KR20230068092A - A method for extracting food menu nouns using parts of speech such as verbs and adjectives, a method for updating a food dictionary using the same, and a system for the same - Google Patents

Abstract

The embodiment searches a web page including the received food name search word, which is executed by a processor according to a control command provided by a food menu noun extraction program code stored in a memory, and searches for a sentence including the food name search word in the searched web page. Collecting; extracting verbs from sentences including collected food name search words; searching for a web page using the extracted verb as a search term and collecting sentences including the verb in the searched web page; and extracting nouns from sentences including the collected verbs; a food menu noun extraction method using parts of speech such as verbs and adjectives may be provided.

Description

A method for extracting food menu nouns using parts of speech such as verbs and adjectives, a method for updating a food dictionary using parts of speech such as verbs and adjectives, and a system therefor food dictionary using the same, and a system for the same}

The present invention relates to a method of extracting food menu nouns using parts of speech such as verbs and adjectives, a method of updating a food dictionary using the same, and a system therefor.

As unstructured data such as e-mail and social media accounts for a large proportion, interest in natural language processing is increasing. As the word of mouth effect of product or service purchase reviews expands, companies are focusing on analyzing their reputation. In addition, with the development of artificial intelligence and the popularization of AI speakers, a change in communication paradigm occurred, changing from the existing keyboard-centered text method to conversational, increasing interest in natural language. Natural language processing is the ability of a computer to analyze a person's natural language and solve a given problem (Lee Jong-hwa et al., 2019). However, it is difficult to analyze the ambiguity of Hangeul, such as homonyms and polysemy. The limitations of many researchers are suggested by the uniqueness of Hangeul, such as the difference between grammatical spoken language and written language, spacing problems such as 'Going into your father's bag', and analysis of omitted sentences such as homonyms, subjects, predicates, and objects (Kim Mi-kyung, Choi So-young, 2020). Real-time review monitoring service is also available, which reads customers' ratings or reviews and has a great influence on purchasing decisions for products or services, monitoring and responding to them in real time. A competitor analysis to find the cause is also possible. Analysis time can be drastically reduced through key keyword and summary analysis through natural language processing in news, and automation of newsletters and SNS postings is possible. It is (Yong-taek Lim, Hee-seok Lim, 2020). Whenever a new issue arises in chatting or Internet language, a new coined word appears, and even though it is a non-standard language, research is being conducted to match it with a vocabulary by replacing it with a standard language (Lee Jong-hwa, 2018; Kim Jin-soo, 2020; Gil Ho-hyun, 2018).

Korean Registered Patent Publication No. 1935109 relates to a method for analyzing word phrase unit sentiment analysis in the fashion field and a storage medium including the same. In the word phrase unit sentiment analysis method, step (a) of collecting unstructured text data for online services and storing it in the management server, and extracting a plurality of emotional vocabulary included in the fashion field from the unstructured text data Step (b), step (c) of constructing a sentence combining at least some of the emotional words, and assigning positive/negative polarity weights to each of the emotional words constituting the sentence combined in step (c) ( step d), step (e) of analyzing the positive/negative polarity of a sentence combining at least some of the emotional vocabulary through positive/negative polarity weights of the emotional vocabulary, and the analysis result of step (e) It is characterized in that it includes a step (f) of analyzing trends in the fashion field through.

Korean Patent Publication No. 2014-0078312 discloses an apparatus, system, and method for providing a text-based sentiment analysis result, which includes an input unit for receiving keywords for an object to be analyzed for sentiment from a user, and sentiment analysis for the received keywords. A control unit that makes a request to the service server and receives a sentiment analysis result as a result of the request; a display unit that displays attributes of the subject according to the received sentiment analysis result and displays text corresponding to the attribute value for each displayed attribute; and A storage unit for storing the received sentiment analysis result, wherein the property is a specific item to be evaluated for the subject of the emotion or to express the emotion, and the property value is an expression that evaluates the property or expresses the emotion for the property. It is characterized by being

Korean Patent Publication No. 2015-0022583 discloses an apparatus and method for extracting keywords, including a search word reception unit that receives the search word from a user terminal, a document collection unit that collects a plurality of documents including the received search word from an external device, and the collection of documents. A frequent noun extracting unit extracting a predetermined number of frequent nouns from among nouns included in the collected documents from the collected documents, and analyzing the collected documents for the frequent nouns and the most frequent nouns. A weight determination unit that determines a weight for each, a validity determination unit that determines validity of each of the frequent nouns based on the determined weight, and keyword extraction that determines effective frequent nouns as keywords for the search word as a result of the validity determination. It is characterized by including wealth.

Korean Registered Patent Publication No. 1042515 provides an editor suitable for the searcher's intention based on the user's intention based on the user's intention analysis result and provides meta data related to the metadata entered through the editor. Search for content with data. Accordingly, it is possible to determine the searcher's intention from information input by the searcher, induce detailed metadata input based on the identified intention, and perform a search using the input metadata.

