KR102550185B1 - Advertising model recommendation system based on artificial intelligence - Google Patents

Abstract

An artificial intelligence-based advertising model recommendation system according to the present invention is characterized in that it includes a computing device, and the computing device includes a display unit for displaying information about recommending an advertisement target and an advertisement model for the advertisement target.

Description

Advertising model recommendation system based on artificial intelligence}

The present invention relates to an artificial intelligence-based advertising model recommendation system, and more particularly, to an artificial intelligence-based advertising model recommendation system for recommending a model that meets an advertising target input from an advertiser.

Recently, the size of the advertising market has been shifting from offline to online, and as a result, anyone can run advertisements online at low media costs, expanding the area of advertising models. Therefore, the digitalization technology of the advertising model agency industry is very necessary.

On the other hand, as the area of advertising models expands in this way, the area that is subject to advertisement naturally also expands. There was a problem in that finding an advertising model was not digitized, increasing the burden on the advertising model agency.

Accordingly, an object of the present invention is to reduce the burden on an advertising model agency by automatically recommending an advertising model that corresponds to a product or service to be advertised by reflecting the latest trends.

The object of the present invention described above is by an artificial intelligence-based advertisement model recommendation system comprising a computing device, wherein the computing device includes a display unit for displaying recommendation information of an advertisement target and an advertisement model therefor. can be achieved

and a server networked with the computing device, wherein the server includes a communication unit; storage unit; crawling unit; and a control unit, wherein when receiving a first user input for the product name of the advertisement target from a computing device, the control unit searches for the product name corresponding to the first user input through a search engine and searches the search engine or server. Obtain search information by crawling the search results for the product name using its own API, classify the obtained search information into a plurality of categories classified according to preset criteria, and a first category among the plurality of categories A first keyword for emotion is included, a second category among the plurality of categories includes a second keyword for an adjective for the product information, and a third category among the plurality of categories is a product similar to the product information. and a third keyword for a search term, wherein the control unit performs an image search for each of the first, second, and third keywords through the search engine, and identifies multiple genders with a large number of genders recognized in the image search. and, if the plurality of genders is female, the control unit first recommendation information for a female advertisement model as a result of a search through the search engine for the first keyword, the second keyword, and the search term "female model". and obtains second recommendation information for a male advertisement model as a result of a search using the first keyword, the second keyword, and a search term such as male model through the search engine if the male is male, and the control unit obtains the first recommendation information. identifies a plurality of female advertisement models, identifies and displays a first female advertisement model not related to the third keyword among the plurality of female advertisement models on the display unit, and displays a plurality of male advertisements in the second recommendation information. A model is identified, and a first male advertisement model not related to the third keyword is identified and displayed on a display unit among the plurality of male advertisement models.

The control unit acquires search results for dramas and movies in which the first male advertisement model and the first female advertisement model appeared through the search engine, and among the search results for dramas and movies, dramas and movies searched a predetermined number of times or more. A first image for a movie and adjectives and adverbs included in the first image are identified, and the identified adjectives and adverbs are displayed on a display unit together with the first male advertisement model and the first female advertisement model, The computing device is network-connected to a camera arranged for shooting an advertisement, and when the camera transmits an image and video captured of the advertisement site to the server, the controller transmits the identification to the image and video captured the advertisement site. A first virtual advertisement cover synthesized with adjectives and adverbs, a first male advertisement model, and a first female advertisement model is displayed on the display unit.

The control unit recognizes the faces of the first male advertisement model and the second female advertisement model having different sizes in the first virtual advertisement cover, and sets the face size of each of the first male advertisement models to 20 to 25 cm vertically. The overall ratio is adjusted so that the face size of the second female advertisement model is 19 to 24 cm, and the synthesized second virtual advertisement cover is displayed on the display unit in its actual size.

