System and method for providing personal dictionary building service

Abstract

The present invention relates to a system and a method for providing a service for building a personal dictionary through personalized character string-tag matching for each user. According to a system and a method for building a personal dictionary according to the present invention, in recommending a tag for building a personal dictionary, top tags are recommended in the order of scores determined on the basis of variables such as the cumulative number of selections of tags, whether the tags are manually input, recent selection history, whether a user is a dictionary creator, and whether the tags are included in a provider database, so that personalized characteristics for each user can be well reflected.

Description

System and method for providing personal dictionary building service

[0001] The present invention relates to a technology for providing a service for building a personal dictionary through string-tag matching personalized for each user.

[0002] When people write, there may be differences in the degree of their literary talent, but everyone has probably struggled with using appropriate phrases and sentences to accurately convey their intentions to the other person.

[0003] In particular, everyone has probably had the experience of having difficulty remembering or finding good phrases that they had written or seen in the past, which resulted in having to rewrite the text anew, and of being worried because the newly written text was not to their liking, unlike the good memories of the existing phrases.

[0004] Additionally, when working collaboratively in small teams to create documents, you may have had the experience of finding it difficult to achieve consistency and efficiency in the work due to differences in expression between individuals.

[0005] Recently, with the development of artificial intelligence algorithms, services have been released that allow users to easily and conveniently write desired sentences by simply entering keywords. However, these services are the result of machine learning based on big data, and thus only provide general phrases and sentences, and the problem is that they cannot provide phrases and sentences personalized for each user.

[0006] Additionally, document creation services based on big data like this inevitably have the disadvantage of being exposed to security issues, copyright issues, etc.

[0007] Therefore, there is a growing need for a document writing service that addresses security and copyright issues and enables more convenient and efficient document creation based on individual user experiences.

[0008] (Patent Document 1) US 11093557 B2 (August 17, 2021)

[0009] (Patent Document 2) US 11010371 B2 (May 18, 2021)

[0010] The present invention aims to provide a system and method for providing a service capable of building a personal dictionary of a personalized string-tag matching structure based on small-scale data experienced by an individual or a team.

[0011] The personal dictionary construction system according to the present invention for solving the above-mentioned problem is a system that provides a service for constructing a personal dictionary through string-tag matching personalized for each user, and comprises a user terminal including a string selection unit for selecting a string for a user to create a tag, a string transmission unit for transmitting the string selected by the string selection unit to a service provider server, and a tag selection input unit for allowing the user to select or manually input one tag from a plurality of tags transmitted from the service provider server; And a string receiving unit that receives a string from the string transmitting unit, a first character counting unit that counts the number of characters in the string received by the string receiving unit and compares it with a first reference value, a summary extracting unit that generates a summary that summarizes the string if the first character counting unit determines that the number of characters is greater than or equal to the first reference value, a second character counting unit that counts the number of characters in the string received by the string receiving unit or the number of characters in the summary generated by the summary extracting unit and compares it with a second reference value, a word extracting unit that extracts all words included in the string or the summary if the second character counting unit determines that the number of characters is less than the second reference value, a keyword extracting unit that extracts a keyword included in the string or the summary if the second character counting unit determines that the number of characters is greater than or equal to the second reference value, a tag recommendation unit that extracts a tag corresponding to a word extracted by the word extracting unit or a keyword extracted by the keyword extracting unit from a user database or a supplier database and transmits the tag to a tag selection input unit of the user terminal, and a dictionary that matches a tag transmitted from the tag selection input unit with the string and stores the tag in the user database. A service provider server including a storage unit, a score calculation unit that calculates the score of tags stored in the dictionary storage unit and stores the score in a user database;, wherein the tag recommendation unit extracts upper tags having high scores based on scores stored in the user database and transmits the extracted tags to the tag selection input unit of the user terminal, and the score calculation unit calculates the tag score using as variables the cumulative number of tag selections, whether the tag is manually entered, recent selection history, whether the tag is a pre-creator, and whether the tag is included in a supplier database.

