KR101103671B1 - Method, system and computer readable recording medium for extracting the most relevant images dynamically and providing them responsive to users' request - Google Patents

Abstract

The present invention relates to a method, a system and a computer readable recording medium for extracting and providing a most suitable image dynamically in response to a user's query. To this end, the present invention comprises the steps of receiving a query about an image to be searched by the user from a user terminal device, searching for and finding an image group associated with the received query, in the order in which the images in the found image group are arranged And dynamically determining whether the matched query is completely matched, extracting a matched image when confirming a perfect match, and providing the extracted image to the user terminal device.

Image, matching, description, grouping

Description

TECHNICAL, SYSTEM AND COMPUTER READABLE RECORDING MEDIUM FOR EXTRACTING THE MOST RELEVANT IMAGES DYNAMICALLY AND PROVIDING THEM RESPONSIVE TO USERS 'REQUEST }

The present invention relates to a method, a system and a computer readable recording medium for dynamically extracting and providing a most suitable image in response to a user's query. More particularly, the present invention provides an image that meets a request received from a user. A method, system, and method for extracting an optimal image for each group and providing the user to the group by selecting a group by calculating an association with each image group and calculating a relationship with a user request among images corresponding to each group; A computer readable recording medium.

With the recent rapid spread of the Internet, it has become an indispensable necessity in modern life. Most users who use the Internet access the Internet through a browser and search for information through an Internet portal site. When a user enters a search word in the search box of the Internet portal, the Internet portal extracts various information corresponding to the search word from the database and provides the search result to the user. The extracted information is divided into categories such as dictionaries, knowledge information, blogs, cafes, specialty materials, sites, books, news, web pages, images, and videos, and delivered to the user for display.

Among the images, there are a lot of similar images, and users prefer search results of various images, so it is desirable to remove only the representative image and pass the remaining images to the user through duplicate judgment among extracted images. If all the images are processed in real time in the search request, satisfactory results may not be obtained due to the increase in the cost of the disk and the network and the increase in the search time.

Therefore, the images that can be searched by the user are searched in advance before the user's search request, and the same images are grouped and stored, and after the user actually inputs a search word, the images are quickly retrieved from the grouped images. In general, even if the same image is the same resolution and size, even if you try to group the same image to group the same image even if the Internet is rapidly spreading in recent years as the Internet is an indispensable necessity have. Most users who use the Internet access the Internet through a browser and search for information through an Internet portal site. When the user enters a search word in the search box of the Internet portal, the Internet portal extracts various information corresponding to the search word from the database and provides the search result to the user. The extracted information is displayed to users by dividing them into categories such as dictionaries, knowledge information, blogs, cafes, specialty materials, sites, books, news, web pages, images and videos.

Among the images, there are a lot of similar images, and users prefer search results of various images, so it is desirable to remove only the representative image and pass the remaining images to the user through duplicate judgment among extracted images. If all the images are processed in real time in the search request, satisfactory results may not be obtained due to the increase in the cost of the disk and the network and the increase in the search time.

Therefore, there is a method of quickly extracting the image from the grouped images when the user actually inputs a search word after grouping and storing the images, but in general, even the same image has different resolutions and sizes, thereby grouping the images together. There were disadvantages that were hard to do.

As an example of a solution to this drawback, after extracting a thumbnail (thumbnail of an image having a constant size and resolution) for each image, signature values are obtained from these thumbnails, and the derived signature values are compared and compared. I'm using a method to determine if images are the same image.

However, even when using this method, only one specific image of each image group is selected as a representative image. Sometimes, even if a user inputs a search term and a title, which are related to other images of the group, but not to the representative image, Representative images that are not associated are exposed to the user, and when comparing images, signature values extracted from thumbnails of images are compared so that if the images have different patterns, the signature values are identical and misread as the same image. In this case, there is a drawback that a completely different image can be exposed in this case.

An object of the present invention is to solve the above-mentioned problems of the prior art.