It further includes a beam projector and a mounting device connected to the computing device through a network, wherein the beam projector emits an image for a second virtual advertisement cover as a light source, and the mounting device includes a mounting unit for holding the beam projector; a fixing unit fixedly coupled to the computing device; and a connecting member for connecting and supporting the mounting portion and the fixing portion. And characterized in that it comprises a stop member to move and fix the connecting member.

According to the present invention, it is possible to reduce the burden on an advertising model agency by automatically recommending an advertising model that corresponds to a product or service to be advertised by reflecting the latest trend.

1 is a diagram showing the configuration of an advertisement model recommendation system based on artificial intelligence according to an embodiment of the present invention.
2 illustrates the configuration of a computing device and a server of an advertisement model recommendation system based on artificial intelligence according to an embodiment of the present invention.
3 illustrates a method of operating an advertisement model recommendation system based on artificial intelligence according to an embodiment of the present invention.
4 illustrates that an advertisement model according to an embodiment of the present invention is identified and displayed on a display unit of a computing device.
5 illustrates an operation of synthesizing a virtual advertisement cover according to an embodiment of the present invention.
6 illustrates the configuration of a computing device and a beam projector according to an embodiment of the present invention.
7 shows the configuration of a beam projector and a mounting device according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the drawings, the same reference numerals or symbols refer to components performing substantially the same function, and the size of each component in the drawings may be exaggerated for clarity and convenience of description. However, the technical idea of the present invention and its core configuration and operation are not limited to the configurations or operations described in the following embodiments. In describing the present invention, if it is determined that a detailed description of a known technology or configuration related to the present invention may unnecessarily obscure the subject matter of the present invention, the detailed description will be omitted.

In the embodiments of the present invention, terms including ordinal numbers, such as first and second, are used only for the purpose of distinguishing one component from another, and expressions in the singular number are plural unless the context clearly indicates otherwise. contains an expression of In addition, in the embodiments of the present invention, terms such as 'comprise', 'include', and 'have' refer to one or more other features, numbers, steps, operations, elements, parts, or combinations thereof. Or it should be understood as not precluding the possibility of addition. In addition, in an embodiment of the present invention, a 'module' or 'unit' performs at least one function or operation, may be implemented as hardware or software, or may be implemented as a combination of hardware and software, and is integrated into at least one module. and can be implemented with at least one processor. Also, in an embodiment of the present invention, at least one of a plurality of elements refers to not only all of the plurality of elements, but also each one or all combinations of the plurality of elements excluding the rest. In addition, "configured (or configured) to" may be, depending on the situation, for example, "suitable for," "having the capacity to," "~ Used interchangeably with “designed to,” “adapted to,” “made to,” or “capable of.” "Configured (or set) to" may not necessarily mean only "specifically designed to" hardware. Instead, in some contexts, the phrase "device configured to" may mean that the device is "capable of" in conjunction with other devices or components. For example, the phrase "a processor configured (or configured) to perform A, B, and C" may include a dedicated processor (eg, embedded processor) to perform the operation, or by executing one or more software programs stored in a memory device. , may mean a general-purpose processor (eg, CPU or application processor) capable of performing corresponding operations.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the drawings. This is to explain in detail to the extent that those skilled in the art can easily practice the invention, and thus, the technical spirit and scope of the present invention are not limited. .

1 is a diagram showing the configuration of an advertisement model recommendation system based on artificial intelligence according to an embodiment of the present invention, and FIG. 2 is a computing device of an advertisement model recommendation system based on artificial intelligence according to an embodiment of the present invention It shows the configuration of a server, and FIG. 3 shows how an advertisement model recommendation system based on artificial intelligence according to an embodiment of the present invention operates, and FIG. 4 shows an advertisement model according to an embodiment of the present invention. It shows what is identified and displayed on the display unit of the computing device, Figure 5 shows the operation of synthesizing a virtual advertisement sign according to an embodiment of the present invention, Figure 6 is a computing according to an embodiment of the present invention It shows the configuration of the device and the beam projector, and FIG. 7 shows the configuration of the beam projector and the mounting device according to an embodiment of the present invention.