[0012] Preferably, when calculating a score in the above score calculation unit, the cumulative number of selections of tags among the score variables may become a default value, and the remaining score variables may act as weights assigned to the default value according to priority.

[0013] Preferably, the priorities may be given in the following order: manual input, recent selection history, pre-generated content, and inclusion in a supplier database.

[0014] Additionally, the user database includes a tag recommendation database in which words or keywords, tags matching the words or keywords, and scores of the tags are stored, and a dictionary database in which tags and strings matching the tags are stored.

[0015] Meanwhile, a method for constructing a personal dictionary according to the present invention provides a service for constructing a personal dictionary through personalized string-tag matching for each user, comprising: a string selection step for selecting a string for which a user wishes to create a tag on a user terminal; a string transmission step for transmitting the string selected in the string selection step from the user terminal to a service provider server; a string reception step for receiving the string transmitted in the string transmission step to the service provider server; a first character count determination step for counting the number of characters in the string received in the string reception step on the service provider server and comparing the count with a first reference value; a summary extraction step for generating a summary that summarizes the string if the number of characters is determined to be greater than or equal to the first reference value in the first character count determination step on the service provider server; a second character count determination step for counting the number of characters in the string received in the string reception step or the number of characters in the summary generated in the summary extraction step on the service provider server and comparing the count with a second reference value; a word extraction step for extracting all words included in the string or the summary if the number of characters is determined to be less than the second reference value in the second character count determination step on the service provider server; A keyword extraction step for extracting keywords included in a string or summary when it is determined that the number of characters is greater than or equal to a second reference value in the second character count determination step on the service provider server; A tag recommendation step for extracting tags corresponding to words extracted in the word extraction step or keywords extracted in the keyword extraction step on the service provider server from a user database or a provider database and transmitting the tags to the user terminal; A tag selection input step for selecting or manually inputting one tag from among a plurality of tags transmitted from the service provider server on the user terminal; A dictionary storage step for matching the tag selected or manually input in the tag selection input step with the string on the service provider server and storing the tag in the user database;And a score calculation step for calculating the score of the tag stored on the service provider server and storing the score in the user database; wherein the tag recommendation step extracts upper tags having high scores based on the scores stored in the user database and transmits the extracted tags to the user terminal, and in the score calculation step, the score of the tag is calculated using as variables the cumulative number of selections of the tag, whether it is manually entered, recent selection history, whether it is a pre-creator, and whether it is included in the provider database.;

[0016] Preferably, in the score calculation step, when calculating the score, the cumulative number of selections of tags among the score variables may become a default value, and the remaining score variables may act as weights assigned to the default value according to priority.

[0017] Preferably, the priorities may be given in the following order: manual input, recent selection history, pre-generated content, and inclusion in a supplier database.

[0018] The personal dictionary construction system and method according to the present invention enable construction of a personal dictionary with a personalized string-tag matching structure based on small-scale data experienced by each individual or team, thereby providing personalized phrases and sentences to each user, thereby enabling more convenient and efficient creation of documents based on each user's experience.

[0019] In addition, when recommending tags for building a personal dictionary, the top tags are recommended in order of scores determined by considering the cumulative number of tag selections, whether the tag was manually entered, recent selection history, whether the tag was created by the dictionary creator, and whether the tag is included in the supplier database, so that personalized characteristics of each user can be well reflected.

[0020] Additionally, it can resolve security and copyright issues that may arise when providing document writing services by building a personal dictionary.

[0021] FIG. 1 and FIG. 2 are diagrams schematically showing the configuration of a personal dictionary building system according to an embodiment of the present invention.

[0022] FIG. 3 is a diagram schematically showing the data structure of a user database in a personal dictionary building system according to an embodiment of the present invention.

[0023] Figure 4 is a flow chart schematically illustrating a personal dictionary construction method according to an embodiment of the present invention.

[0024] Figure 5 is a flow chart showing in detail the process of a personal dictionary construction method according to an embodiment of the present invention.