In addition, another object of the present invention is to extract and provide a most suitable image dynamically in response to a user's query within a preset group of images.

In addition, another object of the present invention is to minimize the search space and search time when extracting and providing an image corresponding to the query of the user by arranging the images in the order of reliability in the group and compressing the image information in the group.

The characteristic structure of this invention for achieving the objective of this invention as mentioned above, and achieving the effect peculiar to this invention mentioned later is as follows.

According to an aspect of the present invention, a method for providing an image most suitable for an image search query of a user on a communication network, the method comprising: receiving a query regarding an image to be searched by the user from a user terminal device; Searching and finding an image group associated with the query, and dynamically determining whether or not the image is matched with the received query in the order in which the images in the found image group are arranged, and extracting a matched image when confirming the perfect match; And providing the extracted image to the user terminal device.

According to another aspect of the present invention, in a system for providing an image most suitable for an image search query of a user on a communication network, means for receiving a query regarding an image to be searched by the user from a user terminal device. And means for searching for and finding a group of images associated with the received query, and dynamically determining whether to match the received query in the order in which the images in the found image group are arranged, and matching when confirming a perfect match. A system is provided that includes an image retrieval unit having means for extracting the extracted image, and means for providing the extracted image to the user terminal device.

As described above, according to the present invention, it is possible to provide an image extracted from the most accurate source to the user's query without being a duplicate image to the user searching for the image.

In addition, according to the present invention, it is possible to extract and provide the most suitable image dynamically in response to a user's query in a preset image group.

In addition, according to the present invention, it is possible to significantly reduce the likelihood that an image irrelevant to a query becomes a representative image and is provided to a user due to the same signature value even if it is another image.

Moreover, according to the present invention, the images are arranged and compressed in the order of reliability in a group, thereby minimizing the image retrieval memory and the retrieval speed.

DETAILED DESCRIPTION OF THE INVENTION The following detailed description of the invention refers to the accompanying drawings that show, by way of illustration, specific embodiments in which the invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the invention. It should be understood that the various embodiments of the present invention are different but need not be mutually exclusive. For example, certain features, structures, and characteristics described herein may be implemented in other embodiments without departing from the spirit and scope of the invention in connection with an embodiment. It is also to be understood that the position or arrangement of the individual components within each disclosed embodiment may be varied without departing from the spirit and scope of the invention. Accordingly, the following detailed description is not to be taken in a limiting sense, and the scope of the present invention is defined only by the appended claims, along with the full range of equivalents to which such claims are entitled. Like reference numerals in the drawings refer to the same or similar functions throughout the several aspects.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement the present invention.

[Preferred Embodiments of the Invention]

Complete system configuration

1 is a diagram schematically illustrating the overall configuration of a system for extracting and providing a most suitable image dynamically based on a query of a user, according to an embodiment of the invention.

As shown in FIG. 1, the entire system according to an exemplary embodiment of the present invention includes an image server 200 which stores a communication network 100, grouping images, and dynamically extracts an image most suitable for a user's query. ), A plurality of web servers 400 that search and provide contents (including images extracted from the image server 200) according to a user query received from the user terminal device 300 and the user terminal device 300. Can be.

First, the communication network 100 may be configured regardless of communication modes such as wired and wireless, and may include a local area network (LAN), a metropolitan area network (MAN), and a wide area network (WAN). Network). Preferably, the network referred to in the present invention may be a known World Wide Web (WWW).

According to an embodiment of the present invention, the image server 200 converts the images corresponding to the search object into thumbnails having a predetermined size and resolution, respectively, in order to quickly perform an image search suitable for a query input by the user. By comparing the extracted signature values, the same group of images having the same signature value may be performed.

In addition, according to an embodiment of the present invention, the image server 200 is the title of the same image, the file name, the original source of the image (meaning the source from which the image was retrieved, such sources, such as news, blogs, cafes, dictionaries Extracts information such as resolution, image registration date, etc., and processes the information into description information, and calculates and stores the reliability of each image by assigning a specific weight to each of the description information. To perform the function. In this case, the highest confidence image may be designated as the representative image of the corresponding image group.