Korean Registered Patent Publication No. 0886687 automatically extracts Chinese unregistered words. When a web document containing Chinese sentences is input, the html tag of the input web document is removed, and meta tags and general tags are processed for each sentence in the web document. A method of extracting unregistered words centered on the root using the analysis result, a method of extracting unregistered words centered on single syllable tokens, and a method of extracting unregistered words centered on single syllable tokens, and unregistered verbs with four syllables. Using at least one of a method of extracting a word, a method of extracting a non-registered word capable of words by determining whether a word of a monosyllabic token is possible, and a method of extracting an unregistered word by using a word included in meta tag information It is characterized in that unregistered words are extracted. According to the present invention, it is possible to easily and quickly build a dictionary for Chinese analysis through an unregistered Chinese word extraction method, and in particular, dictionary reinforcement for new words and unregistered terms can greatly improve accuracy in an actual web document translation system. to be

Conventional technology relates to a technique of extracting a specific vocabulary and analyzing the extracted vocabulary to derive a sentiment result, set a keyword, or estimate a user's intention. The vocabulary extracted here is only a vocabulary recognized as a standard language or a vocabulary widely used among the public and registered in the Internet dictionary. Therefore, it is difficult to extract and analyze various new words that are expanded and reproduced by reflecting the rapidly changing society and culture of today.

In this regard, Korean Registered Patent Publication No. 2019756 discloses an online contextual advertising intelligent device and method based on language analysis for automatic recognition of new words. However, No. 2019756 is a technology for detecting new words among randomly collected documents, and it is realistically very difficult to set an appropriate collection target among almost infinite information on the web. In particular, in the case of food names, each person often refers to the food in various expressions, and often refers to the food in a variety of expressions depending on the recipe of the food, the manufacturing region of the food, the recipe of the food, fusion cuisine, etc. It is recognized as one of the important tasks to collect and organize various expressions that can be grouped into one standardized food name.

Korean Registered Patent Publication No. 1935109 Korean Patent Publication No. 2014-0078312 Korean Patent Publication No. 2015-0022583 Korean Registered Patent Publication No. 1042515 Korean Registered Patent Publication No. 0886687 Korean Registered Patent Publication No. 2019756

Lee Jong-hwa, Lee Moon-bong, and Kim Jong-won. (2019). A study on Korean natural language processing using TF-IDF. Information Systems Research, 28(3), 105-121. Kim Mi-kyung, Choi So-young. (2020). Characteristics of homonym processing in patients with aphasia. Journal of Special Education, 36(2), 67-80. Lim Yong-taek, Lim Hee-seok. (2020). Comparative analysis of stock price direction prediction models using corporate review information. Journal of the Korean Convergence Society, 11(8), 165-171. Jonghwa Lee. (2018). A study on generalization of emotion words using SNS hashtags. Internet Electronic Commerce Research, 18(4), 53-63. Jinsu Kim. (2020). Sentiment prediction using emotion and context information in unstructured documents. The Journal of Convergence Information (formerly Journal of the Society for Small and Medium Business Convergence), 10(10), 40-46. Gil Ho-hyun. (2018). A Study on Korean Stopword Lists for Text Mining. Korean Language, 78, 1-25.

An object of the present invention is to provide a noun extraction method using a term that describes the action or action of a noun in a text sentence or expresses a state of nature.

The present invention is a method for extracting food menu nouns using parts of speech such as verbs and adjectives to search for food nouns by using verbs associated with food name search words and to store and utilize unregistered food nouns, and to update a food dictionary using the same It is intended to provide a method and a system therefor.

The embodiment searches a web page including the received food name search word, which is executed by a processor according to a control command provided by a food menu noun extraction program code stored in a memory, and searches for a sentence including the food name search word in the searched web page. Collecting; extracting verbs from sentences including collected food name search words; searching for a web page using the extracted verb as a search term and collecting sentences including the verb in the searched web page; and extracting nouns from sentences including the collected verbs; a food menu noun extraction method using parts of speech such as verbs and adjectives may be provided.

In another aspect, determining whether the extracted noun is a registered noun on the dictionary database, extracting and displaying unregistered nouns not registered in the dictionary database; food menu noun using parts of speech such as verbs and adjectives further comprising extraction methods can be provided.

In another aspect, the client device transmits the received food name search term to the server, the server searches for a web page including the received food name search term, collects sentences including the food name search term in the searched web page, and , Extract verbs from sentences including the collected food name search terms, search web pages using the extracted verbs as search terms, collect sentences including the verbs from the searched webpages, and search for nouns from the sentences including the collected verbs. It is possible to provide a system for extracting food menu nouns using parts of speech such as verbs and adjectives.

In another aspect, the server may provide a system for extracting food menu nouns using parts of speech such as verbs and adjectives for searching a web page including the food name search term on a site corresponding to pre-registered interest monitoring site list information. there is.

