KR20220063658A - Automated Technology-Based Personalized Advertising System and Methods - Google Patents

Abstract

The present invention relates to a personalized advertisement system and method using semantic technology and ontology, which analyzes a searcher's propensity when the searcher performs search on the web to display personalized search results and personalized advertisements according to the propensity. According to the present invention, the system comprises: a webpage collection module; an index database; an indexing module; a search engine searching the index database according to input keywords to output search results; a user database; a propensity analysis module analyzing the propensity of the webpage selected by the user from the search results provided by the search engine to shows the user's search propensity in real-time and managing the propensity cumulatively in the user database; an advertisement database classifying and storing advertisements according to the propensity; an advertisement module receiving the user's propensity information from the propensity analysis module to search the advertisement database and provide personalized advertisements of the corresponding propensity; and a user interface module identifying the user connected through the Internet, storing the user information in the user database to manage the users, outputting the personalized search results by reflecting the user's propensity when the search results of the search engine are output to the user, and at the same time, providing the personalized advertisements transferred from the advertisement module.

Description

Automated Technology-Based Personalized Advertising System and Methods

The present invention relates to advertisement technology of a web document search system, and more particularly, to a searcher's

Using semantic technology and ontology that analyzes scents and shows personalized search results and personalized advertisements according to preferences

It relates to a personalized advertising system and method.

In general, typical search sites such as Google, Naver, Dreamwiz, Daum, and Yahoo provide website information

Database for classification and storage according to criteria, and new website information while continuously traversing the web

A search robot to collect systematically, a user who uses the search site by converting the collected data into a database

It consists of a search engine that allows users to search for gold. When a search site user enters a keyword, the search engine

It provides a list of sites similar to the keyword by searching the base.

<3> FIG. 1 is a diagram showing the overall structure of a general search system.

<4> Referring to FIG. 1 , the Internet search engine is configured to enable a search for documents existing on the web.

As an information retrieval system, it can be broadly divided into data collection (S1), index (S2), and search (S3) parts. In the data collection (S1) part

is a document collection program (12) called spiders, crawler, etc. based on link information on the World Wide Web

(www) collects web documents stored in computers all over the world connected to the network 11 and provides a database (1)

3) is saved in

<5> In the index (S2) part, the index of web documents collected to speed up the search and reduce the amount of data to be stored

(index) information is stored in the index database 16 . And in the search (S3) part, the searcher 17 wants

Each time information is input, index information stored in the database 16 is searched, and the order determined by each search engine 18

According to the ranking system 20, the ranking of the search results is determined, and the search results according to the ranking are presented to the searcher 17.

ball At this time, the search engine 18 executes the spider program 12 through the spider control 19 to improve the performance of the search.

control, and the index module 14 and the analysis module 15 analyze the collected web documents to process indexing.

<6> These Internet search engines are classified into a directory search engine, a keyword search engine, and a meta search engine according to the search method.

is split The keyword search engine collects web documents by a web document collection program and indexes the collected documents.

It is stored in the database of the search engine and searches for the desired information by keyword matching for the user's query.

all.

In the conventional web document search using an Internet search engine, processing results are shown to a large number of searchers in the same way.

Because of this, there is a problem in that it cannot reflect the differences in dispositions according to individuals.

<8> The present invention has been proposed to solve the above problems, and an object of the present invention is to search

The semantic technology and ontology that show personalized search results and personalized advertisements

It is to provide a personalized advertising system and method for use.

In order to achieve the above object, the system of the present invention includes: a web page collection module for collecting web documents; index

database; Indexing to classify the web pages and store them in the index database for easy retrieval

module; a search engine that searches the index database according to the input keyword and outputs a search result; user day

turbo base; It analyzes the propensity of the web page selected by the user from the search results provided by the search engine, and analyzes the user’s

a propensity analysis module for displaying a search propensity and accumulatively managing the user database; Advertisements according to your preferences

Advertisement database that is stored in the same manner; an advertisement module receiving the user's disposition information from the disposition analysis module, searching the advertisement database, and providing personalized advertisements of the corresponding disposition; and users connected through the Internet.

separate, manage users by storing user information in the user database, and search results of the search engine

When outputting a result to a user, a personalized search result is output by reflecting the user's propensity, and at the same time, the advertisement

and a user interface module that provides a personalized advertisement delivered from the module.

