Method, system and non-transitory computer-readable recording medium for recommending content for writing - Patents.com

Abstract

According to one aspect of the present invention, a method for recommending content for composition is provided, the method including the steps of extracting primary keywords from a user document consisting of at least one block, and determining recommended content related to the user document by referring to at least one of style attributes assigned to the primary keywords in the user document and attributes of a block including the primary keywords.

Description

[Technical field]

[0001] The present invention relates to a method, system, and non-transitory computer-readable medium for recommending content for writing. [Background technology]

[0002] Usually, writing (or writing a piece of paper) can be done to achieve a variety of goals. For example, a personal statement can be written to achieve the goal of getting a job or entering a university, and a thesis can be written to achieve the goal of earning a degree or achieving academic success.

[0003] In the process of writing as described above, it is common to refer to various sources related to the composition (e.g., papers, news, reports, etc.) in order to improve the quality of the composition.

[0004] However, in the past, there was no technology that could automatically recommend writing-related materials during the writing process, so users had to waste a lot of time and effort searching for and finding materials related to writing, and there was also the problem of reduced concentration on writing. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Korean Patent Publication No. 10-2021-0114622 Summary of the Invention [Problem to be solved by the invention]

[0006] An object of the present invention is to solve all of the problems of the prior art mentioned above.

[0007] Another object of the present invention is to drastically reduce the time and effort consumed in searching for and finding materials related to writing by automatically recommending materials (or content) related to writing based on keywords created during the writing process. [Means for solving the problem]

[0008] A representative configuration of the present invention for achieving the above object is as follows.

[0009] According to one aspect of the present invention, a method for recommending content for composition is provided, the method including the steps of extracting primary keywords from a user document consisting of at least one block, and determining recommended content related to the user document by referring to at least one of style attributes assigned to the primary keywords in the user document and attributes of a block including the primary keywords.

[0010] According to another aspect of the present invention, there is provided a system for recommending content for composition, the system including: a keyword extraction unit that extracts major keywords from a user document consisting of at least one block; and a content determination unit that determines recommended content related to the user document by referring to at least one of a style attribute assigned to the major keyword in the user document and an attribute of a block including the major keyword.

[0011] In addition, other methods for embodying the present invention, other systems, and a non-transitory computer readable recording medium having a computer program for carrying out the methods are also provided. Effect of the Invention

[0012] According to the present invention, by automatically recommending materials (or contents) related to writing based on keywords created during the writing process, it is possible to achieve a dramatic reduction in the time and effort consumed in the process of searching for and finding materials related to writing. [Brief description of the drawings]

[0013] [Figure 1] 1 is a diagram showing a schematic configuration of an entire system for recommending content for writing according to an embodiment of the present invention. [Diagram 2] 2 is a diagram illustrating in detail an internal configuration of a content recommendation system according to an embodiment of the present invention. [Diagram 3] 2 is a diagram illustrating an example of a user interface screen provided by a content recommendation system according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] The following detailed description of the present invention will be made with reference to the accompanying drawings, which show, by way of example, specific embodiments in which the present invention may be practiced. Such embodiments are described in sufficient detail to enable one skilled in the art to practice the present invention. It should be understood that the various embodiments of the present invention are different from one another but are not necessarily mutually exclusive. For example, specific shapes, structures and characteristics described herein may be embodied in one embodiment without departing from the spirit and scope of the present invention. It should also be understood that the location or arrangement of individual components within each embodiment may be changed without departing from the spirit and scope of the present invention. Therefore, the following detailed description is not to be taken in a limiting sense, and the scope of the present invention should be taken to include the scope of the claims and all equivalents thereto. In the drawings, like reference numerals indicate the same or similar components throughout the various aspects.

[0015] In this specification, content is a general concept that refers to digital information or individual information elements consisting of characters, codes, voice, audio, images, videos, etc. Such content may be composed of data such as text, images, videos, audio, links (e.g., web links), etc., or a combination of at least two of such data.

[0016] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, various preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings in order to enable those skilled in the art to which the present invention pertains to easily practice the present invention.

[0017] Overall system configuration

[0018] FIG. 1 is a diagram showing a schematic configuration of an entire system for recommending content for writing according to an embodiment of the present invention.

[0019] As shown in FIG. 1, the overall system according to an embodiment of the present invention may include a communication network 100, a content recommendation system 200, and a device 300.