In another aspect, the server collects sentences including verbs in other web pages except for web pages that overlap with the same web page as the web page already searched based on the food name search term, and the food using parts of speech such as verbs and adjectives. A system for extracting menu nouns can be provided.

In another aspect, the server searches each of the extracted nouns on a pre-stored dictionary database, and classifies each of the extracted nouns into registered nouns registered in the pre-stored dictionary database and unregistered nouns not registered in the dictionary database. It is possible to provide a system for extracting food menu nouns using parts of speech such as verbs and adjectives.

In another aspect, the server may provide a system for extracting food menu nouns using parts of speech such as verbs and adjectives for extracting registered food nouns from among the registered nouns by analyzing semantic information of the registered nouns on the dictionary database. there is.

In another aspect, the server calculates a degree of similarity between the registered food noun and the unregistered food noun by determining whether syllables between the registered food noun and the unregistered food noun are identical, and the server calculates a degree of similarity between the registered food noun and the unregistered food noun. It is possible to provide a system for extracting food menu nouns using parts of speech such as nouns and verbs and adjectives that calculate extraction frequency information of each of the nouns and the registered food name nouns.

In another aspect, the client device receives the unregistered nouns, sorts and displays the unregistered nouns based on the similarity or the extraction frequency information, the client device receives the registered food noun, and the registered food It is possible to provide a system for extracting food menu nouns using parts of speech such as verbs and adjectives in which the registered food nouns are sorted and displayed based on the detection frequency of the nouns.

In another aspect, the client device receives and displays sentence information including the selected unregistered noun from the server in response to selection of any one of the displayed unregistered nouns, and in the sentence information, the selected unregistered noun is highlighted and displayed as a verb. A system for extracting food menu nouns using parts of speech such as and adjectives can be provided.

On the other hand, the client device registers text information for registration, which is text information dragged from a displayed sentence, in a user dictionary database as semantic information of the selected unregistered noun information Extracting food menu nouns using parts of speech such as verbs and adjectives system can be provided.

In another aspect, the client device transmits text information for registration, which is text information dragged from a displayed sentence, and the selected unregistered noun information to the server, and the server transmits a plurality of text information for registration matched to the selected unregistered noun information. is collected from client devices, calculates the number of pieces of text information for registration showing a degree of similarity equal to or greater than a preset value, and if the number is equal to or greater than the preset value, any one of the text information for registration is used as semantic information of the non-registered noun information in the dictionary database. It is possible to provide a system for extracting food menu nouns using parts of speech such as verbs and adjectives registered in .

Embodiments according to the present invention may provide a method of constructing a more extensive food noun dictionary using verbs and adjectives expressing characteristics of nouns in sentences.

In addition, the embodiment extracts food menu nouns capable of extracting various food nouns using verbs extracted from food name search words by using the fact that food names are different but verbs and adjectives expressing food use the same expression. A method and a system therefor can be provided.

In addition, the embodiment may provide a food menu noun extraction method and system for extracting unregistered nouns not registered in a dictionary database and utilizing nouns expressed in various ways according to recent trends as advertisement tags.

In addition, the embodiment can provide a food menu noun extraction method and system for extracting unregistered nouns that are not registered in the dictionary database and updating semantic information about nouns expressed in various ways according to recent trends in the dictionary database. there is.

In addition, the embodiment may provide a method for extracting food menu nouns and a system therefor, which enables checking information on nouns of food names modified by specific terms.

1 presents a schematic diagram of a computer system showing various computing devices that may be used alone or in a networked configuration, in accordance with embodiments of the present disclosure.
2 is for explaining internal configurations of a client device and a server according to an exemplary embodiment.
3A to 3C are flowcharts of a food menu noun extraction method using parts of speech such as verbs and adjectives according to various embodiments of the present invention.
4 to 7 schematically illustrate a user interface displayed on a client device according to execution of a food menu noun extraction program.

Since the present invention can apply various transformations and have various embodiments, specific embodiments will be illustrated in the drawings and described in detail in the detailed description. Effects and features of the present invention, and methods for achieving them will become clear with reference to the embodiments described later in detail together with the drawings. However, the present invention is not limited to the embodiments disclosed below and may be implemented in various forms. In the following embodiments, terms such as first and second are used for the purpose of distinguishing one component from another component without limiting meaning. Also, expressions in the singular number include plural expressions unless the context clearly dictates otherwise. In addition, terms such as include or have mean that features or elements described in the specification exist, and do not preclude the possibility that one or more other features or elements may be added. In addition, in the drawings, the size of components may be exaggerated or reduced for convenience of description. For example, since the size and thickness of each component shown in the drawings are arbitrarily shown for convenience of description, the present invention is not necessarily limited to the illustrated bar.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings, and when describing with reference to the drawings, the same or corresponding components are assigned the same reference numerals, and overlapping descriptions thereof will be omitted. .

