KR102434054B1 - Thumbnail template generating device including skin treatment information, and operating method thereof - Google Patents

Abstract

An operating method of a template generating device according to an embodiment of the present invention may comprise the steps of: receiving a request for requesting the generation of a template which is exposed to a device and which includes incentive information for inducing the inflow of users; obtaining display size information of the device on which the template is to be displayed; determining a template size corresponding to the display size; determining a template type corresponding to the request; determining a component layout which meets the request and includes component sizes and positions included in the template type; checking whether the request includes internal information requesting application of an internal factor, which is an element stored in the template generating device, and assigning a weight; when the internal factor is included in the request, readjusting the component layout to conform to the internal factor; and generating a result template conforming to the request. The present invention can easily provide a consumer with a thumbnail instance which meet the needs of the consumer.

Description

Thumbnail template generating device including skin treatment information, and operating method thereof

The present disclosure relates to a customer participation type thumbnail template generating apparatus including skin treatment information and a template operation method.

The non-face-to-face situation caused by the pandemic has induced people to recharge, rest, and personal reorganization time, and explosively increased interest in beauty and skin treatments.

As factors for consumers to decide on skin treatment for skin beauty, treatment cost, treatment equipment, and medical staff are considered. exposing to and mocking However, the thumbnail banner instance is composed of a background layer, a component layer, etc., and there are countless combinations of various designs, colors, objects, and components to configure each, so it is not easy to produce an appropriate banner instance to induce consumers.

To solve this, some of the so-called 'beauty platform' companies that expose dermatology clinics and connect dermatology clinics and consumers provide a function that automatically creates and creates thumbnail templates for the convenience of dermatology clinics. However, the automatically generated thumbnail template produces only a uniform result compared to the various combinations of various components. Accordingly, there is a need for an advanced technology for automatically generating an appropriate thumbnail instance that precisely meets the needs of the consumer.

Registered Patent Publication No. 10-1647442 B1 (2016.08.10.)

An object of the present disclosure is to provide a customer participation type thumbnail template generating apparatus and a template operation method including skin treatment information.

The problems to be solved by the present disclosure are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the following description.

A method of operating an apparatus for generating a thumbnail template for solving the above-described problem includes the steps of receiving a request requesting generation of a thumbnail template that is exposed to a device and includes incentive information for inducing an inflow of a user, the thumbnail template is displayed Acquiring display size information of the device to be used, determining a thumbnail template size corresponding to the display size, determining a thumbnail template type corresponding to a request, a component size corresponding to the request, and included in the thumbnail template type; Determining the component layout including the position, checking whether internal information requesting to apply the internal factor, which is an element stored in the thumbnail template generating device, is included in the request and giving weight to the request, the internal factor is the request When included in , it may include the steps of re-adjusting the component layout to conform to the internal factor and generating a result thumbnail template matching the request.

According to an exemplary embodiment, the thumbnail template type is a text-type thumbnail template composed of only letters, a text-based image thumbnail template that displays letters and images corresponding to dermatological procedures, and a mechanical thumbnail that emphasizes medical devices used in dermatological procedures. A template, a stimulus-type thumbnail template containing stimulus keywords to stimulate user demand, an age-type thumbnail template targeting dermatological treatment targets, a cost-type thumbnail template informing the cost of dermatological procedures, and drug ingredients used in dermatological procedures It may be characterized by including a component-type thumbnail template that emphasizes the

According to an exemplary embodiment, the thumbnail template type is based on the sales information in the platform where the thumbnail template generating device is used and the trend information on the web, the instance that generated the maximum sales, the instance that recorded the maximum conversion rate, and the interest within a predetermined time. Instances that have soared, instances that contain keywords of interest set as keywords of interest by many are learned, and instances that generated the maximum sales as a result of learning, instances that recorded the maximum conversion rate, instances whose interest soared within a predetermined time, and keywords of interest by many It may be substantially the same as any one of the instances including the set interest keyword, but may include an artificial intelligence (AI) thumbnail template that is a thumbnail template corresponding to the request.

According to an exemplary embodiment, the AI thumbnail template may include a background layer, an image layer, and a keyword layer.

According to an exemplary embodiment, the internal factor indicates that different weights are given based on sales information, search log information, interest setting information, and trend information crawled on the web in the platform in which the thumbnail template generating device is used. can be characterized.

According to an exemplary embodiment, the step of determining whether internal information is included and assigning weights may include, when the request includes a first sub-request that mimics the instance generating the maximum revenue in the platform, it is added to the component layout of the instance generating the maximum revenue. Step 1 weighting, if the request includes a second sub-request that mimics the instance with the highest conversion rate in the platform, adding a second weight to the component layout of the instance generating the maximum conversion rate, interest in the request soars in the platform When a third sub-request that imitates an instance is included, giving a third weight to the component layout of the instance of increasing interest, and setting multiple users when the request includes a fourth sub-request that imitates a multiple user-set interest keyword instance It may be characterized in that it comprises the step of giving a fourth weight to the component layout of the keyword instance of interest.

According to an exemplary embodiment, the method of operation of the thumbnail template generating apparatus is a result of artificial intelligence-based learning of instances of generating maximum sales, instances of generating maximum conversion rates, instances of surge in interest, and instances of setting interest keywords set by users, and maximum sales The method may further include the step of giving a plurality of fifth weights corresponding to the occurrence instance, the maximum conversion rate occurrence instance, the interest surge instance, and the multiple user-set interest keyword setting instance.

According to an exemplary embodiment, the receiving of the request may include receiving the request generated from the sales management apparatus.

As an exemplary embodiment for solving the above-described problems, a computer-readable recording medium may be combined with a computer, which is hardware, and a program for executing the method may be stored.

As an exemplary embodiment for solving the above problems, the thumbnail template generating device includes a communication interface and a memory configured to receive a request from the sales management device, and the memory is web crawling configured to collect trend information of dermatological procedures An artificial neural network processing module configured to generate maximum sales instance, maximum sales conversion rate occurrence instance, interest surge instance, and multiple user-set interest keyword instances by learning sales information and trend information in the platform in which the module and thumbnail template generator are used, and and a thumbnail template generating module configured to generate a result thumbnail template corresponding to the request.

Other specific details of the present disclosure are included in the detailed description and drawings.

An apparatus for generating a thumbnail template and an operating method thereof according to an exemplary embodiment of the present disclosure provide an environment in which a customer can easily create a template including a layout and keywords desired by the customer, thereby generating a thumbnail instance that meets the needs of the consumer. It can be easily provided to consumers.

In addition, an apparatus for generating a thumbnail template and an operating method thereof according to an exemplary embodiment of the present disclosure automatically generate a thumbnail template that maximizes the attracting effect by using internal elements within the platform and/or external elements on the web in which the thumbnail template generating apparatus is used. can be produced with

In addition, the apparatus for generating a thumbnail template and an operating method thereof according to an exemplary embodiment of the present disclosure generate an artificial intelligence template using an artificial neural network, thereby producing an appropriate banner instance without a specific and detailed request input from the production requester.

Effects of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

1 is a block diagram illustrating a platform environment in which an apparatus for generating a thumbnail template according to an exemplary embodiment of the present disclosure is used.
2 is a block diagram illustrating an apparatus for generating a thumbnail template according to an exemplary embodiment of the present disclosure.
3 is a block diagram illustrating a sales management apparatus according to an exemplary embodiment of the present disclosure.
4 is a diagram conceptually illustrating the generation of a thumbnail template by the apparatus for generating a thumbnail template according to an exemplary embodiment of the present disclosure.
5 is a diagram illustrating a layout of a thumbnail template according to an exemplary embodiment of the present disclosure.
6 is a diagram showing the configuration of an artificial intelligence template according to an exemplary embodiment of the present disclosure.
7 is a flowchart illustrating an operation method of an apparatus for generating a thumbnail template according to an exemplary embodiment of the present disclosure.
8 is a flowchart illustrating an operation method of an apparatus for generating a thumbnail template according to an exemplary embodiment of the present disclosure.
9 is a block diagram illustrating an operation of generating an artificial intelligence (AI) template using an artificial neural network of the apparatus for generating a thumbnail template according to an exemplary embodiment of the present disclosure.

