KR20190024503A - Method for forecasting machine industry trend based on search frequency and system thereof - Google Patents

Abstract

Provided is a method for forecasting a machine industry trend performed in a server receiving a search word for machine equipment from a client connected through a network. According to one embodiment of the present invention, the method may comprise the steps of: receiving a search word from a client terminal to collect a search result for corresponding machine equipment in a machine equipment database; generating logs based on the collected search result; filtering the generated logs; deriving a result value for machine industry by the filtering; and forecasting a trend for the machine industry based on the result value.

Description

TECHNICAL FIELD The present invention relates to a method for predicting a machine industry trend based on a search frequency,

The present invention relates to a method and system for predicting machine industry trends based on search frequency.

Currently, most of the machinery companies in Korea are operated offline, and they are not registered online. Therefore, overseas buyers are having difficulty in searching for and purchasing machines manufactured and sold domestically.

Also, there was no way for overseas buyers to be assured of quality when purchasing used machines sold in the country.

In addition, there has been an attempt to database information of machine manufacturers and machine products existing in the country, but there were difficulties in inputting them into the database due to the different formats.

In addition, there has been a problem that it is difficult to predict the machine-related demand of overseas buyers in the present system.

In addition, in the case of a conventional B2B site, since the information registered on the site can be searched and confirmed by the seller and the buyer, the seller can not perform the target marketing and the foreign buyer can not provide customized information.

In order to solve the above problems, the present invention provides a method for predicting machine industry trends based on a search frequency on a network.

A method for receiving a purchase request for a used machine from a client connected through a network according to an embodiment of the present invention and executing the same on a server for purchasing the used machine, Selecting a specialist for the used machine and transmitting a request for creating a check list, receiving a check list created by the selected expert, receiving the check list created by the selected expert, Transmitting the check list to the client and confirming the intention to proceed; signing a contract for the used machine and depositing a down payment if the continuation request is received from the client; And depositing a balance on the used machine and issuing an export certificate upon confirming the residual deposit from the client.

According to one embodiment, the product information on the used machine is provided to the client through the web page in the server, and the purchase request can be performed from the client based on the product information provided on the web page.

According to one embodiment, the check list may include a check whether the used machine matches the product information, and a check result for a condition of each used item of the used machine.

The method for reclaiming used machines through a network according to an embodiment of the present invention includes a step of refunding the down payment on the used machine when receiving a stop request regarding the progress from the client after the step of asking the user to continue the process .

According to one embodiment, the expert can be selected based on the relevance score and the reliability score with the used machine among the experts registered in advance in the server.

A method executed in a server for inputting machine product information described in a web site according to an embodiment of the present invention includes receiving an online link address of the website, accessing a website of the link address, and performing a crawl And collecting the machine product information, wherein the product information may be a model number, a product name, a product photograph, and a description of the machine product.

According to one embodiment, collecting the machine product information may collect the model number by crawling numbers, models, and serial keyword values of the website.

According to one embodiment, the step of collecting the machine product information may crawl the web site, extract data, and then determine the machine product name by combining a plurality of predetermined machine keywords.

According to an exemplary embodiment, the step of collecting the machine product information may recognize a dot and a pattern of the web page to extract a product photograph of the machine product.

According to one embodiment, the details of the product may be obtained by extracting the contents of the main photograph at the bottom of the main photograph, excluding the contents of the main photograph.

According to an embodiment, when the product information is collected, the method may further include transmitting a confirmation message to the manager based on the collected product information, and transmitting an error message to the manager when the product information can not be collected .

A system for receiving a search word from a client terminal through a network according to an embodiment of the present invention and displaying a search result for a corresponding machine in a machine database includes a machine corresponding to the search word, A server for collecting, from the machine database, parts included in the parts category and the parts category of the machine, attachments of the machine, and attachments included in the attachment category, a machine corresponding to the search word on the first screen And a client terminal for displaying the parts corresponding to the component category on the second screen and displaying the attachments corresponding to the attachment category on the third screen.

According to an embodiment, the server accesses a web site containing information of a machine device, performs a crawl, collects the machine product information, and stores the machine product information in the machine database.

According to one embodiment, the machine product information may be a model number, a product name, a product photograph, and a product description of the machine product.

A method performed by a server for receiving a search word from a client terminal connected through a network and displaying a search result for the corresponding machine device in the machine database according to an embodiment of the present invention, Collecting, in the machine database, attachments included in the attachment category, the attachment category included in the attachment device, the component category corresponding to the component category corresponding to the component category corresponding to the search word, the parts corresponding to the component category, Configuring a web page to display a machine device corresponding to the attachment category on a first screen, displaying parts corresponding to the component category on a second screen, and displaying attachments corresponding to the attachment category on a third screen, and The web page It may comprise the step of transmitting to the client terminal.