[0025] *Explanation of key symbols in the drawing*

[0026] 100: User terminal 110: String selection section

[0027] 120: String transmission section 130: Tag selection input section

[0028] 200: Service Provider Server 210: String Receiver

[0029] 221: First character count determination unit 222: Second character count determination unit

[0030] 223: Summary Extraction Unit 231: Word Extraction Unit

[0031] 232: Keyword Extraction Unit 240: Tag Recommendation Unit

[0032] 250: Pre-storage unit 260: Score calculation unit

[0033] 271: Supplier Database 272: User Database

[0034] 273: Supplier database creation section 274: Tag recommendation database

[0035] 275: Dictionary Database

[0036] S100: String selection stage S200: String transmission stage

[0037] S300: String reception stage S400: First character count determination stage

[0038] S410: Summary extraction step S500: Second character count determination step

[0039] S610: Word extraction stage S620: Keyword extraction stage

[0040] S700: Tag recommendation stage S800: Tag selection input stage

[0041] S900: Pre-storage stage S1000: Score calculation stage

[0042] Hereinafter, a personal dictionary construction system and method according to an embodiment of the present invention will be described in detail with reference to the attached drawings. However, detailed descriptions of well-known functions and configurations that may unnecessarily obscure the gist of the present invention will be omitted.

[0043] First, a personal dictionary construction system according to an embodiment of the present invention will be described in detail with reference to FIGS. 1 to 3.

[0044] FIG. 1 and FIG. 2 are diagrams schematically showing the configuration of a personal dictionary construction system according to an embodiment of the present invention, and FIG. 3 is a diagram schematically showing the data structure of a user database in a personal dictionary construction system according to an embodiment of the present invention.

[0045] As shown in FIG. 1, a personal dictionary construction system according to an embodiment of the present invention is a system that provides a service of constructing a personal dictionary through string-tag matching personalized for each user, and is largely composed of a user terminal (100) and a service provider server (200), and the personal dictionary construction service can be implemented as software based on SaaS (Software-as-a-Service) through an Internet browser on an online cloud platform.

[0046] Referring to FIG. 2, a user terminal (100) includes a string selection unit (110) for selecting a string for which a user wishes to create a tag, a string transmission unit (120) for transmitting the string selected in the string selection unit (110) to a service provider server (200), and a tag selection input unit (130) for allowing a user to select or manually input one tag from a plurality of tags transmitted from the service provider server (200).

[0047] The string selection unit (110) is implemented as a web extension program of an Internet browser installed on a user terminal (100), so that the user can select a string to be transmitted to a service provider server (200) by dragging a specific phrase from a newspaper article, document, data, etc. accessed through the Internet browser.

[0048] In addition, the string selection unit (110) is implemented as a web-based cloud application that is accessed through an Internet browser installed on a user terminal (100), and allows the user to input and drag a specific phrase to select a string to be transmitted to the service provider server (200).

[0049] In addition, the string selection unit (110) is implemented as a voice recognition program installed in the user terminal (100) to convert a voice input by the user into a string and select a string to be transmitted to the service provider server (200).

[0050] The string transmission unit (120) is implemented as a communication module built into the user terminal (100) and transmits the string selected by the string selection unit (110) to the service provider server (200) via wired or wireless communication.

[0051] The tag selection input unit (130) allows the user to select or manually input one tag from a plurality of tags received from the service provider server (200) after transmitting a string to the service provider server (200).

[0052] The tag selected or entered in the tag selection input unit (130) is transmitted to the service provider server (200) through the communication module built into the user terminal (100).

[0053] The tag selection input unit (130), like the string selection unit (110), can be implemented as an editing program or voice recognition program implemented as a web extension program or cloud application of an Internet browser installed on a user terminal (100).