Advantages and features of the present disclosure and methods of achieving them will become apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present disclosure is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only the present embodiments allow the disclosure of the present disclosure to be complete, and those of ordinary skill in the art to which the present disclosure pertains. It is provided to fully understand the scope of the present disclosure to those skilled in the art, and the present disclosure is only defined by the scope of the claims.

The terminology used in the present disclosure is for the purpose of describing the embodiments and is not intended to limit the present disclosure. In this disclosure, the singular may also include the plural unless specifically stated otherwise in the phrase. As used in the disclosure, “comprises” and/or “comprising” does not exclude the presence or addition of one or more other components in addition to the stated components. Like reference numerals refer to like elements throughout the disclosure, and "and/or" may include each and every combination of one or more of the recited elements. Although "first", "second", etc. are used to describe various elements, these elements are not limited by these terms, of course. These terms are only used to distinguish one component from another. Accordingly, it goes without saying that the first component mentioned below may be the second component within the spirit of the present disclosure.

The word "exemplary" is used in this disclosure in the sense of "used as an illustration or illustration." Any embodiment described as “exemplary” in this disclosure should not necessarily be construed as preferred or advantageous over other embodiments.

Embodiments of the present disclosure may be described in terms of a function or a block performing a function. Blocks, which may be referred to as 'parts' or 'modules' of the present disclosure, etc., include logic gates, integrated circuits, microprocessors, microcontrollers, memories, passive electronic components, active electronic components, optical components, hardwired circuits, and the like. It may be physically implemented by analog or digital circuitry, such as, and optionally driven by firmware and software. Also, the term “unit” as used in the disclosure refers to a hardware element such as software, Field Programmable Gate Array (FPGA), or Application Specific Integrated Circuits (ASIC), and “unit” may perform certain roles. However, "part" is not meant to be limited to software or hardware. A “unit” may be configured to reside on an addressable storage medium and may be configured to refresh one or more processors. Thus, by way of example, “part” refers to elements such as software elements, object-oriented software elements, class elements, and task elements, and processes, functions, properties, procedures, subroutines, and programs. It may include segments of code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables. The functionality provided within elements and “parts” may be combined into a smaller number of elements and “parts” or further separated into additional elements and “parts”.

Embodiments of the present disclosure may be implemented using at least one software program running on at least one hardware device and may perform a network management function to control an element.

Spatially relative terms "below", "beneath", "lower", "above", "upper", etc. It can be used to easily describe the correlation between a component and other components. A spatially relative term may be understood as a term that includes different directions of components during use or operation in addition to the directions shown in the drawings. For example, when a component shown in the drawing is turned over, a component described as "beneath" or "beneath" of another component is placed "above" of the other component. can get Accordingly, the exemplary term “below” may include both directions below and above. Components may also be oriented in other orientations, and thus spatially relative terms may be interpreted according to orientation.

In each step, the identification code is used for convenience of description, and the identification code does not describe the order of each step, and each step may be performed differently from the specified order unless the specific order is clearly stated in the context. have.

Unless otherwise defined, all terms (including technical and scientific terms) used in this disclosure may be used with the meanings commonly understood by those of ordinary skill in the art to which this disclosure belongs. In addition, terms defined in a commonly used dictionary are not to be interpreted ideally or excessively unless clearly specifically defined.

Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings.

1 is a block diagram illustrating a platform environment 10 in which an apparatus 100 for generating a thumbnail template according to an exemplary embodiment of the present disclosure is used.

The platform environment 10 provides a function that connects consumers and suppliers. According to an exemplary embodiment, the platform environment 10 may be an intangible virtual space that is used as a base for potential customers of dermatology hospitals by collecting, classifying, and integrated management of dermatology hospital information providing services such as procedure information and price policies of dermatology hospitals. have. A consumer (or a patient, or a customer) who is a potential customer of a dermatology hospital can check the procedure information and price policy of the dermatology hospital through the platform environment 10, and the dermatology hospital can check the dermatology procedure information and price policy in the platform environment 10 etc can be posted.

In addition, the dermatology hospital may attract consumers through the platform environment 10 . For example, a dermatological hospital may induce customers by displaying thumbnail banner instances including various information on dermatological procedures through the platform environment 10 . Here, thumbnail is a miniaturization of , and it is a miniaturized graphic file image with various sizes and shapes in the forward or direct direction that contains the type of treatment, price information, and keywords to attract customers in a small image.

The platform environment 10 includes a thumbnail template generating device 100 and a plurality of sales management devices 200 , and the plurality of sales management devices 200 include a first sales management device 201 and a second sales management device. a device 202 , and an n-th sales management device 203 . Although not shown in the drawings, the platform environment 10 includes a device that is a user terminal of a consumer. The thumbnail template generating apparatus 100 , the plurality of sales management apparatuses 200 , and the device (user terminal of the consumer) may communicate with each other through the network 300 .

The thumbnail template generating apparatus 100 may include a template generating module, a web crawling module, and a machine learning module (in the present disclosure, a machine learning module is mixed with an artificial neural network processing module).

According to an exemplary embodiment of the present disclosure, the thumbnail template generating apparatus 100 may receive a request from the sales management apparatus 200 and generate a thumbnail template. The request may or may not include an internal factor application request.

The thumbnail template generating apparatus 100 according to an exemplary embodiment of the present disclosure may generate an appropriate thumbnail banner instance even if an internal factor application request is not included or the request is limited. According to an exemplary embodiment of the present disclosure, the thumbnail template generating apparatus 100 includes internal elements (sales, conversion rate, multiple user-set interest keywords, etc.) in the platform environment 10, and external elements obtained through a web crawling module. Thumbnails with optimal component size, location, and layout through either re-adjusting the component size, position, and layout of the thumbnail template in a rule-based method based on (increasing interest keywords, etc.) By creating a template, you can create a thumbnail banner instance and display it on the device.

Here, communication through the network 300 , ie, data transmission and reception, may be performed by wire or wirelessly. To this end, the thumbnail template generating apparatus 100 and the communication unit (not shown) of each of the plurality of sales management apparatuses 200 communicate with each other through a wired communication module connected to the Internet through a local area network (LAN), and a mobile communication base station through a mobile communication base station. A mobile communication module that accesses a network to transmit and receive data, a wireless local area network (WPAN) series such as Wi-Fi, or a wireless personal area network (WPAN) series such as Bluetooth and Zigbee It may be composed of a short-range communication module using a communication method of

Thumbnail template generating apparatus 100, and a plurality of sales management apparatus 200 is a network 300 through the technical standards or communication method (eg, GSM (Global System for Mobile communication), CDMA (Code Division Multi Access) ), CDMA2000 (Code Division Multi Access 2000), EV-DO (Enhanced Voice-Data Optimized or Enhanced Voice-Data Only), WCDMA (Wideband CDMA), HSDPA (High Speed Downlink Packet Access), HSUPA (High Speed Uplink Packet Access) ), Long Term Evolution (LTE), Long Term Evolution-Advanced (LTE-A), etc.) can transmit and receive radio signals with at least one of a base station, an external terminal, and an external server.

As the wireless technology of the present disclosure, for example, WLAN (Wireless LAN), Wi-Fi (Wireless-Fidelity), Wi-Fi (Wireless Fidelity) Direct, DLNA (Digital Living Network Alliance), WiBro (Wireless Broadband), WiMAX (World Interoperability for Microwave Access), HSDPA (High Speed Downlink Packet Access), HSUPA (High Speed Uplink Packet Access), LTE (Long Term Evolution), LTE-A (Long Term Evolution-Advanced), and the like.

