KR20160123485A

KR20160123485A - Method and system for constructing database based on image, method and system for searching interested product and part using the same

Info

Publication number: KR20160123485A
Application number: KR1020150053545A
Authority: KR
Inventors: 이석준
Original assignee: 이석준
Priority date: 2015-04-16
Filing date: 2015-04-16
Publication date: 2016-10-26
Also published as: KR101761263B1

Abstract

The present invention relates to a method and a system for constructing a database based on an image, and a method and a system for searching interested products and parts using the same. Particularly, the present invention relates to a method for constructing a database based on an image which matches each image and keyword for products and parts and constructs a database for each group, inputs an image, searches interested products and parts, and provides a search result as a part group used for the interested parts or a product group related to the interested parts, a system thereof, a method and system for searching interested products and parts using the same. The system includes an image input part, a group setting part, and a storage part.

Description

TECHNICAL FIELD The present invention relates to an image-based database construction method and system, and a method and system for searching for a product of interest and a component of interest using the same.

The present invention relates to an image-based database construction method and system, and a method and system for searching for a product of interest and a component of interest using the method and system. More specifically, An image-based database construction method and system capable of inputting an image to search for a product or a part of interest, and to provide a product group related to a part of interest or a part of interest as a search result; And a method and system for searching for a part of interest.

Generally, as the IT industry and the Internet infrastructure develop, various information can be searched and acquired through various portal sites and search sites on the Internet. Portal sites and search sites use text-based search methods that are universally used and provide search results that match when users type certain keywords.

Also, in recent years, various researches have been conducted on a search service for outputting search results based on images. In this case, if the user inputs an image to search, matching images can be searched and provided.

On the other hand, in the case of a conventional search service based on a keyword, there is a problem that the accuracy of the search result is poor due to a difference in language or terms between information to be searched by a user and information stored on the Internet.

In addition, even in the case of a search service based on a conventional image, there is a problem in that it is difficult to obtain an accurate search result because it is searching an image on the Internet that matches features such as colors, textures, and shapes.

In particular, conventionally, when a user inputs a keyword or an image for a desired product to be searched and requests a search, not only accurate information on a product of interest but also information on parts used in a product of interest and manufacturer information There is no search service available at all.

Therefore, when a manufacturer of a product that manufactures a specific product or a manufacturer of a component that manufactures a specific part searches for a similar product or part, searches for a purchaser for sales of the manufactured part, or searches for a seller for purchase of the component , It is necessary to repeatedly input different keywords or images to acquire information. Therefore, it takes a lot of time for searching for information, and even if information is searched, accurate search results are not provided.

SUMMARY OF THE INVENTION The present invention has been conceived in view of the above-mentioned problems, and it is an object of the present invention to provide an information processing apparatus and a method of providing information on a product to be searched by a user, And an object of the present invention is to provide a system and method for searching for a target product and a target part using the same.

In addition, the present invention can build a database in which images and keywords for a product and a part are matched and stored in mutually dependent groups, in order to provide comprehensive information about a product of interest, parts used in the product of interest, The present invention relates to a method and system for constructing an image based database, and a method and system for searching for a target product and a target part using the same.

The objects of the present invention are not limited to the above-mentioned objects, and other objects not mentioned can be clearly understood by those skilled in the art from the following description.

According to an aspect of the present invention, there is provided a method of generating a product image, the method comprising the steps of: (1) inputting an image of a product, digitally coding the product image, (2) assigning a keyword associated with the product to the parent group, and storing the product image set as the parent group in the parent database cluster; (3) inputting an image of a component used in the product, digitally coding the image, and setting a coded component image to a subgroup dependent on the parent group; And (4) assigning a keyword associated with the part to the lower group, and storing the part image set as the lower group in the lower database cluster.

In a preferred embodiment, the step (2) sets product information including the kind, quantity, price and manufacturer of the product in the upper group, and stores the product information together with the product image in the upper database cluster.

In a preferred embodiment, the step (4) includes setting the part information including the kind of the part, the applicable product group, the quantity, the price and the manufacturer to the lower group and storing it in the lower database cluster together with the part image do.

In a preferred embodiment, the first (1) and the third (3) steps perform the digital coding using image processing including vector quantization.