1 presents a schematic diagram of a computer system showing various computing devices that may be used alone or in a networked configuration, in accordance with embodiments of the present disclosure. For example, this figure illustrates a computer system 10 having a server 200 and a client device 100 communicating over a network 300 .

The client device 100 may be a mobile terminal 101 or a fixed terminal 102 . For example, the client device 100 includes a smart phone, a mobile phone, a navigation device, a computer, a laptop computer, a digital broadcasting terminal, a personal digital assistant (PDA), a portable multimedia player (PMP), a tablet PC, and the like.

The server 200 may be implemented as a computing device or a plurality of computing devices that communicate with at least one client device 100 through the network 300 to provide commands, codes, files, content, services, and the like.

The communication method is not limited, and short-distance wireless communication between devices as well as a communication method utilizing a communication network (eg, a mobile communication network, a wired Internet, a wireless Internet, and a broadcasting network) that the network 300 may include may also be included. For example, the network 300 includes a personal area network (PAN), a local area network (LAN), a campus area network (CAN), a metropolitan area network (MAN), a wide area network (WAN), and a broadband network (BBN). , one or more arbitrary networks such as the Internet. In addition, the network 300 may include any one or more of network topologies including a bus network, a star network, a ring network, a mesh network, a star-bus network, a tree or a hierarchical network, and the like. Not limited.

The client device 100 may prompt a user to submit a search term to initiate a search operation using the search term. The server 200 receives a search word and performs a search operation using the search word. In addition, the server 200 may perform an operation of providing search results to the client device 100 . In addition, the server 200 may transmit the requested information to the client device 100 in response to a request for additional information received from the client device 100 based on the search result information provided to the client device 100 .

For example, the server 160 may provide a file for installing an application for extracting food menu nouns to the client device 100 connected through the network 300 . In this case, the client device 100 may install an application for extracting food menu nouns using a file provided from the server 200 . In addition, services provided by the server 200 by accessing the server 200 under the control of an operating system (OS) included in the client device 100 and at least one program (for example, a browser or the installed application). I can provide content. For example, when the client device 100 transmits a service request message to the server 200 through the network 300 under the control of an application, the server 200 transmits a code corresponding to the service request message to the client device 100. ), and the client device 100 can provide content to the user by configuring and displaying a screen according to the code under the control of the application.

2 is for explaining internal configurations of a client device and a server according to an exemplary embodiment.

2 shows an example of one client device 100 and one server 200, and their internal configurations are described. In addition, the same or similar internal components of the client device 100 and the server 200 may be applied to another client device or another server that may be included in the network environment described in FIG. 1 .

The client device 100 and the server 200 may include at least one memory 110 and 210, at least one processor 120 and 220, communication modules 130 and 230, and input/output interfaces 140 and 240, respectively. can The memories 110 and 210 are computer-readable recording media and may include a random access memory (RAM), a read only memory (ROM), and a permanent mass storage device such as a disk drive. In addition, the memories 110 and 210 may store an operating system and at least one program code (for example, a code for a browser installed and driven in the client device 100 or the above-described application). These software components may be loaded from a computer-readable recording medium separate from the memories 110 and 210 using a drive mechanism. The separate computer-readable recording medium may include a computer-readable recording medium such as a floppy drive, a disk, a tape, a DVD/CD-ROM drive, and a memory card. In another embodiment, software components may be loaded into the memory 110 or 210 through the communication module 130 or 230 rather than a computer-readable recording medium. For example, at least one program is a program installed by files provided by developers or a file distribution system (eg, the server 200 described above) that distributes installation files of applications through the network 300 (eg, the above-described server 200). It may be loaded into the memory 110 or 210 based on the above-described application). The processors 120 and 220 may be configured to process commands of a computer program by performing basic arithmetic, logic, and input/output operations. Instructions may be provided to the processors 120 and 220 by the memories 110 and 210 or the communication modules 130 and 230. For example, the processors 120 and 220 may be configured to execute received instructions according to program codes stored in a recording device such as the memory 110 and 210 . The communication modules 130 and 230 may provide a function for the client device 100 and the server 200 to communicate with each other through the network 300 and to provide a function for communicating with other client devices or other servers. can For example, a request generated by the processor 120 of the client device 100 according to a program code stored in a recording device such as the memory 110 is transferred to the server 200 through the network 300 under the control of the communication module 130. ) can be transmitted. Conversely, control signals, commands, contents, files, etc. provided under the control of the processor 220 of the server 200 pass through the communication module 230 and the network 300 to the communication module 130 of the client device 100. ) through the client device 100. For example, control signals or commands of the server 200 received through the communication module 230 may be transmitted to the processor 220 or memory 210, and content or files may be transferred to the client device 100 further. It can be stored in a storage medium that can include.