In addition, the communication technology of the present disclosure is Bluetooth (Bluetooth??), RFID (Radio Frequency Identification), infrared communication (Infrared Data Association; IrDA), UWB (Ultra Wideband), ZigBee, NFC (Near Field Communication), Wi- Fi (Wireless-Fidelity), Wi-Fi Direct, Wireless USB (Wireless Universal Serial Bus), TTL (Transistor-Transistor Logic), USB, IEEE1394, Ethernet, MIDI (Musical Instrument Digital Interface), RS232, RS422, RS485, optical communication (Optical Communication), using at least one of a coaxial cable communication (Coaxial Cable Communication) technology, may include a technology for supporting communication.

2 is a block diagram illustrating an apparatus 100 for generating a thumbnail template according to an exemplary embodiment of the present disclosure.

Thumbnail template generating device 100 is a mobile phone, a smart phone (smart phone), a laptop computer (laptop computer), a digital broadcasting terminal, PDA (personal digital assistants), PMP (portable multimedia player), navigation, slate PC (slate PC) , tablet PC (tablet PC), ultrabook (ultrabook), wearable device (eg, smartwatch, glass-type terminal (smart glass), HMD (head mounted display)), workstation, server , but may be an electronic device such as a cloud server, but is not limited thereto, and collectively refers to an electronic processing device that provides a computing function for processing data, or a combination of electronic processing devices.

The communication interface 110 may be configured to receive a request from the sales management device. The communication interface 110 may communicate with an external device. Accordingly, the thumbnail template generating apparatus 100 may transmit/receive information to and from an external device through the communication interface 110 . The communication interface 110 may include at least one of a WiFi (Wireless-Fidelity) chip, a Bluetooth® chip, a wireless communication chip, a Near Field Communication (NFC) chip, and a Radio Frequency Identification (RFID) chip. . A description overlapping with FIG. 1 will be omitted.

The API (Application Programming Interface) server 120 may provide a programming interface. Through the API server 120 , a web client in the platform environment 10 , and a mobile client can be run as applications. API refers to a language format used for communication between an operating system and an application program. An API is implemented by having a program module or routine and calling a function that provides a connection to a specific subroutine for execution within the program.

The web server 130 provides a web interface. Using the web server 130, the web crawling module 143 can access the World Wide Web.

The API server 120 and the web server 130 are connected to one or more application servers, and in an exemplary embodiment, the processor 150 may function as an application server.

The memory 140 may be a local storage medium supporting various functions of the processor 150 . The memory 140 may store an application program that can be driven by the processor 150 , data for an operation of the processor 150 , and instructions. At least some of these applications may be downloaded from the outside through wireless communication. The application program may be stored and installed in the memory 140 and driven to perform an operation (or function) by the processor 150 .

Memory 140 is DDR SDRAM (Double Data Rate Synchronous Dynamic Random Access Memory), LPDDR (Low Power Double Data Rate) SDRAM, GDDR (Graphics Double Data Rate) SDRAM, RDRAM (Rambus Dynamic Random Access Memory), DDR2 SDRAM, DDR3 It may be a volatile memory including a dynamic random access memory (DRAM) such as SDRAM or DDR4 SDRAM.

However, embodiments of the present disclosure need not be limited thereto. In an exemplary embodiment, the memory 140 should retain data even when power supplied to the processor 150 is cut off, and may be provided as a writable non-volatile memory to reflect changes. have. However, the memory 140 is not limited thereto, and the memory 140 includes, but is not limited to, flash memory or resistive memory cells such as EPROM or EEPROM, resistive RAM (ReRAM), phase change RAM (PRAM), magnetic RAM (MRAM), and MRAM (MRAM). Spin-Transfer Torgue MRAM), Conductive bridging RAM (CBRAM), Ferroelectric RAM (FeRAM), and various other types of memory may be applied. Alternatively, the memory 140 may include an embedded multimedia card (eMMC), a universal flash storage (UFS), or a Compact Flash (CF), Secure Digital (SD), Micro-SD (Micro Secure Digital) , Mini-SD (Mini Secure Digital), xD (extreme digital), or memory stick (Memory Stick) can be implemented in various types of devices. In the present disclosure, it is described that all instruction information is stored in one memory 140 for convenience of description, but the present disclosure is not limited thereto, and the memory 140 may include a plurality of memories.

According to an exemplary embodiment of the present disclosure, the memory 140 may include a template generation module 141 , a web crawling module 143 , and an artificial neural network processing module 145 . In the present disclosure, when the template generation module 141 , the web crawling module 143 , and the artificial neural network processing module 145 provided in the memory 140 are fetched by the processor 150 , the processor 150 ) within the template generation unit (not shown), the web crawling unit (not shown), and the artificial neural network processing unit 151, it will be widely understood by those skilled in the art that it can operate as a logical operation unit, respectively.

The web crawling module 143 accesses social network services, search word trends, social clubs and cafes related to skin beauty, trend analysis tools, etc. through the world wide web, and keywords, issue keywords, of interest related to dermatology surgeries Trend information such as (hot keyword) and popular dermatology procedure information can be mechanically collected and indexed (crawling).

The template generation module 141 is based on internal factors (sales, conversion rate, multiple user set interest keywords, etc.) in the platform environment 10 and external factors (interest surge keywords, etc.) acquired through the web crawling module 143 Thus, it is possible to readjust the size, position, and layout of the components of the thumbnail template in a rule-based manner.

The artificial neural network processing module 145 may create a thumbnail banner instance by generating a thumbnail template having an optimal component size, position, and layout through learning of internal and external elements.

According to an exemplary embodiment of the present disclosure, the artificial neural network processing module 145 learns the sales information and trend information in the platform environment 10 in which the thumbnail template generating apparatus 100 is used, thereby generating the maximum sales instance, the maximum sales. It may be configured to generate a conversion rate occurrence instance, an interest surge instance, and a plurality of user-set interest keyword instances.

The processor 150 processes one or more commands necessary for controlling the thumbnail template generating apparatus 100, performs an operation according to the commands, and performs a determination according to program logic, etc. Organic operations of various functional units of the platform environment 10 is configured to control overall. The processor 150 may process signals, data, information, etc. input or output through the communication interface 110 or drive an application program stored in the memory 140 to provide or process appropriate information or functions to the user. . The processed data may be stored in the memory 140 , used to build the database server 160 , or transmitted to the outside through the communication interface 110 . Such a processor 150 may be implemented as a general-purpose processor, a dedicated processor, or an application processor. In an exemplary embodiment, the processor 150 includes a computational processor (eg, a central processing unit (CPU)) including dedicated logic circuits (eg, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), etc.) , GPU (Graphic Processing Unit), AP (Application Processor), etc.), but is not limited thereto. In an exemplary embodiment, the processor 150 is a digital signal processor (DSP) capable of converting an analog signal to digital and high-speed processing, a micro controller unit (MCU), or a neural processing unit (NPU) specialized for processing an artificial neural network. It is not excluded that it is implemented as such.

When the processor 150 functions as an application server, the artificial neural network processing unit 151 may be hosted. The processor 150 may couple to one or more database servers 160 , which in turn enable access to one or more information storage repositories or database servers 160 .

In addition to the operation related to the application program executed by the thumbnail template generating device 100 and the thumbnail template generating device 100, the processor 150 includes learning for building an artificial intelligence learning model, repetitive four-ruling operations necessary for learning, and It is possible to execute reasoning on the learning data using artificial intelligence to which the built learning model is applied and to control various modules for artificial intelligence processing.

In addition to the operation related to the application program executed by the thumbnail template generating device 100 and the thumbnail template generating device 100, the processor 150 includes learning for building an artificial intelligence learning model, repetitive four-ruling operations necessary for learning, and It is possible to execute reasoning on the learning data using artificial intelligence to which the built learning model is applied and to control various modules for artificial intelligence processing. In this case, in addition to the artificial intelligence operating inside the processor 150 , the artificial neural network processing unit 151 , which is a processing device specialized in artificial intelligence learning and calculation, may be provided in the thumbnail template generating apparatus 100 . In FIG. 1, the artificial neural network processing unit 151 is shown with a dotted line, which collectively refers to an artificial intelligence-only processor implemented separately from the processor 150, or a processing module of a logical concept implemented inside the processor 150. The artificial neural network processing unit 151 may mean a logical functional unit implemented by the processor 150, or may refer to an ASIC or FPGA-based physical implementation unit separately provided for AI learning, and there is no limitation on the implementation form. .

