WO2023043270A1

WO2023043270A1 - Machine learning-based web page template recommendation method and device therefor

Info

Publication number: WO2023043270A1
Application number: PCT/KR2022/013903
Authority: WO
Inventors: 오철원
Original assignee: 주식회사 팀솔루션
Priority date: 2021-09-17
Filing date: 2022-09-16
Publication date: 2023-03-23
Also published as: KR20230041454A

Abstract

A template recommendation method for creating a web page, according to one embodiment of the present invention, may comprise the steps of: receiving, from a user, category information, for each category item, for a web page to be created; extracting, as first template candidates, templates, among a plurality of pre-registered templates, having category information having a predetermined level of or higher degree of similarity with the received category information; providing the extracted first template candidates to the user; receiving a user input for selecting at least one of the first template candidates; and creating the web page on the basis of the selected first template candidate.

Description

Machine learning-based web page template recommendation method and device therefor

This specification proposes a method for recommending a web page template based on machine learning and an apparatus therefor.

Recently, artificial intelligence (AI) technology is rapidly developing, and services using artificial intelligence technology are widely provided in various fields. Machine learning is a subset of artificial intelligence (AI). Instead of explicitly programming computers to learn and improve, the focus is on training computers to learn from data and improve from experience. In machine learning, algorithms are trained/learned to find patterns and correlations in large data sets and make optimal decisions and predictions based on the analysis. Machine learning applications improve through application and become more accurate as the available data increases. Applications of machine learning are spread all around us, from living spaces to shopping carts, entertainment media, and medical care, and are developing more rapidly with the recent expansion of the application range.

There have been several attempts to apply/apply webpage generation methods using machine learning technology in the past, but due to the high technical difficulty of machine learning technology itself, there were many difficulties for non-experts to use it to create webpages.

Therefore, in this specification, the field of machine learning is applied to the 'template recommendation method', which is the basis for web page creation, and a web page creation/editing tool is provided so that users can more easily compose/edit web pages, so that users can Its purpose is to efficiently create a web page with a desired design simply by selecting/editing a template recommended through the platform.

A method for recommending a template for creating a web page according to an embodiment of the present invention, comprising: receiving category information about a web page to be created from a user for each category item; extracting, from among a plurality of pre-registered templates, a template having category information having a higher degree of similarity with the input category information than a preset level, as a first template candidate; providing the extracted first template candidate to the user; receiving a user input for selecting at least one of the first template candidates; and generating a web page based on the selected first template candidate. can include

According to an embodiment of the present invention, there is an effect that non-experts who do not have a high technical understanding of machine learning can easily create and edit web pages.

In addition, according to one embodiment of the present invention, since components to be inserted for each area of the template are recommended, the user does not need to create or search for components individually, increasing usability and convenience, and freedom in creating/editing web pages. has a very high effect.

Other effects of the present invention will be described below with reference to the respective drawings and embodiments.

1 and 2 are block diagrams of a web page generating device according to an embodiment of the present invention.

3 is a flowchart illustrating a template recommendation method for generating a web page according to an embodiment of the present invention.

4 is a diagram illustrating a category information input window for each category item according to an embodiment of the present invention.

5 is a diagram illustrating a decision tree according to an embodiment of the present invention.

6 is a diagram illustrating a screen for recommending/providing a first template candidate according to an embodiment of the present invention.

7 is a flowchart illustrating a component recommendation method according to an embodiment of the present invention.

8 is a diagram illustrating a first template candidate being edited according to an embodiment of the present invention.

9 is a diagram illustrating an embodiment of component candidate extraction according to an embodiment of the present invention.

10 is a diagram illustrating an example of recommending component selection and template editing according to an embodiment of the present invention.

11 is a diagram illustrating a template market according to an embodiment of the present invention.

Since the technology to be described below can have various changes and various embodiments, specific embodiments will be illustrated in the drawings and described in detail. However, this is not intended to limit the technology described below to specific embodiments, and it should be understood to include all modifications, equivalents, or substitutes included in the spirit and scope of the technology described below.

