KR102280495B1 - Apparatus and method for providing search service based on artificial intelligence - Google Patents

Abstract

The present invention relates to an artificial intelligence-based search service providing apparatus and method for forming a scoring matrix by reflecting a content page from which a selection command is received among search results. When a selection command is received on the search result providing screen for a search result, a search result providing unit displaying contents corresponding to the selected search result and a content page receiving a selection command among the search results displayed by the search result providing unit are reflected. and a matrix forming unit for forming a scoring matrix, wherein the search result providing unit reflects the scoring matrix formed in the matrix forming unit to provide a search result provision screen for the search word inputted. The effect of providing an apparatus and method for providing a search service based on artificial intelligence that can provide convenience by more easily finding an object to be searched by the device is derived.

Description

Apparatus and method for providing search service based on artificial intelligence {APPARATUS AND METHOD FOR PROVIDING SEARCH SERVICE BASED ON ARTIFICIAL INTELLIGENCE}

The present invention relates to an apparatus and method for providing a search service based on artificial intelligence, and more particularly, to an apparatus and method for providing a search service based on artificial intelligence to form a scoring matrix by reflecting a content page to which a selection command is received from among search results will be.

Search results, such as Internet pages and documents, are ordered through scores of relevance between the search terms of the computer and the pages to be searched. In this case, the ordering is determined manually by a computer algorithm.

In order to overcome this manually determined limitation, it is necessary to develop a technology that can create a correlation scoring matrix that dynamically finds search results individually and repeatedly for each user. In this case, it is preferable that the algorithm proceeds in a fixed manner with a certain rule.

In general, information retrieval refers to the act of obtaining a part related to a desired content from collective information.

Here, the automated information retrieval system is used to alleviate the so-called "information overload", and many universities and public libraries have built an information retrieval system to provide access to various documents such as books and journals, and , these web search engines are one of the most easily encountered information retrieval systems on a daily basis.

Furthermore, there is a data integration providing system that simultaneously searches multiple databases or systems with a single query in a single interface and lists the search results on a single screen with respect to the information retrieval system.

By using this data integration providing system, the inconvenience of having to repeat the same search sequentially through multiple systems can be reduced, and at the same time, the search results of multiple systems are provided in a single interface, allowing users to selectively collect the data they want. can do.

In this case, as a prior art for an integrated search service method and system, there is Korean Patent Registration No. 10-1910191 (Title of the Invention: Integrated Search System).

The prior art includes a data collection module that collects a search target from a database on the web using a data collector or collects attached files; an index processing module that performs document filtering and data index processing on the data collected by the data collection module using a Hangul morpheme analyzer; a search processing module driven by a standard Xml-based search interface, after operator processing a search word requested by a user, searching for data corresponding to the search word from among the materials indexed by the index processing module, and processing the search result; an additional service providing module that provides additional services including spelling check, automatic completion of search terms, search word recommendation, recent search word provision, popular search word provision, personalization function provision, and object extraction function; and extracts the title, author, and product name of the data collected in the data collection module, indexes it, and stores it in its own memory. When there is a search request for the stored data from the user, the search result takes precedence over the search processing module and an in-memory retrieval module that processes and provides to the user.

Then, based on the location information collected by the GPS module of the computing device that the user logged into the integrated search service accessed the integrated search service, country information for each time the user accesses the integrated search service is extracted in the order of the number of access points. Five countries are extracted.

If a search term is input from the user and there is no search request within 5 seconds, the search result in the language with the most access points is provided, and within 1 minute from the time when the search result in the language with the most access points is provided, the user If there is no selection for the search result from the search result, the search result is provided in the language of the country with the second largest number of access points.

In addition, if the user does not select the search result within 50 seconds of providing the search result in the language of the country with the second highest number of access points, the search result in the language of the country with the third highest number of access points is provided.

And if there is no selection for the search result from the user within 40 seconds from the time when the search result in the language of the third country with the third access point is provided, the search result in the language with the fourth most access point is provided, If the user does not select the search result within 40 seconds from the point in time of providing the search result in the language of the country with the fourth largest number of access points, the search result in the language of the country with the fifth most access point is provided.

Further comprising an automatic language conversion search module that provides a country selection tab if the user does not select the search result within 30 seconds from the point in time when the access point provides search results in the fifth most national language A search service provision system is presented.

