Electronic device for automatically generating short form on basis of data collected through artificial intelligence, and method of using same

Abstract

The present disclosure relates to an electronic device for automatically generating a short form on the basis of data collected through artificial intelligence, wherein a processor is configured to collect first data and second data from at least one markup language body through a content collection module, and provide at least one short form related to the markup language body through a short form provision module.

Description

Electronic device for automatically generating short forms based on data collected through artificial intelligence and method using the same

[0001] The present disclosure relates to an electronic device that automatically generates short forms based on data collected through artificial intelligence, and a method using the same. More specifically, the present disclosure relates to a device that automatically generates short forms related to a markup language text using data extracted from the markup language text source through an artificial intelligence learning model, and a method using the same.

[0002] With the advancement of video data, short-form video formats with short playback times are attracting attention. Despite their short duration, short-form videos are powerful enough to capture users' attention if they're relevant to their interests. This may explain the recent demand for short-form videos.

[0003] Users with mobile devices can use them to access online shopping websites or news websites. In this case, compiling information from these websites and generating short-form content in real time can help users reach out more effectively, increasing sales and click-through rates. This creates a need to extract data contained in web pages accessed by users in real time and generate short-form content to achieve the intended purpose of the web page.

[0004] An embodiment of the present disclosure is proposed to solve the above-described problem, and can automatically provide content that is expected to be of high interest to users by extracting attribute information through various data from a markup language body source and generating it in short form.

[0005] The problems to be solved by the present disclosure are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below.

[0006] An electronic device for automatically generating a short form based on data collected through artificial intelligence according to one aspect of the present disclosure includes a content collection module for collecting data related to automatic generation of the short form; and a processor for controlling the operation of a short form providing module for providing data related to automatic generation of the short form as the short form, wherein the processor is configured to collect first data and second data from at least one markup language body through the content collection module, and to provide at least one short form related to the markup language body through the short form providing module.

[0007] In addition, the processor may be configured to, through the content collection module, confirm rank information corresponding to each of the first data and the second data and event information corresponding to the markup language body, and, through the short form provision module, reflect rank information corresponding to the first data and event information corresponding to the first markup language body or the second markup language body from which the first data is collected, thereby generating a first short form based on the first data, and, through the short form provision module, providing the first short form.

[0008] In addition, the processor may be configured to generate a second short form based on the second data by reflecting rank information corresponding to the second data and event information corresponding to the first markup language body or the second markup language body from which the second data is collected through the short form providing module, and to provide the second short form through the short form providing module.

[0009] In addition, the processor may be characterized in that, when collecting third data from a markup language body other than the first markup language body or the second markup language body through the content collection module, the processor is set to provide a third short form corresponding to the third data collected from the other markup language body based on information accumulated in a category database and a dictionary database in the process of generating the first short form and the second short form through the first data and the second data through the short form providing module.

[0010] In addition, the processor may be configured to identify keywords based on texts constituting the first data and the second data, extract a first keyword for the first data and the second data using a preset first regular expression, extract a second keyword after extraction of the first keyword using a preset second regular expression, extract a third keyword using a preset third regular expression, and provide keywords having an extraction frequency greater than or equal to a preset frequency among the extracted third keywords as separate keyword data, and store the separate keyword data in a dictionary database.

[0011] In addition, the processor may be configured to identify keywords based on texts constituting the first data and the second data, provide keywords with an extraction frequency higher than a preset frequency among the keywords as separate keyword data, and, when the separate keyword data is stored in a dictionary database for storing the keywords, determine a regular expression for extracting a separate keyword in the first data and the second data as a fourth regular expression.

[0012] In addition, the processor may include a data classification module for classifying data related to automatic generation of the short form, and may be characterized by mapping categories and sounds corresponding to the first data and the second data through the data classification module.

[0013] In addition, the processor may be configured to check the number of identical texts between the texts constituting the first data and the texts constituting the second data through the data classification module, and if the number of identical texts confirmed is greater than or equal to a preset number, classify the first data and the second data as similar content through the data classification module, and if the number of identical texts confirmed is less than a preset number, classify the first data and the second data as dissimilar content through the data classification module.

[0014] In addition, the processor may be configured to check the first category and the second category through the category database, and if the first data and the second data are similar contents, map the first data and the second data to the first category through the data classification module, and if the first data and the second data are dissimilar contents, map the first data to the first category while mapping the second data to the second category through the data classification module.

[0015] In addition, the processor may be configured to map a first sound to the first data according to a category to which the first data is mapped through the data classification module, and to map a second sound to the second data according to a category to which the second data is mapped through the data classification module.