[0020] First, the communication network 100 according to an embodiment of the present invention may be configured regardless of the type of communication, such as wired communication or wireless communication, and may be configured as various communication networks, such as a local area network (LAN), a metropolitan area network (MAN), and a wide area network (WAN). Preferably, the communication network 100 in this specification may be the well-known Internet or World Wide Web (WWW). However, the communication network 100 is not necessarily limited thereto, and may include at least a part of a well-known wired / wireless data communication network, a well-known telephone network, or a well-known wired / wireless television communication network.

[0021] Next, the content recommendation system 200 according to an embodiment of the present invention can communicate with a device 300 (to be described later) through the communication network 100, extract a main keyword from a user document consisting of at least one block, and determine recommended content related to the user document by referring to at least one of a style attribute assigned to the main keyword in the user document and an attribute of a block including the main keyword. Meanwhile, such a content recommendation system 200 may be a digital device having a memory means and a microprocessor and having a computing capacity, and may be, for example, a server system operated on the communication network 100.

[0022] The configuration and functions of the content recommendation system 200 according to an embodiment of the present invention will be explained in detail below.

[0023] Next, the device 300 according to one embodiment of the present invention is a digital device having a function of communicating after connecting to the content recommendation system 200, and any digital device having a memory means, a microprocessor, and computing power, such as a smartphone, tablet, smart watch, smart band, smart glasses, desktop computer, notebook computer, workstation, PDA, web pad, mobile phone, etc., may be adopted as the device 300 according to the present invention.

[0024] According to an embodiment of the present invention, the device 300 may further include an application program for performing functions according to the present invention. Such an application may exist in the form of a program module in the device 300. The nature of such a program module may be generally similar to the keyword extractor 210, the content determiner 220, the communicator 230, and the controller 240 of the content recommendation system 200 described below. Here, at least a part of the application may be replaced with a hardware or firmware device capable of performing substantially the same or equivalent functions, if necessary.

[0025] Content recommendation system configuration

[0026] Hereinafter, the internal configuration of the content recommendation system 200 and the functions of each component thereof, which perform important functions for implementing the present invention, will be described in detail.

[0027] FIG. 2 is a diagram illustrating in detail the internal configuration of a content recommendation system 200 according to an embodiment of the present invention.

[0028] As shown in FIG. 2, the content recommendation system 200 according to an embodiment of the present invention may include a keyword extraction unit 210, a content determination unit 220, a communication unit 230, and a control unit 240. According to an embodiment of the present invention, the keyword extraction unit 210, the content determination unit 220, the communication unit 230, and the control unit 240 of the content recommendation system 200 may be program modules, at least some of which communicate with an external system (not shown). Such program modules may be included in the content recommendation system 200 in the form of an operating system, an application module, or other program modules, and may be physically stored in various known storage devices. Also, such program modules may be stored in a remote storage device that can communicate with the content recommendation system 200. Meanwhile, such program modules include, but are not limited to, routines, subroutines, programs, objects, components, data structures, etc. that perform specific tasks or execute specific abstract data types, which will be described later, according to the present invention.

[0029] Meanwhile, although the content recommendation system 200 has been described above, such description is illustrative, and it will be apparent to those skilled in the art that at least some of the components or functions of the content recommendation system 200 may be embodied within the device 300 or a server (not shown) or included in an external system (not shown) as necessary.

[0030] First, the keyword extractor 210 according to an embodiment of the present invention can perform a function of extracting main keywords from a user document that is composed of at least one block.

[0031] According to an embodiment of the present invention, a user can input text (here, text may include letters, numbers, symbols, or combinations thereof) to the keyword extraction unit 210 (or a server or platform supporting the function of the keyword extraction unit 210) in order to write a composition on a predetermined document (e.g., a self-introduction, a thesis, a report, etc.) (although the user may also input images, graphs, tables, etc. in addition to the text). According to an embodiment of the present invention, the text input by the user can form at least one block, and the at least one block can constitute the predetermined document (hereinafter, referred to as a "user document"). Here, a block according to an embodiment of the present invention can mean a single paragraph or a plurality of paragraphs whose degree of coherence corresponds to a predetermined level or higher.

[0032] Next, the keyword extraction unit 210 according to an embodiment of the present invention may perform pre-processing on a user document (here, the user document may include a document that is being created (i.e., not yet completed) by the user) created based on a user input. For example, the keyword extraction unit 210 according to an embodiment of the present invention may remove text (e.g., blank characters, special symbols, etc.) that is not used in the process of recommending content from the user document. As another example, the keyword extraction unit 210 according to an embodiment of the present invention may classify text in the user document into morpheme units using a morphological analyzer (e.g., Komoran, Kkma, etc.).

