KR100970335B1 - Method for updating interest keyword of user and system for executing the method - Google Patents

Abstract

A method of updating a keyword of interest of a user and a system for performing the method are disclosed. The interest category of the user is determined according to the size of the weight by determining a related category corresponding to the search keyword of the user and updating the keyword of interest of the user from keywords in the related category, or by weighting the recent search keyword of the user. Provides a way to update.

Keywords of interest, keyword suggestions, related keywords, related categories, recent logs, weighted recent keyword search history, keyword updates, entries, content

Description

How to update keyword of interest of user and system for performing the method {METHOD FOR UPDATING INTEREST KEYWORD OF USER AND SYSTEM FOR EXECUTING THE METHOD}

The present invention relates to an information retrieval system for providing a keyword retrieval service, and more particularly, a user's interest for recommending related keywords to a user and providing various contents related to each keyword based on the keyword retrieval in the information retrieval system. A method of updating a keyword and a system for performing the method.

Today, with the rapid development of communication networks such as the Internet, information retrieval through communication networks is becoming very common. The most common search service method performed in an information retrieval system is a keyword method. An information retrieval system providing such a keyword retrieval service, when a keyword is input from a user, a search result including the keyword (for example, a web site including the keyword, an article including the keyword, and a file name including the keyword). Provide an image to the user terminal).

That is, according to a conventional keyword search service method and an information search system for performing the method, one or more contents are provided as a list of search results for a specific keyword input from a user terminal.

As keyword search becomes more frequent, new advertisement methods such as inserting an advertisement related to a search word into a search result or providing the search list in association with each other have been in the spotlight. Among them, keyword advertisement is an advertisement type in which an advertiser exclusively exposes an advertisement only to a search result page when a user searches for a keyword including a keyword after purchasing a specific keyword. Since such keyword advertising can only show the contents of the advertisement to people who are interested in a particular product or issue, it is possible to increase the targeted advertisement effect and increase the clickthrough rate of the advertisement.

Existing information retrieval system has a problem in that it does not provide a variety of keyword advertising because it recommends only the ads that match the keyword input by the user by simply exposing the advertisement corresponding to each keyword for each keyword.

In addition, there are no keyword recommendation criteria for providing keyword recommendation based on a user's keyword search or providing various contents corresponding to each keyword.

Existing information retrieval system has a limitation in providing various contents corresponding to the user's interest in providing a search result related to a keyword input by the user.

The present invention provides a method and system for updating a user's interest keyword that can prepare a keyword recommendation criteria for providing a keyword of interest of a user and provide various contents as well as the keyword of interest.

That is, on the information retrieval system, the user's keyword search is recommended based on the user's keyword search and keyword recommendation criteria for providing various contents for each keyword of interest are provided.

The present invention includes determining a related category for a search keyword input by a user; And updating a list of interest keywords to be recommended to the user based on the related category.

The present invention comprises the steps of recording the keyword search history of the user; And updating a list of interest keywords to be recommended to the user based on the keyword search history.

The present invention provides a user interface for inputting a search keyword by a user; And an interest keyword generation unit configured to generate an interest keyword list to be recommended to the user based on the search keyword input through the user interface.

A method of updating a user interest keyword according to the present invention and a system for performing the method may provide keyword recommendation criteria for recommending a keyword of interest based on a user's keyword search.

That is, it is possible to recommend an optimal keyword of interest to the user and effectively provide various contents related to each keyword of interest.

Hereinafter, a method of updating a keyword of interest of a user and a system for performing the method will be described with reference to the accompanying drawings.

An information retrieval system providing a keyword retrieval service may search for at least one content such as a web site including the search keyword, an article including the search keyword, and a file name including the search keyword when a search keyword is input from a user. Provide as search results for keywords.

The information retrieval system according to the present invention updates and provides a list of interest keywords to be recommended based on the user's search keyword in order to recommend keywords according to the user's interests and guide various contents.

In particular, the present invention provides a method of updating an interest keyword that determines a related category corresponding to a user's search keyword and generates the interested keyword list using the related category.