Terms such as first, second, A, B, etc. may be used to describe various elements, but the elements are not limited by the above terms, and are merely used to distinguish one element from another. used only as For example, without departing from the scope of the technology described below, a first element may be referred to as a second element, and similarly, the second element may be referred to as a first element. The terms and/or include any combination of a plurality of related recited items or any of a plurality of related recited items. For example, 'A and/or B' may be interpreted as meaning 'at least one of A or B'. Also, '/' can be interpreted as 'and' or 'or'.

In the terms used in this specification, singular expressions should be understood to include plural expressions unless clearly interpreted differently in context, and terms such as “comprising” refer to the described features, numbers, steps, operations, and components. , parts or combinations thereof, but it should be understood that it does not exclude the possibility of the presence or addition of one or more other features or numbers, step-action components, parts or combinations thereof.

Prior to a detailed description of the drawings, it is to be clarified that the classification of components in the present specification is merely a classification for each main function in charge of each component. That is, two or more components to be described below may be combined into one component, or one component may be divided into two or more for each more subdivided function. In addition, each component to be described below may additionally perform some or all of the functions of other components in addition to its main function, and some of the main functions of each component may be performed by other components. Of course, it may be dedicated and performed by .

In addition, in performing a method or method of operation, each process constituting the method may occur in a different order from the specified order unless a specific order is clearly described in context. That is, each process may occur in the same order as specified, may be performed substantially simultaneously, or may be performed in the reverse order.

The web page generating device proposed in this specification is an electronic/web server/apparatus/device that executes an application/program/website/webpage implemented so that the webpage generating method/embodiment proposed in this specification can be performed/executed. / may correspond to the terminal. Therefore, even if not separately described below, the method/embodiment proposed in this specification can be interpreted as being performed/executed through the server/device/device/terminal where the application/program/website/webpage is running, , the operation of each server/device/device/terminal may be interpreted as the operation/function of the application/program/website/webpage.

In particular, FIG. 1 is a block diagram showing the configuration of a web page generating device 100 according to an embodiment of the present invention, divided by function, and FIG. 2 is a web page generating device 100 according to an embodiment of the present invention. It is a block diagram that divides the configuration by hardware.

First, referring to FIG. 1 , the web page generating device 100 may include a web page generating unit 110, a template storage unit 120, a template recommendation unit 130, and/or a template market unit 140. .

The web page generator 110 may correspond to a component that creates and edits a web page. More specifically, the web page generation unit 110 corresponds to a configuration that provides a function of uploading, creating, editing, arranging, deleting, and/or manipulating templates and components, which are elements constituting a web page, based on user input. can do. The template may correspond to a form/format of a web page that is pre-generated and pre-stored in the web page generating device 100, and a component may be placed in the template as an element in which data is visualized. Examples of components may include images, videos, photos, text, graphs, tables, GUIs, icons, tags, and the like. The web page generation unit 110 may provide an environment in which the user freely composes a web page by providing a function of selecting/uploading/editing/deleting such templates and/or components. Furthermore, the web page generation unit 110 may additionally provide a source code-based editing function that can be modified by referring to the source code in order to implement a high-level customizing function. Through this, users (especially experts) can more delicately create/edit web pages with desired designs.

The template storage unit 120 may correspond to a configuration for storing a template of a web page generated by the web page generator 110 . The template storage unit 120 may store a template using a storage space included in the web page generating device 100 or may store a template using a cloud, which is an online storage space. The template storage unit 120 may build a database including various templates and detailed information (eg, category information) on them in the aforementioned storage space. The templates stored/registered in the database can be used for recommending and selling templates.

The template recommendation unit 130 may correspond to a component that recommends a template that is a basis for creating a web page and/or a component to be inserted into the template.

In particular, as a first embodiment, the template recommendation unit 130 may perform a function of recommending a template based on similarity of (service) category information. Here, the category information refers to service-related information related to a web page, and may be input by a user for each preset category item. The reason for recommending templates based on the similarity of category information is the service field to be provided through the web page, the main service customer group that will use the web page, the main and additional functions of the web page, the design concept of the web page, and the design concept of the web page. This is because the higher the degree of similarity, such as color and/or job of the operator/manager of the web page, the higher the possibility that a template having a similar design/layout/composition will be borrowed.