A system for recommending an advertisement model based on artificial intelligence according to the present invention includes a computing device 100 including a display unit 110 displaying a target of an advertisement and recommendation information of an advertisement model therefor, and a server 200 networked therewith. includes

Artificial intelligence according to an embodiment of the present invention is to learn these algorithms when the operation of the present invention is performed, and to operate the advertising model recommendation system according to the learned algorithm, GMM (Gaussian Mixture Model), Machine learning-based artificial intelligence algorithms such as SVM (Support Vector Machine) or deep learning-based artificial intelligence algorithms such as CNN (Convolutional Neural Network), GAN (Generative Adversarial Network), RNN (Recurrent Neural Network), AE (Autoencoder) may consist of

The target of advertisement means an object that is the target of advertisement for selling various services and products. may refer to services and products that are the target of. Here, service refers to the provision of tangible and intangible products, including all activities of conducting business by providing intangible services to customers who use the right to use, and more specifically, theaters, movie theaters, concert halls, stadiums, museums, art galleries, and zoos. , theme parks, national parks, etc., may refer to use rights. In addition, the product includes all kinds of tangible items that can be sold, and may mean a right to use such a product.

Computing device 100 may be, for example, a personal computer, server computer, handheld or laptop device, mobile device (mobile phone, PDA, media player, etc.), multiprocessor system, consumer electronic device, mini computer, mainframe computer, any Distributed computing including the above-described system or device, and an edge computing environment that processes data at an edge where data is generated rather than a central server, and the configuration is not limited to the description.

The computing device 100 may include at least one processor and memory. Here, the processor may include, for example, a central processing unit (CPU), a graphic processing unit (GPU), a microprocessor, an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), and the like, and a plurality of can have a core.

The memory may be volatile memory (eg, RAM, etc.), non-volatile memory (eg, ROM, flash memory, etc.), or a combination thereof. Additionally, the computing device 100 may include additional storage. Storage includes, but is not limited to, magnetic storage, optical storage, and the like. The storage may store computer readable instructions for implementing one or more embodiments disclosed herein, and may also store other computer readable instructions for implementing an operating system, application programs, and the like. Computer readable instructions stored in storage may be loaded into memory for execution by a processor.

In addition, the computing device 100 may include a user input unit 120 and an output device. The user input unit 120 may include, for example, a keyboard, mouse, pen, voice input device, touch input device, infrared camera, video input device, or any other input device. Also, an output device may include, for example, one or more displays, speakers, printers, or any other output device or the like. Also, the computing device may use an input device or an output device provided in another computing device as the user input unit 120 or an output device. Additionally, the computing device may include a communication module that enables the computing device to communicate with other devices. Here, the communication module may include a modem, network interface card (NIC), integrated network interface, radio frequency transmitter/receiver, infrared port, USB connection, or other interface for connecting the computing device to other computing devices. The communication module may include a wired connection or a wireless connection.

Each component of the computing device 100 may be connected by various interconnections such as a bus (eg, peripheral component interconnection (PCI), USB, firmware (IEEE 1394), optical bus structure, etc.), They may be interconnected by networks. Terms such as "component" and "system" as used herein generally refer to a computer-related entity that is hardware, a combination of hardware and software, software, or software in execution.

The server 200 according to an embodiment of the present invention is network-connected to the computing device 100, can store various data, and other information included in the AI-based advertisement model recommendation system through a program or application. You can control external devices.

The server 200 according to an embodiment of the present invention includes a communication unit 210, a storage unit 220, a crawling unit 230 and a control unit 240.

The communication unit 210 according to an embodiment of the present invention may communicate with the computing device 100 or another external electronic device in a wired or wireless communication method. Therefore, in addition to a connector including a connector or a terminal for wired connection, various other communication methods may be implemented. For example, it may be configured to perform at least one communication among Wi-Fi, Bluetooth, Zigbee, infrared communication, Radio Control, UWM (Ultra-Wide Band), Wireless USB, and NFC (Near Field Communication). The communication unit 210 may include communication modules such as Bluetooth Low Energy (BLE), Serial Port Profile (SPP), Wi-Fi Direct, infrared communication, Zigbee, and Near Field Communication (NFC). In addition, the communication unit 210 may be implemented in the form of a device, S/W module, circuit, chip, or the like.