In addition, the present invention updates an interest keyword for generating the interest keyword list using a search keyword that a user has recently searched, that is, weighting the latest log and using a search keyword corresponding to the latest log according to the magnitude of the weight. Provide a method.

Referring to FIG. 1, a method of updating a keyword of interest using an associated category will be described in detail. 1 is a diagram illustrating an entire process of a method of updating a keyword of interest using an associated category.

In step S101, the information search and interest keyword update system obtains at least one related keyword associated with the search keyword input by the user. The association keyword may be obtained based on the degree of association between words.

A method of measuring numerical association with respect to association between words will be described in detail.

To measure the degree of association between the words, word statistics information is obtained through a word included in a document set, a document, a word classification for the word, or a document classification for the document.

Subsequently, the obtained word statistical information is standardized. At this time, the word statistical information may be standardized into a multidimensional vector set, a real type random variable set, a combined probability distribution of random variables, or a discrete random variable set.

The word statistical information can be formulated using any one of the following methods (1) to (4).

(1) setting the word, the document, the word classification or the document classification as a column of the multidimensional vector set having independent respective dimensions of the multidimensional space, and mapping the words to the vectors of the multidimensional space, respectively. The word statistics information is formulated by setting as rows of the multidimensional vector set.

(2) set the word, the document, the word classification, or the document classification as a column of the real type random variable set, and associate the word with a random variable each having a real value to perform a row of the real type random variable set The word statistics information is formulated by setting as.

(3) The formalization method of the combined probability distribution includes the number of documents in which two words appear together for each word pair for the word, the number of documents in which both words do not appear, and the document in which the two words appear separately. Based on the number of word-word combinations, which are counts, a joint probability distribution of random variables corresponding to each word pair is generated to form the word statistical information. At this time, a corresponding probability probability distribution may exist for each word pair, and the random variable may be defined in an event space of rows and columns including only occurrences or non-occurrences of the word.

(4) A formalization method to a discrete random variable set sets the word as a column of a discrete random variable set to mean each independent event in the event space where a random variable is defined, and sets the word to mean a discrete random variable. The word statistics information is formalized by setting as rows of a random variable set. The discrete random variable may be generated using a crossover frequency, which is the number of documents in which the word appears like other words, and each frequency value of the discrete random variable set is one word (row) present in an arbitrary document. Corresponds to the probability that there are other words (columns) for.

The word association between the words is measured based on the standardized word statistical information. In this case, the multi-dimensional vector if set on the basis of the word statistics structured as, by calculating Im bus L _p, cosine coefficient, the expansion die coefficient, expanded jacquard coefficient, or correlation between the two vectors of the multi-dimensional vector set of the It can be measured as word association.

On the other hand, when based on the word statistical information formulated in the set of real-type random variable, it is possible to calculate the correlation coefficient or consistency for the two random variables of the real-type random variable set can be measured as the word association degree.

In addition, when based on the word statistical information formulated by the combined probability distribution, by using the combined probability distribution for the two random variables to calculate the jacquard coefficient, dice coefficient, odds ratio, mutual information or mutual information by event It can be measured as the word association.

Finally, in the case of the word statistical information formulated into the discrete random variable set, each word included in the column of the discrete random variable set is set as each independent event in the event space in which the random variable is defined, and the discrete random variable set Each word included in may be set as a discrete random variable, and the word association may be measured using the discrete random variable set.

As such, word frequency information is generated by measuring frequencies according to various features among words, documents, word classifications or document classifications associated with the document set, and the word statistical information is formalized using vectors, random variables, and combined probability distributions. By interpreting, it is possible to measure the numerical association of words with respect to the relationships between the words. In addition, by using the crossover frequency between the words as a set of discrete random variables, it is also possible to measure asymmetric word associations between the words.

The related keywords associated with the search keyword may be obtained based on the degree of association between the words measured through the word association measure.

In step S102, the information retrieval and interest keyword updating system classifies a category for each of the related keywords obtained in step S101. The method of classifying the category for each of the relevant keywords may include purchase data of an advertiser who purchases an ad word (hereinafter referred to as “advertiser data”) or search data of a user in a search engine or shopping site (hereinafter referred to as “user data”). Is called).