The prior art has the advantage of providing a convenient search environment by providing a fast indexing and search function, support for various server environments, a standardized Xml-based search interface, and various search additional functions as an open source-based search engine, There is a disadvantage in that it cannot provide more diverse information because it does not provide search data from the web and the app in an integrated way.

US 10-2017-0093713 A US 10-2014047 B1 US 10-1910191 B1

The present invention is derived from such a technical background, and in providing web search data, it is possible to provide different data search results for each user by reflecting the scoring matrix generated according to the user's personal search history, An object of the present invention is to provide an apparatus and method for providing a search service based on artificial intelligence that can provide convenience by more easily finding a target.

In addition, an artificial intelligence-based search service providing apparatus and method that can provide more satisfactory search result data by identifying the personal needs of the user using the search service and providing the user's desired search result as if reading the user's mind would like to provide

The present invention for achieving the above object includes the following configuration.

That is, the artificial intelligence-based search service providing apparatus according to an embodiment of the present invention includes a search word input unit for receiving a search word, and when a selection command is received on a search result provision screen for a search word input through the search word input unit, the selected search result is displayed. and a matrix forming unit configured to form a scoring matrix by reflecting a search result providing unit for displaying corresponding contents and a content page receiving a selection command from among the search results displayed by the search result providing unit, wherein the search result providing unit includes the matrix It is characterized in that by reflecting the scoring matrix formed in the forming unit to provide a search result providing screen for the input search word.

In one aspect of the present invention, the search result providing unit learns the scoring matrix formed in the matrix forming unit based on machine learning, and provides a search result providing screen by reflecting the learned contents.

On the other hand, the artificial intelligence-based search service providing method performed by the artificial intelligence-based search service providing device includes the steps of: a search word input unit receiving a search word, and a search result providing unit receiving a selection command on a search result provision screen for the inputted search word displaying content corresponding to the selected search result, and forming a scoring matrix by a matrix forming unit reflecting a content page to which a selection command is received from among the displayed search results, wherein the displaying comprises the steps of: It is characterized in that by reflecting the formed scoring matrix to provide a search result providing screen for the input search word.

According to an aspect of the present invention, the step of displaying the content corresponding to the selected search result comprises learning the scoring matrix formed in the matrix forming unit based on machine learning, and providing a search result providing screen by reflecting the learned content. characterized in that

According to the present invention, in providing web search data, it is possible to provide different data search results for each individual user by reflecting the scoring matrix generated according to the user's personal search history, so that the object to be searched can be more easily found. The effect of providing an artificial intelligence-based search service providing apparatus and method that can provide convenience is derived.

In addition, an artificial intelligence-based search service providing apparatus and method that can provide more satisfactory search result data by identifying the personal needs of the user using the search service and providing the user's desired search result as if reading the user's mind can provide

1 is a block diagram showing the configuration of an apparatus for providing an artificial intelligence-based search service according to an embodiment of the present invention;
2 is a flowchart of a method for providing a search service based on artificial intelligence according to an embodiment of the present invention.

It should be noted that the technical terms used in the present invention are only used to describe specific embodiments, and are not intended to limit the present invention. In addition, the technical terms used in the present invention should be interpreted as meanings generally understood by those of ordinary skill in the art to which the present invention belongs, unless otherwise defined in particular in the present invention, and excessively comprehensive It should not be construed in the meaning of a human being or in an excessively reduced meaning.

Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the accompanying drawings.

1 is a block diagram illustrating the configuration of an apparatus for providing an artificial intelligence-based search service according to an embodiment of the present invention.

According to an embodiment, the search service providing apparatus 10 may be mounted on a user terminal.

Here, the user terminal is an IP-assigned terminal and performs network communication through the Internet or the like. For example, desktop PC (desktop PC), slate PC (slate PC), notebook computer (notebook computer) PMP (Portable Multimedia Player), ultrabook (ultrabook), wearable device (wearable device, for example, a watch-type terminal (smartwatch) ), glass-type terminals (smart glass), HMD (head mounted display), and the like. Of course, the user terminal to which the present invention is applicable is not limited to the above type, and may be interpreted to include all types of terminals capable of communicating with an external device.