A method for predicting trends in a machine industry performed by a server that receives a query for a machine from a client connected through a network according to an embodiment of the present invention includes receiving a search word from the client terminal, Collecting search results for the device, generating logs based on the collected search results, filtering the generated logs, deriving result values for the machine industry by filtering, And performing a trend prediction for the machine industry on the basis of the trend forecast.

According to an embodiment of the present invention, before performing the trend prediction, collecting a plurality of media for each country, performing keyword crawling for each of the collected media, and extracting economic information for each country .

According to an exemplary embodiment of the present invention, the step of predicting trends may be performed by considering both the result of the filtering and the extracted country-specific economic information.

According to one embodiment, the filtering of the generated logs may include filtering the generated logs by a predetermined period, and deriving the resultant values may include calculating a periodical result value for the machine industry based on the filtered logs .

According to one embodiment, filtering the generated logs may filter the generated logs by region.

According to one embodiment, deriving the results may derive regional results for the machinery industry based on the filtered logs.

A method for providing customized information on the machine industry performed by a server for inputting a search word for a machine device from a client connected through a network and providing a search result according to an embodiment of the present invention includes: Generating a result for the regional machine industry by filtering; predicting regional trends for the machine industry based on the result; And providing the web page on which the customized machine information for the terminal corresponding to the IP is described when there is the connected IP in the region having the result value in the predicted region-specific trend.

According to one embodiment, the generating of the logs may generate the logs based on the information on the items selected by the client corresponding to the search word, the search result, and the search result.

According to an embodiment of the present invention, the step of providing the web page in which the customized machine information is described may include a step of, when there is a client terminal having an IP connected thereto in an area having a result value, The information on the web page can be displayed on the upper part of the web page.

According to an embodiment of the present invention, the step of providing the web page in which the customized machine information is described may include a step of, when there is a client terminal having an IP connected thereto in an area having a result value, Can exclude information from the web page.

According to one embodiment of the present invention, by providing customized machine industry information actively to foreign buyers, foreign buyers can search and utilize more accurate information in a short period of time. Based on the reliability of information search, foreign buyers can easily and easily It is possible to contact the domestic machinery companies and increase the intention to purchase.

According to an embodiment of the present invention, the analysis of foreign buyer's search, keyword, category, preference, inquiry type, click trend analysis is analyzed in real time through analysis of behavior pattern of foreign buyers based on artificial intelligence, , Overseas buyers can receive customized product information, and machine sellers can be targeted for marketing.

According to an embodiment of the present invention, machine makers are able to conduct marketing around the world with only a few minutes of time and effort required for existing offline marketing, and even if there is no expert in overseas sales, the system enables overseas marketing and export.

1 is a configuration diagram of a system according to an embodiment of the present invention.
FIG. 2 is a flowchart illustrating a method for purchasing used machines on-line according to an embodiment of the present invention.
FIG. 3 is a flowchart illustrating a method for purchasing used machines on-line according to an embodiment of the present invention.
FIG. 3 illustrates a process in which a client terminal withdraws a purchase in a method of purchasing a used machine through online, according to an embodiment of the present invention.
4 is a flowchart of a database registration method of a machine product according to an embodiment of the present invention.
5 is an illustration of an example of a crawl for a web page introducing a machine product in accordance with an embodiment of the present invention.
6 is a flowchart illustrating a method for searching for a machine product in accordance with an embodiment of the present invention.
7 is a diagram showing a search result screen for a mechanical device according to an embodiment of the present invention.
FIG. 8 shows a company search screen and a product search screen on a search result screen for a machine according to an embodiment of the present invention.
9 is a flow chart illustrating a method for predicting machine industry trends according to an embodiment of the present invention.
10 is a flowchart illustrating a method for providing per-user customized information regarding machine industry trends according to an embodiment of the present invention.

While the invention is susceptible to various modifications and alternative forms, specific embodiments thereof are shown by way of example in the drawings and will herein be described in detail. It should be understood, however, that the invention is not intended to be limited to the particular embodiments, but includes all modifications, equivalents, and alternatives falling within the spirit and scope of the invention.