For example, in the case of most online shopping mall web pages, a template having a layout in which a product category selection interface is placed on the left side and products included in the selected product category and a product introduction interface are placed on the right side is commonly borrowed. Since consumers using online shopping malls are very accustomed to such online shopping mall layouts/compositions, when a web page is constructed using a template from which a completely new layout is borrowed, there is a risk that consumers' satisfaction and convenience may significantly decrease. In addition, this layout/composition is very efficient because it is easy to grasp the product at a glance.

In view of this point, the template recommendation unit 130 may recommend, as a first template candidate, a template having a higher degree of similarity with category information of a web page to be created by the user than a predetermined level. Through this, the user does not have to create a template directly from scratch, reducing the difficulty and time of work, and since the layout of similar service fields is borrowed, the convenience of using the web page is secured to a certain level or higher for consumers using the service. It works. A more specific template recommendation operation of the template recommendation unit 130 will be described in detail below with reference to FIG. 3 .

Similarly, as a second embodiment, the template recommendation unit 130 may provide a function of recommending a component based on the similarity of the template layout/composition/composition. In this embodiment, the template recommendation unit 130 may recommend a component to be inserted into a specific area based on the similarity of neighboring components (eg, component type, location, layout, composition, composition, arrangement, etc.) there is. This is also because the higher the similarity of neighboring components, the higher the likelihood that components to be inserted in a specific area will be similar, and inserting similar components is efficient in constructing the entire web page. A more specific component recommendation operation of the template recommendation unit 130 will be described in detail below with reference to FIG. 7 .

The template and/or component recommended by the template recommendation unit 130 may be provided to the user through the web page generator 110, and the user inputs (eg, Drag and drop input, selection input, etc.) can be performed and edited to easily compose the desired web page. The completed web page may be stored/registered in the template storage unit 120 as a template.

The template market unit 140 may correspond to a configuration that provides a market interface through which templates can be sold and purchased. In particular, the template market unit 140 may upload and sell at least one template stored/registered in the template storage unit 120 to the market or purchase a template uploaded to the market based on a user input. The purchased template may be provided to the user through the web page creation unit 110 .

The template market unit 140 may provide a user with various information such as seller information for each template, sales information (eg, sales price, expiration date, category information, etc.), purchase history information, and popularity ranking information. Furthermore, the template market unit 140 also provides this information to the template recommendation unit 130 so that the template recommendation unit 130 can utilize it as learning/sample data for appropriately recommending a template desired by the user with higher accuracy. can do.

Referring to FIG. 2 , the web page generating device 100 may include a control unit 210, a memory unit 220, a display unit 230, a communication unit 240, and/or a user input unit 250.

The controller 210 may control other components included in the web page generating apparatus 100 to perform the embodiments proposed in this specification. Therefore, in this specification, the web page generating device 100 may be replaced with the control unit 210 and described. The controller 210 includes at least one CPU (Central Processing Unit), MPU (Micro Processor Unit), MCU (Micro Controller Unit), AP (Application Processor), or any type of processor well known in the art. can be configured. The controller 210 may perform calculations for at least one application and/or program for executing a method according to embodiments of the present invention.

The memory unit 220 may store various digital data such as video, audio, photos, moving pictures, and applications. In particular, the memory unit 220 may store various information related to web page generation, such as a plurality of templates and category information for each template. The memory unit 220 may correspond to various digital data storage spaces such as a flash memory, a hard disk drive (HDD), a solid state drive (SSD), and a cloud.

The display unit 230 may correspond to a component that outputs various visually recognizable objects. In particular, the display unit 230 may perform a function of outputting visual objects necessary for performing the embodiments proposed in this specification, such as web pages, templates, and components.

The communication unit 240 may communicate with an external device/server using at least one wired/wireless communication protocol.

The user input unit 250 may use/equip with at least one sensor to sense various user inputs to the web page generating device 100 and transmit sensing results to the control unit 210 . The at least one sensor may include, for example, a gravity sensor, a geomagnetic sensor, a motion sensor, a gyroscope sensor, an acceleration sensor, an infrared sensor, an inclination sensor, a brightness sensor, an altitude sensor, an olfactory sensor, a temperature sensor, It may include at least one of a depth sensor, a pressure sensor, a bending sensor, an audio sensor, a video sensor, a Global Positioning System (GPS) sensor, a touch sensor, and a grip sensor.