Furthermore, according to an embodiment of the present invention, when the image server 200 receives an image search query of the user from the user terminal device 300 or the web server 400 through the communication network 100, description information and / or The reliability can be used to determine whether the user's query matches or to find and provide the most suitable image. In this case, the most suitable image can be found through various methods such as user preference resolution and user preference source, rather than matching with the user query.

On the other hand, the user terminal device 300 according to an embodiment of the present invention is a digital device including a function that allows a user to communicate after connecting to the web server 400 through the communication network 100, a personal computer ( For example, a user terminal device according to the present invention may be any digital device having a computing capability by mounting a microprocessor such as a desktop computer, a notebook computer), a workstation, a PDA, a web pad, a mobile phone, or the like. And may be adopted as 300. In addition, the user terminal device 300 may further include a web browser (not shown) program for allowing a user to request and receive content from the web server 400.

According to an embodiment of the present invention, the web server 400 communicates with the image server 200 and the user terminal device 300 through the communication network 100. For example, the web server 400 may be an operation server of an Internet search portal site. In this case, the web server 400 may include a web content search engine (not shown) to input a query keyword input by a user. After storing, the content corresponding to the query keyword may be searched, and the search result may be provided for the user to browse. The content provided as a search result may be various information about news, knowledge, games, communities, and the like. Of course, if necessary, the web content search engine may be included in a computing device or a recording medium that is physically different from the web server 400. In addition, although FIG. 1 illustrates that the image server 200 and the web server 400 are separately configured, the image search service is included in the content search service according to the needs of those skilled in the art for implementing the present invention. In addition, the image server 200 may be configured to be included in the web content search engine, or the image server 200 may be included in the web server 400.

Image Server Configuration

Hereinafter, the internal configuration of the image server 200 performing important functions for the implementation of the present invention and the function of each component will be described.

2 is a diagram illustrating in detail the internal configuration of the image server 200 according to an embodiment of the present invention. 2, an image server 200 according to an embodiment of the present invention includes an image grouping unit 210, an image searching unit 220, a communication unit 230, a control unit 240, and a database 250. It can be seen that the image grouping unit 210 can be again composed of the image processing unit 212, the image comparator 214, the representative image selection unit 216 and the like. According to an embodiment of the present invention, at least some of the image grouping unit 210, the image retrieving unit 220, the communication unit 230, the control unit 240, and the database 250 are a web server 400 and a web. Program modules communicating with at least one of a content search engine (not shown) and the user terminal device 300. Such program modules may be included in the image server 200 in the form of operating systems, application modules, and other program modules, and may be physically stored on various known storage devices. In addition, these program modules may be stored in a remote storage device that can communicate with the image server 200. On the other hand, such program modules include, but are not limited to, routines, subroutines, programs, objects, components, data structures, etc. that perform particular tasks or execute particular abstract data types, described below, in accordance with the present invention.

First, the image grouping unit 210 according to an embodiment of the present invention may perform a function of generating thumbnail, signature, and description data for all images that may be search targets of a user. In addition, the grouping function of reviewing the generated data, grouping the same images into one group, and selecting a representative image may be further performed. Hereinafter, the internal configuration of the image grouping unit 210 and the function of each component will be described with reference to FIG. 2.

More specifically, the image grouping unit 210 of the present invention may include an image processing unit 212, an image comparing unit 214, and a representative image selecting unit 216.

The image processing unit 212 according to an embodiment of the present invention searches for images that can be searched from a user from their respective sources, generates thumbnails and signatures for the corresponding images, and stores the generated data in a database ( 250) to save.

The image comparison unit 214 according to an embodiment of the present invention compares the signature values of the images stored in the database 250 to group images having the same signature value into each group and store related information in the database 250. Perform the function. In addition, the image comparison unit 212 may also perform a function of obtaining description data of each image and storing it in the database 250. In addition, the image comparison unit 214 may perform a function of calculating reliability using description data of each image.