In this case, the category classification based on the advertiser data applies the principle that the same advertiser purchases the advertisement word of the same category. On the other hand, the category classification based on the user data applies a method in which a user inputs a search keyword through a search engine or a shopping site and designates the category most selected as the category of the corresponding word.

In step S103, the information retrieval and interest keyword updating system calculates a category association degree for the corresponding related keyword for the category classified for each related keyword in the step S102.

In this case, when the categories are classified by the advertiser data, 10 to 20 advertisement words are manually selected and input for each category, and all remaining advertisement words are assigned to a specific category according to the above principle. By calculating the probability of belonging can be calculated by the degree of association for each category.

On the other hand, when categorizing a category by the user data, the degree of relevance for each category may be calculated by calculating a probability that users select a specific category as a category of the search keyword from a search result for the search keyword.

In operation S104, the information retrieval and interest keyword updating system may determine an association category corresponding to the search keyword based on the degree of association for each category calculated in operation S103.

FIG. 2 is a diagram illustrating a related keyword and a category classification table as an example of a search keyword corresponding to a 'camera' to explain a process of classifying a category by a related keyword and calculating a category association degree.

As a word associated with a search keyword of the camera 201, a number of related keywords 202, such as a digital camera, a lens, a tripod, and a polaroid camera, may be determined according to the degree of association between words.

Then, the category 203 for each of the related keywords 202 is classified using the advertiser data or the user data. In this case, at least one category 203 exists for one related keyword 202, and each category has a probability, that is, an association degree 204, determined by the advertiser data or the user data.

For example, 'dica', a related keyword 202 of the camera 201, may be classified into categories 203 such as home appliances / cameras / digital cameras, home appliances / cameras / camera supplies, and the home appliances / cameras / digital cameras. The category of and the category of the home appliance / camera / camera article may have different associations 204 according to the advertiser data or the user data.

In this way, the category 203 is classified for each relevant keyword 202 corresponding to the camera 201, and the degree of association 204 of each classified category is calculated.

Subsequently, the category 203 classified for each of the relevant keywords 202 is added with the degree of association 204 for each category. According to Figure 2, by the same category, (1) home appliances / camera / digital camera = 0.8 + 0.2 + 0.10 = 1.10, (2) home appliances / camera / camera supplies = 0.15 + 0.1 + 0.7 = 0.95, (3) home appliances / Relevance of each category can be summed as camera / camera lens = 0.6.

The categories associated with the camera 201 may be understood to include home appliances / cameras / digital cameras, home appliances / cameras / camera supplies, home appliances / cameras / camera lenses.

In the step (S104), it is preferable to determine a category having the largest value of the sum of the related degrees as a related category of the search keyword.

In step S105, the information retrieval and interest keyword update system reads the keywords belonging to the related category determined in the step S104 and generates and provides the keywords belonging to the related category as a list of interest keywords for recommending to the user.

In step S106, when the information search and interest keyword update system selects a particular interest keyword from the interest keyword list provided in step S105, the information search and interest keyword update system provides at least one content related to the selected interest keyword.

3 is a user interface screen of an information search and interest keyword update system, and illustrates an example of a user interface screen for providing a content related to a keyword list of interest and a specific keyword of interest.

The user interface screen of FIG. 3 includes a received item 301, a user menu 302, a content display area 303 (304) 305, and an interest keyword list 306.

The received item 301 may include news, blogs, web pages, images, knowledge shopping, videos, book information, local information, and the like.

The user menu 302 is a menu configuration for directly changing or editing the layout of the user interface screen.

The content display areas 303, 304, and 305 mean areas for displaying content related to each of the received items. In this case, the content display area 303 displays content corresponding to knowledge shopping among the received items, and may provide a knowledge shopping list including a specific keyword of interest. The content display area 304 displays a content corresponding to a search advertisement among the received items, and may provide a related advertisement list including a specific keyword of interest. The content display area 305 displays a content corresponding to a web page among the received items and may provide a web page list including a specific keyword of interest.

The interest keyword list 306 includes a keyword updated based on the user's search keyword, and according to the interest keyword update method of FIG. 2, the interest keyword list 306 includes an interest keyword generated through a related category for the search keyword.