According to an exemplary embodiment of the present disclosure, the artificial neural network processing unit 151 may implement artificial intelligence. Artificial intelligence refers to a machine learning method based on an artificial neural network that mimics human biological neurons and enables machines to learn. In the AI methodology, input data and output data are provided together as training data according to the learning method, so the answer (output data) to the problem (input data) is determined (supervised learning), and only input data is provided without output data In unsupervised learning in which the solution (output data) of the problem (input data) is not determined because of , can be divided into reinforcement learning in which learning proceeds in the direction of maximizing these rewards. In addition, the methodology of artificial intelligence can be divided according to the architecture, which is the structure of the learning model. The architectures of widely used deep learning technologies are Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), It can be divided into transformers, generative adversarial networks (GANs), and the like.

The artificial neural network processing unit 151 generates a neural network, trains the neural network, or performs an operation based on received input data, and an information signal based on the result of the execution. ) or retrain the neural network. Neural network models are CNN (Convolution Neural Network) such as GoogleNet, AlexNet, VGG Network, R-CNN (Region with Convolution Neural Network), RPN (Region Proposal Network), RNN (Recurrent Neural Network), S-DNN (Stacking) -based deep neural network), S-SDNN (State-Space Dynamic Neural Network), Deconvolution Network, DBN (Deep Belief Network), RBM (Rested Boltzman Machine), Fully Convolutional Network, LSTM (Long Short-Term Memory) Network, Various types of models such as Classification Network, Transformer, BERT, GPT-3, and GPT-4 may be included, but are not limited thereto. The artificial neural network processing unit 151 may include one or more processors for performing operations according to models of the neural network.

The database server 160 refers to a set of data that is integrated and managed for the purpose of being shared and used by storing various types of information. The database server 160 may temporarily or semi-permanently store data. For example, the database server 160 includes an operating program (OS) for driving at least one device, data for hosting a website, or data related to an application (eg, a web application). can be saved. In addition, the database may store the modules in the form of computer code as described above. The database server 160 is managed through middleware separate from the application program.

Examples of the database server 160 include a hard disk (HDD: Hard Disk Drive), SSD (Solid State Drive), flash memory (flash memory), ROM (Read-Only Memory), RAM (RAM: Random Access Memory) etc. may exist. Such a database may be provided in a built-in type or a detachable type.

The database server 160 includes a relational database (RDB), a key-value type database, an object type database, a document type database, a memory database, and the like.

According to an exemplary embodiment of the present disclosure, the thumbnail template generating apparatus 100 may receive a request from the sales management apparatus 200 and generate a thumbnail template. The request may or may not include an internal factor application request.

The thumbnail template generating apparatus 100 according to an exemplary embodiment of the present disclosure may generate an appropriate thumbnail banner instance even if an internal factor application request is not included or the request is limited. According to an exemplary embodiment of the present disclosure, the thumbnail template generating apparatus 100 includes internal elements (sales, conversion rate, multiple user-set interest keywords, etc.) in the platform environment 10, and external elements obtained through a web crawling module. Thumbnails with optimal component size, location, and layout through either re-adjusting the component size, position, and layout of the thumbnail template in a rule-based method based on (increasing interest keywords, etc.) By creating a template, you can create a thumbnail banner instance and display it on the device.

According to an exemplary embodiment of the present disclosure, the thumbnail template generating apparatus 100 may receive a request for generating a thumbnail template including incentive information for inducing a user's inflow from the sales management apparatus 200 . .

The thumbnail template generating apparatus 100 may obtain display size information of the device on which the thumbnail template is to be displayed, and determine the thumbnail template size corresponding to the display size.

The thumbnail template generating apparatus 100 may determine a thumbnail template type corresponding to the request, and determine a component size, position, and layout including a size and position of a component included in the thumbnail template type.

The thumbnail template generating apparatus 100 may check whether the request includes internal information requesting to apply the internal factor, which is an element stored in the thumbnail template generating apparatus. When the request includes an internal factor application request, the thumbnail template generating apparatus 100 may assign a weight to the request and readjust the component size position and layout to match the internal factor. As a result, the thumbnail template generating apparatus 100 may generate the result thumbnail template and complete the production of the thumbnail banner instance. The thumbnail template generating apparatus 100 may display a thumbnail banner instance on the device.

An apparatus for generating a thumbnail template and an operating method thereof according to an exemplary embodiment of the present disclosure provide an environment in which a customer can easily create a template including a layout and keywords desired by the customer, thereby generating a thumbnail instance that meets the needs of the consumer. It can be easily provided to consumers.

In addition, an apparatus for generating a thumbnail template and an operating method thereof according to an exemplary embodiment of the present disclosure automatically generate a thumbnail template that maximizes the attracting effect by using internal elements within the platform and/or external elements on the web in which the thumbnail template generating apparatus is used. can be produced with

In addition, the apparatus for generating a thumbnail template and an operating method thereof according to an exemplary embodiment of the present disclosure generate an artificial intelligence template using an artificial neural network, thereby producing an appropriate banner instance without a specific and detailed request input from the production requester.

3 is a block diagram illustrating a sales management apparatus 200 according to an exemplary embodiment of the present disclosure.

The communication interface (I/F) 210 may communicate with an external device. Accordingly, the sales management apparatus 200 may transmit/receive information to and from an external device such as the thumbnail template generating apparatus 100 through the communication interface 210 . The communication interface 210 may include at least one of a WiFi (Wireless-Fidelity) chip, a Bluetooth® chip, a wireless communication chip, a Near Field Communication (NFC) chip, and a Radio Frequency Identification (RFID) chip. . A description overlapping with FIG. 1 will be omitted.

The web client 220 is also referred to as a web browser, moves in the web server 130, communicates in two directions, and outputs documents or files in a format such as Hyper Text Markup Language (HTML). It is a graphical user interface (GUI) based application software.

The web client 220 may access the thumbnail template generating system or the artificial neural network processing system through a web interface supported by the web server 130 . For example, the web client 220 may include a browser such as Internet Explorer® developed by Microsoft®, Chrome® developed by Google®, and Safari® developed by Apple Inc.®.

The client application 230 is an application program or service that can access a remote service on another computer system such as a server through the network 300 . In an exemplary embodiment, the client application 230 requests a service provided by the thumbnail template generating device 100 (request), and provides the necessary factors for the request according to the method desired by the thumbnail template generating device 100, , a program or system having a function of expressing a response (response) returned from the thumbnail template generating device 100 in a manner appropriate to the user.

The program client 240 enables, for example, a platform environment 10 building entity to create and manage a dermatology hospital listing on the network 300 in an online manner, and data between the program client 240 and the network 300 . It may be a platform-implemented application that performs communication (eg, a credit ticket® application developed by Fasttrain®). The program client 240 may access the thumbnail template generating system or the artificial neural network processing system through the program interface provided by the API server 120 .

The sales management apparatus 200 according to an exemplary embodiment of the present disclosure may generate a request indicating a thumbnail banner instance creation request, and transmit the request to the thumbnail template generation apparatus 100 .

The request may include the size of the banner instance, the size, position, and layout of the component. For example, the sales management device 200 sets the size of the banner instance to a size of 100x100 pixels, to place it at the bottom of the text frame banner instance as a component, and to display the dermatological treatment equipment as a background image , and a request each including placing the keyword in the upper center of the text component may be transmitted to the thumbnail template generating apparatus 100 .