Referring to FIG. 3 , the apparatus for creating a web page may receive category information about a web page to be generated from a user for each preset category item (S301). Here, the predetermined category items include a service field to be provided through the web page, a main service customer group using the web page, a main function of the web page, an additional function of the web page, a design concept of the web page, a color of the web page, and / or the category information related to the web page service field, such as the occupation of the web page operator, can be set by the administrator/operator as an item for receiving input from the user.

As illustrated in FIG. 4 , the web page generating device may provide the user with an input window for receiving category information to be used for recommending a template. The user may input category information about a web page to be created for each category item presented in the input window.

Referring again to FIG. 3, next, the web page generating device selects a template having category information having a similarity with the input category information that is higher than or equal to a predetermined level, among a plurality of templates pre-registered/pre-stored in the template storage unit, It can be extracted as a first template candidate (S302). Extraction of the first template candidate based on similarity may be performed in various ways according to embodiments.

As an embodiment, the web page generating device may extract, as a first template candidate, a template whose matching rate/number/degree with input category information exceeds a preset ratio/number/degree among a plurality of templates. In this case, a weight is assigned to category information having a high degree of importance, and a matching rate/number/degree may be derived. For example, if the importance of an item in the field of service provision is higher than that of other items, a weight of 0.5 may be assigned to the number of relevant fields, and when matching information on the corresponding item, the number of matches will be calculated as 1.5 instead of 1. can

As another embodiment, the web page generation device builds a template similar group classification model by AI learning a plurality of templates pre-registered/pre-stored in the template storage based on machine learning, and using the built model, the first Template candidates can be extracted. The template similar group classification model may correspond to a model that classifies and outputs the template similar group based on the matching rate/number/degree of category information input for the template. At this time, the web page generating device may build/create a template similar group classification model by utilizing/application/applying various machine learning technologies, and a similar group classification model construction method using a decision tree will be described later with reference to FIG. 5 do.

As shown in FIG. 5 , the web page generating device may generate a decision tree 500 in which classification criteria for each decision step (S501 to S503) correspond to category items.

To this end, first, the web page generating device may classify into a predetermined number (eg, 10) template similarity groups based on template similarity between a plurality of templates. Template similarity may refer to the similarity of visual/design elements such as type, arrangement, layout, composition, size, design, and color of components included in the template. The web page generating device may perform AI learning on templates for each similarity group and extract category information common to each similarity group. The web page generating device designates the similar group of templates as the final node of the decision tree 500, and the classification criterion for each step toward each final node is the final node for the category item corresponding to each step (S501 to S503) (i.e., , template similar group) can be set as extraction category information.

For example, as illustrated in FIG. 5 , when the final node is the first template similar group and the category information derived from the first template similar group is 'shopping mall', 'shopping mall operator', and 'female', the first Classification criteria for each decision step (S501 to S503) toward the template similar group may be set as follows.

- S501-1 of the first decision step (S501) (service provision field item): shopping mall

- S502-1 of the second decision step (S502) (web page operator job): shopping mall operator

- S503-1 of the third decision step (S503) (web page service customer): female

The web page generating device may predict/derive a template similarity group having a high similarity to the input category information by inputting the category information input from the user into the decision tree 500 thus completed.

The web page generating device extracts the template classified as the predicted/derived template similar group as the first template candidate, or directly generates the first template candidate by extracting features after AI learning of the template of each template similar group. You may.

Referring back to FIG. 3 , next, the web page generating device may provide the first template candidate extracted/generated in this way to the user (S303).

As illustrated in FIG. 6 , the apparatus for generating a web page recommends a template that matches the characteristics/attributes of a web page that the user wants to create by providing/outputting the extracted/generated first template candidates 610 to 640 to the user. can When a pre-registered/pre-stored template is provided, a recommendation order may be determined based on popularity/sales information of the template. For example, a template with high popularity or high sales volume may be provided/recommended to the user by being ranked higher in the recommendation ranking.