According to another aspect of the present invention, there is provided an image processing apparatus comprising: an image input unit for receiving an image of a product or part; A group setting unit for setting a product image as a higher group and a lower group dependent on the higher group in case of a part image used in the product; And a storage unit configured to store the grouped images and to construct a database by setting respective associated keywords in the upper group and the lower group.

In a preferred embodiment, the image input unit performs image processing including vector quantization for the product image or the part image.

In a preferred embodiment, the storage unit stores the image of the parent group in a parent database cluster, and the image of the child group is stored in a child database cluster that is dependent on the parent database cluster.

In a preferred embodiment, the storage unit sets product information including a type, quantity, price, and manufacturer of the product in the upper group, and stores the product information together with the product image in the upper database cluster.

In a preferred embodiment, the storage unit sets part information including the applicable product group, kind, quantity, price, and manufacturer for the part in the lower group and stores the part information together with the part image in the lower database cluster.

Further, the present invention provides a method of manufacturing a product, comprising the steps of: (1) building a database storing product images and part images in a plurality of products and a plurality of parts used in each product in a higher group and a lower group subordinate to the higher group; (2) receiving a search image for a product of interest through user input; (3) after digitally coding the search image, comparing the coded search image with images stored in the database to search for a similar product or part; And (4) when a product image of the higher group is searched, providing a part image of a lower group dependent on the higher group together, and when a part image of the lower group is searched, And providing an image together with the image of interest.

In a preferred embodiment, the step (4) provides rankings according to similarity to the search images for the searched product images or part images, and provides each image in the order according to the ranking.

In a preferred embodiment, the step (3) derives a similar degree by comparing the continuity and the pattern of the code string with respect to the images stored in the database and the retrieved image.

In a preferred embodiment, the upper group and the lower group of the step (1) include product information including a type of product, a quantity, a price and a manufacturer, a type of the component, an applicable product group, a quantity, The parts information including the manufacturer is set in each group.

In a preferred embodiment, the step (4) provides the product information together when the product image of the parent group is searched, and provides the part information when the part image of the child group is searched.

In a preferred embodiment, a keyword corresponding to each product or each part is set in the upper group and the lower group of the step (1).

In a preferred embodiment, the step (2) further inputs a search keyword for a product of interest, and the step (3) compares the keyword of each group stored in the database with the search keyword to obtain a similar product or part Of the image.

In addition, the present invention provides a computer-readable recording medium storing a database for storing a product image and a part image in a plurality of products and a plurality of parts used in each product in a higher group and a lower group subordinate to the higher group, respectively; An interest product input unit for receiving a search image of a product of interest to be searched by a user; A similar product retrieval unit for retrieving an image of a similar product or part by comparing the retrieval image inputted from the interested product input unit with the product image and the part image stored in the database; And a similar product search unit, when a product image of the higher-level group is searched, a part image of a lower-level group subordinate to the higher-level group is provided together, and when a part image of the lower-level group is searched, And a search result providing unit for providing a product image of the upper group together with the search result.

In a preferred embodiment, the search result providing unit assigns rankings according to similarities to the search images, and provides each image in the order according to the ranking, with respect to the searched product image or part image.

In a preferred embodiment, the similar-product searching unit compares the search image and the images stored in the database with the continuity and pattern of the code string to derive a similar degree.

In a preferred embodiment, the higher-level group of the database further stores and stores product information including a product type, a quantity, a price, and a manufacturer, and the lower group stores the type of the component, the applicable product group, The part information including the manufacturer is further set and stored.

In a preferred embodiment, the search result providing unit provides the product information when the product image of the upper group is searched, and provides the part information when the sub-group image is searched.

In a preferred embodiment, a keyword corresponding to each product or each part is further set and stored in the upper group and the lower group of the database.

In a preferred embodiment, the interested product input unit is further configured to receive a search keyword for a product of interest, and the similar product search unit compares the keyword of each group stored in the database with the search keyword to obtain an image of a similar product or part .

According to the above-mentioned problem solving means, in the present invention, an image of a product or a part is input, a product image is set as a higher group, and in the case of a part image used in a product, the product image is set as a lower group subordinate to the higher group, It is possible to construct a database in which images and keywords for a plurality of products and a plurality of parts used in each product are matched and stored in mutually dependent groups, .