The terms first, second, etc. may be used to describe various elements, but the elements should not be limited by terms. Terms are used only for the purpose of distinguishing one component from another.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting. The singular expressions include plural expressions unless the context clearly dictates otherwise. In the present application, the terms "comprises" or "having" and the like are used to specify that there is a feature, a number, a step, an operation, an element, a component or a combination thereof described in the specification, But do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, or combinations thereof.

Hereinafter, various embodiments will be described in detail with reference to the accompanying drawings. Referring to the accompanying drawings, the same or corresponding components are denoted by the same reference numerals, and a duplicate description thereof will be omitted.

1 is a configuration diagram of a system according to an embodiment of the present invention. Referring to FIG. 1, the system 10 includes a client terminal 110 and a server 120, and the server 120 may include a database (database) server 122.

It is needless to say that the components shown in FIG. 1 are not essential, and a system having more or fewer components can be implemented. Hereinafter, each component will be described.

Each component of Figure 1 is typically connected through a network. For example, as shown in FIG. 1, the client terminal 110 and the server 120 may be connected to each other through a network. Here, the network means a connection structure in which information can be exchanged between respective nodes such as a plurality of terminals and servers 120. An example of such a network is a 3rd Generation Partnership Project (3GPP) network, a Long Term A wireless LAN, a WAN (Wide Area Network), a PAN (Personal Area Network), a LAN (Personal Area Network) But are not limited to, a Bluetooth network, a Zigbee network, a Radio Frequency Identification (RFID) network, and the like.

The client terminal 110 may be a communication device connectable to a network such as a desktop computer, a notebook computer, a smart phone, or a tablet PC. The client terminal 110 is connected to the server 120 via a network.

The server 120 according to an embodiment of the present invention receives a request for purchase of a used machine from a client connected through a network, and can purchase a used machine. At this time, the product information on the used machine is provided to the client through the web page on the server 120, and the client can apply for purchase through the client terminal based on the product information provided on the web page.

The server 120 according to an embodiment of the present invention may input machine product information described in a website into a database. For example, the server 120 may receive the online link address of the website, access the website of the link address, perform the crawl, and collect the machine product information. At this time, the machine product information may be the model number of the machine product, the product name, the product photograph, and the product description. In addition, the machine product information may be information on the enterprise that produced the machine product.

The server 120 according to an embodiment of the present invention may receive a search word from the client terminal 110 through a network and provide search results for the corresponding machine in the machine database.

The server 120 according to an exemplary embodiment of the present invention may include a device category corresponding to a search word input from the client terminal 110 through a network, Attachments included in the attachment category and attachment category of the device may be collected and provided in the machine database.

At this time, the client terminal 110 according to the embodiment of the present invention displays the machine corresponding to the search term on the first screen, displays the parts corresponding to the part category on the second screen, The attachments can be displayed on the third screen.

In addition, the server 120 may receive a search term for a machine tool from a client terminal 110 connected through a network, and may perform a trend prediction for the machinery industry.

In addition, the server 120 receives a query for a machine tool from a client terminal 110 connected through a network, predicts trends in the regional machine industry, and provides customized information on the machine industry by region .

FIG. 2 is a flowchart illustrating a method of purchasing a used machine through an online system according to an embodiment of the present invention.

Referring to FIG. 2, a method is provided in which the server 120 receives an application for purchase of a specific used machine from the client terminal 110 and purchases the used machine instead.

In step S201, the server 120 requests deposit of the down payment to the client terminal in connection with the purchase request of the used machine, and confirms the deposit of the down payment. When a purchase request for a specific used machine is received online from the client terminal 110 to the server 120, the server 120 transmits a part of the price of the device for the purchase request as a down payment to the client terminal 110 can do. At this time, the acceptance may mean that the server 120 receives the purchase request for the used machine selected from the web page by the client terminal. At this time, after the deposit request is made, if the deposit is confirmed for the purchase order, the server 120 performs the next step. At this time, the server 120 can send a part of the down payment to the seller to reserve the used machine. In addition, the server 120 may conclude a purchase contract with the seller on condition. A conditional purchase contract is, for example, a contract to check for a used machine and purchase it if there is no abnormality. If there is a defect in the machine product, the contract can be withdrawn.

In step S202, the server 120 selects an expert for the specific used machine that has received the purchase application. If you are an expert on a specific used machine, you are a person who has expert knowledge to check the machine with knowledge of the used machine in the field. For example, it can be divided into experts on machine tools, experts on molding machines, experts on agricultural machinery, and experts on medical devices. If the used machine received the purchase request is a medical device, the server 120 can preferentially select an expert related to the medical device from a list of experts stored in advance. When there are a plurality of experts in the field, the server 120 can select one expert from the list of experts held up to that time based on business relevance and performance. For example, in the case of a purchase application for an agricultural machine, a person who holds a professional certificate for an agricultural machine may be given a merit, or a person who has performed a lot of purchasing of an agricultural machine may be given a merit.