[0016] A method for automatically generating a short form based on data collected through artificial intelligence performed by an electronic device according to another aspect of the present disclosure may include the steps of collecting first data and second data from at least one markup language body through a content collection module of the electronic device; and providing at least one short form related to the markup language body through a short form providing module of the electronic device.

[0017] In addition, the method may further include a step of confirming rank information corresponding to each of the first data and the second data and event information corresponding to the markup language body through the content collection module; and a step of generating a first short form based on the first data by reflecting rank information corresponding to the first data and event information corresponding to the first markup language body or the second markup language body from which the first data is collected through the short form providing module; and a step of providing the first short form through the short form providing module may further be included.

[0018] In addition, the method may further include a step of generating a second short form based on the second data by reflecting rank information corresponding to the second data and event information corresponding to the first markup language body or the second markup language body from which the second data is collected through the short form providing module; and may further include a step of providing the second short form through the short form providing module.

[0019] In addition, when collecting third data from a markup language body other than the first markup language body or the second markup language body through the content collection module, the method may further include providing a third short form corresponding to the third data collected from the other markup language body based on information accumulated in a category database and a dictionary database in the process of generating the first short form and the second short form through the first data and the second data through the short form providing module.

[0020] In addition, the method may be characterized in that, through a processor of the electronic device, a keyword is identified based on texts constituting the first data and the second data, a first keyword for the first data and the second data is extracted using a first regular expression set in advance through the processor, a second keyword is extracted using a second regular expression set in advance through the processor after extraction of the first keyword, a third keyword is extracted using a third regular expression set in advance through the processor, and, through the processor, a keyword whose extraction frequency is greater than or equal to a preset frequency among the extracted third keywords is provided as separate keyword data, and the separate keyword data is stored in a dictionary database through the processor.

[0021] According to the aforementioned problem solving means of the present disclosure, a short-form automatic generation electronic device can automatically generate a short-form video using data related to the main body of a markup language from a source of a markup language body accessed by a user through a terminal through a search engine such as a crawling engine or a machine learning processor, thereby providing immediate video information on content of interest to the user.

[0022] Furthermore, according to various embodiments of the present disclosure, short-form videos are automatically generated, eliminating the need to manually create catalogs containing content. According to various embodiments of the present disclosure, an electronic device for automatically generating short-form videos utilizes artificial intelligence to extract a large amount of content related to a small number of web pages visited by a user, and automatically generates short-form videos through similar content analysis.

[0023] The effects of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

[0024] FIG. 1 is a schematic block diagram of a system for automatically generating short forms based on data collected through artificial intelligence according to various embodiments of the present disclosure.

[0025] FIG. 2 is a schematic block diagram of components of a short-form automatic generation electronic device according to various embodiments of the present disclosure.

[0026] FIG. 3 is a schematic flowchart of a method for automatically generating a short form according to various embodiments of the present disclosure.

[0027] FIG. 4 is a flowchart illustrating a process for generating a short-form automatic generation process model according to various embodiments of the present disclosure.

[0028] FIG. 5 is a flowchart of a short form generation process reflecting additional information of a markup language body according to various embodiments of the present disclosure.

[0029] FIG. 6 is a detailed flowchart regarding short form generation through a short form automatic generation process model according to various embodiments of the present disclosure.

[0030] Throughout this disclosure, the same reference numerals denote the same components. This disclosure does not describe all elements of the embodiments, and any content that is common in the technical field to which this disclosure pertains or that overlaps between embodiments is omitted. The terms "part, module, element, block" used in the specification may be implemented in software or hardware, and depending on the embodiments, multiple "parts, modules, elements, blocks" may be implemented as a single component, or a single "part, module, element, block" may include multiple components.

[0031] Throughout the specification, when a part is said to be "connected" to another part, this includes not only direct connection but also indirect connection, and indirect connection includes connection via a wireless communication network.

[0032] Additionally, when a part is said to "include" a component, this does not mean that it excludes other components, but rather that it may include other components, unless otherwise specifically stated.

[0033] Throughout the specification, when we say that an element is "on" another element, this includes not only cases where the element is in contact with the other element, but also cases where another element exists between the two elements.

[0034] The terms first, second, etc. are used to distinguish one component from another, and the components are not limited by the aforementioned terms.

[0035] Singular expressions include plural expressions unless the context clearly indicates otherwise.

[0036] The identification codes for each step are used for convenience of explanation and do not describe the order of each step. Each step may be performed in a different order than specified unless the context clearly indicates a specific order.

[0037] The operating principle and embodiments of the present disclosure are described below with reference to the attached drawings.

[0038] As used herein, the term "device according to the present disclosure" encompasses a variety of devices capable of performing computational processing and providing results to a user. For example, the device according to the present disclosure may include a computer, a server device, and a portable terminal, or may be any one of them.