The input/output interfaces 140 and 240 may be means for interface with the input/output devices 141 and 241 . For example, the input device may include a device such as a keyboard or mouse, and the output device may include a device such as a display for displaying a communication session of an application. As another example, the input/output interfaces 140 and 240 may be means for interface with a device in which functions for input and output are integrated into one, such as a touch screen. As a more specific example, the processor 120 of the client device 100 is a service configured using data provided by the server 200 or the client device 100 in processing a command of a computer program loaded into the memory 110. A screen or content may be displayed on the display through the input/output interface 140 .

Also, in other embodiments, the client device 100 and the server 200 may include more components than those of FIG. 2 . However, there is no need to clearly show most of the prior art components. For example, the client device 100 is implemented to include at least some of the above-described input/output devices 141 or other components such as a transceiver, a Global Positioning System (GPS) module, a camera, various sensors, and a database. may further include.

3A to 3C are flowcharts of a food menu noun extraction method using parts of speech such as verbs and adjectives according to various embodiments of the present invention.

Referring to FIG. 3A , in the food menu noun extraction method (S100) using parts of speech such as verbs and adjectives according to an embodiment of the present invention, a search is performed using the food name (S110), and a sentence including the food name is searched. Collecting (S120), extracting verbs from sentences including food names (S130), performing a search using the extracted verbs (S140), collecting sentences including verbs (S150), It may include extracting a noun corresponding to the food name from the sentence including the verb (S160) and comparing the extracted food name with a pre-registered food name and storing it (S170).

Referring to FIG. 3B , a method of extracting food menu nouns using parts of speech according to another embodiment (S200) includes performing a search using food names (S210), collecting sentences including food names (S220), Extracting verbs from sentences including food names (S230), performing a search by using verbs whose frequency of detection of the same verb is higher than a preset value (S240), collecting sentences including verbs (S250), It may include extracting a noun corresponding to the food name from the sentence including the verb (S260) and comparing the extracted food name with a pre-registered food name and storing it (S270).

Referring to FIG. 3C , a method for extracting food menu nouns using parts of speech (S300) according to another embodiment includes performing a search using food names (S310), collecting sentences including food names (S320), Extracting verbs from sentences including food names (S330), performing a search using extracted verbs (S340), collecting sentences including verbs (S350), Extracting the noun (S360), determining whether the extracted noun is a registered noun in the dictionary database (S370), classifying the noun as an unregistered noun if the extracted noun is not a registered noun in the dictionary database (S371) , If the extracted noun is a registered noun in the dictionary database, determining whether the corresponding noun corresponds to a food name (S380), classifying the registered noun as a non-food noun if it does not correspond to a food name (S381). ) and classifying the registered noun as a registered noun (S390) if the registered noun corresponds to the food name.

Hereinafter, each step of the food menu noun extraction method (S100, S200, S300) using parts of speech such as verbs and adjectives according to an embodiment of the present invention will be described in detail.

The client device 100 may provide the following functions performed by the processor 120 according to a control command provided by a client-side food menu noun extraction program code stored in the memory 110 .

The client device 100 may receive food name search word information input from the user.

The client device 100 may transmit the received food name search word information to the server 200 .

In various embodiments, a user may input food name search word information to the server 200 through the input/output device 241 of the server 200 .

The processor 220 of the server 200 may load the server-side food menu noun extraction program code onto the memory 210 and execute the server-side food menu noun extraction program.

The server 200 performs a search function performed by the processor 220 according to a control command provided by the server-side food menu noun extraction program code, a noun extraction function, a noun extraction function, a comparison function of detected words, and storage/transmission of information. functions can be provided.

The crawler of the server 200 traverses the web servers connected to the network 300 based on the received food name search word information, searches for a web page including the food name search word, and collects at least one sentence from the searched web page. can

According to various embodiments, the server 200 may collect web pages based on pre-registered interest monitoring site list information. In detail, the interest monitoring site list information may include information such as an interest site address, an interest media company site, an interest URL, a blog address, and an SNS address.

In some embodiments, the server 200 may receive interest monitoring site list information from the client device 100 .

In some embodiments, the list of monitoring sites of interest may be modified, deleted, or added.

The server 200 may search for a web page including a food name search word through the site of interest on the interest monitoring site list and collect at least one sentence including the food name search word in the web page.

The server 200 may parse the searched web page to identify a plurality of sentences included in the web page. In some embodiments, the server 200 may identify a final ending on the web page and identify a plurality of sentences within the web page based on the identified final ending. However, it is not limited thereto, and it is possible to identify symbols such as periods, question marks, commas, etc. included in the web page, and identify each sentence included in the web page based on the identified codes.

The server 200 may extract a sentence including a food name search word from among the identified sentences. The server 200 may extract and collect a plurality of sentences from a plurality of searched web pages.

The server 200 may extract a verb from each of the collected sentences. A verb is a large class of words that represent the action and state of an object and perform a descriptive function in a sentence. Verbs are words that indicate the movement or process of a person or thing, and adjectives are words that indicate the state or quality of a person or thing. According to various embodiments, the server 200 may extract a verb from each of the collected sentences based on a morpheme analysis technique and/or a natural language processing technique, but the method of extracting the verb is not limited to the above technique. . Also, verbs here refer to adjectives and verbs.