In addition, the server 120 can select an expert based on the reliability score. The reliability score may be, for example, a score obtained based on the delivery date and quality among the inspection work performed in the past by the relevant expert.

In addition, the server 120 can select an expert based on the relevance to the used machine and the reliability score. For example, you can select the expert who has the highest score by adding the relevance score and confidence score to the used machine.

In step S203, the server 120 sends the check list created by the expert to the client terminal 110, and confirms the intention of proceeding. The checklist is a pre-determined form that checks for items that must be verified in connection with the purchase of a used machine. At this time, the check list can be stored in advance in the database, and there can be another check list for each used machine field. Selected experts may be provided with checklists appropriate for the machine. When the selected expert carries out the inspection of the used machine, all the items in the check list can be recorded, and the recorded check list can be transmitted to the server 120 and accepted. The server 120 sends the created check list to the client terminal 110 and can confirm whether to continue the purchase of the used machine.

According to one embodiment of the present invention, when there is a problem in the check list, the system 10 can inform the client in various ways. For example, the problems found in the checklist may be referred to separately from the overall evaluation results provided with the checklist.

The client can determine whether or not to purchase by checking the status of the used machine using the check list received through the client terminal 110. [

In step S204, if the server 120 receives a purchase progress request for the used machine from the client terminal 110, the server 120 enters a contract for the used machine and deposits the down payment to the seller. For example, if the client wishes to continue purchasing the used machine, the client terminal 110 may send a continuation request to the server 120. When the server 120 receives the continuation request from the client terminal 110, the server 120 transmits the down payment to the seller to confirm the transaction. At this time, if the purchase contract with the seller has not yet been concluded for the used machine, the server 120 can formally conclude the purchase contract with the seller. At this time, the server 120 notifies the client terminal 110 that the contract has been concluded for the used machine, and can request the deposit of the balance except for the down payment on the used machine.

In step S205, when the server 120 confirms the remittance of the used machine, the server 120 deposits the remainder to the seller and issues an export certificate.

FIG. 3 illustrates a process in which a client terminal withdraws a purchase in a method of purchasing a used machine through on-line according to an embodiment of the present invention.

Referring to FIG. 3, a method in which the client terminal 110 withdraws a purchase by viewing a check list provided by the server 120 to the client terminal 110 is illustrated.

In step S301, the server 120 requests the client to deposit the down payment in connection with the purchase request of the used machine and confirms the deposit of the down payment. This step corresponds to S201 of FIG. 2, so a detailed description will be omitted.

In step S302, the server 120 selects a specialist for a specific used machine that has received the purchase application, and transmits a check list creation request. Since this step corresponds to S202 of FIG. 2, a detailed description will be omitted.

In step S303, the server 120 receives a check list created by an expert, sends the received check list to the client terminal 110, and confirms the intention of proceeding. This step corresponds to S203 of FIG. 2, so a detailed description will be omitted.

In step S304, when the server 120 receives the pause request from the client, the server 120 notifies the seller that the purchase is not made, and returns all or a part of the money deposited from the client to the client. For example, if the client checks the checklist and the machine is defective or defective, you may not want to purchase it. At this time, the client can transmit a pause request to the server 120 through the client terminal 110. When the server 120 receives the progress stop request, the server 120 sends a notification to the seller to cancel the purchase. You may then send all or part of the down payment to the client and return it. Through this process, the client can make a secure purchase for the used machine.

4 is a flow diagram of a method for entering machine product information on a website in a database according to an embodiment of the present invention.

In the mechanical product database registration method, it is important how to formalize the informal data. According to one embodiment of the present invention, tens of thousands of machine data can be organized into a single format formatted through pattern analysis.

Referring to FIG. 4, a method of inputting product information of a machine product existing on-line into a database includes inputting an online link address of a website introducing a machine product, accessing a link site web site, and performing a crawl And collecting product information of the machine product, wherein the product information is a model number, a product name, a product photograph, and a description of the machine product.

In step 401, the server 120 receives an online link address of a web site introducing the machine product. At this time, the web page related to the machine product connected by the link may include the following information.