[0039] Here, the computer may include, for example, a notebook, desktop, laptop, tablet PC, slate PC, etc. equipped with a web browser.

[0040] The above server device is a server that processes information by communicating with an external device, and may include an application server, a computing server, a database server, a file server, a game server, a mail server, a proxy server, and a web server.

[0041] The above portable terminal may include, for example, a wireless communication device that ensures portability and mobility, and may include all kinds of handheld-based wireless communication devices such as a PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), WiBro (Wireless Broadband Internet) terminal, a smart phone, and a wearable device such as a watch, a ring, a bracelet, an anklet, a necklace, glasses, contact lenses, or a head-mounted device (HMD).

[0042] FIG. 1 is a schematic block diagram of a system for automatically generating short forms based on data collected through artificial intelligence according to various embodiments of the present disclosure.

[0043] Referring to Figure 1, a system for automatically generating short forms based on data collected through artificial intelligence (hereinafter referred to as the "short form automatic generation system (10)") includes an electronic device (100) and a terminal (200). Each node can exchange data with other nodes. Each node can be connected via a network.

[0044] An electronic device (100) according to various embodiments of the present disclosure is a device that automatically generates short-form content. Short-form content refers to content created in a short video format. The electronic device (100) can automatically generate and provide short-form content to a user based on data collected from specific sites or markup texts that the user surfs or crawls. The electronic device (100) can transmit or receive data to or from another device (e.g., a terminal (200)) via wired and / or wireless connections.

[0045] A terminal (200) according to various embodiments of the present disclosure may be a device that receives a short form generated from an electronic device (100). In addition, the terminal (200) may provide the electronic device (100) with learning data necessary for the electronic device (100) to create a short form generation model using artificial intelligence through learning data. The terminal (200) may include a device carried by a user, such as a mobile phone, a laptop computer, a personal computer, or a tablet. In other words, the terminal (200) may be any device carried by a user, connected to the electronic device (100) via a network, and capable of exchanging data between the two.

[0046] FIG. 2 is a schematic block diagram of components of a short-form automatic generation electronic device according to various embodiments of the present disclosure.

[0047] Referring to FIG. 2, the electronic device (100) may include, but is not limited to, a processor (110), a category database (120), and a dictionary database (130) as internal components. Each node may exchange data with other nodes. Each node may be directly electrically connected or may be wired and / or wirelessly connected via a network. The electronic device (100) of the present disclosure may perform the functions of the processor (110) through a separate server instead of the processor (110).

[0048] An electronic device (100) according to various embodiments of the present disclosure is a device that verifies data collected by a user through a terminal (200) or acquired through input performed through the terminal (200). For example, the electronic device (100) can verify Internet cookie data, Internet log data, web page data, etc. that a user searches for on an Internet web page by accessing the Internet web page through the terminal (200). That is, the electronic device (100) can verify in real time the contents that the user encounters using the terminal (200), and can process data related to the contents to generate short forms that the user may be interested in.

[0049] Referring to FIG. 2, the processor (110) includes, but is not limited to, a content collection module (111), a data classification module (112), and a short-form provision module (113).

[0050] The content collection module (111) according to the embodiment can collect data from at least one markup language body. For example, the markup language body can refer to an HTML body. The content collection module (111) can collect all data contained in the HTML body by converting it into text, and can also collect images, videos, etc.

[0051] The data classification module (112) according to the embodiment can map categories and sounds corresponding to data in the markup language body. For example, the data classification module (112) can determine the mutual similarity between data and classify categories based on the similarity. The data classification module (112) can map sounds appropriate for each category to each data in response to the categorization of data. Accordingly, the processor (110) can generate a short form with a set time (e.g., 1 minute) according to the number of data, categories, etc.

[0052] The short-form provision module (113) according to the embodiment can provide at least one short form related to the markup language body to the terminal (200). For example, the short-form provision module (113) can generate a short form corresponding to the data of the markup language body based on a learned model based on a short-form generation model for operating the data classification module (112) and provide the short form to the terminal (200). That is, the short-form provision module (113) can generate and provide content that may be of interest to a user possessing the terminal (200) in the form of a short form. In particular, the short-form provision module (113) can generate in real time a short form related to the content provided on a web page that the user is viewing in real time through the terminal (200) and provide the short form to at least a portion of the web page that the user is viewing in real time. As another example, the short-form provision module (113) can generate a short-form related to the content provided on a web page that the user is viewing in real time through the terminal (200) and provide it in a pop-up format on at least a portion of the web page that the user is viewing in real time.