Representative image selector 216 according to an embodiment of the present invention finds the image most likely to be searched by the user using the description data and / or reliability obtained by the image comparison unit 214 to represent the representative of the image group It selects an image and stores it in the database 250.

However, the image processing unit 212, the image comparing unit 214, and the representative image selecting unit 216 illustrated above are not limited to the above examples and perform a function, for example, the image comparing unit 214. Some of the functions performed by the user may be performed by the image processing unit 212 or the representative image selecting unit 216, or vice versa, variously designed by those skilled in the art. have.

Next, when the image search unit 220 according to an embodiment of the present invention receives a user's image search query, the image search unit 220 searches for the image groups stored in the database 250 and performs an image group associated with the user's query. And a function of dynamically finding and providing a most suitable image in the corresponding image group.

In addition, the communication unit 230 according to an embodiment of the present invention has a function to enable the image server 200 to communicate with devices such as the user terminal 300 and the web server 400 through the communication network 100. To perform.

In addition, the control unit 240 according to an embodiment of the present invention performs a function of controlling the flow of data between the image grouping unit 210, the image search unit 220, the communication unit 230 and the database 250.

Hereinafter, a detailed process of selecting a representative image through the representative image selecting unit 216 will be described according to an embodiment of the present invention.

Representative image selection

3 is a flowchart illustrating a series of processes for selecting a representative image in the image grouping unit 210 including the representative image selecting unit 216 according to an embodiment of the present invention.

According to FIG. 3, the image comparison unit 214 according to an embodiment of the present invention compares the signature values stored in the database 250 and bundles images having the same signature value into one group (S310). As mentioned above, the signature value is generated based on the thumbnail generated by the image processing unit 212 according to an embodiment of the present invention.

Next, the image comparison unit 214 generates description data from each of the images grouped into one group (S320). The description data may include, but is not limited to, an image title, a file name, an origin of an image, a corresponding Uniform Resource Locator (URL), a resolution, a registration date, and an author. Also, the description data of the image group may be stored in the database 250 as the description data of the image group except for the overlapping part of the description data of each extracted image for comparison with the user's search query.

Next, the image comparison unit 214 calculates the reliability of the images in the group by using the generated description data (S330). For example, if the original source is credible, such as news or a dictionary, you can calculate the reliability by giving higher weights to the original source, and lower weights to the original source if the credibility of the image is low, such as a personal blog or cafe. To calculate the reliability. In addition, if the morpheme extracted by parsing an image title and a file name among the description data, or an expression including the same is repeatedly present in the description data, a higher weight is given to the image title and / or file name of the corresponding image. The reliability can also be calculated. In addition, a method of giving a high weight to the resolution of the image having a high resolution or a high weight to the image registration date of the most recently registered image based on the image registration date can be considered. Thus, the final reliability can be expressed as the sum of the weighted values of each of the description data of each image.

However, the calculation method is only one example and vice versa, or a combination of the various conditions mentioned above, or the reliability may be calculated in various other ways. In addition, when description data of a plurality of images is the same, it may be determined that the same image is searched in duplicate, and the duplicate image may be removed in the group.

Based on the reliability calculated in the above manner, the representative image selecting unit 216 may arrange the images in the order of the reliability in each image group and select the most reliable image as the representative image (S340). . In addition, images with different description data in the near future can be placed at various distances by weighting them so that the reliability of the image having the largest difference with the description data is the same or almost similar. Images can be placed so that the query can be digested in a short time. Each image group in which images are placed can compress the image information in the group in order to perform the process of determining and providing a representative image dynamically according to a user's query in the future. The capacity is reduced, and the searching time can be shortened.