1. Model number

2. Machine Product Name

3. Product pictures (jpg, png, gif files)

4. Details (text and jpg, png, gif files)

In step 402, the server 120 accesses a web page linked to the link and performs a crawl. At this time, crawling refers to a process of taking a web page as it is and extracting data therefrom. The item automatically input as machine product information to the database of the server 120 by crawling may be, for example, the model number of the machine product, the name of the machine product, the product photograph, the details (text and jpg, png, gif file) . This will be described in detail with reference to FIG.

In step 403, the server 120 verifies whether the data extracted by the crawl is in a manner suitable for database input. For example, the system can verify that the data extracted by the crawl has data that matches the business information.

According to an embodiment of the present invention, the server 120 may divide data extracted after crawling into a business database and a product database to input machine product information. The items of the company database registered in the server 120 according to an embodiment of the present invention may be composed of basic information, detailed information, a logo, a keyword, a category, and the like.

The item of the product database registered in the server 120 according to an embodiment of the present invention may be composed of basic information, detailed information, a photograph, a keyword, a category, and the like.

For example, the server 120 can check whether the data extracted by the crawling includes data matching the model number, the product name, the product photograph, and the detailed contents. At this time, if there is data that does not match any of the model number, the product name, the product photograph, and the details, or if there is empty data, the server 120 may transmit an error or confirmation message to the administrator. For example, if all the pages are picture files, the crawler can not recognize the data, and the operator can manually upload the data to the database through the alarm message of the server 120.

In step 404, the server inputs the data to the database as it is, in the case of data matching the model number, product name, product photograph, and details. If the format corresponding to one of the model number, the product name, the product photograph, and the details is not satisfied, the server can ask the server administrator for confirmation before the data is input to the database.

According to one embodiment of the present invention, the big data construction through the crawling described above can be done, and the information of the manufacturers such as machines, equipment, or parts such as customization in the industry group can be easily and easily registered. The database thus registered makes it easy to search based on machine product specifications.

5 is an illustration of an example of a crawl for a web page introducing a machine product in accordance with one embodiment.

According to one embodiment, the model number, the machine product name, the product photograph, the details (text and jpg, png, gif file) and the like can be automatically input into the database of the server 120 by the crawling. The following various methods can be used to automatically input mechanical product information of a web page into a database by crawling.

Referring to Figure 5 (a), the model number of the machine product "DPR-CI 4 / 6FP" is shown in a first portion 510, which is the top of the image. According to one embodiment, the model number of the machine product information can be extracted by crawling on numeric, model, and serial keyword values.

Below it, the machine name "CENTRAL IMPRESSION FLEXOGRAPHIC PRINTING PRESS" is shown. According to one embodiment, the machine product name of the machine product information can identify the machine name by combining tens of thousands of machine keywords held in the database based on the text obtained through crawling.

Referring to Figure 5 (a), a main picture of the machine product is shown in a second portion 520, which is an interruption of the image. According to one embodiment, a main picture can be extracted by recognizing a picture or a picture point (DOT) and a pattern in relation to product picture recognition among machine product information. For example, a crawl can be used to extract an image of an outline, recognize a pattern, and compare it with previously registered images of machine products to extract the main photo of the product.

Referring to Figure 5 (a), the details of the machine product are shown in the third portion 520, which is the bottom of the image. As shown in the figure, various information about the machine product, for example, an installation method, a driving method, a sample made of a machine product, or the like may be included in the details. According to one embodiment, the details of the product information of the machine product information can be extracted by extracting the content of the lower part except the contents of the main picture extracted above.

Referring to FIG. 5 (b), a web page generated using model information, machine name, main photograph, and details of the extracted machine product is shown. The client terminal 110 can easily grasp the product information through the generated web page based on such information. Furthermore, a web page can be used for convenience of the client by adding a purchase application for the product, adding the product as an item of interest, and a button for contacting the company.

6 is a flow chart illustrating a search method for a machine product in accordance with one embodiment.

Referring to FIG. 6, a method of displaying a search result for a corresponding machine device in a predetermined machine database by receiving a search word according to an embodiment is shown.

In step S601, the server 120 acquires attachments corresponding to the machine corresponding to the search term, the component category of the mechanical device corresponding to the search word, the parts corresponding to the component category, the attachment category of the mechanical device, and the attachment category, Lt; / RTI >

In step S602, the server 120 displays the machine corresponding to the search term on the first screen, displays the parts corresponding to the part category on the second screen, and displays the attachments corresponding to the attachment category on the third screen Create a web page.

It will be apparent to those skilled in the art that the order in which one screen, two screens, three screens may be displayed according to the embodiment may be changed according to the embodiment.

Although not shown in FIG. 6, the server can transmit the generated web page to the client terminal.