4 is a diagram illustrating an example of a user setting screen for setting a user environment for the user interface screen of FIG.

The user setting screen of Fig. 4 includes a keyword input menu 401, a list generation menu 402, a reception item selection menu 403, a reception type selection menu 404, and an update environment setting menu 405. do.

The keyword input menu 401 is a menu for inputting a keyword of interest, and the user directly interested in the keyword input menu 401 without selecting an interest keyword of the interest keyword list 306 provided on the user interface screen. You can also enter a keyword.

The list generation menu 402 is a menu for generating a keyword list of interest by selecting at least one keyword of interest, and the keyword list of interest is inputted directly through the keyword input menu 401 or as shown in FIG. A specific keyword of interest may be selected and configured from the keyword list of interest 306.

The reception item selection menu 403 is a menu for selecting a reception item exposed on the user interface screen. In this case, the reception items 301 and the content display areas 303, 304, 305 of the user interface screen of FIG. 3 are provided only for the reception items selected through the reception item selection menu 403.

The reception type selection menu 404 may include means for receiving the user interface screen of FIG. 3 including the interest keyword list 306 and the content display area 303, 304, 305 (eg, E-mail, Menu for selecting a website, a mobile terminal, etc.).

The update environment setting menu 405 is a menu for setting an update setting environment (automatic update or manual update) for the interest keyword list 306 and / or the content display areas 303, 304, 305.

When a user selects a specific interest keyword from the interest keyword list 306 on the user interface screen, the content display areas 303, 304, and 305 display content related to the selected interest keyword for each received item. In this case, the content display areas 303, 304, and 305 may be configured only for a reception item selected by the user through the reception item selection menu 403.

The content display areas 303, 304, and 305 may include related advertisements related to interest keywords selected by the user by default, wherein the related advertisements are knowledge shopping lists and / or related to the interest keywords. It may also include advertisements corresponding to the search advertisement list.

Meanwhile, a method of updating a keyword of interest using the latest log will be described in detail with reference to FIG. 5. 5 is a diagram illustrating the entire process of the method of updating a keyword of interest using the latest log.

In step S501, the information retrieval and interest keyword updating system records the recent keyword retrieval history of the user using the keyword retrieval service during the preset recent recording period. In this case, the recent keyword search history of the user includes a search keyword input by the user during the recent recording period and a search time in which the search keyword is input.

In step S502, the information retrieval and interest keyword updating system weights each search keyword recorded in the last recording period.

The search keyword weight may be defined as in Equation 1 below.

Where W is the weight, Ta is the last record period, Tb is the current time, and Tc is the search time.

According to Equation 1, it can be seen that the weight (W) for the search keyword increases as the search time becomes more recent. When the same keyword exists among the search keywords recorded in the recent recording period, it is preferable to add the weights for the same search keywords.

In step S503, the information retrieval and interest keyword updating system generates the search keyword recorded in the last recording period as the interest keyword list according to the weight given in step S502.

After the weight is given for each of the search keywords recorded in the latest recording period, the recorded search keywords are sorted in ascending order of weight. In this case, the search keywords may be selected and sorted according to the number of preset keywords constituting the keyword list of interest. For example, if the number of keywords in the keyword list of interest is set to 10, only 10 search keywords are selected in order of magnitude of the weight, and the keyword is generated as the keyword list of interest.

In this case, each time a search keyword is input from the user, the weight is calculated using Equation 2, and the interest keyword list is updated according to the calculated weight.

The recent recording period is changed at a predetermined unit time period, and the keyword search history corresponding to the changed recent recording period is recorded. When the unit time is set to 24 hours, it is preferable to change the latest recording period at 0 o'clock every day. For example, when the recent recording period is set to 3 days, the recent 3 days are changed once a day and the interest keyword list is updated using the search keywords of the 3 days.

In this way, the keyword list of interest may be automatically updated, and manually updated only when a user request is made.

In operation S504, the information retrieval and interest keyword update system provides a list of interest keywords generated in operation S503 through the user interface screen of FIG. 3 and selects a specific interest keyword from the interest keyword list. Provide at least one content related to a keyword of interest.