The communication unit 210 according to an embodiment of the present invention may include the above various communication modules, and may include an IoT communication module having an IoT network for each carrier, and the IoT communication module may include a separate communication unit 210. It can mean all IoT communication networks that enable services based on various platforms by connecting a plurality of objects with a network. If such an IoT communication module is used, a smoother communication network can be provided within a set area.

The storage unit 220 according to an embodiment of the present invention may receive information from the computing device 100 through the communication unit 210 or receive information from an external platform and store it. Among the received collected information, product information and sales information corresponding to keywords may also be received and stored. The storage unit 220 may store various data according to the processing and control of the control unit 240 to be described later. The storage unit 220 is accessed by the control unit 240 and can read, record, modify, delete, or update data. The storage unit 220 includes a flash-memory, a hard-disc drive, and a solid-state drive (SSD) to preserve data regardless of whether or not system power is supplied to the server 200. ) and the like. In addition, the storage unit 220 may include a volatile memory such as a buffer or RAM for temporarily loading data processed by the control unit 240 .

The control unit 240 according to an embodiment of the present invention may perform control for the operation of various elements of the server 200 . The control unit 240 executes a control program (or instruction) for performing such a control operation, an inactive memory in which the control program is installed, a volatile memory in which at least a part of the installed control program is loaded, and the loaded control program It may include at least one processor or CPU (Central Processing Unit). In addition, such a control program may be stored in other external electronic devices as well as the server 200 .

The control program may include program(s) implemented in the form of at least one of BIOS, device driver, operating system, firmware, platform, and application program (application). As an embodiment, the application program is pre-installed or stored in the server 200 at the time of manufacturing the server 200, or receives data of the application program from the outside at the time of later use, and based on the received data, the server ( 200) can be installed. Data of the application program may be downloaded from an external server such as an application market to the server 200 for recommending an advertisement model based on artificial intelligence, but is not limited thereto. Meanwhile, the controller 240 may be implemented in the form of a device, S/W module, circuit, chip, or the like, or a combination thereof.

The crawling unit 230 according to an embodiment of the present invention connects a plurality of search engines, and when searching for user input for any one of the plurality of search engines, a plurality of contents displayed on the web is transferred to an external platform or server ( 200) to collect information by crawling them through the API. Crawling in the present invention is implemented so that information can be collected by repeating the process of finding the website address of each of a plurality of search engines without using the API, and searching the URL of the website address in addition to using the API. All means may be included. In addition, external platforms refer to using APIs provided by a plurality of search engines themselves, and for example, APIs in external platforms may include Google, Naver, Daum, Yahoo, and the like.

3 illustrates a method of operating an advertisement model recommendation system based on artificial intelligence according to an embodiment of the present invention.

Referring to FIG. 3 , when the server 200 according to an embodiment of the present invention receives a first user input for product information to be advertised (S10), it crawls search results for product information through a search engine. Acquiring search information (S20), classifying the acquired search information according to a plurality of categories (S30), identifying multiple genders after image search for keywords in a plurality of categories (S40), and Recommendation information is obtained through keyword search (S50), and advertisement models not related to similar products are identified in the recommendation information (S60).

In more detail, when the server 200 according to an embodiment of the present invention receives the first user input for the product name of the advertisement target from the computing device 100, the server 200 responds to the first user input. search engine through a search engine and obtain search information by crawling search results for product names using the search engine or the server 200's own API, and classify the obtained search information according to a predetermined criterion. can be classified into categories. Here, the first user input for the product name means, for example, assuming that the target product of the advertisement is beer, the advertiser inputs a word for beer or a foreign language meaning beer through the computing device 100. Accordingly, beer can be searched through a search engine, and search information obtained by crawling beer search results can be obtained using an API. In this case, the first category of the plurality of categories is included in a predetermined standard, for example, a first keyword for emotion is included in the first category, a second keyword is included in an adjective for product information, and a third category is a product. A criterion may be set to include a third keyword for a search term that is similar to information. A plurality of categories include all keywords related to the product that consumers can feel recognized for. For example, categories and keywords include adverbs among products and frequently used phrases, places and times where products are mainly used, seasons, and weather. etc. may also be included.