Referring back to FIG. 3 , next, the web page generating device may receive a user input for selecting at least one of the first template candidates (S304), and generate a web page based on the selected first template candidate (S304). S305). In particular, the apparatus for creating a web page may provide an environment in which the user can freely edit the first template candidate by providing an editing/editor tool/function/interface for the selected first template candidate.

The template of the web page generated based on the selected first template candidate may be stored in the database together with related information. Here, the related information includes the type, location, layout, composition, composition, arrangement, design, color, category information, etc. of the components (eg, 610-1 to 610-6 in FIG. 6) included in the final template template. may correspond to relevant information. Furthermore, as will be described later, when a template is registered and sold in the template market, information such as popularity/sales ranking, cumulative sales amount, rating, etc. may also be stored in the database for the corresponding template as related information.

7 is a flowchart illustrating a component recommendation method according to an embodiment of the present invention, and FIG. 8 is a diagram illustrating a first template candidate being edited according to an embodiment of the present invention.

The component recommendation method proposed in this flowchart will be described focusing on the case where it is applied in the process of editing the first template candidate selected through the above-described template recommendation method, but is not limited thereto, and the user can use the first template candidate without selecting the first template candidate. Of course, it can also be applied to the case of directly creating a template from scratch.

Referring to FIGS. 7 and 8 , the apparatus for creating a web page may first receive a user input (eg, a drag input, etc.) designating a component insertion area 820 within the first template candidate 810 being edited. (S701).

Next, the web page generating apparatus may recognize types and location information of the components 810-1 to 810-4 included in the surrounding/surrounding area except for the area specified in step S701 (S702). Here, the type information of the components 810-1 to 810-4 may include image, video, photo, text, graph, table, GUI, icon, (HTML) tag, and/or combination information thereof, and the component 810 -1 to 810-4) may include geometry (eg, x, y coordinate information), layout, arrangement, composition, size, and/or combination information of each component.

Next, the web page generating device may search for and extract a second template candidate in the database where the similarity of the type and location of the recognized components 810-1 to 810-4 is higher than a preset level (S703). . In this case, the web page generating apparatus may reduce search time/burden by searching for the second template candidate only within the same similar template group as the first template candidate 810 .

Next, the web page generating device may extract component candidates included in the designated area 820 from the extracted second template candidates (S704).

As illustrated in this figure, the apparatus for generating a web page includes a plurality of second template candidates 910 having a high similarity to the neighboring components 810-1 to 810-4 of the first template candidate 810 illustrated in FIG. ~ 940) can be extracted. The web page generating apparatus may extract at least one component candidate 910 - 1 to 940 - 3 included in the designated area 820 from the extracted second template candidates 910 to 940 . Referring to this drawing, components 910-1 to 910-3 are included in the first second template candidate 910, components 920-1 are included in the second second template candidate 920, and components 920-1 are included in the third second template candidate 920. Components 930 - 1 and 930 - 2 may be extracted as component candidates in 930 and components 940 - 1 to 940 - 3 in the fourth second template candidate 940 .

Referring back to FIG. 7 , next, the web page generating apparatus may provide the extracted component candidates to the user (S705), and may receive a user input for selecting at least one of the extracted component candidates (S706). The web page generating device may insert the selected component candidate into a designated area of the first template candidate (S707).

Referring to FIG. 10 , the apparatus for generating a web page may provide a user with a selection interface 1010 through which at least one of the extracted component candidates 910-1 to 940-2 may be selected. The user inputs a selection (for example, a specific second template candidate 910-2, 930-2, 940-1) can be selected and dragging and dropping to the designated area 820) can be performed, and the web page generating device can perform component candidates selected by the user (910-2, 930-2, 940- 1) may be inserted into the designated area 820. The web page generating device applies an automatic fitting function when inserting the component candidates 910-2, 930-2, and 940-1, and adjusts the size, arrangement, and composition of the component candidates 910-2, 930-2, and 940-1. , Layout, etc. can be inserted by automatically adjusting/fitting to the designated area. For example, as illustrated in this figure, when a plurality of component candidates 910-2, 930-2, and 940-1 are selected by a user input, the web page generating apparatus selects three component candidates 910-2. , 930-2, and 940-1) can be inserted into the designated area 820 after automatically adjusting their size, shape, and layout so that all of them can be inserted into the designated area 820 without duplication.