[0053] The processor (110) may include individual modules (111, 112, 113). Here, the individual modules (111, 112, 113) may refer to functional blocks according to the functions that the processor (110) operates. Specifically, the individual modules (111, 112, 113) may correspond to functional blocks that are given names according to the functions of the processor (110).

[0054] The processor (110) according to an embodiment of the present disclosure may be implemented as a memory (not shown) that stores data regarding an algorithm for controlling the operation of components within an electronic device (100) or a program that reproduces the algorithm, and at least one functional block that performs the aforementioned operation using the data stored in the memory. In this case, the processor (110) and the memory may be implemented as separate chips. Alternatively, the processor (110) and the memory may be implemented as a single chip.

[0055] The processor (110) can control one or more of the components discussed above in combination to implement various embodiments according to the present disclosure described in FIGS. 3 to 6 below in an electronic device (100).

[0056] A communication unit (not shown) according to an embodiment may include one or more components that enable communication with an external device (e.g., a terminal (200) of FIG. 1), and may include, for example, at least one of a broadcast reception module, a wired communication module, a wireless communication module, a short-range communication module, and a location information module.

[0057] The wired communication module may include various wired communication modules such as a Local Area Network (LAN) module, a Wide Area Network (WAN) module, or a Value Added Network (VAN) module, as well as various cable communication modules such as a Universal Serial Bus (USB), a High Definition Multimedia Interface (HDMI), a Digital Visual Interface (DVI), RS-232 (recommended standard 232), power line communication, or plain old telephone service (POTS).

[0058] The wireless communication module may include a wireless communication module that supports various wireless communication methods such as GSM (global System for Mobile Communication), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), UMTS (universal mobile telecommunications system), TDMA (Time Division Multiple Access), LTE (Long Term Evolution), 4G, 5G, and 6G, in addition to a WiFi module and a Wireless Broadband module.

[0059] The short-range communication module is for short-range communication, and can support short-range communication using at least one of Bluetooth™, RFID (Radio Frequency Identification), Infrared Data Association (IrDA), UWB (Ultra Wideband), ZigBee, NFC (Near Field Communication), Wi-Fi (Wireless-Fidelity), Wi-Fi Direct, and Wireless USB (Wireless Universal Serial Bus) technologies.

[0060] The memory according to the embodiment can store data supporting various functions of the electronic device (100), a program for the operation of the processor (110), can store input / output data (e.g., images, videos, etc.), and can store a plurality of application programs (or applications) running on the electronic device (100), data for the operation of the electronic device (100), and commands. At least some of these application programs can be downloaded from an external server via wireless communication.

[0061] Such memory may include at least one type of storage medium among flash memory type, hard disk type, SSD (Solid State Disk type), SDD (Silicon Disk Drive type), multimedia card micro type, card type memory (e.g., SD or XD memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, and optical disk. In addition, the memory may be a database that is separate from the electronic device (100) but connected by wire or wirelessly.

[0062] At least one component may be added or deleted to correspond to the performance of the components illustrated in FIG. 2. Furthermore, it will be readily apparent to those skilled in the art that the relative positions of the components may be altered to correspond to the performance or structure of the device.

[0063] Meanwhile, each component illustrated in FIG. 2 refers to software and / or hardware components such as a Field Programmable Gate Array (FPGA) and an Application Specific Integrated Circuit (ASIC).

[0064] FIG. 3 is a schematic flowchart of a method for automatically generating a short form according to various embodiments of the present disclosure.

[0065] In step S310, a processor (e.g., processor (110) of FIG. 2) may collect data from a markup language text. For example, the processor may collect data within a web page that a user is surfing using a terminal (e.g., terminal (200) of FIG. 1) via a content collection module (e.g., content collection module (111) of FIG. 2). Here, the data may include first data and second data, and the first data and second data are examples of various data that can be extracted from a markup language text source.

[0066] According to an embodiment, a processor can extract the markup language body source of original pages of various web pages, such as websites for purchasing products and news sites providing news. Accordingly, the processor can extract the markup language body source of the original pages and store it in memory. For example, the processor can extract the markup language body source from a web page where a user is shopping and check various data such as product type, product image, product review, product price, and product details. In another example, the processor can extract the markup language body source from a web page where a user is viewing news and check various data such as images used in the news, news content, news comments, and news creation time. In this way, the processor can collect various data from the real-time markup language body source that the user is viewing through a terminal, making it easy to identify content of interest to the user in real time.

[0067] In step S320, the processor may map categories and sounds corresponding to the data. The processor may map categories and sounds corresponding to the first data and the second data through a data classification module (e.g., the data classification module (112) of FIG. 2).