In addition, the present invention is characterized in that the present invention includes a database in which a product image and a part image are set as a parent group and a subgroup that is subordinate to the parent group, and when a search image for a product of interest is input from a user, When an image of a similar product or part is searched for by comparing with a part image, when a product image of a higher group is searched, a part image of a lower group subordinate to the higher group is provided together. When a part image of a lower group is searched It is possible to provide the product image of the upper group to which the sub-group belongs, so that the information of the product group to be used in the product of interest, the information of the product group to which the component of interest is applied, There is also an effect of providing more comprehensive information.

1 is a diagram for explaining a database building system according to an embodiment of the present invention;
2 is a diagram for explaining a detailed structure of a database;
3 is a diagram for explaining a database building method according to an embodiment of the present invention.
FIG. 4 illustrates a system for searching for a product of interest and a component of interest, according to an embodiment of the present invention. FIG.
5 is a diagram for explaining a network environment of a search system of a product of interest and a component of interest;
6 is a diagram for explaining a search system for a product of interest and a component of interest according to another embodiment of the present invention;
FIG. 7 is a diagram for explaining a method for searching a product of interest and a component of interest, according to an embodiment of the present invention; FIG.

It should be understood that the specific details of the invention are set forth in the following description to provide a more thorough understanding of the present invention and that the present invention may be readily practiced without these specific details, It will be clear to those who have knowledge.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to FIGS. 1 to 7, but the present invention will be described with reference to the portions necessary for understanding the operation and operation according to the present invention.

FIG. 1 is a view for explaining a database building system according to an embodiment of the present invention, and FIG. 2 is a view for explaining a detailed structure of a database.

1 and 2, a database building system according to an embodiment of the present invention includes an image input unit 110, a group setting unit 120, and a storage unit 130.

The image input unit 110 may be provided to receive and store an image of a product or part, and to receive a product image of a plurality of products and a part image of a plurality of parts used in each product.

In this case, the image input to the image input unit 110 may be an image of a product or a part directly captured, a design drawing, or a 3D modeling image. Preferably, the image input unit 110 may include a front, And an image obtained by photographing all six sides including the bottom. If there are a plurality of images for the same product or part, the same product group or the same part group can be set using the index and the tag.

In addition, the image input unit 110 digitally codes and stores a product image or a part image. Preferably, the image input unit 110 may be configured to perform digital coding using image processing including vector quantization. Accordingly, the image compression can be performed to minimize the storage capacity, and the code sequence and pattern analysis for each image can be efficiently performed.

Alternatively, the image input unit 110 may include a separate coding unit for performing the digital coding on the images input from the image input unit 110.

The group setting unit 120 is used to set a product image and a part image as separate groups. In the case of a product image, the group setting unit 120 sets the product image and the part image as a higher group, and in the case of a part image used in the product, To be set as a lower group.

That is, by the group setting unit 120, the product image and the part image are classified into a high-level group and a low-level group, and the groups are connected in a mutually dependent relationship.

Preferably, the images set by the group setting unit 120 as the upper group or the lower group may be images digitally coded through the above-described image processing.

The storage unit 130 is for storing images grouped by the group setting unit 120 and establishing a database. When storing the grouped images, the storage unit 130 sets respective associated keywords to the upper group and the lower group at the time of storing the grouped images And store it.

2, the storage unit 130 includes an upper database cluster 131 in which the image of the upper group is stored, a lower database cluster 131 in which the image of the lower group is stored, And a lower database cluster 132, which is the same.

Also, the storage unit 130 stores the image of the upper group, that is, the product image, in the upper database cluster 131, and the image of the lower group and the part image are stored in the lower database cluster 132 do.

At this time, the lower database may store a plurality of subgroups dependent on the upper group. For example, a plurality of parts 1 images for the part 1 used in a specific product are included in one lower group, 2 is included in another subgroup and is stored on the lower database.

In addition, keywords associated with products or parts are set and stored in each group. At this time, the storage unit 130 may be configured to analyze a product image or a part image to automatically set a keyword, or may be configured to set a keyword through user input. Preferably, the subgroups may include images of key components and their keywords, which are dependent on the images and keywords of each product.

The storage unit may further store product information and part information in the upper group and the lower group, respectively.