[0033] Next, the keyword extraction unit 210 according to an embodiment of the present invention may extract major keywords from the user document (or the user document on which preprocessing has been performed) using a natural language processing technique. For example, the keyword extraction unit 210 according to an embodiment of the present invention may extract major keywords from the user document based on a result of performing Term Frequency-Inverse Document Frequency (TF-IDF), which corresponds to a natural language processing technique. Here, according to an embodiment of the present invention, the TF-IDF may mean a statistical value indicating how important a certain word is in a specific document. More specifically, the keyword extraction unit 210 according to an embodiment of the present invention may determine keywords with high importance in the user document based on a result of performing the TF-IDF, and may extract a predetermined number of keywords as major keywords from the keywords determined as the keywords with high importance (for example, the top five keywords from the keywords determined as the keywords with high importance may be extracted as major keywords).

[0034] Next, the content determination unit 220 according to one embodiment of the present invention may perform a function of determining recommended content related to the user document by referring to at least one of the style attributes assigned to the main keywords in the user document and the attributes of the block including the main keywords.

[0035] According to an embodiment of the present invention, the content determining unit 220 can assign scores to the main keywords extracted from the user documents by the keyword extracting unit 210 and can apply weights to the scores.

[0036] For example, the content determination unit 220 according to an embodiment of the present invention may assign scores to the main keywords extracted from the user document based on the importance order according to the result of performing the TF-IDF. More specifically, assuming that the first keyword, the second keyword, the third keyword, the fourth keyword, and the fifth keyword are extracted as the main keywords from the user document and the importance order according to the result of performing the TF-IDF is 3rd, 2nd, 1st, 5th, and 4th, respectively, the first keyword, the second keyword, the third keyword, the fourth keyword, and the fifth keyword may be assigned 3 points, 4 points, 5 points, 1 point, and 2 points, respectively. Meanwhile, the score according to an embodiment of the present invention may be set to a maximum of 5 points, but is not necessarily limited thereto.

[0037] In addition, the content determination unit 220 according to an embodiment of the present invention may apply a weight to a score assigned to the corresponding primary keyword by referring to a style attribute assigned (or set) to the corresponding primary keyword in the user document. For example, the content determination unit 220 according to an embodiment of the present invention may apply a weight (e.g., double) to a score assigned to the corresponding primary keyword by referring to the fact that the corresponding primary keyword is set in bold as a style attribute assigned to the corresponding primary keyword in the user document. As another example, the content determination unit 220 according to an embodiment of the present invention may apply a weight to a score assigned to the corresponding primary keyword by referring to the fact that the corresponding primary keyword is set to be included in the title (or subtitle) of the user document as a style attribute assigned to the corresponding primary keyword in the user document. Here, according to an embodiment of the present invention, when a primary keyword is set to be included in a title (or subtitle) of a user document (here, whether a primary keyword is set to be included in a title (or subtitle) of a user document may be determined with reference to the font size of the primary keyword (for example, when the font size of the primary keyword is larger than the font size with the highest frequency in the user document (or the font size of other primary keywords in the user document) by a predetermined level or more), a higher weighting value may be applied as the font size of the primary keyword increases. More specifically, according to an embodiment of the present invention, when the font size of the primary keyword is 20 [pt] (here, [pt] may indicate a predetermined unit of font size), a weighting value of 2 times may be applied, and when the font size of the primary keyword is 24 [pt], a weighting value of 2.4 times may be applied. That is, according to an embodiment of the present invention, when a primary keyword is set to be included in a title (or subtitle) of a user document, a weighting value applied to a score given to the primary keyword may increase in proportion to an increase in the font size of the primary keyword.

[0038] In addition, the content determining unit 220 according to an embodiment of the present invention may apply a weight to the score assigned to the corresponding major keyword by referring to the attribute of the block including the major keyword. Here, according to an embodiment of the present invention, the attribute of the block may include the importance of the block, and a predetermined level may be assigned to each block based on the attribute of the block. According to an embodiment of the present invention, the attribute of the block may be determined (or set) by referring to the type of the user document. Specifically, according to an embodiment of the present invention, the importance of each of at least one block constituting the user document may differ depending on the type of the user document. The content determining unit 220 according to an embodiment of the present invention may set the importance of the corresponding block for at least one block constituting the user document by referring to a lookup table related to the type of the user document and the importance of at least one block constituting the corresponding user document, and may assign a predetermined level to the corresponding block based on the importance. For example, assuming that the type of the user document is a thesis, the first block included in the abstract of the user document, the second block included in the body, and the third block included in the conclusion may have different importance, and the order of importance may be the first block, the third block, and the second block, according to the lookup table. Therefore, the content determination unit 220 according to an embodiment of the present invention may set the importance of the first block, the second block, and the third block constituting the user document by referring to the lookup table, and may assign higher levels to the first block, the third block, and the second block, according to the importance. Next, the content determination unit 220 according to an embodiment of the present invention may determine in which block of the user document the main keyword extracted from the user document is included, and may apply a weight to the score assigned to the main keyword by referring to the level assigned to the corresponding block.