In addition, for example, as a wireless communication device that ensures portability and mobility, navigation, 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, smartphone ), it is natural that all kinds of handheld-based wireless communication devices such as a smart pad, a tablet PC, and the like may be included.

In an embodiment, the communication method between the search service providing apparatus 10 and the search service management server 30 is not limited, and the network may include a communication network (eg, a mobile communication network, a wired Internet, a wireless Internet, a broadcasting network). It is possible to perform data transmission and reception not only in a communication method that utilizes , but also in a short-range wireless communication method between devices.

Here, the network is a network such as 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), a broadband network (BBN), and the Internet. It may include one or more arbitrary networks.

Further, the network may include any one or more of a network topology including, but not limited to, 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. does not

In one embodiment, the search service management server 30 builds a machine learning-based search engine scoring algorithm through interaction feedback with the user for each user who has subscribed to the service through the search service providing device 10, so that the user It can be stored and managed separately.

For example, when a search service dedicated application is driven in the search service providing apparatus 10 , the search service management server 30 provides data necessary for running the search service dedicated application in the search service providing apparatus 10 .

In an embodiment, the search service management server 30 includes a service platform that drives an application providing a user interface to provide a search service using a scoring matrix according to an embodiment.

As another example, the search service management server 30 stores, manages, and provides source data necessary for driving a website that provides a search service according to an embodiment through a web page accessible from the search service providing device 10 . It also includes a platform that can perform the tasks necessary to run the overall website.

The search service management server 30 stores basic member information for users who have subscribed to the service, monitors the user's searches and selections in search results, and generates and stores a search engine scoring matrix for each user. Alternatively, the search engine scoring matrix received from the search service management server 30 is stored and managed by matching it with the user's basic member information.

Afterwards, when a request for a search engine scoring matrix for a specific user is received from the search service providing apparatus 10 , the corresponding user's scoring matrix is extracted from the stored scoring matrix to match the user's basic information and sent to the search service providing apparatus 10 . can provide

The display unit 20 is interpreted to cover all technical configurations that can display information in the user terminal as visible data on the screen. In addition, the display unit 20 may be implemented with a technical configuration that provides a user interface through which a manipulation signal such as a touch can be input.

The search service providing apparatus 10 according to an embodiment builds a machine learning-based search engine scoring algorithm through interaction feedback with the user, reads the user's search intent, and provides a result that can maximize user satisfaction It is a technology for a device that proposes an artificial intelligence search algorithm for

As can be seen from FIG. 1 , the apparatus 10 for providing a search service according to an exemplary embodiment includes a communication unit 100 , a search word input unit 110 , a search result provision unit 120 , and a matrix forming unit 130 .

The communication unit 100 may include both a communication module for supporting wired communication and a mobile communication module for supporting wireless communication. The mobile communication module includes technical standards or communication methods for mobile communication (eg, Global System for Mobile communication (GSM), Code Division Multi Access (CDMA), Code Division Multi Access 2000 (CDMA2000), Enhanced Voice (EVDO) -Data Optimized or Enhanced Voice-Data Only), WCDMA (Wideband CDMA), HSDPA (High Speed Downlink Packet Access), HSUPA (High Speed Uplink Packet Access), LTE (Long Term Evolution), LTE-A (Long Term Evolution-) Advanced), etc.), transmits and receives a radio signal to and from at least one of a base station and an external terminal on a mobile communication network.

In an embodiment, the communication unit 100 communicates with the search service management server 30 .

The search word input unit 110 receives a search word from the user. In an embodiment, the search word input unit 110 may receive a search word input through a touch screen method provided by the display unit 20 .

Alternatively, the search word input unit 110 may receive a search word from a technical configuration capable of performing data input, such as a keyboard operated in conjunction with the search service providing device 10 .

In one embodiment, the search word input unit 110 receives a search word through a user terminal possessed by the user. At this time, the user terminal used by the user to input the search word may be a PC, a smartphone, a tablet PC, a smart watch, or the like. There are no restrictions on devices that can access the web.

In addition, the search word input unit 110 may input information through a search window having a horizontally long rectangular shape, and the shape of the search window is not limited. When a search word is searched through the search word input unit 110, web and app search data for the search word are respectively searched.

When a selection command is received on the search result providing screen for the search word input by the search word input unit 110 , the search result providing unit 120 displays contents corresponding to the selected search result through the display unit 20 .