Here, the product information includes various information for describing the product, and may be information including, for example, the type, quantity, price, and manufacturer of the product. Also, in the case of the part information, it may be various information about the part, for example, information including the type of the part, the applicable product group, the quantity, the price and the manufacturer.

That is, a database construction system according to an embodiment of the present invention may be configured such that a product image of a plurality of products and a part image of a plurality of parts used in each product are displayed in a mutually dependent relationship in which keywords matching with respective images are set The databases stored in the upper database cluster 131 and the lower database cluster 132 as a group can be constructed.

3 is a diagram for explaining a database building method according to an embodiment of the present invention.

Referring to FIG. 3, a database building method performed in the database building system according to an embodiment of the present invention will be described. However, all the functions performed in the database building method shown in FIG. 3 are performed in the database building system described with reference to FIG. 1 and FIG. 2, so that all the functions described with reference to FIG. 1 and FIG. It should be noted that all the functions performed in the database building method according to the preferred embodiment of the present invention and described with reference to FIG. 3 are performed in the database building system according to the preferred embodiment of the present invention.

First, a product image for a product is received and digitally coded, and then the coded product image is set as a higher group (S110).

At this time, the product image can be received through the image input unit. Preferably, the image obtained by photographing all six sides including front, rear, left, right and top and bottom of the product is input. In addition, when the product image is input, the image input unit performs digital coding using image processing including vector quantization.

In addition, the coded product image is set as a higher group by the group setting unit, and the upper group is linked to the lower group images, which will be described later, in a dependent relationship.

Next, the product image set as the parent group is stored in the parent database cluster (S120).

At this time, the storage unit assigns the keyword associated with the product to the upper group, and then stores the image of the upper group, that is, the product image, in the upper database cluster.

In addition, the storage unit may store various information about the product in the upper group. In this case, the product information including the type, quantity, price, and manufacturer of the product may be stored.

Next, the component image of the component used in the product is input and digitally coded, and then the coded component image is set as a sub-group that is subordinate to the parent group (S130).

At this time, the image input unit receives the component image and performs digital coding, and the coded component image is set to the lower group by the group setting unit. In addition, a plurality of subgroups depending on the upper group may exist.

Next, the part image set as the lower group is stored in the lower database cluster (S140).

At this time, the storage unit assigns the keyword associated with the part to the lower group, and then stores the image of the lower group, that is, the part image, in the lower database cluster. In addition, a plurality of subgroups may exist in the lower database cluster.

In addition, the storage unit stores various information about the part in the lower group. At this time, information including the type of the part, the applicable product group, the quantity, the price, and the manufacturer can be stored as part information.

Meanwhile, steps S130 and S140 may be performed before performing steps S110 and S120. If there are a plurality of parts used in a specific product, steps S130 and S140 May be repeatedly performed.

In addition, the database building method according to an embodiment of the present invention can be implemented as a computer-readable code on a computer-readable recording medium. A computer-readable recording medium includes all kinds of recording apparatuses in which data that can be read by a computer system is stored. Examples of the computer-readable recording medium include a ROM, a RAM, a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like, and also implemented in the form of a carrier wave (for example, transmission over the Internet) . The computer readable recording medium may also be distributed over a networked computer system so that computer readable code can be stored and executed in a distributed manner.

FIG. 4 is a view for explaining a search system of a product of interest and a component of interest according to an embodiment of the present invention, FIG. 5 is a view for explaining a network environment of a search system of a product of interest and a component of interest, FIG. 5 is a diagram for explaining a search system for a product of interest and a component of interest according to another embodiment of the present invention. FIG.

4 to 6, the interested product search system 200 according to an embodiment of the present invention includes a database 210, an interested product input unit 220, a similar product searching unit 230, (240).

The database 210 stores information including images of a plurality of products and a plurality of parts used in each product. In particular, the database 210 stores a product image of a product and parts images of parts used in each product And a lower group subordinate to the upper group.

Preferably, the database 210 is configured to store the image of the upper group in the upper database cluster, and to store the image of the lower group in the lower database cluster that is dependent on the upper database cluster.

In the database 210, product information including product type, quantity, price, and manufacturer may be set and stored in the upper group for each product, and the type of component for each component, Part information including the product group, the quantity, the price, and the manufacturer can be set and stored in the lower group.

