer system 100 may provide a user interface for refreshing related keywords (ie, keywords other than the first keyword) mapped to the map 140 in the form of a mandala.

In addition, the computer system 100 may provide a user interface for deleting or modifying related keywords mapped to the map 140 in the form of a mandala. The user can delete or modify the selected related keyword by selecting the displayed related keyword.

A method of mapping related keywords to the map 140 in the mandala form and a detailed display method of the map 140 in the mandala form will be described in more detail with reference to FIGS. 3 to 5 to be described later.

In the above, descriptions of the technical features described above with reference to FIG. 1 may be applied to FIGS. 2 and 6 as they are, so a duplicate description will be omitted.

FIG. 3 illustrates a method of mapping keywords related to a keyword input to a user to a map in a mandal-art form, according to an example.

In FIG. 3, a method of mapping keywords (key keywords) input by the user by the computer system 100 and related keywords to the map 140 in the form of a mandala is illustrated.

As illustrated, a plurality of related keywords may be searched for a keyword (key keyword) input by a user. Also, for a core keyword, content (eg, an image) related to the corresponding core keyword may be searched.

The core keyword may be mapped to the center of the map 140 in the form of a mandala (ie, the center of the first table of depth 1), and the related keywords may be mapped around the keyword mapped to the center.

In addition, content searched for a corresponding key keyword may also be mapped to the map 140 in the form of a mandala.

A detailed display method of the mandala-shaped map 140 to which content is mapped will be described in more detail with reference to FIG. 4 to be described later.

As described above, the description of the technical features described above with reference to FIGS. 1, 2 and 6 may be applied to FIG. 3 as it is, so a duplicate description will be omitted.

4 and 5 illustrate a map in the form of a mandal-art in which related keywords for keywords input to a user are mapped, according to an example.

In FIGS. 4 and 5, a map 140 in the form of a mandala of 2 depths is illustrated.

In the illustrated mandala-shaped map 140, the first keyword is illustrated as “job”. Eight related keywords related to the first keyword are mapped in the first table 410. Each of the eight related keywords mapped to the first table 410 may be a second keyword or a third keyword described above.

In the illustrated example, each of the second tables including the second table 420 is illustrated as not having a related keyword mapped except for the central region, but this is only for convenience of explanation, and each of the second tables At least some of the parts excluding the central area may be filled with related keyword(s).

As illustrated, in the map 140 in the form of a mandala, the transparency of at least a portion of the first table and the second table may be set differently according to the degree of relevance to the first keyword. For example, (in the illustrated example, only solid lines and dotted lines are separated for convenience of explanation), as keywords with higher relevance to the first keyword, the portion corresponding to the corresponding keyword in the first table 410 and the second table 420 Can be displayed darker. Through the display form of the map 140 in the form of mandala, the user can easily grasp the degree of relevance of the keyword mapped to the map 140 in the form of mandala with respect to the first keyword. In the illustrated example, "unemployment rate" and "social enterprise" have high relevance for the first keyword "job", but "sharing economy" and "autonomous driving" are shown to have low relevance.

Through the display form of the map 140 in the form of mandala, the user can easily grasp the degree of relevance of the keyword mapped to the map 140 in the form of mandala with respect to the first keyword.

As illustrated in FIG. 4, a content 430 corresponding to a related keyword mapped to the first table 410 may be displayed on at least one second table of the second tables of the mandala-shaped map 140. . For example, as shown, an image (eg, despair image) corresponding to the "N four generation" may be displayed in a second table corresponding to the related keyword "N four generation" mapped to the first table 410, An image (eg, robot image) corresponding to "deep learning" may be displayed in the second table corresponding to the related keyword "deep learning" mapped to the first table 410.

The content 430 displayed in the second table is an image according to an image search for a related keyword mapped to the first table 410 (e.g., an image that is searched first, or an image most selected by users), an image It may include a slide show of a plurality of images according to the search, a gif image based on the plurality of images, or a video according to a video search for a related keyword mapped to the first table 410. Also, the content 430 displayed on the second table may be a result of a patent search for a related keyword mapped to the first table 410.

Alternatively, the content 430 may be a content (image) related to a first keyword or a second keyword among contents (images or photos) included in posts posted in connection with the SNS account of the user who entered the first keyword. have. For example, the content 430 is an image related to a first keyword or a second keyword, and has a high similarity to content (images or photos, etc.) included in posts posted in connection with the SNS account of the user who entered the first keyword. It may be a thing, or it may be a content (image) having the opposite.