[0068] A processor according to an embodiment may identify the content contained in the first data and the second data. For example, the processor may identify that the first data is about sports and map the first data to a sports category. Subsequently, the processor may identify that the first data is about sports and map the first data to a sound matching sports. For another example, the processor may identify that the second data is about popular music and map the second data to a popular music category. Subsequently, the processor may identify that the second data is about popular music and map the second data to a sound matching popular music. In other words, the processor may identify the content of data collected from a markup language text source, classify categories of individual data, and map sounds with appropriate moods based on the categories. Here, the category information and sound information may be pre-stored in memory, and may include category information and sound information that are cumulatively updated and stored while the processor generates short forms using a short form generation model.

[0069] In step S330, the processor may provide a short form associated with the markup language body. For example, the processor may provide at least one short form associated with at least one markup language body to the user's terminal via a short form providing module (e.g., the short form providing module (113) of FIG. 2 ).

[0070] A processor according to an embodiment may provide a user with a short form corresponding to content of real-time interest in real time. For example, the processor may generate a short form related to content provided on a web page the user is viewing in real time through the terminal and provide it on at least a portion of the terminal's display.

[0071] FIG. 4 is a flowchart illustrating a process for generating a short-form automatic generation process model according to various embodiments of the present disclosure. A data classification module (e.g., the data classification module (111) of FIG. 2 ) can compare texts constituting first and second data collected through a content collection module (e.g., the content collection module (111) of FIG. 2 ) to determine the number of identical texts contained in each data.

[0072] Referring to FIG. 4, in step S410, the data classification module can determine whether the number of identical texts among the texts constituting the first data and the second data is greater than or equal to a preset number (e.g., 3). Here, the preset number may be stored in memory. If the number of identical texts is greater than or equal to the preset number, the data classification module can branch to step S420 and proceed with the process. If the number of identical texts is less than the preset number, the data classification module can branch to step S440 and proceed with the process.

[0073] In step S420, the data classification module can classify the first and second data into similar content. The data classification module can determine whether the data are similar based on attribute information of the collected data. For example, the data classification module can collect title text from data within a news webpage and determine whether the data are similar. The news webpage may list various news titles. The data classification module can compare the title texts of various news articles and determine that the titles belong to the same category if the number of identical texts exceeds a preset number. As another example, the data classification module can collect product brand and product name texts from data within a shopping mall webpage and determine whether the data are similar. The shopping mall webpage may list various products. The data classification module can compare the brand and product name texts of various products and determine that the products belong to the same category if the number of identical texts exceeds a preset number.

[0074] In step S430, the data classification module may map the first data and the second data to a first category. The data classification module may classify the first data and the second data into similar content and map the first data and the second data to the same category.

[0075] In step S440, the data classification module may classify the first data and the second data as dissimilar content. The processor may identify the first category and the second category from a category database (e.g., the category database (120) of FIG. 2). Here, the first category and the second category may be different categories, while the individual categories may be of the same class. Accordingly, the first category and the second category may each have subcategories.

[0076] According to an embodiment, the data classification module may map the first data to a first category and the second data to a second category if the first and second data correspond to dissimilar content. That is, the data classification module may determine that the first and second data correspond to dissimilar content and map each data to a different category. For example, the data classification module may classify the first data into the sports news category and the second data into the economic news category based on news text on a news webpage.

[0077] A data classification module according to an embodiment may map first data and second data to a first sound and a second sound according to their respective mapped categories. This may be a process of mapping sounds that match the content that the data visualizes and expresses. When the processor maps the first data to the first category, the processor may map the first sound to the first data. In this case, the first sound may be a sound that matches the first category. As another example, when the processor maps the second data to the second category, the processor may map the second sound to the second data. In this case, the second sound may be a sound that matches the second category. In other words, when generating a short form, the processor may match sounds according to genre or mood, such as a product or news, to generate the short form.

[0078] FIG. 5 is a flowchart of a short form generation process reflecting additional information of a markup language body according to various embodiments of the present disclosure.

[0079] In step S510, a processor (e.g., processor (110) of FIG. 2) can check rank information corresponding to each data and event information corresponding to the markup language body.

[0080] According to an embodiment, a processor may verify rank information corresponding to each of the first data and the second data and event information corresponding to at least one markup language body through a content collection module (e.g., the content collection module (111) of FIG. 2). For example, when generating a short form, the processor may additionally collect rank information of a web page where a product is being sold or a news web page, event information on the corresponding web page, etc. Through this, the processor verifies rank information corresponding to the data and event information in progress in the markup language body source.