7 is a diagram showing a search result screen for a machine according to an embodiment.

Referring to FIG. 7A, an associated search term of the search term is displayed under the search result for the search term.

For example, if an excavator is entered as a search term, the associated search term may be Hyundai, Doosan, etc., which manufacture excavators. Also, a carter filler, which is a part of an excavator, can be displayed as an associated search term. These related search terms can be predetermined and databaseized by the administrator. That is, the associated search term may be an associated search term selected by the administrator. In addition, such an associated search term can be recommended by the algorithm of the system. For example, an associated search term may be the most searched term after a particular search term is searched.

Also, sub-categories and connection categories of excavators can be displayed. As an example of a sub-category, a part category can be displayed. The component category of the excavator can be, for example, a cylinder, a chain, a cover, a motor, and the like. As an example of a connection category, an attachment category may be displayed.

Also, referring to FIG. 7 (a), on the screen below the associated search term, the devices corresponding to the search term are displayed.

Referring to FIG. 7 (b), in addition to the mechanical device corresponding to the related search word and the search term, a part category of the mechanical device corresponding to the search term and a screen showing the corresponding parts can be displayed. For example, an HEC excavator motor, an excavator chain, etc., which is a part of an excavator, may be displayed.

Although not shown in FIG. 7, an attachment category corresponding to a search word can be displayed. For example, an attachment category of an excavator may include a breaker, a quick coupler, a hammer, and the like.

This category classification can be directly performed by the server administrator. For example, the server administrator can directly pre-sort categories into smaller categories and store them in the database for use.

According to one embodiment of the present invention, the category classification is shown in the search result, and the machine manufacturer or specification can be searched simultaneously. This makes it possible to search for machine categories, manufacturers, and specifications.

Through this search, overseas buyers can easily and easily search the machine devices, and the similarity, synonyms, and related words analysis can shorten the search time and improve the accuracy of the site, thereby improving the reliability of the site.

According to one embodiment of the present invention, a customized category for the user may be provided. This will be described with reference to FIG.

FIG. 8 illustrates an enterprise search screen and a product search screen on a search result screen for a machine according to an embodiment.

Referring to FIG. 8A, a company search screen is displayed on a search result screen for a machine according to an exemplary embodiment. At this time, the category corresponding to the company is displayed among the categories corresponding to the search word. For example, in the enterprise mode when searching with an excavator, Hyundai Construction Machinery HAMMERS, JCARE Co., Ltd., which manufactures excavators, can be shown.

Referring to FIG. 8 (b), a product search screen is displayed on a search result screen for a machine according to an embodiment. At this time, a category corresponding to the product is displayed among the categories corresponding to the search word. For example, excavator parts, excavators, and excavator buckets can be shown as categories when searching with an excavator.

FIG. 9 is a flowchart illustrating a method for predicting machine industry trends in a server receiving a query for a machine according to an embodiment.

In step 911, the server 120 may generate a log by using the website of the client terminal 110. [ Here, the log may include a machine manufacturer search result by the client, a machine product search result, a result of the selection after the search (for example, a machine category selection), a machine maker contact type, and the like. In this case, the machine vendor contact type may be a method in which the client terminal accesses the seller or the server manager by an additional action. The machine vendor contact type can be, for example, e-mail, telephone, note, etc.

At step 912, the server 120 may filter the log generated by the client. In this case, log filtering can be performed by period (daily, weekly, monthly, quarterly, yearly), region (city, country, continent), classification (buyer classification - manufacturing, distribution industry, service industry). For example, filtering by IP in Asia can be performed to find logs performed by users who are connected in Asia. In addition, filtering of the search result and the selection result in the past one year is performed, and information on the search and selection performed by the user who has accessed the past one year can be confirmed. This allows you to know the frequency and frequency of searches for specific regions, specific time periods, and specific categories.

In step 913, the server 120 may derive a result by filtering. For example, the server 120 may know that more than 80% of the users in Maharashtra, India in August 2017 are searching for construction machines, and as a result, domestic construction machinery and construction machinery You can find out the statistical results that you are looking for a lot of parts. Also, by filtering the search results and the selection results, the server 120 can find out that more than 70% of the local users search for medical devices, and in August 2017, Statistics can be found.

In step 921, the server 120 may collect a plurality of media. At this time, the plurality of media may be collected by country, or may be collected by region.