According to the user interest keyword updating method of FIG. 5, the interest keyword list 306 of the user interface screen is composed of interest keywords generated from the user keyword search history of the latest recording period.

The method of updating a user interest keyword according to the present invention may be implemented in the form of program instructions that can be executed by various computer means and recorded in a computer readable medium. The computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. Program instructions recorded on the media may be those specially designed and constructed for the purposes of the present invention, or they may be of the kind well-known and available to those having skill in the computer software arts. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tape, optical media such as CD-ROMs, DVDs, and magnetic disks, such as floppy disks. Magneto-optical media, and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine code generated by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like. The hardware device described above may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa.

An interest keyword update system for performing such a method of updating a keyword of interest of a user will be described. 6 is a diagram illustrating an internal configuration of a user interest keyword update system according to the present invention.

As illustrated in FIG. 6, the interest keyword update system 600 may include a user interface 601, an interest keyword generator 602, a content provider 603, and a recorder 604.

The user interface unit 601 includes input means for inputting a search keyword, selecting a keyword of interest, or setting a user environment, such as a reception item and a reception type, for a user interface screen providing content for the keyword of interest. do.

The interest keyword generation unit 602 generates an interest keyword list for recommending to the user based on the search keyword input through the user interface unit 601.

The content providing unit 603 provides at least one content related to the selected interest keyword when the user selects a specific interest keyword from the generated interest keyword list. The content providing unit 603 may provide content including a related advertisement corresponding to the selected keyword of interest by default, news, blog, web page, image, knowledge shopping, video, book information related to the keyword of interest, Content corresponding to a reception item selected by a user among local information may be provided.

The recorder 604 may store various contents for each keyword.

In detail, when generating an interest keyword by using the related category of the search keyword, the interested keyword generator 602 may include an associated keyword acquisition unit, a category classification unit, a category association degree calculator, and an interest keyword update unit. It may include.

The related keyword obtaining unit obtains at least one related keyword according to the degree of association between words, and includes word statistical information through a word included in a document set, a document, a word classification for the word, or a document classification for the document. And a word association measurer configured to measure word associations between the words based on the word statistics information acquirer, an attainer for shaping the word statistics information, and the at least one word statistical information. The formalization unit may format the word statistical information into a multidimensional vector set, a real type random variable set, a combined probability distribution of random variables, or a discrete random variable set.

The related keyword obtaining unit may acquire at least one word having a word association degree equal to or greater than a preset degree of association with respect to a search keyword based on the measured word association between the words, and use these words as a related keyword for the search keyword. .

The category classification unit classifies each of the related keywords obtained by the related keyword obtaining unit by category. This may be classified based on purchase data (advertiser data) of an advertiser who purchases an ad word or search data (user data) of a user in a search engine or a shopping site.

The category relevance calculator calculates a category relevance for each related keyword. In this case, when the categories are classified according to the advertiser data, 10 to 20 advertisement words are manually selected and input for each category, and all other advertisement words are one advertisement word based on the above principle. Can be calculated by calculating the probability belonging to a specific category. Meanwhile, when categorizing a category by the user data, the degree of association of each category may be calculated by calculating a probability that users select a specific category as a category of the search keyword from a search result for the search keyword.

The category relevance calculator calculates a category-related degree for each related keyword, and then adds the calculated degree of relevance for each same category.

The interest keyword updater determines a category having the highest correlation as the related category of the search keyword from the result of the category relevance calculator and generates a keyword belonging to the related category as the interest keyword list.

On the other hand, if a user wants to generate an interest keyword by using a recent log of the search keyword, the interest keyword generator 602 may include a recorder 604, a weight determiner, and an interest keyword updater.

The recorder 604 stores a search keyword and a search time input through the user interface 601 during a preset recent recording period.

The weight determining unit assigns a weight according to the search time to each of the search keywords stored during the recent recording period.