The search result providing unit 120 calculates the relevance of pages derived as a search result with an input search word.

The matrix forming unit 130 forms a scoring matrix by reflecting a content page to which a selection command is received from among the search results displayed by the search result providing unit 120 . In an embodiment, the matrix forming unit 130 may store the generated scoring matrix in its own storage unit or transmit it to the search service management server 30 together with user information through the communication unit 100 .

The matrix forming unit 130 generates a scoring matrix by calculating the relevance of pages derived as a search result from the search result providing unit 120 with an input search word.

In an embodiment, the matrix forming unit 130 calculates a cluster based on a method of calculating a cluster based on the similarity of the content of the search term and calculating the cluster based on the similarity of a user click (that is, the search term of the same request tends to click the same result) ) can be used to form a scoring matrix.

However, the present invention is not limited thereto, and in this case, a method or algorithm for generating a scoring matrix may be variously applied.

That is, in order to apply the scoring matrix to training data using artificial intelligence, a training set scoring matrix can be proposed.

The matrix forming unit 130 recognizes keywords input by the user as search data and feedback given by the user through selection of a search result page.

By repeatedly identifying the feedback given through the selection of the search result page, it is possible to continuously find and optimize the user's intention. That is, it is possible to propose a search algorithm that continuously iterates to create a scoring matrix and predict the final result page.

In one aspect of the present invention, the matrix forming unit 130 forms a scoring matrix by calculating the association between the search word input through the search word input unit 110 and the words included in the content page.

The search result providing unit 120 reflects the scoring matrix formed in the matrix forming unit 130 and provides a search result providing screen for the input search word through the display unit 20 .

The search result providing unit 120 performs a function of providing application search data, which is an application search result, and web search data, which is a web search engine search result, for a search word input through the search word input unit 110 , respectively.

At this time, the meaning of the search word entered by the user is automatically analyzed and searched based on the scoring matrix to analyze the meaning the user wants to search.

The search result providing unit 120 provides web and app search data through the display unit 20, and at the same time, the existing search data is accumulated and analyzed by artificial intelligence. Search result data may be provided.

In one aspect, the search result providing unit 120 learns the scoring matrix formed by the matrix forming unit 130 based on machine learning, and provides a search result providing screen by reflecting the learned contents.

In more detail, when a selection command is received from a context page displaying a search result providing screen, the search result providing unit 120 displays a content page corresponding to the selected result through the display unit 20 . Display.

The search result providing unit 120 may display a different search result providing screen for each user by a scoring matrix that is generated differently for each user. That is, the search result list is rearranged on the display screen by reflecting the user's scoring matrix on the context page displaying the search result provision screen.

The search results page contains exact results that directly satisfy the search term request. In addition, the recommendation guide result may be displayed on a part of the result screen displayed by reflecting the scoring matrix.

In addition, the selection of information content of the context page is mainly reflected in the scoring matrix, and the information content displayed as a search result is based on popularity, time-validity, and relevance of the user's personalized request. If the user wants to understand in detail the information of the context page, he clicks the information to access the content page.

The matrix forming unit 130 reflects the degree of association between a search word input by a user in the scoring matrix and a content page selected by an action such as a click on the search result provision screen.

In one embodiment, a high score weight of a variable designated to display a cafe article on a scoring matrix is generated for a user who prefers a cafe article among the search results. In addition, for a user who prefers a news article, a high score weight of a variable designated to display a news article among the article types is generated.

Also, for example, in the case of a user who prefers an article with many images, the ratio of the image and text included in each article in the search result list included in the context page may be included in the scoring matrix and reflected.

The personalized modeling information that can be formed by the scoring matrix specifically determines the user's attributes (eg, gender, age, etc.), status (eg, pregnancy, job search, etc.), interests (eg, horror movies, rock music, etc.). likes) and consumption habits (eg, buying electronic products, etc. mainly), and the like.

At this time, the personalization modeling information reflects the creation and submission of personalized information by the user, the analysis of the user search log, and the automatic analysis of the user's entire page browsing log by forming a scoring matrix. can be created

2 is a flowchart of a method for providing a search service based on artificial intelligence according to an embodiment of the present invention.