[0054] Meanwhile, the service provider server (200) includes a string receiving unit (210) that receives a string from the string transmitting unit (120), a first character count determining unit (221) that counts the number of characters in the string received by the string receiving unit (210) and compares the count with a first reference value, a summary extracting unit (223) that generates a summary that summarizes the string if the first character count determining unit (221) determines that the number of characters is greater than or equal to the first reference value, a second character count determining unit (222) that counts the number of characters in the string received by the string receiving unit (210) or the number of characters in the summary generated by the summary extracting unit (223) and compares the count with a second reference value, a word extracting unit (231) that extracts all words included in the string or summary if the second character count determining unit (222) determines that the number of characters is less than the second reference value, and a keyword that extracts a subject word included in the string or summary if the second character count determining unit (222) determines that the number of characters is greater than or equal to the second reference value. It includes an extraction unit (232), a tag recommendation unit (240) that extracts tags corresponding to words extracted from the word extraction unit (231) or keywords extracted from the keyword extraction unit (232) from a user database (272) or a supplier database (271) and transmits them to a tag selection input unit (130) of the user terminal (100), a dictionary storage unit (250) that matches tags transmitted from the tag selection input unit (130) with the string and stores them in the user database (272), and a score calculation unit (260) that calculates scores of tags stored in the dictionary storage unit (250) and stores them in the user database (272).

[0055] The string receiving unit (210) is implemented as a communication module equipped in the service provider server (200) and receives a string from the string transmitting unit (120) of the user terminal (100) via wired or wireless communication.

[0056] The first character count determination unit (221), the summary extraction unit (223), the second character count determination unit (222), the word extraction unit (231), and the keyword extraction unit (232) are configured to extract words or keywords from a string for string-tag matching.

[0057] The first character count determination unit (221) counts the number of characters in the string received by the string receiving unit (210) and compares it with the first reference value.

[0058] If the number of characters in the string counted by the first character count determination unit (221) is greater than or equal to the first reference value (e.g., 100), the summary extraction unit (223) generates a summary.

[0059] It is preferable that the summary extraction unit (223) use an extractive summarization method that extracts important or core sentences from a given string, and various known summary extraction algorithms such as TextRank can be used.

[0060] The second character count determination unit (222) counts the number of characters in the string received by the string receiving unit (210) or the number of characters in the summary generated by the summary extraction unit (223) and compares it with the second reference value.

[0061] If the number of characters counted by the second character count determination unit (222) is less than the second reference value (e.g., 20), all words included in the string or summary are extracted through the word extraction unit (231).

[0062] On the other hand, if the number of characters counted by the second character count determination unit (222) is greater than or equal to the second reference value (e.g., 20), the keyword extraction unit (232) extracts the subject words included in the string or summary.

[0063] The word extraction unit (231) extracts all words included in a string or summary by removing unnecessary characters such as particles and stop words using preprocessing algorithms such as tokenization, cleaning, and normalization.

[0064] The keyword extraction unit (232) extracts important or core words from a given string using a keyword extraction algorithm such as count-based vectorization (CountVectorizer) or word embedding, and various known keyword extraction algorithms can be used.

[0065] That is, in the present invention, when extracting words or keywords from a string for string-tag matching, the accuracy and efficiency of word or keyword extraction can be improved by implementing a step-by-step process of extracting a summary, extracting keywords, and extracting words according to the number of characters in the string.

[0066] The tag recommendation unit (240) extracts tags corresponding to words extracted from the word extraction unit (231) or keywords extracted from the keyword extraction unit (232) from the user database (272) or the provider database (271) and transmits them to the tag selection input unit (130) of the user terminal (100) through a communication module provided in the service provider server (200).

[0067] To this end, referring to FIG. 3, the user database (272) may include a tag recommendation database (274) storing words or keywords, tags matching the words or keywords, and scores of the tags.

[0068] For example, in the tag recommendation database (274), tags such as “computer”, “software”, and “HTML” are matched and stored for the word “JAVA” or subject word, and each tag is stored with a score such as 100 points, 200 points, and 50 points.

[0069] The tag recommendation unit (240) extracts top tags (e.g., top 4) with high scores based on the scores stored in the tag recommendation database (274) and transmits them to the tag selection input unit (130) of the user terminal (100).

[0070] If there is no tag corresponding to a word extracted from the word extraction unit (231) or a subject word extracted from the keyword extraction unit (232) in the user database (272), a tag is extracted from the supplier database (271).

[0071] The supplier database (271) is a universal database provided by the supplier so that all users can use it. The supplier database creation unit (273) periodically randomly crawls Internet data to create universal tags and stores the updated tags.