[0081] A processor according to an embodiment may learn by classifying first data and second data into respective categories. For example, the first data may be news-related data, mapped to the first category, and may not need to be frequently updated and stored. For another example, the second data may be product-related data, mapped to the second category, and may need to be frequently updated and stored. This may vary depending on whether each piece of data is non-volatile or volatile. In other words, the categories of the present disclosure may be classified in various ways depending on the nature or type of data. Accordingly, the processor may generate a short-form generation model through a process of classifying each piece of data, and develop the short-form generation model itself by learning based on input based on the short-form generation model. The processor may cumulatively apply and learn data received from the user's terminal through the short-form generation model, thereby updating the short-form generation model itself, and may then apply the updated short-form generation model to new data.

[0082] In step S520, the processor can generate a first short form and a second short form. The processor can generate a first short form based on the first data by reflecting rank information corresponding to the first data and event information corresponding to the first markup language text or the second markup language text from which the first data is collected through a short form providing module (e.g., the short form providing module (113) of FIG. 2). The processor can generate a second short form based on the second data by reflecting rank information corresponding to the second data and event information corresponding to the first markup language text or the second markup language text from which the second data is collected through a short form providing module.

[0083] FIG. 6 is a detailed flowchart regarding short form generation through a short form automatic generation process model according to various embodiments of the present disclosure.

[0084] Referring to FIG. 6, in step S610, a processor (e.g., processor (110) of FIG. 2) can identify keywords in text constituting data. The processor can identify keywords based on text constituting first data and second data.

[0085] According to an embodiment, the processor may extract a first keyword for the first data and the second data using a preset first regular expression. After extracting the first keyword, the processor may extract a second keyword using a preset second regular expression.

[0086] In step S620, the processor can extract the nth keyword using the nth regular expression. For example, the processor can extract the nth keyword for data using a preset nth regular expression. For example, the preset regular expression may be an expression for extracting data from the markup language body source of a domain or site accessed by the user through the user's terminal (e.g., terminal (200) of FIG. 1) or based on the domain or site visited.

[0087] In an embodiment, the first regular expression may be an expression that follows the convention of interpreting keyword information from A to D in the markup language body as "a." The processor may use the first regular expression to extract essential information for generating a short form. Here, the essential information may be attribute information required to generate the short form. For example, in the case of a product, the attribute information may be the product category, product name, product image, product price, etc. For another example, in the case of a web novel, the attribute information may be the web novel title, the web novel image, etc. For another example, in the case of a news article, the attribute information may be the news article title, the news article image, the news article comment, etc.

[0088] According to an embodiment, the second regular expression may be an expression for extracting more general data than the data extracted by the first regular expression. For example, extracting the first keyword from the first data through the first regular expression may extract information contained in a unique keyword in the first markup language body. For example, the unique keyword may be an item code, an item number, a product code, etc. For another example, extracting the second keyword from the first data through the second regular expression may extract a keyword that is more commonly used than the data extracted by the first regular expression in the first markup language body. Thereafter, extracting the third keyword through the third regular expression may extract a keyword that is more general than the second keyword extraction through the second regular expression. That is, the first keyword, the second keyword, the third keyword, and the nth keyword may correspond to general keywords as n increases.

[0089] In an embodiment, if n is 3 or greater among the nth regular expressions for extracting the nth keyword, the expression may be classified into the else area. For example, the else area may correspond to an area for extracting keywords that users may commonly encounter.

[0090] In step S630, the processor may determine whether the extraction frequency of a keyword is greater than or equal to a preset extraction frequency. After extracting the first and second keywords using the first and second regular expressions, the processor may determine which of the third keywords extracted using the third regular expression have an extraction frequency greater than or equal to the preset frequency. The preset frequency (e.g., three times) may be stored in memory. The third keywords extracted at a frequency greater than or equal to the preset frequency may be provided to the user.

[0091] In step S640, the processor may provide separate keyword data. The processor may provide keywords among the third keywords whose extraction frequency is greater than a preset frequency as separate keyword data. This may be a process in which the third regular expression or higher is used as an else area to provide content that frequently appears in the log to a developer (e.g., an administrator), and when the developer stores or automatically updates and stores the content in a dictionary database (e.g., the dictionary database (130) of FIG. 2), the processor recognizes the content as a keyword and extracts attribute information from the data. For example, when the developer stores log information in a dictionary database, the processor can extract data recognized as a keyword through the log information. For another example, when the processor automatically updates and stores log information in a dictionary database, the processor can extract data recognized as a keyword through the log information. In this way, all keyword data can be stored in a dictionary database. The processor can build a more accurate short-form generation model by repeatedly creating a regular expression based on the results obtained through the keyword extraction process and extracting keywords again using the created regular expression.