In step 922, the server 120 may perform a keyword crawl on the collected media to extract data from the plurality of media. At this time, the data may be information that has an influence on the demand of machinery such as economic information. At this time, the media may mean all media including texts such as newspapers and magazines. For example, the server 120 may crawl economic newspapers or economic magazines to extract text and perform keyword crawls for the industry. For example, the server 120 can extract information that the state invested 10 trillion won in the construction of the Maharashtra region infrastructure in August 2017. Alternatively, the server 120 may extract information that the per capita medical expenditure has increased as the income level of Vietnam increases in August 2017.

In step 930, the server 120 can perform trend prediction by combining the result of filtering obtained in step 913 and the economic information extracted in step 922. [ For example, the server 120 is investing 10 trillion won in the construction of the Maharashtra region infrastructure in India, and because the search result of the construction machine sold in the Maharashtra area now is high, the Maharashtra area visitor The future trend of the machinery industry can be predicted.

This allows a more accurate analysis than the analysis based on the result obtained in step 913. [ At this time, the server 120 can visualize analysis data, and can analyze and predict behavior patterns of clients based on the visualization. For example, the server 120 may provide a visualization service for integrated analysis data. In addition, the server 120 can provide analysis data specialized for a corporation, institution, association, and region in real time online. For example, India can extract data from a large number of machine tools and Bangladesh is searching for soft packaging machines.

This analysis data can be used to build big data for the machinery industry. In order to construct big data, a large amount of data and a variety of technologies should be combined. The server 120 according to an exemplary embodiment of the present invention is a server (120) based on an architecture of a big data integration analysis system optimized based on IBM's BLUEMIX 120) can be interlocked and constructed. All analytical data can then be analyzed based on IBM Bluemix machine learning and data mining techniques. This technique allows you to customize the desired data results to your items.

In addition, a big data dashboard can be developed that can collectively manage all data through analysis of behavior patterns of foreign users through such analysis data. Accordingly, the system 10 according to an embodiment of the present invention can grasp macroscopic information on the Korean machine industry in real time online by grasping information on the Korean machine industry as well as trends of overseas buyers all over the world.

As a result, the system 10 can analyze the behavior pattern of "when, where, who, what, how and why" to search for and purchase domestic machines, and produce various products through the analysis data.

For example, ① Analyze visits by country and city of overseas users ② Analyze the category interest of overseas users ③ Analyze the interest of domestic users in the domestic machine companies ④ Analyze the product interest of overseas users ⑤ Analyze specific products by group (by region, association, ⑥ Data analysis based on data mining technology Real time measurement value ⑦ Recommendation algorithm / pattern analysis number Real time measurement value ⑧ It is possible to derive real time measurement value of number of connections of foreign buyers.

As described above, the data accumulated through analysis of behavior of foreign buyers can be constructed as big data, so that trends of overseas purchasers can be grasped in real time, and in macroscopic framework, all information related to export of machinery industry can be grasped. Based on the objective data produced at this time, machine manufacturers, government agencies, and industrial organizations can systematically manage the Korean machinery industry and make efficient policy decisions.

10 is a flowchart illustrating a method for providing per-user customization information according to an exemplary embodiment.

Steps 1011 to 1030 are the same as the corresponding steps of FIG. 9, and a description thereof will be omitted.

At step 1040, the server 120 according to one embodiment of the present invention may provide customized machine information tailored to the user.

For example, the server 120 may provide customized machine information based on the analysis data and the analyzed behavior pattern. For example, when there is a client terminal having an IP connected thereto in an area having a predicted result value in the trend, information on a machine trend having high demand in the area is preferentially displayed on a screen viewed from a client terminal having the IP .

Although not shown in FIG. 10, the server 120 according to an embodiment may provide a web page having a category and a product page suitable for a user.

If the product and the seller information set in the database structure are displayed as they are when the search / category is selected, the foreign buyer must see unnecessary information. This can result in unnecessary click-through and search time being relatively high. According to an embodiment of the present invention for solving such a problem, a seller and a product according to a category matching a behavior pattern of an overseas buyer can be displayed through analysis of behavior patterns of an overseas buyer. At this time, morphological analysis, data mining and machine learning based on the semantic web ontology can be used to analyze behavior patterns of foreign buyers.

As a result, according to the embodiment of the present invention, since the customized product and the seller information according to the customized category are displayed, the foreign buyer can confirm more accurate information in a short time.

In addition, according to an embodiment of the present invention, it is possible to exclude a specific category through analysis of behavior patterns of foreign buyers. For example, the server 120 may analyze category values, preferences, and search frequency categories of foreign buyers through analysis of various behavior patterns of foreign buyers in the main page provided to the client terminal 110, Can be set.