Among the plurality of categories, the first keyword for emotion may include, for example, happiness, guilt, and surprise, the second keyword may include delicious, refreshing, and pleasant, and the third keyword may include beer such as soju and whiskey. and similar products may be included.

The server 200 according to an embodiment of the present invention classifies categories according to preset criteria for a plurality of categories, searches images for each of the first keyword, the second keyword, and the third keyword through a search engine, and , In image search, a majority gender with a large number of recognized genders is identified, and if the majority gender identified through a search engine is a woman, a female advertisement is obtained as a result of a search with the first keyword, second keyword, and female model search terms through the search engine. First recommendation information for a model is acquired, and if a man is a man, second recommendation information for a male advertisement model (111) may be obtained as a result of a search with the first keyword, second keyword, and male model search terms through a search engine. there is. At this time, identifying the plurality of genders is to determine whether the current advertising trend for the product name to be advertised is advantageous to males or females, and to further enhance the advertising effect.

If the plurality of genders is female, the server 200 according to an embodiment of the present invention identifies a plurality of female advertisement models from the obtained first recommendation information, and identifies a first woman among the plurality of female advertisement models that is not related to the third keyword. The advertisement model is identified and displayed on the display unit 110, and if the majority gender is male, a plurality of male advertisement models 111 are identified from the second recommendation information, and a third keyword and a third keyword among the plurality of male advertisement models 111 are identified. The unrelated first male advertisement model may be identified and controlled to be displayed on the display unit 110 . Identification of an advertisement model related to the third keyword is to exclude a female model or a male model that is already an advertisement model for a product whose advertisement target is similar to the product.

Server 200 according to an embodiment of the present invention obtains search results for dramas and movies in which the first male advertisement model and the first female advertisement model appeared through a search engine, and search results for dramas and movies. The first image 113 for dramas and movies searched a predetermined number of times or more and the adjectives and adverbs 114 included in the first image 113 are identified, and the identified adjectives and adverbs 114 are identified in the first male advertisement. It is controlled to be displayed on the display unit 110 together with the model and the first female advertisement model. This is to obtain an image feeling friendly to the male advertisement model 111 or the female advertisement model, and to obtain a more improved advertising effect by providing the keyword associated with the product to be advertised.

An advertisement model recommendation system based on artificial intelligence according to an embodiment of the present invention includes a camera. A camera may be placed for shooting advertisements, and the computing device 100 may be network-connected to the camera. When the server 200 transmits images and videos captured by the camera of the advertisement site, adjectives and adverbs identified by the server 200, the first male advertisement model and the first female advertisement model are included in the image and video captured of the advertisement site. The expressed virtual advertisement cover may be synthesized and displayed on the display of the computing device 100 .

The server 200 according to an embodiment of the present invention may synthesize a virtual advertisement cover that includes both a male advertisement model 111 and a female advertisement model, rather than an advertisement model of a single gender, according to a user input. The face 116 of the first male advertisement model and the face of the second female advertisement model obtained by the above-described method are recognized, and the face size (116) of the first male advertisement model extracted from each different image is recognized. ) and the face size 117 of the second female advertisement model can be created in a synthesized virtual advertisement cover. This is because the different images are displayed at different ratios of the face size 116 of the first male advertisement model and the face size 117 of the second female advertisement model according to their respective sizes. If they are synthesized without a series of processes, The virtual advertisement cover can give advertisers and buyers a feeling that a first male advertisement model and a second female advertisement model having different ratios are forcibly synthesized. Accordingly, the server 200 recognizes the face of each advertisement model, converts them into average male and female face sizes, and adjusts their ratio to synthesize and create virtual advertisement covers. At this time, in the case of men, it is displayed as a ratio of the face size of the first male advertisement model 118 adjusted to an image with a face size of 20 to 25 cm vertically, and in the case of women, a face size of 19 to 24 cm vertically. The ratio of the face size of the second female advertisement model 119 adjusted to the image may be displayed to match the overall ratio at a certain ratio.