As shown above, Figure 3 is a representative image selection process according to an embodiment of the present invention, according to the needs or selection of those skilled in the art, the description of step S320 is generated in step S310 It may be replaced by extracting description data previously extracted from the image processing unit 212 and stored in the database 250. Also, when the image server finds a new image through a search, the representative image of the images may be replaced. In step S310, the signature values of the new images are obtained, and if the existing image group has the same signature value, the assigned image group is assigned to the corresponding image group. To find a lot of users (such as user queries or clicks) Various modifications and changes may be made, such as an implementation method of recalculating reliability at regular intervals by placing relevant description data items to confirm the image and weighting the reliability calculation in step S330.

Hereinafter, a method of providing a representative image dynamically determined according to a user's query will be described in detail.

Representative image decision

4 is an image search unit 220 according to an embodiment of the present invention dynamically searches for a representative image that best matches the query received from the user terminal device 300 and the search results to the user terminal device 300; A flowchart illustrating an example of a series of processes provided. Prior to FIG. 4, the image search unit 220 receives an image search query of the user from the user terminal device 300 or through the web server 400, and then parses the query if the query includes several words. Analyzes and transforms into morphemes that have meaning, or combinations thereof. Such parsing may be performed in advance through the web server 400, and the image retrieval unit may perform only a function of receiving a parsed image search query. Hereinafter, the form or query itself that has been transformed through parsing will be collectively referred to as an 'image search query'. In addition, the image search query is compared with description data of each image group stored in the database 250 to determine whether the image group is related to the user's image search query, and if relevant, within the image group. Dynamically start representative image search.

The image retrieval unit 220 first determines whether each element of the description data of the previously selected representative image and the image search query are completely matched, and when the representative image is perfectly matched, the process moves to step S460 (S410). .

If it is not matched completely in step S410, it is determined whether or not each element of the description data and the image search query is a perfect match in the order of the images listed in the order of reliability, and if there is an image that matches completely, the process moves to step S460. (S420).

If there is no image having a description data element that perfectly matches the image search query through the steps S410 and S420, it is determined whether or not each element of the description data of the image search query and the description data of the representative image partially matches and partially matches. If yes, the process moves to step S460 (S430). Here, the partial matching may mean whether some of the morphemes that have meaning in the parsed image search query are included in each element (image title, file name, etc.) of the description data of the representative image.

If there is no partial matching with the representative image in step S430, it is determined whether or not partial matching is performed in the order of reliability for the remaining images of the image group, and if there is an image of partial matching, the process moves to step S460 (S440). If not present, the existing representative image is provided (S450). Alternatively, in operation S450, an image may not be provided or a content of no matching image may be provided.

In operation S460, a matching image is provided through operations S410, S420, S430, or S440. Providing an image in steps S450 and S460 may mean providing image information to the user terminal device 300 indirectly or directly through the web server 400 through the communication network 100. Basically, it may include a URL, thumbnail, and source information of a matching image, but is not limited thereto.

Although FIG. 4 uses an example of a method of comparing a user's image search query with an image title to dynamically determine an image, the present invention is not limited thereto, and compares a user's preferred resolution with an image's resolution. To those with ordinary knowledge in the field of the present invention, such as by a method or by a user's preferred source (e.g., by searching for images extracted from the news if preferred) or by a combination of these methods. Various modifications and variations are possible accordingly.

In addition, although FIG. 4 illustrates an embodiment of dynamically extracting and providing a representative image in one image group, the procedure is performed for a plurality of groups when there are a plurality of image groups associated with an image search query. May be performed repeatedly, and the user may be provided with all or part of the plurality of extracted images.

5A and 5B are diagrams exemplarily illustrating web pages including image search results provided to a user terminal device 300 according to a user's prior art and the present invention.

Referring to FIG. 5A, it can be seen that the three images on the left are images that are grouped into the same image group having the same signature, and among them, the image is set as the representative image. According to the related art, once the representative image is determined once, since the same representative image is provided regardless of the user's image search query, sometimes an image having a title that does not fit the user's image search query at all is provided to the user ( According to the present invention, it can be seen that the same image is provided to the user by dynamically extracting an image having a source most suitable for the user's image search query (bottom right).