Through this, foreign buyers will be able to search and select highly information, increasing the re-connection rate and lowering the bounce rate so that as much information as possible is available on the site.

In addition, customized information based on behavioral pattern analysis of buyers around the world can increase the exposure of companies and products.

The system, apparatus, or server according to various embodiments above may include a processor, a memory for storing and executing program data, a permanent storage such as a disk drive, a user interface device such as a touch panel, a key, . ≪ / RTI >

Methods implemented with software modules or algorithms may be stored on a computer readable storage medium as computer readable codes or program instructions executable on the processor. Here, the computer-readable recording medium may be a magnetic storage medium such as a read-only memory (ROM), a random-access memory (RAM), a floppy disk, a hard disk, ), And a DVD (Digital Versatile Disc). The computer-readable storage medium may be distributed over networked computer systems so that computer readable code is stored and executed in a distributed manner. The medium is readable by a computer and can be executed in a processor.

All documents including publications, patent applications, patents, etc. cited in the present invention can be incorporated into the same document as the documents cited individually or concretely in the individual cited documents.

In order to facilitate understanding of the present invention, reference will be made to the preferred embodiments shown in the drawings, and specific terminology has been used to describe the embodiments of the present invention. However, the present invention is not limited thereto. And may include all components that are commonly conceivable to those skilled in the art.

The present invention may be represented by functional block configurations and various processing steps. These functional blocks may be implemented in a wide variety of hardware and / or software configurations that perform particular functions. For example, the present invention may be implemented in integrated circuit configurations such as memory, processing, logic, look-up tables, etc. that may perform various functions by control of one or more microprocessors or other control devices Can be employed. C ++, Java, etc.), including various algorithms implemented as a combination of data structures, processes, routines, or other programming constructs, similar to what components can be executed with software programming or software components. And may be implemented in a programming or scripting language such as an assembler. Functional aspects may be implemented with algorithms running on one or more processors. Further, the present invention can employ conventional techniques for electronic environment setting, signal processing, and / or data processing. Terms such as "mechanism", "element", "means", "configuration" may be used broadly and are not limited to mechanical and physical configurations. The term may include the meaning of a series of routines of software in conjunction with a processor or the like.

The specific implementations described in the present invention are, by way of example, not intended to limit the scope of the invention in any way. For brevity of description, descriptions of conventional electronic configurations, control systems, software, and other functional aspects of such systems may be omitted. Also, the connections or connecting members of the lines between the components shown in the figures are illustrative of functional connections and / or physical or circuit connections, which may be replaced or additionally provided by a variety of functional connections, physical Connection, or circuit connections. Also, unless stated otherwise, such as "essential "," important ", etc., it may not be a necessary component for application.

The use of the terms "above" and similar indication words in the specification of the present invention (particularly in the claims) may refer to both singular and plural. In addition, in the present invention, when a range is described, it includes the invention to which the individual values belonging to the above range are applied (unless there is contradiction thereto), and each individual value constituting the above range is described in the detailed description of the invention The same. Finally, the steps may be performed in any suitable order, unless explicitly stated or contrary to the description of the steps constituting the method according to the invention. But the present invention is not limited thereto. The use of all examples or exemplary terms (e.g., etc.) in the present invention is for the purpose of describing the present invention only in detail and is not intended to limit the scope of the present invention. It will also be appreciated by those skilled in the art that various modifications, combinations, and alterations may be made depending on design criteria and factors within the scope of the appended claims or equivalents thereof.

Claims (4)

A method for predicting trends in the machinery industry performed by a server that receives a query for a machine from a client connected through a network,
Receiving a search word from the client terminal and collecting search results for the corresponding machine in the machine database;
Generating logs based on the collected search results;
Filtering the generated logs;
Deriving a result value for the machine industry by the filtering;
And performing a trend prediction for the machinery industry based on the resultant value.
The method according to claim 1,
Further comprising the steps of: collecting a plurality of media for each country, performing keyword crawling for each of the collected media, and extracting country-specific economic information before performing the trend prediction,
Wherein the step of predicting trends comprises predicting trends in consideration of both the result of the filtering and the extracted country-specific economic information.
The method according to claim 1,
Wherein the filtering the generated logs comprises filtering the generated logs by a predetermined period,
Wherein deriving the result comprises deriving a time-based result for the machinery industry based on the filtered logs.
The method according to claim 1,
Wherein the filtering the generated logs comprises filtering the generated logs by region,
Wherein deriving a result comprises deriving a regional result for the machinery industry based on the filtered logs.

Images