(여기서, W는 가중치, Ta는 최근 기록 기간, Tb는 현재 시간, Tc는 검색 시간)에 의해 산출할 수 있다. 상기 최근 기록 기간에 기록된 검색 키워드 중 동일 키워드가 존재할 경우 동일한 검색 키워드 별로 가중치를 합산한다.The weight according to the search time is a formula

(W is a weight, Ta is a recent recording period, Tb is a current time, and Tc is a search time). If the same keyword exists among the search keywords recorded in the latest recording period, the weights are added for each of the same search keywords.

The interest keyword updating unit selects a predetermined number of search keywords in order of the weights among the search keywords of the recent recording period and generates the selected search keywords as the interest keyword list.

Accordingly, the present invention can generate a list of interest keywords to be recommended to the user by using a related category corresponding to the user's search keyword or by using a recent log of the user's search keyword.

As described above, the present invention has been described by way of limited embodiments and drawings, but the present invention is not limited to the above embodiments, and those skilled in the art to which the present invention pertains various modifications and variations from such descriptions. This is possible.

Therefore, the scope of the present invention should not be limited to the described embodiments, but should be determined not only by the claims below but also by the equivalents of the claims.

1 is a diagram illustrating a process of updating an interest keyword using a related category as an example of a method of updating a user interest keyword according to the present invention.

FIG. 2 is a diagram illustrating a related keyword and a category classification table as an example of a search keyword corresponding to a 'camera' to explain a process of classifying a category by a related keyword and calculating a category association degree.

3 is a diagram illustrating an example of a user interface screen for providing content related to a specific keyword of interest.

4 is a diagram illustrating an example of a user setting screen for setting a user environment for the user interface screen of FIG.

5 is a diagram illustrating a process of updating an interest keyword using a latest log as another example of a method of updating a user interest keyword according to the present invention.

6 is a diagram illustrating a system configuration for performing a method of updating a keyword of interest of a user according to the present invention.

<Explanation of symbols for the main parts of the drawings>

600: Interest Keyword Update System

601: user interface unit

602: Interest keyword generation unit

603: content provider

604: register

Claims (29)