In addition, referring to 5b, the left three images have the same signature value in spite of being different images and are recognized as the same image. Therefore, the left three images are grouped into one image group, and the bottom image is set as the representative image. It can be seen that. According to the present invention, when different images are actually grouped into the same image group according to the same signature value, the wrong image may be provided to the user according to the user's image search query (upper right). Even if these erratic images are included in the same image group, it can be seen that they provide the best image for the user's image search query (bottom right).

Embodiments according to the present invention can be implemented in the form of program instructions that can be executed by various computer means can be recorded on a computer readable medium. The computer readable medium may include a program command, a data file, a data structure, 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 the computer-readable recording medium include magnetic media such as a hard disk, a floppy disk, and a magnetic tape; optical media such as CD-ROM and DVD; magnetic recording media such as a floppy disk; Includes hardware devices specifically configured to store and perform program instructions such as megneto-optical media and 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.

As described above, the present invention has been described by specific embodiments such as specific components and the like. For those skilled in the art to which the present invention pertains, various modifications and variations are possible.

Therefore, the spirit of the present invention should not be limited to the described embodiments, and all of the equivalents or equivalents of the claims as well as the claims to be described later will belong to the scope of the present invention. .

1 is a diagram schematically illustrating the overall configuration of a system for extracting and providing a most suitable image dynamically based on a query of a user, according to an embodiment of the invention.

2 is a diagram illustrating an internal configuration of an image server according to an exemplary embodiment of the present invention in detail.

3 is a flowchart illustrating a series of processes for selecting a representative image in an image grouping unit including a representative image selecting unit according to an embodiment of the present invention.

4 exemplarily illustrates a series of processes in which an image search unit dynamically searches for a representative image that best matches a query received from a user terminal device and provides the search result to the user terminal device according to an embodiment of the present invention. It is a flow chart.

5 is a diagram exemplarily illustrating a web page including an image search result provided to a user terminal device according to a user's prior art and the present invention.

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

100: network

200: image server

210: image grouping unit

212: image processing unit

214: image comparison unit

216: representative image selection unit

220: image search unit

230: communication unit

240: control unit

250: database

Claims (21)