[0039] Meanwhile, the content determination unit 220 according to an embodiment of the present invention may determine recommended content related to a user document by referring to the scores given to the main keywords and the weights applied to the scores. Here, the content according to an embodiment of the present invention may include various contents such as text (e.g., news, papers, reports, etc.), images, videos, etc.

[0040] For example, the content determination unit 220 according to an embodiment of the present invention may determine a content including at least one of the main keywords extracted from the user document as a recommended content related to the user document. Then, the content determination unit 220 according to an embodiment of the present invention may determine a recommended content to be preferentially recommended by referring to the number of main keywords included in the recommended content determined as above. Here, when a plurality of recommended contents each include the same number of main keywords, the content determination unit 220 according to an embodiment of the present invention may determine a recommended content to be preferentially recommended by referring to a score obtained by adding up scores (more specifically, scores to which weighted values ​​are applied) given to the main keywords included in each recommended content.

[0041] More specifically, according to an embodiment of the present invention, it is assumed that the first keyword, the second keyword, the third keyword, the fourth keyword, and the fifth keyword are extracted as major keywords from the user document, and the scores (more specifically, the scores to which weights are applied) given to the respective keywords are 10 points, 12 points, 20 points, 8 points, and 15 points. The content determination unit 220 according to an embodiment of the present invention may determine the first content including the first keyword and the second keyword, the second content including the first keyword, the second keyword, and the third keyword, the third content including the first keyword, the second keyword, the third keyword, and the fourth keyword, and the fourth content including the first keyword, the second keyword, the third keyword, and the fifth keyword, as recommended content related to the user document. The content determination unit 220 according to an embodiment of the present invention determines the recommended content to be preferentially recommended by referring to the number of major keywords included in the recommended content determined as above, and may determine the recommended content to be preferentially recommended by adding up the scores given to the major keywords included in the respective recommended contents for the third content and the fourth content including the same number (four) of major keywords. That is, according to one embodiment of the present invention, the total score given to the main keywords (i.e., the first keyword, the second keyword, the third keyword, and the fourth keyword) included in the third content is 50 points, and the total score given to the main keywords (i.e., the first keyword, the second keyword, the third keyword, and the fifth keyword) included in the fourth content is 57 points, so that the fourth content can be recommended preferentially over the third content. Finally, according to one embodiment of the present invention, recommended contents can be provided to the user in the order of the fourth content, the third content, the second content, and the first content.

[0042] Meanwhile, the content determination unit 220 according to an embodiment of the present invention may dynamically determine recommended content based on changes in main keywords extracted from a user document. For example, the content determination unit 220 according to an embodiment of the present invention may provide recommended content to a user in real time through a user interface screen while the user is creating a document, and may provide content different from previously recommended content to the user, reflecting changes made to the content of the document by the user (e.g., text correction or addition).

[0043] Next, the communication unit 230 according to an embodiment of the present invention can perform a function of enabling data transmission / reception to / from the keyword extraction unit 210 and the content determination unit 220.

[0044] Finally, the control unit 240 according to an embodiment of the present invention can perform a function of controlling data flow between the keyword extraction unit 210, the content determination unit 220, and the communication unit 230. That is, the control unit 240 according to the present invention can control the keyword extraction unit 210, the content determination unit 220, and the communication unit 230 to perform their respective unique functions by controlling the data flow from / to the outside of the content recommendation system 200 or the data flow between each component of the content recommendation system 200.

[0045] FIG. 3 is a diagram illustrating an example of a user interface screen provided by the content recommendation system 200 according to an embodiment of the present invention.

[0046] Referring to FIG. 3, a user interface screen according to an embodiment of the present invention may include a first space 310 and a second space 320.