The artificial intelligence-based search service providing method according to an embodiment uses machine learning to calculate the association between words in the content of pages that the user thinks is correct, and uses a machine learning methodology to determine the intention of the user. Create a reading score.

First, in the artificial intelligence-based search service providing method performed by the artificial intelligence-based search service providing apparatus, a search word input unit receives a search word ( S200 ).

In an embodiment, the search word input unit may receive a search word input through a touch screen method provided by the display unit.

Alternatively, the search word input unit may receive a search word from a technical configuration capable of performing data input, such as a keyboard operated in conjunction with the search service providing device.

In an embodiment, the search word input unit receives a search word through a user terminal possessed by the user. In this case, the user terminal used by the user to input the search word may be a PC, a smartphone, a tablet PC, a smart watch, etc., There are no restrictions on devices that can access the web.

In addition, the search word input unit may input information through a search window having a horizontally long rectangular shape, and the shape of the search window is not limited. When a search word is searched through such a search word input unit, web and app search data for the search word are respectively searched.

The search result providing unit outputs a search result providing screen for the search word input through the search word input unit (S210). And when a selection command is received on the output search result providing screen (S220), the content corresponding to the selected search result is displayed through the display unit (S230).

Specifically, the search result providing unit displays a content page corresponding to the selected result when a selection command is received from a context page displaying a search result providing screen in displaying content corresponding to the selected search result. will do

Thereafter, the matrix forming unit forms a scoring matrix by reflecting the content page to which a selection command is received from among the search results displayed on the display unit (S240).

In an embodiment, the matrix forming unit may store the generated scoring matrix in its own storage unit or transmit it to the search service management server together with user information through the communication unit (S250).

The search result providing unit may provide a search result providing screen for the input search word by reflecting the scoring matrix formed by the matrix forming unit.

In one aspect, in forming the scoring matrix, the search result providing unit calculates and reflects the association between the search term input through the search term input unit and words included in the content page provided by the search result providing unit.

In an embodiment, the matrix forming unit may form the scoring matrix by a method of calculating a cluster based on the similarity of the search word content, a method of calculating a cluster based on the similarity of a user click, and the like.

However, the present invention is not limited thereto, and in this case, a method or algorithm for generating a scoring matrix may be variously applied.

That is, in order to apply the scoring matrix to training data using artificial intelligence, a training set scoring matrix can be proposed.

In addition, in one aspect of the present invention, displaying the content corresponding to the selected search result is to learn the scoring matrix formed in the matrix forming unit based on machine learning, and to provide a search result providing screen by reflecting the learned content, characterized in that do.

That is, the matrix forming unit recognizes the keyword input by the user as search data and the feedback given by the user through the selection of the search result page, and reflects it in the scoring matrix.

By repeatedly grasping the feedback given through the selection of the search result page, it is possible to continuously find and optimize the user's intention. That is, it is possible to propose a search algorithm that continuously iterates to create a scoring matrix and predict the final result page.

In one embodiment, a high score weight of a variable designated to display a cafe article on a scoring matrix is generated for a user who prefers a cafe article among the search results. In addition, for a user who prefers a news article, a high score weight of a variable designated to display a news article among the article types is generated.

Also, for example, in the case of a user who prefers an article with many images, the ratio of the image and text included in each article in the search result list included in the context page may be included in the scoring matrix and reflected.

In an embodiment, the search service management server includes a service platform for driving an application providing a user interface to provide a search service using a scoring matrix according to an embodiment.

As another example, the search service management server stores, manages, and provides source data necessary for driving a website that provides a search service according to an embodiment through a web page accessible from the search service providing device.

It also includes a platform that can perform the tasks necessary to run the overall website.

The search service management server stores basic member information for users who have subscribed to the service, monitors the user's searches and selections in search results, and generates and stores a search engine scoring matrix for each user. Alternatively, the search engine scoring matrix received from the search service management server is stored and managed by matching it with the user's basic member information.

Thereafter, when a request for a search engine scoring matrix for a specific user is received from the search service providing apparatus, the corresponding user's scoring matrix may be extracted from the stored scoring matrix to match the user's basic information and provided to the search service providing apparatus.

The above-described method may be implemented as an application or implemented in the form of program instructions that may be executed through various computer components and recorded in a computer-readable recording medium. The computer-readable recording medium may include program instructions, data files, data structures, etc. alone or in combination.