[0072] The dictionary storage unit (250) matches the tag transmitted from the tag selection input unit (130) with the string and stores it in the user database (272).

[0073] To this end, referring to FIG. 3, the user database (272) may include a dictionary database (275) in which tags and strings matching the tags are stored.

[0074] In this way, the dictionary database (275) in which tags and strings matching the tags are stored becomes a personal dictionary that is personalized and built for each user through the personal dictionary building system according to the present invention.

[0075] That is, when a user searches for a tag through the dictionary database (275), he or she can be provided with a string matching the tag, and can utilize the provided string when writing a document.

[0076] The score calculation unit (260) calculates and updates the scores of tags stored in the tag recommendation database (274).

[0077] At this time, the tag's score is determined by variables such as the number of cumulative selections of the tag, whether it is manually entered, recent selection history, whether it is a pre-created tag, and whether it is included in the supplier database.

[0078] A tag's cumulative selection count is the cumulative number of times a tag has been selected by users. A tag with a higher cumulative selection count is given a higher score, which helps it rank higher among recommended tags.

[0079] Manual tag entry is given the highest priority for personal dictionary building when the user enters a tag manually, rather than selecting a recommended tag. This is given the highest score, while manually entering a tag instead of selecting a recommended tag is given the next highest priority. Optionally, points can be deducted if the user selects an inappropriate tag from the recommended list.

[0080] The recent selection history of tags gives a higher score to tags recently selected by the user, allowing them to be ranked higher among recommended tags.

[0081] Whether or not a dictionary creator is the first user to create a dictionary will give a high score to the tags selected by the user who first created the dictionary, so that they can be ranked higher among the recommended tags when multiple users participate in building a personal dictionary.

[0082] This is to ensure that when collaborating as a team, the tags created by the team leader, the user who first created the dictionary, have priority over the tags created by team members.

[0083] Inclusion in Supplier Database If a tag is included in the Supplier Database (271), it means that it is a universal tag that reflects recent trends, so it is given a high score so that it can be positioned at the top of the recommended tags.

[0084] When calculating a score, the cumulative number of selections of tags among the above score variables becomes the default value, and the remaining score variables can act as weights given to the above default values ​​according to priority.

[0085]

[0086] (Score calculation formula)

[0087] Score = Original Score + Default Value × Weight 1 × Weight 2 × ... × Weight n - Deduction

[0088]

[0089] In the above formula, the penalty is the score given when the user selects an inappropriate tag among the recommended tags.

[0090] In a personal dictionary building system according to an embodiment of the present invention, weights are given in the following order: whether manual input is made, recent selection history, whether the dictionary is created by a person, and whether the dictionary is included in a supplier database.

[0091] For example, a default value based on the cumulative selection count of a tag can be assigned by normalizing the cumulative selection count of all tags matching a word or keyword to a value between 0 and 1 using a sigmoid function.

[0092] Weight 1 can be given a value of 2 if the tag is manually entered, 1.5 if the tag is selected from among the recommended tags, and 1.0 if the tag is not selected from among the recommended tags, depending on whether it is manually entered or not.

[0093] Weight 2 can be assigned a value between 1.4 and 1.0 in order of most recent selection history.

[0094] Weight 3 can be given a value of 1.3 if the user is the dictionary creator who first created the dictionary, and 1.0 if not.

[0095] Weight 4 can be given a value of 1.1 if the tag is included in the supplier database (271), or 1.0 if not, depending on whether the tag is included in the supplier database.

[0096] A penalty of 0.1 may be given if the user selects a recommended tag as inappropriate.

[0097] Additionally, in the above formula, the existing score can be assigned by normalizing the existing scores of all tags matching a single word or keyword to a value between 0 and 1 using the sigmoid function. This is to prevent an error in which older tags continue to maintain higher scores than newer tags due to accumulated scores.

[0098] As described above, the personal dictionary construction system according to the embodiment of the present invention recommends tags for personal dictionary construction by determining the top tags in order of scores based on the cumulative number of tag selections, whether the tag is manually entered, recent selection history, whether the tag is a dictionary creator, and whether the tag is included in a supplier database as variables, thereby allowing personalized characteristics for each user to be well reflected.