[0047] According to an embodiment of the present invention, a block related to a user input may be displayed in the first space 310. Here, according to an embodiment of the present invention, the block related to the user input may correspond to a block in which text is input according to the user input. The content recommendation system 200 (more specifically, the content determination unit 220) according to an embodiment of the present invention may display a block related to the user input separately from other blocks by referring to the occurrence of the user input in the user document. For example, the content recommendation system 200 according to an embodiment of the present invention may display only the block related to the user input without displaying other blocks of the user document in the first space 310. In addition, the content recommendation system 200 according to an embodiment of the present invention may highlight at least some of the blocks related to the user input based on visual elements by referring to the occurrence of the user input in the user document. For example, the content recommendation system 200 according to an embodiment of the present invention may highlight the title of the block related to the user input (e.g., a title, a subtitle, a temporary title) based on at least one of a hue and a thickness by referring to the occurrence of the user input in the user document (see 311 in FIG. 3).

[0048] Also, according to an embodiment of the present invention, recommended content related to a user document may be displayed in the second space 320 (e.g., the title of the recommended content may be displayed). Here, according to an embodiment of the present invention, the first content 321 may be recommended preferentially over the second content 322 based on the recommendation priority order. For example, the first content 321 may be exposed higher than the second content 322 in the second space 320. Also, according to an embodiment of the present invention, when a user selects (or clicks) a tab (or a graphic element representing the content) related to the first content 321 or the second content 322, a detailed page related to the corresponding content may be displayed in the second space 320. For example, when a user selects a tab related to the first content 321, a summary of the first content 321, a link to view the original of the first content 321, etc. may be displayed in the second space 320.

[0049] The above-described embodiments of the present invention may be embodied in the form of program instructions that can be executed by various computer components and recorded on a computer-readable recording medium. The computer-readable recording medium may include program instructions, data files, data structures, and the like, alone or in combination. The program instructions recorded on the computer-readable recording medium may be specially designed and constructed for the present invention, or may be available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices specially configured to store and execute program instructions, such as ROMs, RAMs, flash memories, 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, and the like. The hardware devices may be replaced by one or more software modules to perform the processes of the present invention, and vice versa.

[0050] Although the present invention has been described above using specific details such as specific components and limited examples and drawings, this is merely provided to assist in a more general understanding of the present invention, and the present invention is not limited to the above examples. Those skilled in the art to which the present invention pertains may attempt various modifications and changes from such descriptions.

[0051] Therefore, the concept of the present invention should not be limited to the above-described embodiments, and all scopes equivalent to or modified equivalently to the scope of the claims below, as well as the scope of the claims, fall within the scope of the concept of the present invention. [Explanation of symbols]

[0052] 100:Communication network 200: Content recommendation system 210: Keyword extraction section 220: Content determination unit 230: Communications Department 240: Control unit 300:Device

Claims

1. 1. A method for recommending content for writing, comprising: extracting key keywords from a user document that is composed of at least one block; determining recommended content related to the user document by referring to at least one of a style attribute assigned to the main keyword in the user document and an attribute of a block including the main keyword; A method comprising:

2. The method of claim 1, wherein in the determination step, a weighting value is applied to the score assigned to the primary keyword by referring to at least one of the style attributes and the block attributes, and the recommended content is determined by referring to the score to which the weighting value has been applied.

3. The method of claim 2 , wherein the attributes of the block are determined with reference to a type of the user document.

4. The method of claim 1 , wherein in the determining step, the recommended content is dynamically determined based on changes in main keywords extracted from the user documents.

5. 2. The method of claim 1, further comprising: referring to an occurrence of a user input in the user document such that a block in the user document related to the user input is displayed separately from other blocks.

6. The method of claim 5 , further comprising: highlighting at least a portion of the blocks associated with the user input based on visual elements.

7. A non-transitory computer-readable recording medium having a computer program recorded thereon for carrying out the method according to claim 1.

8. 1. A system for recommending content for composition, comprising: a keyword extraction unit for extracting major keywords from a user document that is composed of at least one block; a content determination unit that determines recommended content related to the user document by referring to at least one of a style attribute assigned to the main keyword in the user document and an attribute of a block including the main keyword; A system comprising:

9. The system of claim 8 , wherein the content determination unit applies a weighting value to the score assigned to the primary keyword by referring to at least one of the style attribute and the block attribute, and determines the recommended content by referring to the score to which the weighting value has been applied.

10. The system of claim 9 , wherein the attributes of the block are determined with reference to a type of the user document.

11. The system of claim 8 , wherein the content determining unit dynamically determines the recommended content based on changes in main keywords extracted from the user document.

12. 9. The system of claim 8, wherein a block related to a user input in the user document is displayed separately from other blocks in the user document with reference to the occurrence of the user input in the user document.

13. The system of claim 12 , wherein at least a portion of the blocks associated with the user input are highlighted based on visual elements.

Images