Although not shown in the flowchart and drawings, the web page generating device may provide a component search function so that a user can directly search for a component to be inserted into the designated area 820 . The user can directly search for and insert a desired component by directly inputting information about a tag to be inserted into the designated area 820 through the corresponding function.

The method for extracting component candidates described above may be performed based on a pre-constructed component recommendation model by AI learning a plurality of templates according to an embodiment. Here, the component recommendation model is a component candidate prediction model built by AI learning the component type, position, composition, arrangement and/or layout of each of a plurality of templates. , an operation of predicting a component candidate having a high possibility of being inserted into the designated area 820 may be performed. In particular, the component recommendation model learns the components 910-1 to 940-3 included in the designated area 820 from the previously extracted second template candidates 910 to 940, and converts the components to the designated area 820. Insertion patterns/characteristics/features can be extracted. Furthermore, the component recommendation model may predict a component candidate having a high possibility of being inserted into the designated region 820 based on the extracted insertion pattern/characteristic/feature, and provide/recommend it to the user.

When the user completes the creation of the web page, the web page generating device templates the web page and registers/stores the web page together with related information in a cloud database. Templates registered/stored in the database can be automatically linked to the template market and registered as sales targets. Registered/stored templates can be used as template sample data recommended/learned when other webs are created later.

Templates may be classified according to category information input by a user when creating a web page and registered for sale in the template market. Templates can be recommended in order based on sales information such as popularity ranking, number of sales, cumulative sales amount, cumulative sales volume, rating, and/or user reviews, and according to the order of recommendation, as illustrated in this figure, the template market is ranked at the top. may be exposed. Components included in the template may also be registered in the template market as a separate sale target, and may be exposed according to a recommendation order as illustrated in this figure.

The template purchased by the user may be loaded into the user's web page generating device, and a web page may be created by freely editing according to the above-described embodiment.

A recommendation ranking (and/or sales information) of each template and/or component may also be stored in a database together with the corresponding template and/or component, and may be used as a criterion for assigning weight when determining similarity. For example, more weight may be assigned to a template and/or component having a higher recommendation rank in determining similarity.

An embodiment according to the present invention may be implemented by various means, for example, hardware, firmware, software, or a combination thereof. In the case of hardware implementation, one embodiment of the present invention provides one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), FPGAs ( field programmable gate arrays), processors, controllers, microcontrollers, microprocessors, etc.

In addition, in the case of implementation by firmware or software, an embodiment of the present invention is implemented in the form of a module, procedure, function, etc. that performs the functions or operations described above, and is stored on a recording medium readable through various computer means. can be recorded. Here, the recording medium may include program commands, data files, data structures, etc. alone or in combination. Program instructions recorded on the recording medium may be those specially designed and configured for the present invention, or those known and usable to those skilled in computer software. For example, recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs (Compact Disk Read Only Memory) and DVDs (Digital Video Disks), floptical It includes hardware devices specially configured to store and execute program instructions, such as magneto-optical media, such as a floptical disk, and ROM, RAM, flash memory, and the like. Examples of program instructions may include high-level language codes that can be executed by a computer using an interpreter or the like as well as machine language codes generated by a compiler. These hardware devices may be configured to act as one or more software modules to perform the operations of the present invention, and vice versa.

In addition, an apparatus or terminal according to the present invention may be driven by a command that causes one or more processors to perform the functions and processes described above. For example, such instructions may include interpreted instructions, such as script instructions such as JavaScript or ECMAScript instructions, or executable code or other instructions stored on a computer readable medium. Furthermore, the device according to the present invention may be implemented in a distributed manner over a network, such as a server farm, or may be implemented in a single computer device.

In addition, a computer program (also known as a program, software, software application, script or code) loaded into a device according to the present invention and executing the method according to the present invention includes a compiled or interpreted language or a priori or procedural language. It can be written in any form of programming language, and can be deployed in any form, including stand-alone programs, modules, components, subroutines, or other units suitable for use in a computer environment. A computer program does not necessarily correspond to a file in a file system. A program may be in a single file provided to the requested program, or in multiple interacting files (e.g., one or more modules, subprograms, or files that store portions of code), or parts of files that hold other programs or data. (eg, one or more scripts stored within a markup language document). A computer program may be deployed to be executed on a single computer or multiple computers located at one site or distributed across multiple sites and interconnected by a communication network.