[0092] In step S650, the processor may store separate keyword data in the dictionary database. The processor may store keyword data of the third keyword or more (e.g., the third keyword, the fourth keyword, etc.) in the dictionary database. The processor may separately check whether attribute information corresponding to the extracted data corresponds to correct information. For example, in relation to product price information, the processor may match the price information extracted from the markup language body source with information indicating pre-stored prices to confirm whether the extracted price information is correct. Through this, the processor can extract and map attribute information based on the initial matching of the product price information without a repetitive matching process.

[0093] In step S660, the processor may determine the fourth regular expression. If separate keyword data is stored in the dictionary database, the processor may determine the regular expression for extracting the separate keyword as the fourth regular expression. Here, the fourth regular expression is an example of a regular expression following the third regular expression.

[0094] According to an embodiment, the processor may utilize the "else" field of a regular expression to verify attribute information of data extracted from the markup language body. The processor may store information extracted at a preset frequency or higher among the information stored in the log through the "else" field in a dictionary database, thereby utilizing it as keywords for future attribute information verification.

[0095] In one embodiment, the processor may recommend to the developer, during the process of verifying data attribute information, information stored in the dictionary database that is repeatedly stored or verified. This may correspond to a process in which the processor repeatedly learns and initially does not recommend information, but as it visits various sites and learns more, the frequency of recommendations increases.

[0096] In one embodiment, the processor can determine the appropriateness of matching between the sound to which data is mapped and the short form generated based on the data. The processor can automatically or manually generate sounds based on categories. For example, the processor can collect sound data based on category keyword attributes. Here, the sound data may be sound data that does not infringe copyright. For another example, the processor can directly generate sound data based on category keyword attributes. For another example, the processor can load sound data stored by the developer.

[0097] According to an embodiment, the processor can match video data and sound data for generating short forms. For example, the processor can set the default weight to 1 / 10 and set the weight according to the popularity of the video data (e.g., number of likes, comments, etc.) to 4 / 10 to 8 / 10. For another example, the processor can assign a weight according to the viewing time of the video data to 2 / 10 and assign a weight according to the developer's (e.g., administrator's) choice within 1 / 10 to adjust the limit of automatic video data matching. Accordingly, the processor can randomly match the sound data by dividing the sound data into n sections (e.g., 10 sections) based on the total weight assigned to the short form to be generated. For example, if 55 short-form automatic generation requests are received, the processor can apply sound data by randomly selecting sound data within the 10th section 10 times, by randomly selecting sound data within the 9th section 9 times, and by randomly selecting sound data within the 1st section 1 time. In this way, the processor can update the weights once a day while maintaining the number of sound data of each section at the same number according to the assigned weights. In addition, the processor can sort and distinguish the weights by priority, such as the most recently used order or the most recently generated order, when the weights match.

[0098] In an embodiment, when a processor collects third data from a markup language body other than a first markup language body or a second markup language body, the processor may provide a third short form corresponding to the third data collected from the other markup language body based on information accumulated in the category database and the dictionary database in the process of generating the first short form and the second short form using the first data and the second data. That is, the processor may generate the third short form by applying the same and / or similar method of generating the first short form and the second short form. This may be that the processor repeatedly learns a short form generation model through machine learning and generates a short form identically and / or similarly on a web page of a new site based on a process of generating short forms on web pages of some sites.

[0099] Meanwhile, the disclosed embodiments may be implemented in the form of a recording medium storing computer-executable instructions. The instructions may be stored in the form of program code, and when executed by a processor, may generate program modules to perform the operations of the disclosed embodiments. The recording medium may be implemented as a computer-readable recording medium.

[0100] Computer-readable storage media include all types of storage media that store instructions that can be deciphered by a computer. Examples include read-only memory (ROM), random access memory (RAM), magnetic tape, magnetic disks, flash memory, and optical data storage devices.

[0101] The disclosed embodiments have been described with reference to the attached drawings as described above. Those skilled in the art will understand that the present disclosure can be implemented in forms other than the disclosed embodiments without altering the technical spirit or essential features of the present disclosure. The disclosed embodiments are illustrative and should not be construed as limiting.

Claims

1. In an electronic device that automatically generates short forms based on data collected through artificial intelligence, A content collection module for collecting data related to the automatic generation of the above short form; and A processor that controls the operation of a short form providing module for providing data related to the automatic generation of the short form to the short form, The above processor, Through the above content collection module, first data and second data are collected from at least one markup language body, An electronic device for automatically generating short forms, characterized in that it is configured to provide at least one short form related to the markup language body through the short form providing module.

2. In paragraph 1, The above processor, Through the above content collection module, rank information corresponding to each of the first data and the second data and event information corresponding to the markup language body are confirmed, Through the short form providing module, a first short form based on the first data is generated by reflecting rank information corresponding to the first data and event information corresponding to the first markup language body or the second markup language body from which the first data is collected. An electronic device for automatically generating short forms, characterized in that it is set to provide the first short form through the short form providing module.