In an exemplary embodiment, the request may include an internal factor application request. The internal factor is an internal factor (sales, conversion rate, multiple user set interest keywords, etc.) in the platform environment 10, and external factors (interest surge keywords, etc.) acquired through the web crawling module 143. include

According to an exemplary embodiment, platform internal elements such as sales, sales conversion rate, and keywords of interest set by a large number of users of dermatology clinics located on the platform where the thumbnail template generating device 100 is used are collected in the platform environment 10 and managed

According to an exemplary embodiment, dermatological procedures are performed from social network services collected from the web through the web crawling module 143 of the thumbnail template generating device 100, search word trends, social clubs and cafes related to skin beauty, trend analysis tools, and the like. Elements outside the platform, such as keywords that have soared interest in related topics, hot keywords, and trend information such as information on popular dermatology procedures, are mechanically collected and indexed (crawling). For example, a keyword with a surge in interest, a popular keyword, or an issue keyword means a word or token in which a search request, query, or command per unit time is equal to or greater than a threshold value.

According to an exemplary embodiment, the sales management device 200 may be operated for business management of a dermatology hospital. The sales management device 200 may request the thumbnail template generating device 100 to create a thumbnail banner instance in the form of a request to promote a dermatological procedure or to expose it to a dermatology hospital information sharing platform.

According to an exemplary embodiment, the sales management apparatus 200 may request, as a first request, to generate a first banner instance including its own dermatology hospital treatment cost, treatment equipment, medical staff, customer attraction keywords, and the like.

According to an exemplary embodiment, the sales management device 200 requests to include its own dermatology hospital treatment cost, treatment equipment, medical staff, and customer attraction keywords as the second request, but the platform environment 10 internal elements (sales, Sales conversion rate, keywords of interest set by multiple users, etc.) and/or external factors (social network services collected from the web, search word trends, social clubs and cafes related to skin beauty, trend analysis tools, etc.) It may be requested to create a second banner instance further including a keyword (hot keyword, trend information, such as popular dermatology treatment information).

According to an exemplary embodiment, the sales management device 200 is the third request, even if its own dermatology hospital treatment cost, treatment equipment, medical staff, customer attraction keywords, etc. are not directly input or included, the platform environment 10 internal elements (sales , sales conversion rate, multiple user-set interest keywords, etc.) and/or external factors (social network services collected from the web, search word trends, social clubs and cafes related to skin beauty, trend analysis tools, etc.) A third banner instance (AI) that is learned based on hot keywords and trend information such as popular dermatology treatment information) and configured to effectively induce consumers by including maximum sales, maximum sales conversion rate, or multiple interest keyword template) can be requested to be created automatically.

4 is a diagram conceptually illustrating thumbnail template generation of the thumbnail template generating apparatus 100 according to an exemplary embodiment of the present disclosure.

The thumbnail template generating apparatus 100 may receive a request from the sales management apparatus 200 . The request is a signal requesting to create a thumbnail banner instance to promote a dermatological procedure or to expose it to a dermatology hospital information sharing platform.

In an exemplary embodiment, the request may include an internal factor application request. The internal factor is an internal factor (sales, conversion rate, keywords of interest set by multiple users, etc.) within the platform environment 10, and external factors obtained through the web crawling module 143 (social network collected from the web) Service, search word trends, social clubs and cafes related to skin beauty, and trend analysis tools related to dermatology surgeries, hot keywords, and trend information such as popular dermatology treatment information) are included.

According to an exemplary embodiment, in response to the first request, the thumbnail template generating apparatus 100 may generate a first banner instance including a dermatology hospital treatment cost, treatment equipment, medical staff, customer attraction keywords, and the like.

According to an exemplary embodiment, the thumbnail template generating device 100 responds to the second request, including dermatology hospital treatment costs, surgical equipment, medical staff, customer attraction keywords, and the like, and the platform environment 10 internal elements (sales, Sales conversion rate, keywords of interest set by multiple users, etc.) and/or external factors (social network services collected from the web, search word trends, social clubs and cafes related to skin beauty, trend analysis tools, etc.) It is possible to create a second banner instance further including keywords (hot keywords, trend information, such as popular dermatology treatment information).

According to an exemplary embodiment, the thumbnail template generating device 100 responds to the third request, even if the dermatology hospital treatment cost, surgical equipment, medical staff, customer attraction keywords, etc. are not directly entered or included, the platform environment 10 Internal elements (Sales, conversion rate, multiple user-set interest keywords, etc.) and/or external factors (social network services collected from the web, search word trends, social clubs and cafes related to skin care, trend analysis tools, etc.) A third banner instance configured to effectively induce consumers by including keywords, hot keywords, trend information such as popular dermatology treatment information), etc. (AI template) can be generated automatically.

In response to the request, the thumbnail template generating apparatus 100 responds to a text-type template 301a, a text-based image template 302a, a mechanical template 303a, a stimulus-type template 304a, an age-type template 305a, and a cost-type template. A template 306a ¸ a component type template 307a, a medical staff emphasis type template 308a, an artificial intelligence (AI) template 309a, and the like may be generated.

The text-type template 301a may be composed of only letters like the exemplary thumbnail image 301b. The text-based image thumbnail template 302a may consist of text and images corresponding to dermatological procedures, like the exemplary thumbnail image 302b.

Mechanical template 303a may be configured to highlight medical devices used in dermatological procedures, such as example thumbnail image 303b . The stimulus-like template 304a may be configured to include stimulus keywords to stimulate a user's demand, such as “for the coming summer,” such as the example thumbnail image 304b.

The age-type template 305a can be configured to target a specific age group by using keywords such as "line around the eyes", "vacation", "end of class", etc., as in the exemplary thumbnail image 305b. . The cost-type template 306a may be configured to inform the cost of a dermatological procedure, such as the exemplary thumbnail image 306b.

The component template 307a may be configured to highlight the components of a drug used in a dermatological procedure, such as an exemplary thumbnail image 307b. The medical staff-emphasized template 308a, like the exemplary thumbnail image 308b, may indicate a medical history, career, gender, etc. of a medical staff performing a dermatological procedure. The AI template 309a will be described in more detail with reference to FIG. 6 .

5 is a diagram illustrating a layout of a thumbnail template according to an exemplary embodiment of the present disclosure.

textual template 301a, text-based image template 302a, machine template 303a, stimulus template 304a, age template 305a, cost template 306a¸ component template 307a, Each of the medical staff highlighting template 308a and the artificial intelligence (AI) template 309a includes at least one component. At least some of the components are text components related to treatment name, treatment components, medical staff information, price information, target age, keywords of interest, and trends, and at least some of the components are background components related to a background color or background image, and another At least a portion may be an image component related to an object image, such as a face, machine, or human appearance.

The text-type template 301a may be composed of text-based components related to a procedure name and price information.

The text-based image thumbnail template 302a may include an image component related to a face image, and a text component related to a procedure name and price information. According to an exemplary embodiment, the face image used in the text-based image thumbnail template 302a may be a face image indicating a skin condition corresponding to a treatment type.

The mechanical template 303a may be configured to highlight medical devices used in dermatological procedures. According to an exemplary embodiment, the image component of the mechanical template 303a may correspond to a machine image such as information on surgical equipment and medical devices used for a procedure, recently introduced machines and equipment, and expensive equipment and devices. .

According to an exemplary embodiment, the stimulus-type template 304a is a stimulus keyword to stimulate the user's demand, such as phrases such as "for the upcoming summer", "preparation for vacation period", "use golden holiday", and the user's demand. It may be configured to include text components such as a stimulating procedure name, and a discount price. According to an exemplary embodiment, the stimulus-type template 304a enlarges the size of components to emphasize keywords such as keywords determined to have high search inflow frequency, keywords related to opened events, target audiences (SAT, students, summer), etc. , the color can be displayed to be complementary to the background color, or it can be highlighted.

The age-type template 305a is a target age keyword that targets a specific age group using keywords such as "eye wrinkles", "vacation", "end of class", "lifting", "elasticity", and "botox", and text related to the name of the procedure By including the component, it can be configured to target a dermatological treatment target. According to an exemplary embodiment, the age-type template 305a corresponds to a senior consumer group, a text component having a relatively large size, a relatively simple layout, a small number of components, or intuitive, such as "wrinkle improvement". It can be processed to emphasize the improvement effect.