<10> In order to achieve the above object, the method of the present invention comprises the steps of: constructing an advertisement database classified by tendency;

When a user connects, it identifies the connected user and determines whether the user is registered in the user database.

step; If the user is accessing for the first time, create an account to manage the user and then open the search bar to the user.

providing a search result when a user inputs a keyword and executes a search; Users in the search results

When a user selects a web page from the web page, the user's selection information is recorded as a log and the web page is retrieved.

analyzing the propensity of; If a user searches again or has previously accessed, the user's previous disposition

retrieving information and searching the advertisement database to select a personalized advertisement suitable for a user's disposition; and

If the user searches again or has accessed before, the user's previous propensity information is retrieved and the user's

A step of providing a personalized search result and the personalized advertisement by reflecting the color tendency

all.

According to the present invention, after analyzing in real time the tendency of web pages selected by the searcher from the search results, cumulative management

It provides the search history of color characters as log information and provides real-time analysis of search tendencies to efficiently search

can be processed with In addition, when providing search results to users, the user's preference

By providing personalized advertisements that reflect search results and user preferences in the field, advertising efficiency can be greatly improved.

The present invention and the technical problems achieved by the practice of the present invention are in the preferred embodiments of the present invention described below

will become clearer by The following examples are merely illustrative to illustrate the present invention,

It is not intended to limit the scope of the invention.

<13> FIG. 2 is a block diagram showing the overall configuration of a personalized advertisement system according to the present invention.

<14> As shown in FIG. 2, the personalized advertisement system 120 according to the present invention includes a web page (document) collection module 121 and an index.

sing module 122, index database 123, search engine 124, user interface module 125, propensity analysis module 126,

User database 127, advertisement module 128, advertisement database 129 is composed of a user connected through the Internet (102)

It provides a personalized search and advertisement service to the users (110).

2, the web page collection module 121 collects web documents on the Internet 102, and the indexing module 122

The collected web pages are classified and stored in the index database 123 for easy retrieval. The search engine 124

A search result is provided by searching the index database 123 according to the input keyword.

<16> The user interface module 125 identifies a user connected through the Internet 102, and stores user information in the user database.

Manage users by storing them in the es (127). And by interworking with the propensity analysis module 126, the user's search propensity information

management and outputting search results to the user 110, reflecting the user's propensity to display search results and personalized advertisements

try The propensity analysis module 126 is a search result provided by the search engine 124 when the user 110 enters a keyword to search.

It analyzes the tendency of the web page selected by the user in the department and shows the user's search tendency in real time, as well as the cumulative view

Thus, the search propensity for each user is identified and stored in the user database 127 .

<17> In the advertisement database 129, various advertisements are classified and stored according to inclinations, and the advertisement module 128 provides search results.

When displaying , the searcher's propensity information is received from the propensity analysis module 126, and the advertisement database 129 determines the corresponding propensity.

By extracting a suitable advertisement, as shown in FIG. 6 , a personalized advertisement 62 along with a personalized search result 61 is displayed.

to provide.

<18> FIG. 3 is a flowchart illustrating a procedure of a personalized advertisement method according to the present invention, and FIG. 4 is a personalized search screen according to the present invention.

, and FIG. 5 is an example of a screen in which a user's tendency is analyzed according to the present invention.

<19> Referring to FIG. 3 , the user interface module 125 of the advertisement system identifies the connected user when the user 110 is connected.

Thus, it is determined whether the user is registered in the user database 127 (S301, S302). User identification may be identified by using the IP information of the accessor or by assigning an ID to each user.

<20> When the user 110 is the first access, an account (management area) for managing the user is created, and then the search bar is provided to the user.

to provide (S303, S304). As shown in Fig. 4, when the user enters a keyword into the search bar and executes a search, the advertisement

The system provides search results and advertisements (S305, S306). At this time, in the case of first access, the user's tendency cannot be known.

Search results are provided in the usual way.

After <21>, when the user selects a web page from the search results, the user's selection information is recorded as a log and

The tendency analysis module 126 of the Go system 120 fetches the corresponding web page and analyzes the tendency of the web page (S307, S308). this

When the web page propensity analysis is performed after extracting words from the web page (document) selected by the user,

The propensity is determined by accumulating scores for each propensity of the extracted word by comparing it with the word in the propensity database. On the other hand, collected

In the case of storing web pages in the index database 123 by analyzing the tendency in advance, the tendency analysis model

The module 126 does not perform a separate disposition analysis, but quickly performs disposition based on the directory information of the web page selected by the user.

can be identified.