For convenience of description, each drawing has been divided and described, but it is also possible to design to implement a new embodiment by merging the embodiments described in each drawing. In addition, the present invention is not limited to the configuration and method of the described embodiments as described above, but the above-described embodiments are configured by selectively combining all or part of each embodiment so that various modifications can be made. It could be.

In addition, although preferred embodiments have been shown and described above, this specification is not limited to the specific embodiments described above, and those skilled in the art in the art to which the specification pertains without departing from the subject matter claimed in the claims Of course, various modifications are possible by the person, and these modifications should not be individually understood from the technical spirit or perspective of the present specification.

It is available in the webpage industry field.

Claims

In the template recommendation method for creating a web page,

Receiving category information about a web page to be created for each category item from a user;

extracting, from among a plurality of pre-registered templates, a template having category information having a higher degree of similarity with the input category information than a preset level, as a first template candidate;

providing the extracted first template candidate to the user;

receiving a user input for selecting at least one of the first template candidates; and

generating a web page based on the selected first template candidate; Including, a template recommendation method for generating a web page.
According to claim 1,

The category items are,

The field of service to be provided through the web page, the main service customer group that will use the web page, the main function of the web page, the additional function of the web page, the design concept of the web page, the color of the web page, and the operator of the web page A template recommendation method for generating a web page, including at least one of the jobs of
According to claim 1,

The step of extracting the first template candidate,

generating a decision tree in which each category item corresponds to a classification criterion for each decision stage;

deriving a template similarity group to which the input category information belongs by inputting the input category information into the decision tree for each decision step; and

extracting a template classified as the derived template similarity group as the first template candidate; Including, a template recommendation method for generating a web page.
According to claim 3,

To create the decision tree,

classifying the plurality of templates into a template similarity group of a predetermined number based on template similarity;

extracting common category information for each template-like group; and

generating the decision tree by setting each of the template similar groups as a final node and setting a classification criterion for each decision stage based on common category information for each similar group; Including, a template recommendation method for generating a web page.
According to claim 3,

providing an editing function for the selected first template candidate; Further comprising a template recommendation method for generating a web page.
According to claim 5,

In the step of providing the editing function,

receiving a user input designating a region to insert a component among the selected first template candidates;

Recognizing a type and position of a component included in a peripheral area excluding a designated area based on the user input;

extracting a second template candidate having a similarity of the type and position of the recognized component higher than a predetermined level;

extracting component candidates included in the designated area from the extracted second template candidates;

providing the extracted component candidate to the user;

receiving a user input for selecting at least one of the extracted component candidates; and

inserting a selected component candidate into the designated area; Including, a template recommendation method for generating a web page.
According to claim 6,

The component includes at least one of a graph, table, image, video, text, GUI (Graphic User Interface), and a combination thereof, a template recommendation method for generating a web page.
According to claim 6,

The second template candidate is extracted from the same template similar group as the selected first template candidate.
According to claim 6,

When a plurality of component candidates are selected by the user input, the step of inserting the selected component candidates into the designated area includes:

automatically adjusting the size and position of the selected component candidate so that it is inserted into the designated area without duplication; Including, a template recommendation method for generating a web page.
According to claim 6,

The step of extracting the component candidate,

A template recommendation method for generating a web page, which is performed based on a pre-built component recommendation model by AI (Artificial Intelligence) learning of the plurality of templates.
According to claim 10,

The component recommendation model is built by AI learning at least one of the type, location, composition, arrangement, and layout of each component of the plurality of templates,

The step of extracting the component candidate,

extracting an insertion pattern of a component included in the designated area from the extracted second template candidate; and

predicting a component candidate to be inserted into the designated region based on the extracted insertion pattern and extracting the component candidate as the component candidate; Including, a template recommendation method for generating a web page.
According to claim 1,

Linking the created web page template to the template market;

Selling linked templates through the template market; and

including the linked template in the plurality of templates; Further comprising a template recommendation method for generating a web page.