An advertisement model recommendation system based on artificial intelligence according to an embodiment of the present invention includes a beam projector 300 and a mounting device 400 of the beam projector 300 .

The beam projector 300 is network-connected to the computing device 100 and, upon receiving an image or video of a virtual advertising sign from the computing device 100, projects the image or video to the outside through a light source such as an LED. play a role

The computing device 100 and the beam projector 300 may be connected by wire or wirelessly, and at this time, the mounting device 400 serves to fix and couple the computing device 100 and the beam projector 300.

The mounting device 400 includes a mounting portion 410 for holding the beam projector 300, a fixing portion 420 fixedly coupled to the computing device 100, and a connection connecting the holding portion 410 and the fixing portion 420. It includes a member 430 and a stop member 440.

The mounting portion 410 is coupled to the beam projector 300 to support the beam projector 300, and includes a screw portion to maintain a fixed coupling with the beam projector 300. They can be fixed by rotationally coupling the screw part to the groove at the lower end of the beam projector 300 .

The fixing part 420 is coupled to one area of the computing device 100, serves to support the load of the beam projector 300 and the mounting part 410, and is preferably the display unit 110 of the computing device 100. ) can be fixed in the form of a clip on one side.

The connecting member 430 serves to interconnect the mounting portion 410 and the fixing portion 420 . At this time, the connecting member 430 may be configured to slide through a fitting structure on both sides of the fixing part 420, through which the mounting part 410 slides and adjusts the distance from the target to be projected. The size of the virtual advertisement cover can be adjusted. For such a sliding movement, one end of the connecting member 430 has a locking structure using locking jaws on both sides of the fixing part 420 and includes a locking part 431 for sliding movement, and the fixing part 420 ) may include a locking groove 432 so that the locking part 431 on both sides is caught so that it is not discharged to the outside and slides inside.

As described above, the beam projector 300 according to an embodiment of the present invention can adjust the size of the screen as the holder 410 moves through the sliding movement, stopping and moving their sliding movement For control, the fixing part 420 further includes a concave-convex part 421 formed in a triangular shape to correspond to the gear shape on the central surface, and the mounting part 410 has a gear shaped to correspond to the concave-convex part 421. A drive gear unit 422 may be further included. The mounting unit 410 may support the load of the beam projector 300 through a support bar to which the driving gear unit 422 is connected. In addition, the mounting portion 410 includes a stop member 440 to keep the movement of the driving gear portion 422 stopped.

The stop member 440 is formed at the other end of the holding portion 410 to stop and hold the movement of the driving gear, serves to fix the movement of the holding portion 410, and a knob 442 for controlling the holding portion And, it includes a fixed stop portion 443 for fixing the drive gear so that it does not rotate any further by being caught on the concave-convex portion 421, and the fixed stop portion 443 further includes an elastic hinge structure 441 that enables bending. include The elastic hinge structure 441 provides elastic force in the direction in which the fixed stop 443 is caught on the concave-convex portion 421 to hold the stop, and rotates the fixed stop 443 upward through the handle 442 It serves to ensure that the fixed state is maintained unless otherwise specified. The handle 442 is for more smoothly controlling the fixed stop 443. Through this, the user can move and fix the beam projector 300 as desired, and the user's convenience can be improved by allowing the virtual advertisement cover to be projected through the beam projector 300 in a screen that fits the actual ratio. can

Although the preferred embodiments of the present invention have been shown and described above, the present invention is not limited to the specific embodiments described above, and is common in the art to which the present invention pertains without departing from the gist of the present invention claimed in the claims. Of course, various modifications are possible by those with knowledge of, and these modified embodiments should not be individually understood from the technical spirit or perspective of the present invention.