The server 200 may extract verbs capable of modifying the food menu by extracting verbs from each of the collected sentences.

In various embodiments, the server 200 may transmit the extracted verb information to the client device 100 . In some embodiments, the server 200 may transmit the extracted adjective information to the client device 100 . In addition, the server 200 may calculate the extraction frequency of the same verb or the same adjective and transmit the resultant information about the extraction frequency of the verb or adjective to the client device 100 .

The server 200 may use the extracted verb as a search word to search for a web page including the verb search word on the web through the network 300 and collect at least one sentence from the searched web page. A technique for collecting sentences may be the same as the above technique.

In various embodiments, server 200 may calculate the frequency of detection of the same term. The server 200 may extract terms whose detection frequency is greater than or equal to a preset value. In addition, the server 200 may use the extracted term having a detection frequency equal to or greater than a preset value as a search term to search for a web page including the term search term and collect at least one sentence including the term from the searched web page.

In various embodiments, the server 200 may perform a duplicate removal process of excluding the same webpage as the webpage already searched based on the food name search word from among searched webpages. Accordingly, it is possible to minimize a problem in that the food name search word input by the user is used as information provided to a user who is searched again.

The server 200 may extract nouns from the collected sentences.

The server 200 may calculate the frequency of extraction of the same noun.

In various embodiments, the server 200 may extract nouns modified by terms that were search words from the collected sentences. Accordingly, the server 200 may extract nouns corresponding to food names, but the extracted nouns may include nouns unrelated to food names.

The server 200 may search for each of the extracted nouns on a pre-stored dictionary database. If the noun is a noun searchable on the dictionary database among the extracted nouns, the server 200 can determine whether the searched noun corresponds to a food name or a non-food name by grasping semantic information of the corresponding noun on the dictionary database. there is. Non-food names may refer to nouns unrelated to food names, such as pronouns and place names. Also, the server 200 may classify nouns that are not searched on the dictionary database as unregistered nouns.

In various embodiments, the server 200 may calculate an estimate of whether the noun corresponds to a food name by analyzing contextual meanings and verbs on the left and right of the noun in a sentence to which each of the extracted nouns belongs. In addition, the server 200 may detect only nouns having an estimated value equal to or greater than a predetermined value, and classify the detected nouns into registered nouns and non-registered nouns by determining whether a search is performed on the dictionary database for each of the detected nouns. The server 200 may determine whether the registered noun corresponds to a food name by grasping semantic information of the registered noun on the dictionary database.

The server 200 may extract a registered food noun corresponding to a food name from registered nouns.

The server 200 may calculate the degree of similarity between the registered food nouns and the unregistered nouns by determining whether the syllables of the non-registered nouns and the registered food nouns are identical.

The server 200 may transmit unregistered nouns to the client device 100 . In addition, the server 200 may transmit extraction frequency information of unregistered nouns to the client device 100 . In addition, the server 200 may transmit similarity information between unregistered nouns and registered food nouns to the client device 100 .

4 to 7 schematically illustrate a user interface displayed on a client device according to execution of a food menu noun extraction program.

Referring to FIG. 4 , when the user inputs a food name search word into the search box sa on the user interface displayed on the client device 100 and selects a search button, the client device 100 returns the input food name search word information. It can be transmitted to the server 200. The server 200 may extract food menu nouns based on the received food name search word information as described with reference to FIGS. 3A to 3B .

When the food name search word input in the search window sa is a registered search word on the dictionary database, the client device 100 receives information on the food name search word registered on the dictionary database from the server 200 and receives the food name search word The dictionary meaning information of may be displayed on the dictionary meaning display area 11 .

In various embodiments, the client device 100, when the input food name search word does not correspond to a search word registered on the dictionary database on the server 200 but corresponds to a search word registered on the user dictionary database, the user dictionary database It is also possible to read semantic information matched to the food name search word on the image and display it on the dictionary meaning display area 11 .

In addition, the client device 100 may receive information on unregistered nouns from the server 200 and display the information on the first and second unregistered noun display areas 12 and 13 . On the first unregistered noun display area 12 , unregistered nouns may be displayed by sorting them in a high order of similarity based on similarity information with registered food nouns. On the second unregistered noun display area 13, unregistered nouns may be displayed in a manner in which detection frequencies are ranked in a high order.

In addition, the client device 100 may receive registered food name noun information from the server 200 and display it on the registered food name display area 14 . On the registered food name display area 14, the detection frequency may be arranged in a high order and the registered food name noun may be displayed.

In various embodiments, the client device 100 may receive and display information on the detected term from the server 200 . In some embodiments, the client device 100 may sort and display the terms received from the server 200 in order of highest frequency of detection.