[0099] Next, a method for building a personal dictionary according to an embodiment of the present invention will be described in detail with reference to FIGS. 4 and 5.

[0100] FIG. 4 is a flow chart schematically illustrating a method for building a personal dictionary according to an embodiment of the present invention, and FIG. 5 is a flow chart illustrating in detail the process of a method for building a personal dictionary according to an embodiment of the present invention.

[0101] A personal dictionary construction method according to an embodiment of the present invention includes a string selection step (S100), a string transmission step (S200), a string reception step (S300), a first character count determination step (S400), a summary extraction step (S410), a second character count determination step (S500), a word extraction step (S610), a keyword extraction step (S620), a tag recommendation step (S700), a tag selection input step (S800), a dictionary storage step (S900), and a score calculation step (S1000), as shown in FIGS. 4 and 5.

[0102] Specifically, a personal dictionary construction method according to an embodiment of the present invention is a method for providing a service of constructing a personal dictionary through personalized string-tag matching for each user, comprising: a string selection step (S100) in which a user selects a string for which a tag is to be created on a user terminal (100); a string transmission step (S200) in which the string selected in the string selection step (S100) is transmitted from the user terminal (100) to a service provider server (200); a string reception step (S300) in which the string transmitted in the string transmission step (S200) is received by the service provider server (200); a first character count determination step (S400) in which the number of characters in the string received in the string reception step (S300) is counted on the service provider server (200) and compared with a first reference value; a summary extraction step (S410) in which a summary is generated that summarizes the string when the number of characters is determined to be equal to or greater than the first reference value in the first character count determination step (S400) on the service provider server (200); A second character count determination step (S500) for counting the number of characters in the string received in the string receiving step (S300) or the number of characters in the summary generated in the summary extraction step (S410) on the server (200) and comparing the count with a second reference value, a word extraction step (S610) for extracting all words included in the string or summary if the number of characters is determined to be less than the second reference value in the second character count determination step (S500) on the service provider server (200), a keyword extraction step (S620) for extracting keywords included in the string or summary if the number of characters is determined to be greater than or equal to the second reference value in the second character count determination step (S500) on the service provider server (200),It includes a tag recommendation step (S700) for extracting a tag corresponding to a word extracted in the word extraction step (S610) or a subject word extracted in the keyword extraction step (S620) on the service provider server (200) from the user database (272) or the provider database (271) and transmitting the tag to the user terminal (100), a tag selection input step (S800) for selecting or manually inputting one tag from among a plurality of tags transmitted from the service provider server (200) on the user terminal (100), a dictionary storage step (S900) for matching the tag selected or manually input in the tag selection input step (S800) with the string on the service provider server (200) and storing it in the user database (272), and a score calculation step (S1000) for calculating the score of the tag stored on the service provider server (200) and storing it in the user database (272).

[0103] The above string selection step (S100) is a step in which the user selects a string for which he or she wishes to write a tag on the user terminal (100).

[0104] Here, the user can access a personal dictionary building service implemented as a SaaS (Software-as-a-Service)-based software through an Internet browser on a user terminal (100), log in to a service provider server (200), and select a string through a string selection unit (110) comprised of an editing program or voice recognition program implemented as a web extension program of an Internet browser installed on the user terminal (100) or a cloud application.

[0105] When logging in, you can load your own personal dictionary, and if you participate in a personal dictionary being built by someone else, you can also load the personal dictionaries of those other people who are participating.

[0106] Continuing, the string transmission step (S200) is a step of transmitting the string selected in the string selection step (S100) from the user terminal (100) to the service provider server (200) via wired or wireless communication through the string transmission unit (120).

[0107] And, the string receiving step (S300) is a step of receiving the string transmitted in the string transmitting step (S200) to the service provider server (200) via wired or wireless communication through the string receiving unit (210).

[0108] Continuing, the first character count determination step (S400) is a step in which the number of characters in the string received in the string reception step (S300) is counted by the first character count determination unit (221) on the service provider server (200) and compared with the first reference value.