<22> The analysis results are accumulated and stored in the log area of the corresponding user or the management area of the database (S309).

<23> And when the user selects the real-time tendency display, as shown in FIG. 5, the real-time

The analysis result is displayed in the form of a pie graph or web page log information selected by the user.

(S310, S311).

<24> On the other hand, if the user searches again or has accessed before, retrieve the user's previous tendency information and search

When the user enters a keyword and executes a search, as shown in FIG. 6, the personalized

A search result 61 and a personalized advertisement 62 are provided (S314 to S316). For example, if the previous search tendency was in the cultural field, many

Among the search results, search results and advertisements in the cultural field are shown first, and search results and advertisements in other fields are shown later.

give. In addition, it is desirable to show the displayed amount of the search results in proportion to the user's tendency, for example, the user's

If the color orientation is cultural 40%, economics 20%, science 20%, social 10%, other 10%, it is the same among the web pages of the search results.

Culture 40%, economy 20%, science 20%, society 10%, other 10%.

After <25>, when the user selects a web page, the user's selection information is recorded as a new log, and the

After the flavor analysis module 126 fetches the web page and analyzes the tendency of the web page, the user's previous tendency is analyzed in real time.

It is updated and the analysis result is stored in the log area of the corresponding user or the management area of the database (S307 ~ S309). and buy

When the user selects the display of real-time tendency, the user's tendency updated in real time is shown as shown in FIG. 5 (S310, S311).

When the search is completed, log information and propensity information are stored in the corresponding user database 127 and then terminated (S312, S313).

<26> In the above, the present invention has been described with reference to one embodiment shown in the drawings, but those of ordinary skill in the art

It will be understood from this that various modifications and equivalent other embodiments are possible.

Claims (4)

a web page collection module that collects web documents;
index database;
an indexing module for classifying the web pages and storing them in the index database for easy retrieval;
a search engine that searches the index database according to the input keyword and outputs a search result;
user database;
The user's search propensity is analyzed in real time by analyzing the propensity of the web page selected by the user from the search results provided by the search engine.
a propensity analysis module for showing and accumulatively managing the user database;
an advertisement database for classifying and storing advertisements according to inclinations;
Personalization of a corresponding tendency by receiving the user's tendency information from the tendency analysis module and searching the advertisement database
an advertisement module that provides an advertisement; and
Identifies users connected through the Internet and manages users by storing user information in the user database
In addition, when outputting the search results of the search engine to the user, the search results personalized by reflecting the user's tendency
A user interface module for outputting results and simultaneously providing the personalized advertisement delivered from the advertisement module;
Personalized advertisement system using semantic technology and ontology, characterized in that. According to claim 1, wherein the index database is classified into a directory according to the tendency of the web page, the web page is stored
is decorated,
The propensity analysis module is semantic, characterized in that the user determines the propensity based on the directory information of the web page selected by the user.
Personalized advertising system using technology and ontology. According to claim 1, wherein the tendency analysis module
After extracting a word from the web page selected by the user, the extracted word is combined with the word in the pre-built propensity database
Semantic technology and ontology, characterized in that the propensity is determined by accumulating the scores for each propensity of the words extracted by comparison
Personalized advertising system using constructing an advertisement database classified by propensity;
When a user connects, it identifies the connected user and determines whether the user is registered in the user database.
step;
When a user accesses for the first time, a search box is provided to the user after creating an account to manage the user, and
providing a search result when a search is executed by entering a self-keyword;
When the user selects a web page from the search results, the user's selection information is recorded as a log and the corresponding web page
Analyzing the tendency of the web page by importing the easy;
If the user searches again or has previously accessed the advertisement, the user's previous disposition information is retrieved and the advertisement
selecting a personalized advertisement suitable for a user's disposition by searching a database; and
If the user searches again or has accessed before, the user's previous propensity information is retrieved and the user's
and providing a personalized search result and the personalized advertisement by reflecting the color tendency.
A personalized advertising method using semantic technology and ontology.