In various embodiments, the client device 100 may display at least one noun and/or a detected term on the first unregistered noun display area 12 , the second unregistered noun display area 13 , and the registered food name display area 14 . A tagged word storage affordance may be displayed in response to selection of at least one term in the displayed area. The client device 100 may store information of all selected nouns and/or verbs as tag words in response to selection of the tag word storage affordance. When a user advertises food related to a search term entered in the search box (sa), a noun closely related to it, for example, a noun or neologism that has the same or similar meaning as the food name search term but is expressed differently, and an adjective related to the food and save them as tag words. In addition, the user uses the stored tag word as a search tag word when creating the advertisement web page, thereby increasing the possibility of exposure of the advertisement registered by the user when general users search for the web page using various search words.

In various embodiments, the client device 100 may transmit registered tag word information to the server 200 . The server 200 may extract nouns that are remaining tagwords excluding registered food nouns and adjectives registered in the dictionary database from among a plurality of tagwords in the received tagword information. The server 200 may determine whether trademark rights exist by examining each of the extracted nouns on an external server capable of confirming whether trademark rights exist. The server 200 may provide information on nouns for which trademark rights exist to the client device 100 . The user can prevent legal problems caused by using a registered tag word as a search keyword by checking nouns for which trademark rights exist among nouns set as tag words.

The client device 100 may transmit selected unregistered noun information to the server 200 in response to selection of any one of a plurality of unregistered nouns displayed on the first and second unregistered noun display areas 12 and 13 . The server 200 may transmit sentence information from which the selected unregistered noun was extracted to the client device 100 . Referring to FIG. 5 , the client device 100 may display sentence information received from the server 200 on the sentence display area 15 . In some embodiments, the unregistered noun selected on the sentence display area 15 may be highlighted and displayed.

In various embodiments, when there are a plurality of sentences from which the selected unregistered noun is extracted, the server 200 may extract a sentence including the selected unregistered noun in the largest number and transmit the extracted sentence to the client device 100 .

The client device 100 may request the server 200 to transmit the webpage including the sentence displayed on the sentence display area 15 in response to selection of the web page movement affordance on the sentence display area 15 . The server 200 may transmit webpage information including sentences to the client device 100 in response. Referring to FIG. 6 , the client device 100 may display web page information 16 received from the server 200 .

In various embodiments, the client device 100 transmits a sentence including the selected verb and the selected unregistered noun in response to selection of any one verb and non-registered nouns in displayed verb information to the server 200 ) can be requested. In response to this, the server 200 may transmit corresponding sentence information to the client device 100 when there is a sentence including the selected verb and the selected unregistered noun. Accordingly, the user can check information related to an unregistered noun modified by a specific term. This allows the user to check sentences containing information related to unregistered nouns of food names modified by terms containing the user's taste, such as 'spicy', 'sue', 'sweet', 'spicy', and 'sweet and sour'. make it possible

Referring to FIGS. 5 to 7 , the client device 100 may provide an interface allowing text to be dragged on a displayed sentence or displayed webpage in response to selection of a description registration affordance. After selecting the description registration affordance, the user may drag at least a part of the text within the displayed sentence or sentences on the displayed web page. The client device 100 may highlight and display the dragged texts td1 and td2 in response to the drag. The client device 100 may display a pre-registration affordance when text dragging is detected. The client device 100 may match the dragged text to the unregistered noun selected in FIG. 4 in response to the selection of the pre-registered affordance and store the semantic information of the unregistered noun in the user dictionary database. In addition, the client device 100 may transmit registration text information and unregistered noun, which are dragged text information selected in FIG. 4 , to the server 200 .

The server 200 may receive unregistered noun information and text information for registration matched by users to the corresponding unregistered noun from a plurality of client devices. For example, the server 200 may receive 10 pieces of text information for registration matched to the same unregistered noun from 10 client devices. The server 200 may detect a similarity between 10 pieces of text information for registration. Among the 10 text information for registration, the texts may completely match each other (when different users drag the same sentence), or only some texts may differ (when different users drag some text within the same sentence). In one case), a lot of text can be different (if different users dragged the text within different sentences).

The server 200 may extract pieces of text information for registration showing similarities greater than or equal to a preset value and calculate the quantitative number of the extracted pieces of text information for registration. As a result of calculating the quantitative number, the server 200 may set any one of the text information for registration among the corresponding text information for registration as the approved semantic information of the unregistered noun when text information for registration exceeding the preset number is confirmed as a result of calculating the quantitative number. . In addition, the server 200 may convert the status of an unregistered noun to a registered noun, register it in a dictionary database, and update the dictionary database by registering corresponding approved registration text information as semantic information of the registered noun whose status has been switched. .

Embodiments according to the present invention described above may be implemented in the form of program instructions that can be executed through various computer components and recorded on a computer-readable recording medium. The computer readable recording medium may include program instructions, data files, data structures, etc. alone or in combination. Program instructions recorded on the computer-readable recording medium may be specially designed and configured for the present invention, or may be known and usable to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical recording media such as CD-ROMs and DVDs, and magneto-optical media such as floptical disks. medium), and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter or the like as well as machine language codes generated by a compiler. A hardware device may be modified with one or more software modules to perform processing according to the present invention and vice versa.