[0109] At this time, if the number of characters in the string counted in the first character count determination step (S400) is greater than or equal to the first reference value (e.g., 100), the summary extraction step (S410) is performed to generate a summary that summarizes the string. The summary extraction step (S410) is performed through the summary extraction unit (223).

[0110] And, the second character count determination step (S500) is a step in which the number of characters in the string received in the string reception step (S300) or the number of characters in the summary generated in the summary extraction step (S410) is counted by the second character count determination unit (222) on the service provider server (200) and compared with the second reference value.

[0111] At this time, if the number of characters is determined to be less than the second reference value in the second character count determination step (S500), the word extraction step (S610) is performed, and if the number of characters is determined to be greater than the second reference value in the second character count determination step (S500), the keyword extraction step (S620) is performed.

[0112] Here, the word extraction step (S610) is a step of extracting all words included in a string or summary by a word extraction unit (231) on the service provider server (200).

[0113] In addition, the keyword extraction step (S620) is a step of extracting keywords included in a string or summary by a keyword extraction unit (232) on the service provider server (200).

[0114] Continuing, the tag recommendation step (S700) is a step in which a tag corresponding to a word extracted in the word extraction step (S610) or a subject word extracted in the keyword extraction step (S620) is extracted from the user database (272) or the provider database (271) by the tag recommendation unit (240) on the service provider server (200) and transmitted to the user terminal (100).

[0115] At this time, the tag recommendation unit (240) extracts top tags (e.g., top 4) with high scores based on the scores stored in the tag recommendation database (274) of the user database (272).

[0116] A tag's score is determined by variables such as the tag's cumulative number of selections, whether it was manually entered, whether it was recently selected, whether it was pre-created, and whether it was included in the supplier database.

[0117] Continuing, the tag selection input step (S800) is a step in which the user selects or manually inputs one tag from among multiple tags transmitted from the service provider server (200) through the tag selection input unit (130) on the user terminal (100).

[0118] At this time, an input window in which the user can manually input tags and a selection window in which the user can input selection / inappropriate information for the recommended tags are displayed on the user terminal (100).

[0119] And, the pre-storage step (S900) is a step in which the tag selected or manually entered in the tag selection input step (S800) is matched with the string by the pre-storage unit (250) on the service provider server (200) and stored in the user database (272).

[0120] Continuing, the score calculation step (S1000) is a step in which the score of the stored tag is calculated by the score calculation unit (260) on the service provider server (200) and stored in the user database (272).

[0121] The score can be calculated by assigning a default value to the cumulative number of tag selections among the above-mentioned score variables, and weighting the remaining score variables based on priority to the default values. Optionally, if a user selects an inappropriate tag among the recommended tags, a deduction can be applied during the score calculation.

[0122] As described above, the personal dictionary construction method according to the embodiment of the present invention recommends tags for personal dictionary construction by determining the top tags in order of scores based on the cumulative number of tag selections, whether the tag is manually entered, recent selection history, whether the tag is a dictionary creator, and whether the tag is included in a supplier database as variables, thereby allowing personalized characteristics for each user to be well reflected.

[0123] Hereinafter, embodiments of the present invention have been described in detail with reference to the attached drawings. However, the embodiments disclosed in this specification and the attached drawings are only used for the purpose of easily explaining the technical idea of ​​the present invention, and are not used to limit the scope of the present invention described in the claims. Accordingly, those skilled in the art will understand that various modifications and equivalent other embodiments are possible therefrom.