3. In paragraph 2, The above processor, Through the short form providing module, a second short form based on the second data is generated by reflecting rank information corresponding to the second data and event information corresponding to the first markup language body or the second markup language body from which the second data is collected. An electronic device for automatically generating a short form, characterized in that it is set to provide the second short form through the short form providing module.

4. In paragraph 3, The above processor, When collecting third data from a markup language body other than the first markup language body or the second markup language body through the above content collection module, An electronic device for automatically generating short forms, characterized in that it is set to provide a third short form corresponding to the third data collected from the other markup language text based on information accumulated in a category database and a dictionary database in the process of generating the first short form and the second short form through the first data and the second data through the short form providing module.

5. In paragraph 1, The above processor, Identify keywords based on the texts constituting the first data and the second data, Extracting the first keyword for the first data and the second data using the first regular expression set in advance, After extracting the first keyword, the second keyword is extracted using the second regular expression set in advance. Extract the third keyword using the third regular expression that has been set, Among the third keywords extracted above, keywords with an extraction frequency higher than a preset frequency are provided as separate keyword data. A short-form automatic generation electronic device characterized in that it is set to store the above separate keyword data in a dictionary database.

6. In paragraph 1, The above processor, Identify keywords based on the texts constituting the first data and the second data, Among the above keywords, keywords with an extraction frequency higher than a preset frequency are provided as separate keyword data. A short-form automatic generation electronic device characterized in that, when the separate keyword data is stored in a dictionary database for storing the keyword, a regular expression for extracting a separate keyword in the first data and the second data is determined as a fourth regular expression.

7. In paragraph 1, The above processor, Includes a data classification module for classifying data related to the automatic generation of the above short form, A short-form automatic generation electronic device characterized in that the categories and sounds corresponding to the first data and the second data are mapped through the data classification module.

8. In paragraph 7, The above processor, Through the above data classification module, the number of identical texts in the texts constituting the first data and the texts constituting the second data is checked, If the number of identical texts confirmed above is greater than or equal to a preset number, the data classification module classifies the first data and the second data as similar content, A short-form automatic generation electronic device characterized in that, if the number of identical texts confirmed above is less than a preset number, the data classification module is set to classify the first data and the second data as dissimilar content.

9. In paragraph 8, The above processor, Through the category database, check the first and second categories, If the first data and the second data are similar contents, the first data and the second data are mapped to the first category through the data classification module, A short-form automatic generation electronic device characterized in that, when the first data and the second data are dissimilar contents, the data classification module is set to map the first data to the first category and map the second data to the second category.

10. In paragraph 9, The above processor, Through the above data classification module, the first sound is mapped to the first data according to the category to which the first data is mapped, A short-form automatic generation electronic device characterized in that the second sound is set to be mapped to the second data according to the category to which the second data is mapped through the data classification module.

11. A method for automatically generating a short form based on data collected through artificial intelligence performed by an electronic device, A step of collecting first data and second data from at least one markup language body through a content collection module of the electronic device; and A method comprising the step of providing at least one short form related to the markup language body through a short form providing module of the electronic device.

12. In paragraph 11, Further comprising a step of checking rank information corresponding to each of the first data and the second data and event information corresponding to the markup language body through the content collection module; A step of generating a first short form based on the first data by reflecting rank information corresponding to the first data and event information corresponding to the first markup language body or the second markup language body from which the first data is collected through the short form providing module; further comprising; A method further comprising a step of providing the first short form through the short form providing module.

13. In paragraph 12, A step of generating a second short form based on the second data by reflecting rank information corresponding to the second data and event information corresponding to the first markup language body or the second markup language body from which the second data is collected through the short form providing module; further comprising; A method further comprising a step of providing the second short form through the short form providing module.

14. In paragraph 13, When collecting third data from a markup language body other than the first markup language body or the second markup language body through the above content collection module, A method further comprising a step of providing a third short form corresponding to the third data collected from the other markup language text based on information accumulated in a category database and a dictionary database during the process of generating the first short form and the second short form through the first data and the second data through the short form providing module.

15. In paragraph 11, Through the processor of the electronic device, a keyword is identified based on the text constituting the first data and the second data, Through the above processor, a first keyword for the first data and the second data is extracted using a preset first regular expression, Through the above processor, after extracting the first keyword, the second keyword is extracted using the preset second regular expression, Through the above processor, the third keyword is extracted using the preset third regular expression, Through the above processor, keywords among the extracted third keywords whose extraction frequency is higher than a preset frequency are provided as separate keyword data, A method characterized in that the separate keyword data is stored in a dictionary database through the above processor.

Images