The content 430 may be displayed on the second table with a predetermined transparency. In other words, the content 430 and the keyword mapped to the second table on which the corresponding content is displayed may be simultaneously displayed.

The predetermined transparency of the content 430 on the second table may be different according to the relationship between the first keyword and the content 430. For example, the higher the relevance of the content 430 to the first keyword, the lower the transparency of the content 430 may be.

Alternatively, in response to a user's selection of the content 430 or a user's interaction with a portion of the displayed content 430, keywords mapped to a corresponding second table may be displayed. For example, when there is a click or touch on the content 430, a slide or swipe input in the up/down/left/right direction, the display of the content 430 is terminated and keywords mapped to the corresponding second table are displayed. Can be displayed. That is, a related keyword mapped to the first table 410 may be displayed at the center of the second table, and the above-described fourth keywords may be displayed around the second table.

Alternatively, when the content 430 is selected by the user or a user's interaction with a portion of the content 430 is sensed, a keyword related to the content 430 may be further determined and displayed. For example, the computer system 100 may further display keyword(s) output by performing a search by inputting the content 430 to the search engine 130 as an input. Alternatively, the computer system 100 may further display the keyword(s) determined based on text information extracted from the content 430 through OCR or the like or from the metadata of the content 430. The keyword(s) may be displayed separately from the second table associated with the content 430, or may be displayed by filling an empty space of the second table.

In FIG. 5, a method of providing a map 140 in the form of a mandala as a card user interface is illustrated.

In the mandala-shaped map 140 of the embodiment, in response to a user's selection or interaction with the first table 410, an idea keyword in which at least two of the keywords mapped to the first table 410 are combined It is determined, and the first table 410 is converted into a card form to display an idea keyword.

Alternatively, as shown, in the mandala-shaped map 140 of the embodiment, at least one of the keywords mapped to the second table 510 in response to the user's selection or the user's interaction with the second table 510 The idea keywords in which the two are combined is determined, and the second table 510 is converted into a card form to display the idea keywords.

The user's selection or interaction may be a click or a touch on the content 430, a slide in an up/down/left/right direction, or a swipe input.

The idea keyword may be displayed on the back side of the first table 410 or the second table 510 in which the first table 410 or the second table 510 is displayed and switched.

The computer system 100, for example, combines a keyword at the center of the first table 410 (ie, a first keyword) and at least one second keyword (a second keyword selected at random or selected by a user) Thus, an idea keyword can be generated, and such an idea keyword can be displayed through a card user interface. For example, when the user selects "deep learning" and "sharing economy" in the first table 410, the computer system 100 determines an idea keyword based on job+deep learning+sharing economy and displays the card user interface. It can be displayed through. A similar description may be applied to the second table 510, and a duplicate description will be omitted.

In the above, descriptions of the technical features described above with reference to FIGS. 1 to 3 and 6 may be applied to FIGS. 4 and 5 as they are, and thus redundant descriptions will be omitted.

The map 140 in the form of a mandala according to the embodiment is related to a mandaland map for deriving ideas in an improved form capable of presenting content such as images as well as text such as keywords. 140) may be referred to as a seedmap.

The aforementioned Word2Vec algorithm for determining an input keyword and a related keyword may be one of keyword embedding techniques.

The Word2Vec algorithm can grasp the similarity between keywords for a list of keywords. The Word2Vec algorithm proceeds in the SkipGram method, and by repeating the process of predicting surrounding keywords through the central keyword, the similarity between keywords can be grasped and keywords can be vectorized. Similar keywords for a specific keyword can be extracted by applying an operation to the vectorized keywords. In the case of determining the relevant keywords only by the Word2Vec algorithm, there is a concern that the result value biased to a specific group (category) may be derived. For example, with respect to the central keyword "cat", the related keyword may be biased toward dog, tiger, lion, fox ... (animal category), and a result value may be derived.

The LDA algorithm may be a topic modeling technique. The LDA algorithm expresses the frequency of occurrence of keywords for each document as a probability and can predict topics (subjects, categories) of specific keywords. The LDA algorithm may make it impossible to grasp the similarity between keywords by simply calculating probability. Meanwhile, the Gaussian LDA algorithm may be an algorithm for replacing LDA in which similarity analysis between keywords is impossible. The similarity between keywords can be identified by using the keyword embedding method for pre-processing of LDA input.