100: computing device, 110: display unit
111: male advertising model, 112: product image
113: first image, 114: adjectives and adverbs
116: face size of the first male advertising model,
117: Face size of the second female advertising model
118: adjusted first male advertising model
119: adjusted second female advertising model
120: user input unit, 200: server
210: communication unit, 220: storage unit
230: crawling unit, 240: control unit
300: beam projector, 400: mounting device
410: mounting part, 420: fixing part
421: uneven part, 422: drive gear part
430: connecting member, 431: hooking part
432: locking groove, 440: stopping member
441: elastic hinge structure, 442: handle, 443: fixed stop

Claims (5)

In the advertising model recommendation system based on artificial intelligence,
Including a computing device,
The computing device includes a display unit for displaying recommendation information of a target of an advertisement and an advertisement model for the target,
It includes a server networked with the computing device,
The server
communications department; storage unit; crawling unit; Including; control unit;
When the control unit receives a first user input for the product name of the advertisement target from the computing device,
Searching for a product name corresponding to the first user input through a search engine and obtaining search information by crawling search results for the product name using the search engine or server's own API;
Classifying the acquired search information into a plurality of categories classified according to preset criteria;
A first category among the plurality of categories includes a first keyword for emotion,
A second category among the plurality of categories includes a second keyword for an adjective for product information,
A third category among the plurality of categories includes a third keyword for a search word that is a product similar to the product information,
The control unit performs an image search for each of the first, second, and third keywords through the search engine, and identifies a plurality of genders having a large number of genders recognized in the image search,
The control unit obtains first recommendation information for a female advertisement model as a result of a search through the search engine for the first keyword, the second keyword, and the search terms "female model" if the plurality of genders is female, If it is a man, second recommendation information about a male advertisement model is obtained as a result of searching for the first keyword, the second keyword, and the search terms such as male model through the search engine;
The control unit identifies a plurality of female advertisement models from the first recommendation information, and identifies and displays a first female advertisement model not related to the third keyword among the plurality of female advertisement models to the display unit;
An artificial intelligence-based advertising model that identifies a plurality of male advertisement models from the second recommendation information and displays a first male advertisement model not related to the third keyword among the plurality of male advertisement models to the display unit. Recommendation system.
delete According to claim 1,
The control unit acquires search results for dramas and movies in which the first male advertisement model and the first female advertisement model appeared through the search engine, and among the search results for dramas and movies, dramas and movies searched a predetermined number of times or more. Identifying a first image of a movie and adjectives and adverbs included in the first image, and displaying the identified adjectives and adverbs together with the first male advertisement model and the first female advertisement model on a display unit;
The computing device is network-connected to a camera disposed for shooting advertisements,
When the camera transmits images and videos of the advertisement site to the server,
The control unit displays a first virtual advertisement cover synthesized by the identified adjective and adverb, the first male advertisement model and the first female advertisement model in the image and video of the advertisement site, to the artificial intelligence that displays on the display unit. based advertising model recommendation system.
According to claim 3,
The control unit recognizes the faces of the first male advertisement model and the second female advertisement model having different sizes in the first virtual advertisement cover, and sets the face size of each of the first male advertisement models to 20 to 25 cm vertically. An artificial intelligence-based advertisement model recommendation system for controlling the face size of the second female advertisement model to be 19 to 24 cm in size so that the second virtual advertisement cover synthesized again is displayed in the actual size on the display unit by adjusting the overall ratio.
According to claim 4,
Further comprising a beam projector and a mounting device networked with the computing device,
The beam projector emits an image of the second virtual advertising cover as a light source,
The mounting device includes a mounting unit for mounting a beam projector; a fixing unit fixedly coupled to the computing device; and a connecting member for connecting and supporting the mounting portion and the fixing portion. and a stopping member for moving and fixing the connection member.

Images