In addition, the database 210 stores not only images of products or parts but also keywords corresponding to each product or each part, and the keywords are set and stored in the upper group and the lower group, respectively. Preferably, the subgroups may be configured to include an image of major parts dependent on images and keywords of each product, and a keyword thereof.

Meanwhile, the database 210 may be constructed by a database building system or a database building method according to an embodiment of the present invention.

The interested product input unit 220 is for receiving a search image and a search keyword for a product of interest to be searched by a user, and is provided with a search image for a product of interest from a user client 10 connected via an Internet network or a wired or wireless communication network, And a search keyword.

In addition, the interested product input unit 220 may be provided to provide an interface for inputting a search image and a search keyword on the screen of the user client 10, and may include a text, a picture, a sound, The user client 10 may be provided in a web page to access the web page through a web browser or may be provided as a separate client file and installed in the user client 10 to provide the interface.

The similar product searching unit 230 is for searching images corresponding to the search image or the search keyword inputted from the interested product input unit 220. The similar product searching unit 230 searches the similar product searching unit 230 for the search image input from the interested product input unit 220, (210), and searches for similar products or parts.

The similar product searching unit 230 may search for similar products or parts by comparing the keyword of each group stored in the database 210 with the search keyword.

When the similar product searching unit 230 searches the database 210 for a similar product or part corresponding to the search image, the similar product searching unit 230 may digitally code the search image, To obtain a similar degree by comparing the continuity and pattern of the code string between the stored images.

At this time, conventionally known binarization algorithms and pattern matching algorithms may be applied to the process of comparing the code strings and patterns between images to derive a similar degree.

6, the similar product searching unit 230 not only searches the database 210, but also images corresponding to the search image or the search keyword input to the interested product input unit 220 on the Internet network May be provided.

For example, the similar product search unit 230 may search for images in a web page existing on the web or search for images in cooperation with an existing search engine 20. [ The similar product searching unit 230 may derive a search result through a method of crossing the text including the pattern and shape of the image and the related search word through the web page or the search engine 20. [

The search result providing unit 240 is for providing the search result searched by the similar product searching unit 230. The search result providing unit 240 searches for a similar product matching the search image or the search keyword on the screen of the user client 10, Or displays an image of the part as a search result.

In this case, when the product image of the upper group is searched in the similar product search unit 230, the search result providing unit 240 may search for a product image of the lower group subordinate to the upper group together with the searched product image .

On the contrary, when the similar product search unit 230 searches for the part image of the lower group, the search result providing unit 240 further provides the product image of the upper group to which the lower group belongs together with the retrieved part image do.

In addition, the search result providing unit 240 provides the product information corresponding to the searched product image together with each image, and also provides the part information corresponding to the searched part image. That is, the search result providing unit 240 may output not only the searched image but also various information including the type, price, and manufacturer of each product or each part as a search result.

Accordingly, the search result providing unit 240 not only provides an image matching with a search image or a search keyword that a user desires to search, but also provides an image of another group that has a dependency relation with a group of the searched image, A comprehensive information including the product of interest, the part used in the product of interest, the kind and manufacturer for the product of interest.

In addition, when providing the searched product image or part image as a search result, the search result providing unit 240 assigns ranking according to similarity with the search image and provides each image in the order according to the ranking .

At this time, the degree of similarity to the search image can be calculated by comparing the code string and the pattern between the images in the similar product searching unit 230 to derive a similar degree.

Meanwhile, the search result providing unit 240 assigns ranking according to similarity with the search image even when the search result is derived from the web page or the search engine 20 by the similar product search unit 230 And each image can be provided in the order according to the ranking.

6, the search result providing unit 240 stores a link to the image or text retrieved from the web page or the search engine 20 in the database 210, The similar product retrieving unit 230 may refer to the similar product retrieving unit 230 to retrieve the retrieval result. Preferably, in the case of an image or text retrieved through the Internet network, only the link is stored until agreement of the copyright is made.

Accordingly, the desired product search system 200 according to an exemplary embodiment of the present invention can search for a desired product using the database 210, which stores images and keywords corresponding to products and parts, As well as information about the product family that can be used in the product of interest and information about the product family to which the component of interest is applied.