Claims

1. A system that provides a service to build a personal dictionary through personalized string-tag matching for each user. A user terminal including a string selection unit for selecting a string for a user to create a tag, a string transmission unit for transmitting the string selected from the string selection unit to a service provider server, and a tag selection input unit for allowing the user to select or manually input one tag from a plurality of tags transmitted from the service provider server; and A string receiving unit that receives a string from the string transmitting unit, a first character count determining unit that counts the number of characters in the string received by the string receiving unit and compares it with a first reference value, a summary extracting unit that generates a summary that summarizes the string if the first character count determining unit determines that the number of characters is greater than or equal to the first reference value, a second character count determining unit that counts the number of characters in the string received by the string receiving unit or the number of characters in the summary generated by the summary extracting unit and compares it with a second reference value, a word extracting unit that extracts all words included in the string or the summary if the second character count determining unit determines that the number of characters is less than the second reference value, a keyword extracting unit that extracts a keyword included in the string or the summary if the second character count determining unit determines that the number of characters is greater than or equal to the second reference value, a tag recommendation unit that extracts a tag corresponding to a word extracted by the word extracting unit or a keyword extracted by the keyword extracting unit from a user database or a supplier database and transmits the tag to a tag selection input unit of the user terminal, and a dictionary that matches a tag transmitted from the tag selection input unit with the string and stores the tag in the user database. A service provider server including a storage unit, a score calculation unit that calculates the score of the tag stored in the dictionary storage unit and stores it in a user database; The tag recommendation unit extracts top tags with high scores based on the scores stored in the user database and transmits them to the tag selection input unit of the user terminal. A personal dictionary building system characterized in that the score of a tag in the above score calculation unit is calculated using as variables the cumulative number of tag selections, whether manual input is made, recent selection history, whether the tag is a dictionary creator, and whether the tag is included in a supplier database.

2. In claim 1, A personal dictionary construction system characterized in that, when calculating a score in the above score calculation unit, the cumulative number of selections of tags among the score variables becomes a default value, and the remaining score variables act as weights assigned to the default value according to priority.

3. In claim 2, A personal dictionary building system characterized in that the above priorities are given in the order of whether manual input is made, recent selection history, whether the dictionary is created by a dictionary creator, and whether the supplier database is included.

4. In claim 1, The above user database is, A tag recommendation database storing words or keywords, tags matching the words or keywords, and scores of the tags, and A personal dictionary building system comprising a dictionary database storing tags and strings matching the tags.

5. A method for providing a service that builds a personal dictionary through personalized string-tag matching for each user. A string selection step in which a user selects a string for which he or she wishes to create a tag on the user terminal; A string transmission step for transmitting the string selected in the above string selection step from the user terminal to the service provider server; A string receiving step for receiving the string transmitted in the above string transmission step to the service provider server; A first character count determination step for counting the number of characters in a string received in the string receiving step on the service provider server and comparing it with a first reference value; A summary extraction step for generating a summary text summarizing a string when the number of characters is determined to be greater than or equal to the first reference value in the first character count determination step on the service provider server; A second character count determination step for counting the number of characters in the string received in the string receiving step or the number of characters in the summary generated in the summary extraction step on the service provider server and comparing the count with a second reference value; A word extraction step for extracting all words included in a string or summary when the number of characters is determined to be less than the second reference value in the second character count determination step on the service provider server; A keyword extraction step for extracting keywords included in a string or summary when the number of characters is determined to be greater than or equal to the second reference value in the second character count determination step on the service provider server; A tag recommendation step for extracting tags corresponding to words extracted in the word extraction step or keywords extracted in the keyword extraction step from a user database or a provider database on a service provider server and transmitting the tags to the user terminal; A tag selection input step in which a user selects or manually inputs one tag from among multiple tags transmitted from the service provider server on a user terminal; A pre-storage step of matching the tag selected or manually entered in the above tag selection input step with the string on the service provider server and storing it in the user database; and A score calculation step for calculating the score of the tag stored on the service provider server and storing it in the user database; The above tag recommendation step extracts top tags with high scores based on the scores stored in the user database and transmits them to the user terminal. A method for building a personal dictionary, characterized in that, in the above score calculation step, the score of a tag is calculated using as variables the cumulative number of selections of the tag, whether it is manually entered, recent selection history, whether it is a dictionary creator, and whether it includes a supplier database.

6. In claim 5, A personal dictionary construction method characterized in that, in the score calculation step, the cumulative number of selections of tags among the score variables becomes a default value, and the remaining score variables act as weights given to the default value according to priority.

7. In claim 6, A method for building a personal dictionary, characterized in that the above priorities are given in the order of whether manual input is made, recent selection history, whether the dictionary is created by a dictionary creator, and whether the supplier database is included.

Images