The cost-type template 306a may be configured to inform the cost of a dermatology procedure using a text component related to the treatment name and price information. For example, the cost template 306a can be used to visually emphasize text related to cost, such as enlarging the size of a component to emphasize the cost compared to other components, displaying a color complementary to the background color, or highlighting. Pricing information can be highlighted. For example, the cost template 306a may emphasize the discount amount and the discount rate through the price information text component, and may adaptively adjust that the treatment name is discounted compared to the average treatment cost in response to the treatment name component.

The component type template 307a includes a text component related to a treatment name and treatment-related components, and may be configured to highlight the components of a drug used in a dermatological procedure.

The medical staff-emphasized template 308a may include medical personnel information indicating the history, career, gender, and the like of medical personnel performing dermatological procedures and text components related to operation-related keywords.

6 is a diagram showing the configuration of an artificial intelligence (AI) template 309a according to an exemplary embodiment of the present disclosure.

The thumbnail template generating device 100 is based on both internal factors such as sales information in the platform environment 10 and external factors such as trend information on the web, the instance generating the maximum sales, the instance recording the maximum sales conversion rate, and the degree of interest within a predetermined time. It is possible to learn the instance including the sharply increased instance, the interest keyword set as the interest keyword by a large number of people.

Thumbnail template generating apparatus 100 as a learning result, the instance that generated the maximum sales, the instance recorded the maximum conversion rate, the instance where the interest soared within a predetermined time, the instance including the interest keyword set as the interest keyword by many and substantially However, it is possible to create an artificial intelligence (AI) template that is a thumbnail template corresponding to the request.

The AI template may include a background layer, an image layer, and a keyword layer as components. According to an exemplary embodiment, the first component layer may be a text component, the second component layer may be an image component, and the third component layer may be a keyword component. In the present disclosure, the keyword component and the text component may have a similar format, but may be conceptually separated because information to be emphasized in the corresponding component is different.

Referring to the right image of FIG. 6 , the thumbnail template generating apparatus 100 may determine to fill the background layer of the thumbnail banner instance with a light background color based on the AI learning result, and the first component layer is And, text emphasizing the target body such as “and” and the treatment name such as “fine wrinkle regeneration injection” can be displayed based on text, and a hospital logo image “Doctors” can be displayed on the second component layer, and the third component layer Keywords emphasized by medical staff such as “dermatologist treatment” can be displayed on a text-based basis. The keywords of all components written in the right image of FIG. 6 are the thumbnail banner instances that recorded the maximum sales in the platform by the artificial intelligence learning device, the thumbnail banner instances that recorded the maximum conversion rate, and the thumbnail banner instances that reflected the keywords set in a large number of interest training data. It is the result data inferred by learning with

In an exemplary embodiment, the thumbnail template generating apparatus 100 is a result of artificial intelligence-based learning of the maximum sales generation instance, the maximum sales conversion rate generation instance, the interest surge instance, and the multiple user-set interest keyword setting instance, the maximum sales generation instance , it is possible to give a plurality of artificial intelligence weights corresponding to each instance of occurrence of a maximum conversion rate, an instance of a surge in interest, and an instance of setting a plurality of user-set interest keywords.

Artificial intelligence according to the present disclosure is CNN (Convolution Neural Network), such as GoogleNet, AlexNet, VGG Network, R-CNN (Region with Convolution Neural Network), RPN (Region Proposal Network), RNN (Recurrent Neural Network), S-DNN (Stacking-based deep Neural Network), S-SDNN (State-Space Dynamic Neural Network), Deconvolution Network, DBN (Deep Belief Network), RBM (Rested Boltzman Machine), Fully Convolutional Network, LSTM (Long Short-Term Memory) Network, Classification Network, Generative Modeling, eXplainable AI, Continual AI, Representation Learning, AI for Material Design, BERT for Natural Language Processing, SP-BERT, MRC/QA, Text Analysis, Dialog System, GPT-3, GPT-4, It can be built using various artificial intelligence structures and algorithms such as Visual Analytics, Visual Understanding, Video Synthesis for vision processing, Anomaly Detection, Prediction, Time-Series Forecasting, Optimization, Recommendation, and Data Creation for ResNet data intelligence. A more detailed AI construction method will be described with reference to FIG. 9 .

7 is a flowchart illustrating an operation method of the thumbnail template generating apparatus 100 according to an exemplary embodiment of the present disclosure.

In step S110 , the thumbnail template generating apparatus 100 may receive a request for generating a thumbnail template that is exposed to the device and includes incentive information for inducing an inflow of a user. According to an exemplary embodiment of the present disclosure, the thumbnail template generating apparatus 100 may receive a request for generating a thumbnail template including incentive information for inducing a user's inflow from the sales management apparatus 200 . . The request is a signal requesting to create a thumbnail banner instance to promote a dermatological procedure or to expose it to a dermatology hospital information sharing platform. In an exemplary embodiment, the request may include an internal factor application request.

In operation S120 , the thumbnail template generating apparatus 100 may acquire display size information of a device on which the thumbnail template is to be displayed. The thumbnail template generating apparatus 100 may obtain display size information of the device on which the thumbnail template is to be displayed, and determine the thumbnail template size corresponding to the display size.

In operation S130, the thumbnail template generating apparatus 100 may primarily determine the thumbnail template size corresponding to the display size.

In step S140 , the thumbnail template generating apparatus 100 may determine a thumbnail template type corresponding to the request.

In operation S150 , the thumbnail template generating apparatus 100 may determine a component layout that meets the request and includes the size and location of components included in the thumbnail template type. The template type is a text template 301a, a text-based image template 302a, a machine template 303a, a stimulus template 304a, an age template 305a, a cost template 306a, a component template ( 307a), a medical staff highlighting template 308a, and an artificial intelligence (AI) template 309a, each template including at least one component.

In step S160, the thumbnail template generating apparatus 100 may check whether the request includes internal information requesting to apply the internal factor, which is an element stored in the thumbnail template generating apparatus. The internal factor is an internal factor (sales, conversion rate, keywords of interest set by multiple users, etc.) within the platform environment 10, and external factors obtained through the web crawling module 143 (social network collected from the web) Service, search word trends, social clubs and cafes related to skin beauty, and trend analysis tools related to dermatology surgeries, hot keywords, and trend information such as popular dermatology treatment information) are included.

The thumbnail template generating apparatus 100 may check whether the request includes internal information requesting to apply the internal factor, which is an element stored in the thumbnail template generating apparatus. When the request includes an internal factor application request, the thumbnail template generating apparatus 100 may assign a weight to the request and readjust the component size position and layout to match the internal factor. As a result, the thumbnail template generating apparatus 100 may generate the result thumbnail template and complete the production of the thumbnail banner instance. The thumbnail template generating apparatus 100 may display a thumbnail banner instance on the device. In an exemplary embodiment, the request may include an internal factor application request. The internal factor is an internal factor (sales, conversion rate, multiple user set interest keywords, etc.) in the platform environment 10, and external factors (interest surge keywords, etc.) acquired through the web crawling module 143. include

In step S170 , when the internal factor is included in the request, the thumbnail template generating apparatus 100 may readjust the component layout to match the internal factor. The step of re-adjusting the component layout to conform to the internal factor will be described in more detail with reference to FIG. 8 .

In step S180 , the thumbnail template generating apparatus 100 may generate a result thumbnail template corresponding to the request. The thumbnail template generating apparatus 100 according to an exemplary embodiment of the present disclosure may generate an appropriate thumbnail banner instance even if an internal factor application request is not included or the request is limited. According to an exemplary embodiment of the present disclosure, the thumbnail template generating apparatus 100 includes internal elements (sales, conversion rate, multiple user-set interest keywords, etc.) in the platform environment 10, and external elements obtained through a web crawling module. Thumbnails with optimal component size, location, and layout through either re-adjusting the component size, position, and layout of the thumbnail template in a rule-based manner based on (increasing interest keywords, etc.) By creating a template, a thumbnail banner instance can be created and displayed on the device.