7 is a view for explaining a method of searching for a product of interest and a component of interest according to an embodiment of the present invention.

Referring to FIG. 7, a method of searching for a product of interest and a component of interest, which is performed in a search system for a product of interest and a component of interest, according to an embodiment of the present invention will be described. However, since the functions performed in the method of searching for a product of interest and the component of interest shown in FIG. 7 are all performed in the searching system of a product of interest and a component of interest described with reference to FIGS. 4 to 6, 6 are performed in a method of searching for a product of interest and a component of interest according to a preferred embodiment of the present invention, and all the functions described with reference to FIG. 6 are performed in accordance with a preferred embodiment of the present invention And in the search system of the parts of interest.

First, a database is established for a plurality of products and a plurality of parts used in each product (S210).

At this time, in the database, a product image of a product and a part image of a product are set and stored as a higher group and a lower group subordinate to the higher group, respectively. Preferably, the upper group and the lower group include product information including a kind, a quantity, a price, and a manufacturer for each product, part information including a type for each part, applicable product group, quantity, And a keyword corresponding to each product or each component can be set.

In addition, the process of building the database may be performed by performing a database building system or a database building method according to an embodiment of the present invention.

Next, according to the user input inputted from the user client, the search image and the search keyword for the product of interest are inputted (S220).

At this time, the interested product input unit may receive the search image and the search keyword from the user client connected through the Internet network or the wired or wireless communication network.

Next, an image matching the search image or the search keyword is searched in the database (S230).

At this time, the similar product search unit digitally codes the search image, and then searches for a similar product or part by comparing the coded search image with the images stored in the database. Preferably, the similar product search unit may derive similarity by comparing the continuity and pattern of the code string between the retrieved image and the images stored in the database.

If the search keyword is input, the similar product search unit may search for an image of a similar product or part by comparing the keyword of each group stored in the database with the search keyword.

On the other hand, the similar product search unit may search the images corresponding to the search image or the search keyword on the Internet network.

Next, the search result for the search image or the search keyword is provided to the user client (S240).

At this time, in the search result providing unit, when a product image of the upper group is searched, a part image of a lower group dependent on the upper group is provided together (S241), and when a part image of the lower group is searched, Together with the product image of the parent group to which the group belongs (S242).

Preferably, the search result providing unit is configured to compare the continuity and the pattern of the code string between the search image and the images stored in the database in the similar product search unit to rank the searched product image and the part image according to the degree of similarity And outputs the retrieved images as a search result in the order according to the ranking.

The search result providing unit may provide product information or part information corresponding to each image as a search result.

Thus, the user can obtain comprehensive information including information about a group of parts that can be used in a product of interest and information about a product group to which a component of interest is applied, including an image of a product or parts of interest.

Meanwhile, the method of searching for a product of interest according to an embodiment of the present invention can be implemented as a computer-readable code on a computer-readable recording medium. A computer-readable recording medium includes all kinds of recording apparatuses in which data that can be read by a computer system is stored. Examples of the computer-readable recording medium include a ROM, a RAM, a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like, and also implemented in the form of a carrier wave (for example, transmission over the Internet) . The computer readable recording medium may also be distributed over a networked computer system so that computer readable code can be stored and executed in a distributed manner.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed embodiments, but, on the contrary, is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the invention.

110: Image input unit
120: Group setting section
130:
210: Database
220: Interested product input section
230: Similar product search department
240: Search result providing service

Claims

(1) inputting an image of the product, digitally coding the image, and setting the coded product image as a higher group;
(2) assigning a keyword associated with the product to the parent group, and storing the product image set as the parent group in the parent database cluster;
(3) inputting an image of a component used in the product, digitally coding the image, and setting a coded component image to a subgroup dependent on the parent group; And
(4) assigning a keyword associated with the part to the subgroup, and storing the part image set as the subgroup in a subordinate database cluster.

The method according to claim 1,
Wherein the step (2) includes setting the product information including the kind, quantity, price, and manufacturer of the product in the upper group and storing the product information together with the product image in the upper database cluster. How to build.

The method according to claim 1,
The step (4) may include setting the part information including the kind of the part, the applicable product group, the quantity, the price and the manufacturer to the lower group and storing the part information together with the part image in the lower database cluster How to build an image-based database.