Specific implementations described in the present invention are examples and do not limit the scope of the present invention in any way. For brevity of the specification, description of conventional electronic components, control systems, software, and other functional aspects of the systems may be omitted. In addition, the connection of lines or connecting members between the components shown in the drawings are examples of functional connections and / or physical or circuit connections, which can be replaced in actual devices or additional various functional connections, physical connection, or circuit connections. In addition, if there is no specific reference such as “essential” or “important”, it may not be a component necessarily required for the application of the present invention.

In addition, the detailed description of the present invention described has been described with reference to preferred embodiments of the present invention, but those skilled in the art or those having ordinary knowledge in the art will find the spirit of the present invention described in the claims to be described later. And it will be understood that the present invention can be variously modified and changed without departing from the technical scope. Therefore, the technical scope of the present invention is not limited to the contents described in the detailed description of the specification, but should be defined by the claims.

system(10)
Client device (100)
server(200)
network(300)
Memory (110, 210)
Processor (120, 220)
Communication module (130, 230)
I/O interfaces (140, 240)
I/O devices (141, 241)

Claims (12)

Performed by the processor according to the control command provided by the food menu noun extraction program code stored in memory
searching for a web page including the received food name search word, and collecting sentences including the food name search word in the searched web page;
extracting verbs from sentences including collected food name search words;
searching for a web page using the extracted verb as a search term and collecting sentences including the verb in the searched web page; and
Extracting nouns from sentences including the collected verbs;
A method for extracting food menu nouns using parts of speech such as verbs and adjectives. According to claim 1,
Determining whether the extracted noun is a registered noun on the dictionary database, extracting and displaying unregistered nouns not registered in the dictionary database; further comprising
A method for extracting food menu nouns using parts of speech such as verbs and adjectives. The client device transmits the received food name search term to the server,
The server searches a web page including the received food name search word, collects sentences including the food name search word in the searched webpage, extracts verbs from the collected sentences including the food name search word, and extracts the extracted verbs. is a search term for web pages, collects sentences including verbs from the searched web pages, and extracts nouns from sentences including collected verbs.
A system for extracting food menu nouns using parts of speech such as verbs and adjectives. According to claim 3,
The server searches for a web page including the food name search term on a site corresponding to pre-registered interest monitoring site list information.
A system for extracting food menu nouns using parts of speech such as verbs and adjectives. According to claim 4,
The server collects sentences including verbs in other web pages except for web pages that overlap with the same web page as the web page already searched based on the food name search term.
A system for extracting food menu nouns using parts of speech such as verbs and adjectives. According to claim 3,
The server searches for each of the extracted nouns on a pre-stored dictionary database and classifies each of the extracted nouns into registered nouns registered in the pre-stored dictionary database and unregistered nouns not registered in the dictionary database
A system for extracting food menu nouns using parts of speech such as verbs and adjectives. According to claim 6,
The server extracts a registered food noun from among the registered nouns by analyzing the semantic information of the registered noun on the dictionary database.
A system for extracting food menu nouns using parts of speech such as verbs and adjectives. According to claim 7,
The server determines whether syllables between the registered food noun and the non-registered food noun are identical to each other, and calculates a degree of similarity between the registered food noun and the unregistered food noun,
The server calculates extraction frequency information of each of the unregistered nouns and the registered food name noun.
A system for extracting food menu nouns using parts of speech such as verbs and adjectives. According to claim 8,
the client device receives the unregistered nouns, sorts and displays the unregistered nouns based on the degree of similarity or the extraction frequency information;
The client device receives the registered food nouns, sorts and displays the registered food nouns based on the detection frequency of the registered food nouns.
A system for extracting food menu nouns using parts of speech such as verbs and adjectives. According to claim 9,
The client device receives and displays sentence information including the selected unregistered noun from the server in response to selection of any one of the displayed unregistered nouns, and the selected unregistered noun is highlighted and displayed in the sentence information
A system for extracting food menu nouns using parts of speech such as verbs and adjectives. According to claim 10,
The client device registers text information for registration, which is text information dragged from a displayed sentence, in a dictionary database for a user as semantic information of the selected unregistered noun information.
A system for extracting food menu nouns using parts of speech such as verbs and adjectives. According to claim 10,
The client device transmits registration text information, which is text information dragged from a displayed sentence, and the selected unregistered noun information to the server;
The server collects text information for registration matched with the selected unregistered noun information from a plurality of client devices, calculates the number of pieces of text information for registration showing similarity equal to or greater than a preset value, and if the number is equal to or greater than the preset value, among the text information for registration. Registering any one text information in the dictionary database as semantic information of the unregistered noun information
A system for extracting food menu nouns using parts of speech such as verbs and adjectives.

Images