8 is a flowchart illustrating an operation method of the thumbnail template generating apparatus 100 according to an exemplary embodiment of the present disclosure. A description overlapping with FIG. 7 will be omitted.

In step S170 , the thumbnail template generating apparatus 100 may give different weights based on sales information, search log information, interest setting information, and trend information crawled on the web in the platform environment 10 .

In step S171 , the thumbnail template generating apparatus 100 may check whether the request includes a first sub-request that imitates the maximum sales generating instance in the platform.

When it is determined that the request is included in the first sub-request, the thumbnail template generating apparatus 100 may give a first weight to the component layout of the instance generating the maximum sales. When the first weight is assigned, the thumbnail template generating apparatus 100 performs step S179. When it is determined that the request is not included in the first sub-request, the thumbnail template generating apparatus 100 may perform step S173.

In step S173, the thumbnail template generating apparatus 100 may check whether the request includes a second sub-request that imitates the instance in which the maximum conversion rate occurs in the platform.

When it is determined that the request is included in the second sub-request, the thumbnail template generating apparatus 100 may assign a second weight to the component layout of the instance in which the maximum conversion rate occurs. When the second weight is assigned, the thumbnail template generating apparatus 100 performs step S179. When it is determined that the request is not included in the second sub-request, the thumbnail template generating apparatus 100 may perform step S175.

In step S175, the thumbnail template generating apparatus 100 may check whether the request includes a third sub-request that imitates an instance of a surge in interest in the platform.

When it is determined that the request is included in the second sub-request, the thumbnail template generating apparatus 100 may assign a third weight to the component layout of the instance of increasing interest. When the third weight is assigned, the thumbnail template generating apparatus 100 performs step S179. When it is determined that the request is not included in the third sub-request, the thumbnail template generating apparatus 100 may perform step S177.

In step S177 , the thumbnail template generating apparatus 100 may check whether a fourth sub-request simulating multiple user-set interest keyword instances is included in the request.

When it is determined that the request is included in the fourth sub-request, the thumbnail template generating apparatus 100 may assign a fourth weight to the component layout of multiple user-set interest keyword instances. When the fourth weight is assigned, the thumbnail template generating apparatus 100 performs step S179. When it is determined that the request is not included in the third sub-request, the thumbnail template generating apparatus 100 may assign a plurality of fifth weights set by the artificial neural network.

The steps of a method or algorithm described in relation to an embodiment of the present disclosure, particularly FIGS. 7 and 8 , may be implemented directly in hardware, as a software module executed by hardware, or by a combination thereof. . A software module may include random access memory (RAM), read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, hard disk, removable disk, CD-ROM, or It may reside in any type of computer-readable recording medium well known in the art to which the present disclosure pertains.

Various embodiments of the present disclosure may be implemented as software including one or more instructions stored in a storage medium (eg, memory) readable by a machine. For example, the processor (eg, the processors 330 and 440 ) of the device may call at least one of one or more instructions stored from a storage medium and execute it. This may enable the device to be operated to perform at least one function according to the called at least one instruction. The one or more instructions may include code generated by a compiler or code executable by an interpreter. The device-readable storage medium may be provided in the form of a non-transitory storage medium. Here, the 'non-transitory storage medium' is a tangible device and only means that it does not include a signal (eg, electromagnetic wave), and this term is used when data is semi-permanently stored in the storage medium. and temporary storage. For example, the 'non-transitory storage medium' may include a buffer in which data is temporarily stored.

According to an exemplary embodiment, the method according to various embodiments disclosed in the present disclosure may be included and provided in a computer program product. Computer program products may be traded between sellers and buyers as commodities. The computer program product is distributed in the form of a device-readable storage medium (eg compact disc read only memory (CD-ROM)), or via an application store (eg Play Store™) or on two user devices. It can be distributed (eg downloaded or uploaded) directly or online between devices (eg smartphones). In the case of online distribution, at least a portion of the computer program product (eg, a downloadable app) is stored at least on a machine-readable storage medium, such as a memory of a manufacturer's server, an application store's server, or a relay server's memory. It may be temporarily stored or temporarily created.

The method of operation of the apparatus for generating a thumbnail template according to the exemplary embodiment of the present disclosure described above may be implemented as a program (or application) and stored in a medium in order to be executed in combination with a server, which is hardware. Here, the program is coded in a computer language, such as C, C++, JAVA, or machine language, that the control unit (CPU) of the computer can read through the device interface of the computer in order for the computer to read the program and execute the methods implemented as the program. Code may be included. Such code may include functional code related to functions defining functions necessary to execute the methods, etc. can In addition, this code may further include additional information necessary for the control unit of the computer to execute the above functions or code related to the storage unit reference to which location (address address) in the internal or external storage unit of the computer should be referenced. . In addition, if the control unit of the computer needs to communicate with any other computer or server located remotely in order to execute the above functions, how should the code communicate with any other computer or server remotely using the communication module of the computer? It may further include a communication-related code for information or media to be transmitted/received during communication.

The storage medium is not a medium that stores data for a short moment, such as a register, a cache, a storage unit, etc., but a medium that stores data semi-permanently and can be read by a device. Specifically, examples of the storage medium include, but are not limited to, a ROM, a RAM, a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like. That is, the program may be stored in various recording media on various servers that the computer can access or in various recording media on the user's computer. In addition, the medium may be distributed in a computer system connected by a network, and computer-readable codes may be stored in a distributed manner.

9 is a block diagram illustrating an operation of generating an artificial intelligence (AI) template using an artificial neural network of the thumbnail template generating apparatus 100 according to an exemplary embodiment of the present disclosure.

The input data trained by the learning model may be in the form of various types of information signals including recognition signals such as text, voice, object recognition information, images, and biometric information, but is not limited thereto. The input data may include an artificial intelligence learning model written to achieve a specific purpose, or a program code for implementing the artificial intelligence learning model. The input data processed by the artificial neural network processing module 145 may preferably be visualization data such as images, videos, and object recognition information, but is not limited thereto, and text, voice, object recognition information, images, and biometric data. It includes various types of information signal types including recognition signals such as information and the like.

According to an exemplary embodiment of the present disclosure, the input data may include a maximum sales generation template, a maximum sales conversion rate generation template, an interest surge template, a template including multiple user interest keywords, and the like, and the internal factors included in the above-described internal factor. It includes a plurality of banner instances corresponding to the element and the external element.

The parameter may refer to a parameter for the architecture indicating the type or structure of the artificial neural network algorithm applied to the artificial intelligence learning model. A key feature of an artificial neural network algorithm is called the backborn.

The artificial neural network network used by the thumbnail template generating apparatus 100 according to an exemplary embodiment of the present disclosure may include a convolutional neural network (CNN, hereinafter referred to as CNN), but is not necessarily limited thereto. RNN, It can be formed as a neural network having various structures and backbones such as transformers. In the present disclosure, for convenience of description, it is exemplified that CNN is applied to the learning model.

CNN spatially integrates a convolution layer that creates a feature map by applying a plurality of filters to each region of the image, and extracts features that are invariant to changes in position or rotation. It may be formed in a structure that alternately repeats the pooling layer several times. Through this, various level features can be extracted from low-level features such as points, lines, and planes to complex and meaningful high-level features.

The convolution layer may obtain a feature map by taking a nonlinear activation function on the dot product of a filter and a local receptive field for each patch of the input image.

Compared with other network structures, CNNs may have the feature of using filters with sparse connectivity and shared weights. Such a connection structure can reduce the number of parameters to be learned, make learning through the backpropagation algorithm efficient, and consequently improve prediction performance.

As such, the features finally extracted through iteration of the convolutional layer and the integration layer are fully connected to a classification model such as a multi-layer perceptron (MLP) or a support vector machine (SVM). -connected layer) and can be used for thumbnail template instance creation learning and inference.