In an embodiment, the word2vec algorithm (keyword embedding) can be used as a result of preprocessing with the LDA algorithm. The purpose of the Gaussian LDA algorithm was to extract the most similar keywords for the input keywords, but in the case of an embodiment, extracting related keywords within various topics (subjects, categories) may be a key point (that is, in order to conceive an idea, It is necessary to come up with a combination of other related things). In an embodiment, by using such a combined algorithm, related keywords may be obtained for various categories without being biased against one category.

The apparatus described above may be implemented as a hardware component, a software component, and/or a combination of a hardware component and a software component. For example, the devices and components described in the embodiments include, for example, a processor 120, a controller, an arithmetic logic unit (ALU), a digital signal processor (120), a microcomputer, and an FPA. (field programmable array), programmable logic unit (PLU), microprocessor 120, or any other device capable of executing and responding to instructions. I can. The processing device may execute an operating system (OS) and one or more software applications executed on the operating system. Further, the processing device may access, store, manipulate, process, and generate data in response to the execution of software. For the convenience of understanding, although it is sometimes described that one processing device is used, one of ordinary skill in the art, the processing device is a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that it may include. For example, the processing device may include a plurality of processors 120 or one processor 120 and one controller. In addition, other processing configurations, such as a parallel processor 120 are possible.

The software may include a computer program, code, instructions, or a combination of one or more of these, configuring the processing unit to operate as desired or processed independently or collectively. You can command the device. Software and/or data may be interpreted by a processing device or, to provide instructions or data to a processing device, of any type of machine, component, physical device, virtual equipment, computer storage medium or device. , Or may be permanently or temporarily embodyed in a transmitted signal wave. The software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the embodiment, or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. -A hardware device specially configured to store and execute program instructions such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those produced by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware device described above may be configured to operate as one or more software modules to perform the operation of the embodiment, and vice versa.

As described above, although the embodiments have been described by the limited embodiments and drawings, various modifications and variations are possible from the above description to those of ordinary skill in the art. For example, the described techniques are performed in a different order from the described method, and/or components such as systems, structures, devices, circuits, etc. described are combined or combined in a form different from the described method, or other components Alternatively, even if substituted or substituted by an equivalent, an appropriate result can be achieved.

Claims (5)

In a method of providing a related keyword performed by a computer system,
Receiving a first keyword input by a user;
Determining a plurality of second keywords as keywords related to the first keyword;
Mapping the second keywords to a first table of a mandala-art map based on the first keyword;
Displaying the mandala-shaped map to which the first keyword and the second keyword are mapped;
Providing a user interface allowing the user to input a third keyword for an empty space of the mandala-shaped map; And
Updating and displaying the mandala-shaped map according to the input of the third keyword from the user
Including,
Each of the second keywords is a keyword according to a relevance search for the first keyword, a keyword according to a trend search for the first keyword, a keyword according to an opposition search for the first keyword, and the first keyword and Including at least two of the keywords searched based on the frequency of selection of related keywords,
The mandala-shaped map is displayed with at least 2 depths,
In a second table corresponding to depth 2 of the mandala-shaped map, a plurality of fourth keywords related to one of the second keywords and the third keyword are determined based on one of the second keywords and the third keyword. Is mapped,
A method of providing a related keyword, wherein transparency of at least a portion of the first table and the second table is set differently according to a degree of relevance to the first keyword. The method of claim 1,
Content corresponding to any one of the keywords is displayed in the second table,
The displayed content may include an image according to an image search for the one keyword, a slide show of a plurality of images according to the image search, a gif image based on the plurality of images, or a video search for the one keyword. Includes a video according to,
In response to the user's interaction with the part of the content, the second table to which the fourth keywords are mapped is displayed, based on the one keyword. The method of claim 2,
When the displayed content is selected by the user, a keyword related to the content is further determined and displayed. The method of claim 1,
The second keywords are selected by the user from among a plurality of keywords presented according to a search based on the first keyword,
The empty space of the mandala-shaped map is an empty space of at least one of the first table and the second table,
According to a command from the user, keywords related to the keyword at the center of the at least one table are determined and mapped in the empty space. The method of claim 1,
In response to the user's interaction with the first table, an idea keyword in which at least two of the keywords mapped to the first table are combined is determined, and the first table is converted into a card form to display the idea keyword. Or
In response to the user's interaction with the second table, an idea keyword in which at least two of the keywords mapped to the second table are combined is determined, and the second table is converted into a card form to display the idea keyword. , How to provide related keywords.

Images