delete In a communication network, a method for providing an image most suitable for a user's image search query, Receiving a query regarding an image to be searched by the user from a user terminal device; A second step of searching for and finding a group of images associated with the received query; A third step of dynamically determining a perfect match with the received query in the order in which the images in the found image group are arranged, and extracting a matched image when confirming a perfect match; And A fourth step of providing the extracted image to the user terminal device; The first step further comprises transforming the received query into a morpheme or a combination of morphemes that have meaning through parsing. In a communication network, a method for providing an image most suitable for a user's image search query, Receiving a query regarding an image to be searched by the user from a user terminal device; A second step of searching for and finding a group of images associated with the received query; A third step of dynamically determining a perfect match with the received query in the order in which the images in the found image group are arranged, and extracting a matched image when confirming a perfect match; And A fourth step of providing the extracted image to the user terminal device; Wherein the grouping of images in the group is performed in order of high reliability of the images. The method of claim 3, And said reliability is calculated as the sum of the weighted values of each element of the description data of said image. The method according to any one of claims 2 to 4, And the exact match is that at least one of the entirety of the received query and an element of description data the image has. The method according to any one of claims 2 to 4, In the third step, if there is no perfect match image, determining whether to partially match the received query in the order in which the images in the found image group are arranged, and extracting the matched image when confirming the partial match. How to include more. The method according to any one of claims 2 to 4, If a plurality of image groups associated with the received query are found, performing a third to fourth step on the plurality of image groups. In a communication network, a method for providing an image most suitable for a user's image search query, Receiving a query regarding an image to be searched by the user from a user terminal device; A second step of searching for and finding a group of images associated with the received query; A third step of dynamically determining a perfect match with the received query in the order in which the images in the found image group are arranged, and extracting a matched image when confirming a perfect match; And A fourth step of providing the extracted image to the user terminal device; And if the extracted image does not exist, extracting a preset representative image title and transmitting the extracted representative image title to the user terminal device. The method of claim 8, And wherein the predetermined representative image title is an image with the highest confidence in the image group. In a communication network, a method for providing an image most suitable for a user's image search query, Receiving a query regarding an image to be searched by the user from a user terminal device; A second step of searching for and finding a group of images associated with the received query; A third step of dynamically determining a perfect match with the received query in the order in which the images in the found image group are arranged, and extracting a matched image when confirming a perfect match; And A fourth step of providing the extracted image to the user terminal device; Grouping the images into one group of images having the same signature value; Generating description data from each image grouped into the one image group; Calculating reliability of the images using the generated description data; And Placing the images in order of reliability within the image group. A computer-readable recording medium having recorded thereon a computer program for executing the method according to any one of claims 2 to 4 and 8 to 10. delete In a communication network, a system for providing an image most suitable for a user's image search query, Means for receiving, from a user terminal device, a query about an image that the user wants to search; Means for searching for and finding a group of images associated with the received query; Means for dynamically determining a perfect match with the received query in the order in which the images in the found image group are arranged, and extracting a matched image when confirming perfect match; and An image search unit having means for providing the extracted image to the user terminal device; And said image query receiving means further comprises means for transforming said received query into a morpheme or a combination of morphemes that have meaning through parsing. In a communication network, a system for providing an image most suitable for a user's image search query, Means for receiving, from a user terminal device, a query about an image that the user wants to search; Means for searching for and finding a group of images associated with the received query; Means for dynamically determining a perfect match with the received query in the order in which the images in the found image group are arranged, and extracting a matched image when confirming perfect match; and An image search unit having means for providing the extracted image to the user terminal device; The grouping of images in the group is performed in the order of high reliability of the images. 15. The method of claim 14, And said reliability is calculated as the sum of the weighted values of each element of the description data of said image. The method according to any one of claims 13 to 15, The matching image extracting means is configured to determine whether to partially match the received query in the order in which the images in the found image group are arranged, if there is no perfect match, and to extract the matched image upon partial matching check. The system further comprises means. The method according to any one of claims 13 to 15, The exact match is a system in which at least one of the entirety of the received query matches an element of description data that the image has. The method according to any one of claims 13 to 15, When a plurality of image groups associated with the received query are found, The means for extracting the matched image may dynamically determine whether to match the received query in the order in which the images are arranged for each of the plurality of image groups, and extract the matched image for each image group upon confirming perfect match. , And the means for providing the extracted image to the user terminal device provides the extracted image for each of the plurality of image groups to the user terminal device. In a communication network, a system for providing an image most suitable for a user's image search query, Means for receiving, from a user terminal device, a query about an image that the user wants to search; Means for searching for and finding a group of images associated with the received query; Means for dynamically determining a perfect match with the received query in the order in which the images in the found image group are arranged, and extracting a matched image when confirming perfect match; and An image search unit having means for providing the extracted image to the user terminal device; And the means for providing the extracted image to the user terminal device extracts a preset representative image title when the extracted image does not exist and transmits the preset representative image title to the user terminal device. The method of claim 19, And the predetermined representative image title is an image of the highest confidence in the image group. In a communication network, a system for providing an image most suitable for a user's image search query, Means for receiving, from a user terminal device, a query about an image that the user wants to search; Means for searching for and finding a group of images associated with the received query; Means for dynamically determining a perfect match with the received query in the order in which the images in the found image group are arranged, and extracting a matched image when confirming perfect match; and An image search unit having means for providing the extracted image to the user terminal device; Grouping images having the same signature value into one group, generating description data from each image grouped into the one image group, calculating reliability of the images using the generated description data, and And an image grouping unit to arrange the images in order of reliability.

Images