A user interface unit; An interest keyword generation unit including a related keyword acquisition unit, a category classification unit, a category association degree calculator, and an interest keyword update unit; In the user interest keyword update method of the user interest keyword update system composed of a content providing unit, Receiving a search keyword from a user in the user interface unit; Providing, by the interest keyword generator, a list of interest keywords to be recommended to a user who has entered the search keyword based on the input search keyword; Providing the list of keywords of interest may include: Acquiring at least one related keyword from the related keyword acquiring unit according to the degree of association of words with respect to the search keyword, and classifying the at least one category to which the related keyword belongs to each of the related keywords in the category classifier; And calculating a degree of association with the related keyword for each of the classified categories in the category association degree calculator, and summing the calculated degree of association for each of the same categories, and adding the sum in the interest keyword update unit. Determining the category with the highest correlation as the related category to which the search keyword belongs, and generating a keyword belonging to the determined related category as the interest keyword list. delete delete The method of claim 1, Calculating the degree of association with the related keyword, And calculating a probability that an advertisement keyword matching the related keyword belongs to a specific category by using the principle that the same advertiser purchases an advertisement keyword corresponding to the same category. The method of claim 1, Calculating the degree of association with the related keyword, Calculating a probability that users select a specific category as a category of the search keyword from a search result for the search keyword that matches the related keyword. delete The method of claim 1, Providing at least one content related to the selected interest keyword when the user selects a specific interest keyword from the interest keyword list in the content provider; How to update the user interest keyword further comprising. The method of claim 7, wherein Providing at least one content related to the keyword of interest, And a related advertisement corresponding to the keyword of interest by default. The method of claim 7, wherein Providing at least one content related to the keyword of interest, And at least one receiving item among news items, blogs, web pages, images, knowledge shopping, videos, book information, and local information related to the keyword of interest. The method of claim 7, wherein Providing at least one content related to the keyword of interest, And a received item preset from the user among received items including news, blog, web page, image, knowledge shopping, video, book information, and local information related to the keyword of interest. A user interface unit; Recording unit; An interest keyword generation unit including a weight determination unit and an interest keyword update unit; In the user interest keyword update method of the user interest keyword update system composed of a content providing unit, Recording a keyword search history for a search keyword input from a user through the user interface unit in the recording unit; Providing, by the interested keyword generator, a list of interested keywords to be recommended to a user who has entered the search keyword based on the recorded keyword search history; Recording the keyword search history, Store a search time for inputting the search keyword in association with the input search keyword during a recent recording period for recording the keyword search history, Providing the list of keywords of interest may include: In the weight determining unit, the latest recording is performed by a formula: W = 24 hours * Ta- (Tb-Tc), where Ta is the recent recording period, Tb is the current time to which the weight is given, and Tc is the search time. Assigning a higher weight to each of the search keywords stored in the period, and then adding the weighted values to the same search keywords for each of the search keywords stored in the period; Selecting a predetermined number of search keywords in order of magnitude of the weighted weights, and generating the selected search keywords as the interest keyword list. delete delete The method of claim 11, Providing the list of keywords of interest may include: Re-weighting the search keyword stored in the recent recording period each time a search keyword is input from the user in the weight determining unit; Rearranging the keyword list of interest based on the weighted value again by the keyword interested updating unit; How to update the user interest keyword further comprising. The method of claim 11, Recording the keyword search history, Updating the keyword search history of the changed recent recording period after changing the recent recording period at a unit time interval; How to update the user interest keyword further comprising. delete The method of claim 11, Providing the list of keywords of interest may include: And updating the interest keyword list according to user's setting. delete The method of claim 11, Providing at least one content related to the selected interest keyword when the user selects a specific interest keyword from the interest keyword list in the content provider; How to update the user interest keyword further comprising. The method of claim 19, Providing at least one content related to the keyword of interest, And a related advertisement corresponding to the keyword of interest by default. The method of claim 19, Providing at least one content related to the keyword of interest, And receiving at least one of a received item including news, blog, web page, image, knowledge shopping, video, book information, and local information related to the keyword of interest. The method of claim 19, Providing at least one content related to the keyword of interest, And a received item set by the user from among received items including news, blog, web page, image, knowledge shopping, video, book information, and local information related to the keyword of interest. Implementing the method of any one of claims 1, 4, 5, 7-11, 14, 15, 17, 19, 20-22. A computer-readable recording medium in which a program for recording is recorded. A user interface to receive a search keyword from a user; And An interest keyword generation unit configured to provide a list of interest keywords to be recommended to a user who inputs the search keyword based on the search keyword input through the user interface, The keyword of interest generation unit, A related keyword obtaining unit obtaining at least one related keyword according to the degree of association between words with respect to the search keyword; A category classification unit classifying at least one category to which the related keyword belongs, for each of the related keywords; A category association degree calculator configured to calculate an association degree with the corresponding keyword for each of the classified categories, and then add the calculated association degree by the same category; And an interest keyword updater configured to determine a category having the highest associated degree as the related category to which the search keyword belongs, and generate a keyword belonging to the determined related category as the interest keyword list. delete A recorder for recording keyword search details for the search keyword input from the user through the user interface; And, An interest keyword generation unit configured to provide a list of interest keywords to be recommended to a user who has entered the search keyword based on the keyword search history recorded in the recording unit; The keyword of interest generation unit, For each of the search keywords stored in the last recording period by W = 24 hours * Ta- (Tb-Tc), where Ta is the recent recording period, Tb is the current time weighted, and Tc is the search time. A weight determination unit for assigning higher weights as the search time is more recent and then summing the assigned weights for each of the same search keywords; A user interest keyword updater including an interest keyword updater configured to select a predetermined number of search keywords in order of magnitude of the sum of the weighted weights among the search keywords stored in the recent recording period and to generate the selected search keywords as the interest keyword list; system. The method of claim 24 or 26, Content providing unit for providing at least one content related to the selected keyword of interest when the user selects a particular keyword of interest in the list of interest keywords User interest keyword update system further comprising. The method of claim 27, The content providing unit, And a related advertisement corresponding to the keyword of interest by default. The method of claim 27, The content providing unit, User interest keyword update system, characterized in that it provides content for at least one of the received items including news, blogs, web pages, images, knowledge shopping, video, book information, local information related to the keyword of interest .

Images