The method according to claim 1,
Wherein the step (1) and the step (3) perform the digital coding using image processing including vector quantization.

An image input unit for receiving and storing images of products or parts;
A group setting unit for setting a product image as a higher group and a lower group dependent on the higher group in case of a part image used in the product; And
And a storage unit configured to store the grouped images and to construct a database after setting respective associated keywords in the upper group and the lower group.

6. The method of claim 5,
Wherein the image input unit performs image processing including vector quantization for the product image or the part image.

6. The method of claim 5,
Wherein the storage unit stores the image of the upper group in an upper database cluster and the image of the lower group in a lower database cluster that is dependent on the upper database cluster.

8. The method of claim 7,
Wherein the storage unit sets product information including a type, a quantity, a price, and a manufacturer for the product in the upper group, and stores the product information together with the product image in the upper database cluster.

8. The method of claim 7,
Wherein the storage unit stores, in the lower database cluster, part information including a applicable product group, kind, quantity, price, and manufacturer for the part, in the lower group and together with the part image, in the lower database cluster. Building system.

(1) building a database for storing a product image and a part image in a plurality of products and a plurality of parts used in each product in a higher group and a lower group subordinate to the higher group, respectively;
(2) receiving a search image for a product of interest through user input;
(3) after digitally coding the search image, comparing the coded search image with images stored in the database to search for a similar product or part; And
(4) When a product image of the higher group is searched, a part image of a lower group dependent on the higher group is provided together. When a part image of the lower group is searched, a product image The method comprising the steps of: providing an image-based interest product;

11. The method of claim 10,
Wherein the step (4) further comprises the step of assigning rankings according to a degree similar to the search image to the searched product images or part images, and providing the images in the order according to the rankings. How to search for parts of interest.

11. The method of claim 10,
Wherein the step (3) comprises comparing the continuity and the pattern of the code string with respect to the search image and the images stored in the database to derive a similar degree.

11. The method of claim 10,
Wherein the upper group and the lower group of the step (1) include product information including a product type, a quantity, a price and a manufacturer, and part information including a type of the component, applicable product group, quantity, Is set for each group. &Lt; Desc / Clms Page number 17 >

14. The method of claim 13,
Wherein the step (b) includes providing the product information when the product image of the upper group is searched, and providing the part information when the sub-group image is searched. How to search for products and parts of interest.

11. The method of claim 10,
Wherein a keyword corresponding to each product or each part is set in the upper group and the lower group of the step (1).

16. The method of claim 15,
The step (2) further receives a search keyword for a product of interest,
Wherein the step (3) comprises comparing the keyword of each group stored in the database with the keyword to search for an image of a similar product or part.

A database for storing a product image and a part image in a plurality of products and a plurality of parts used in each product in a higher group and a lower group subordinate to the higher group;
An interest product input unit for receiving a search image of a product of interest to be searched by a user;
A similar product retrieval unit for retrieving an image of a similar product or part by comparing the retrieval image inputted from the interested product input unit with the product image and the part image stored in the database; And
Wherein when a product image of the higher group is searched from the similar product search unit, a part image of a lower group dependent on the higher group is provided together, and when a part image of the lower group is searched, And a search result providing unit that provides a product image of the group.

18. The method of claim 17,
Wherein the search result providing unit provides rankings according to similarities to the search images and provides each image in the order of ranking according to the searched product image or part image, Of the search system.

18. The method of claim 17,
Wherein the similar product searching unit compares the search image and the images stored in the database with the continuity and pattern of the code string to derive a similar degree.

18. The method of claim 17,
Product information including a kind, a quantity, a price and a manufacturer of a product is further set and stored in the upper group of the database, and the lower group stores part information including the type of the component, applicable product group, quantity, Is set and stored.

21. The method of claim 20,
Wherein the search result providing unit provides the product information when the product image of the upper group is searched and provides the part information when the sub-group image of the lower group is searched. Search system of parts of interest.

18. The method of claim 17,
Wherein a keyword corresponding to each product or each part is further set and stored in the upper group and the lower group of the database.

23. The method of claim 22,
Wherein the interested product input unit is further configured to receive a search keyword for a product of interest,
Wherein the similar product search unit searches for an image of a similar product or part by comparing the keyword of each group stored in the database with the search keyword.