The tuned parameter according to an exemplary embodiment of the present disclosure may refer to a detailed setting value determined by tuning an architecture for constructing and utilizing an artificial neural network network used by the thumbnail template generating apparatus 100 .

As a result of the learning model learning the input data, the component size, component position, background color, etc. can be inferred. Component size, component position, and background color are elements constituting a thumbnail banner instance, and as a result of repeated operations on input data, the corresponding elements can be learned to have an appropriate layout to attract consumers.

According to an exemplary embodiment, the thumbnail template generating device 100 is based on the sales information in the platform environment 10 and the trend information on the web, the instance that generated the maximum sales, the instance that recorded the maximum sales conversion rate, and the interest soared within a predetermined time. Instance, an instance containing an interest keyword set as a keyword of interest by a number of people, and an instance that generated maximum sales as a result of learning, an instance that recorded the maximum conversion rate, an instance whose interest level surged within a predetermined time, set as an interest keyword by many It is possible to generate an artificial intelligence (AI) thumbnail template that is substantially the same as any one of the instances including the keyword of interest, but is a thumbnail template corresponding to the request.

According to an exemplary embodiment, the artificial neural network processing unit 151 is a result of artificial intelligence-based learning of the maximum sales generation instance, the maximum sales conversion rate generation instance, the interest surge instance, and the multiple user-set interest keyword setting instance, the maximum sales generation instance, A plurality of fifth weights may be given to each of the instance in which the maximum conversion rate occurs, the instance in which the interest is soaring, and the instance in which the user-set interest keyword is set.

In the above, embodiments of the present disclosure have been described with reference to the accompanying drawings, but those skilled in the art to which the present disclosure pertains can realize that the present disclosure may be embodied in other specific forms without changing its technical spirit or essential features. you will be able to understand Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive.

Claims (10)

A method of operating an apparatus for generating a thumbnail template, the method comprising:
Receiving a request for requesting generation of a thumbnail template exposed to the device and including incentive information for inducing an inflow of a user from the sales management apparatus;
obtaining display size information of the device on which the thumbnail template is to be displayed;
determining a thumbnail template size corresponding to the display size;
determining a thumbnail template type corresponding to the request;
determining a component layout that meets the request and includes a size and a location of a component included in the thumbnail template type;
To the request, an internal factor that is an element stored in the thumbnail template generating device and that includes an internal element that is information from inside the platform in which the thumbnail template generator is used and an external element that is information from outside the platform is applied checking whether the requested internal information is included;
assigning different weights to the internal factors;
when the internal factor is included in the request, re-adjusting the component layout to match the internal factor; and
generating a result thumbnail template corresponding to the request;
The inner element is
It is collected and managed within the platform, and includes the sales, sales conversion rate, and multiple setting interest keyword information of users who have subscribed to the platform of a plurality of dermatology clinics registered in the platform,
The external element is
It includes search word trends acquired through the web crawling module, keywords that surge interest related to dermatology procedures, issue keywords, and information on popular dermatology procedures.
The step of assigning different weights to each other is
determining that the maximum revenue generating instance corresponds to a stimulus-type template including a text component when it is confirmed that the request includes a first sub-request requesting to imitate the maximum revenue generating instance in the platform;
assigning a first weight to a component layout related to a size of a first text component corresponding to the interest surge keyword;
assigning a second weight to the background color of the stimulus-type template so as to approximate a color of the first text component and a complementary color;
When it is confirmed that the request includes a second sub-request requesting to imitate an instance in which the maximum conversion rate occurs in the platform, the instance in which the maximum conversion rate occurs corresponds to a text-based image template including an image component and a text component judging;
assigning a third weight to the component layout related to the size of the second text component corresponding to the treatment name and price information; and
and assigning a fourth weight to a component layout related to a size of an image component corresponding to a face image representing a skin condition corresponding to the treatment name. According to claim 1,
The thumbnail template type is
A text-type thumbnail template composed of only letters, a text-based image thumbnail template that displays letters and images corresponding to dermatological procedures, a mechanical thumbnail template that emphasizes medical devices used in dermatological procedures, and stimulus keywords to stimulate user demand A stimulus-type thumbnail template that includes, an age-type thumbnail template that targets dermatological treatment targets, a cost-type thumbnail template that informs the cost of dermatological procedures, an ingredient-type thumbnail template that emphasizes the ingredients of drugs used in dermatological procedures, and performs dermatological procedures A method of operating a thumbnail template generating apparatus, characterized in that it comprises a medical staff highlighting thumbnail template indicating the history of the medical staff. 3. The method of claim 2,
The thumbnail template type is
Based on the sales information in the platform where the thumbnail template generating device is used and the trend information on the web, the instance that generated the maximum sales, the instance that recorded the maximum sales conversion rate, the instance where the interest level surged within a predetermined time, the interest set as the interest keyword by many Instances that include a keyword of interest set as a keyword of interest by the plurality of instances that learn an instance including a keyword, and generate the maximum sales as a learning result, an instance that records the maximum sales conversion rate, an instance whose interest has surged within the predetermined time Substantially the same as any one of the above, but comprising an artificial intelligence (AI) thumbnail template that is a thumbnail template corresponding to the request. 4. The method of claim 3,
The AI thumbnail template is
background layer;
image layer; and
A method of operating a thumbnail template generating apparatus, characterized in that it includes a keyword layer. delete According to claim 1,
The step of assigning different weights to each other is
When the request includes a fourth sub-request that imitates multiple user-set interest keyword instances, the method further comprising the step of assigning a fifth weight to the component layout of the multiple user-set interest keyword instances, generating a thumbnail template How the device works. 7. The method of claim 6,
As a result of artificial intelligence-based learning of the maximum sales generation instance, the maximum turnover rate generation instance, the interest surge instance, and the multiple user-set interest keyword instances, the maximum sales generation instance, the maximum conversion rate generation instance, the interest The method of operating a thumbnail template generating apparatus, characterized in that it further comprises the step of assigning a plurality of sixth weights corresponding to each of the spike instance and the plurality of user-set interest keyword setting instances. delete delete In the thumbnail template generator,
a communication interface configured to receive a request from the sales management device; and
including memory,
The memory is
Web crawling module configured to collect trend information of dermatological procedures;
An artificial neural network processing module configured to generate a maximum sales occurrence instance, a maximum sales conversion rate occurrence instance, an interest surge instance, and a plurality of user-set interest keyword instances by learning the sales information and the trend information in the platform in which the thumbnail template generating device is used; and
a thumbnail template generating module configured to generate a result thumbnail template matching the request;
The request is
an element stored in the thumbnail template generating device, including an internal element that is information from inside a platform in which the thumbnail template generating device is used, and an external element that is information from outside the platform, and assigning different weights to each element comprising a configured internal factor;
The inner element is
It is collected and managed within the platform, and includes the sales, sales conversion rate, and multiple setting interest keyword information of users who have subscribed to the platform of a plurality of dermatology clinics registered in the platform,
The external element is
It includes search word trends acquired through the web crawling module, keywords that surge interest related to dermatology procedures, issue keywords, and information on popular dermatology procedures.
The thumbnail template generation module,
When it is confirmed that the request includes a first sub-request for requesting to imitate the highest revenue generating instance in the platform, it is determined that the maximal revenue generating instance corresponds to a stimulus-type template including a text component, and the A first weight is given to the component layout related to the size of the first text component corresponding to the keyword of increasing interest, and a second weight is given to the background color of the stimulus-type template so as to approximate the color of the first text component and the complementary color, ,
When it is confirmed that the request includes a second sub-request requesting to imitate an instance in which the maximum conversion rate occurs in the platform, the instance in which the maximum conversion rate occurs corresponds to a text-based image template including an image component and a text component and assigning a third weight to the component layout related to the size of the second text component corresponding to the treatment name and price information,
and assigning a fourth weight to a component layout related to a size of an image component corresponding to a face image representing a skin condition corresponding to the treatment name.

Images