The program instructions recorded on the computer-readable recording medium are specially designed and configured for the present invention, and may be known and used by those skilled in the art of computer software.

Examples of the computer-readable recording medium include a hard disk, a magnetic medium such as a floppy disk and a magnetic tape, an optical recording medium such as a CD-ROM and DVD, and a magneto-optical medium such as a floppy disk. media), 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 not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware device may be configured to operate as one or more software modules to perform processing according to the present invention, and vice versa.

Although the above has been described with reference to the embodiments, those skilled in the art will understand that various modifications and changes can be made to the present invention without departing from the spirit and scope of the present invention as set forth in the following claims. will be able

10: search service providing device 20: display unit
30: search service management server 100: communication unit
110: search word input unit 120: search result provision unit
130: matrix forming part

Claims (8)

a search word input unit for receiving a search word;
a search result providing unit configured to display contents corresponding to the selected search result when a selection command is received on a search result providing screen for a search word input through the search word input unit; and
and a matrix forming unit that forms a scoring matrix by reflecting a content page to which a selection command is received from among the search results displayed by the search result providing unit;
The search result providing unit reflects the scoring matrix formed in the matrix forming unit and provides a search result providing screen for the input search word,
The matrix forming unit,
A scoring matrix is formed by calculating a correlation between the input search word and words included in a content page to which the selection command is received,
Reflects the degree of relevance between the search term entered by the user in the scoring matrix and the content page selected by the user on the search result provision screen,
The search result providing unit displays a different search result provision screen for each user by a scoring matrix generated differently for each user, but reflects the user's scoring matrix on a context page for displaying the search result provision screen relocate,
Personalized modeling information is formed by the scoring matrix including at least one information of a user's attribute, state, interest, and consumption habit, but by forming a scoring matrix by reflecting the personalization information created and submitted by the user is created,
The search result providing unit automatically analyzes the meaning of the input search word based on a scoring matrix to analyze the meaning that the user wants to search, an artificial intelligence-based search service providing apparatus.
delete The method of claim 1,
The search result providing unit,
An apparatus for providing a search service based on artificial intelligence, comprising learning the scoring matrix formed in the matrix forming unit based on machine learning, and providing a search result providing screen by reflecting the learned contents.
The method of claim 1,
The search result providing unit
When a selection command is received from a context page displaying a search result providing screen, an apparatus for providing a search service based on artificial intelligence, characterized in that it displays a content page corresponding to the selected result.
An artificial intelligence-based search service providing method performed by an artificial intelligence-based search service providing device, the method comprising:
receiving a search word input by a search word input unit;
displaying, by a search result providing unit, contents corresponding to the selected search result when a selection command is received on a search result provision screen for the input search word; and
Forming a scoring matrix by a matrix forming unit reflecting a content page to which a selection command is received from among the displayed search results;
The displaying comprises providing a search result providing screen for the input search word by reflecting the formed scoring matrix,
Forming the scoring matrix comprises:
It is characterized in that the correlation between the input search word and the words included in the content page is calculated,
Reflects the degree of relevance between the search term entered by the user in the scoring matrix and the content page selected by the user on the search result provision screen,
The search result providing unit displays a different search result provision screen for each user by a scoring matrix generated differently for each user, but reflects the user's scoring matrix on a context page for displaying the search result provision screen relocate,
Personalized modeling information is formed by the scoring matrix including at least one information of a user's attribute, state, interest, and consumption habit, but by forming a scoring matrix by reflecting the personalization information created and submitted by the user is created,
The search result providing unit automatically analyzes the meaning of the input search word based on a scoring matrix to analyze the meaning that the user wants to search, an artificial intelligence-based search service providing method.
delete 6. The method of claim 5,
The step of displaying the contents corresponding to the selected search result comprises:
An artificial intelligence-based search service providing method, comprising: learning the scoring matrix formed in the matrix forming unit based on machine learning, and providing a search result providing screen by reflecting the learned content.
6. The method of claim 5,
The step of displaying the contents corresponding to the selected search result comprises:
When a selection command is received from a context page for displaying a search result providing screen, an artificial intelligence-based search service providing method comprising displaying a content page corresponding to the selected result.

Images