KR102706992B1 - Method and apparatus for providing sns-based design and marketing recommendation service applied with artificial intelligence algorithm - Google Patents

Abstract

A method and a device for providing an SNS-based marketing recommendation service are disclosed. According to one embodiment of the present disclosure, a method for providing an SNS-based marketing recommendation service, which is performed by a device, includes: receiving information related to multiple types of businesses operated by a specific company and information related to multiple types of SNS channels managed by the specific company from a terminal device used by a specific company; identifying keywords for inflow by each of the multiple types of SNS channels and the number of visits based on the keywords for inflow through the information related to the multiple types of SNS channels; obtaining recommendation information related to marketing content to be uploaded to each of the multiple types of SNS channels based on the keywords for inflow by each of the multiple types of SNS channels, the number of visits, and the information related to the multiple types of businesses; and transmitting the obtained recommendation information to the terminal device, wherein the recommendation information may include information related to a ratio of marketing content by each of the multiple types of businesses to be uploaded to each of the multiple types of SNS channels, weights by each of the multiple types of SNS channels, and information recommending a composition of marketing content to be uploaded to each of the multiple types of SNS channels.

Description

Method and apparatus for providing SNS-based design and marketing recommendation service applied with artificial intelligence algorithm {METHOD AND APPARATUS FOR PROVIDING SNS-BASED DESIGN AND MARKETING RECOMMENDATION SERVICE APPLIED WITH ARTIFICIAL INTELLIGENCE ALGORITHM}

The present disclosure relates to technologies related to SNS-based marketing, and more specifically, to a method and device for providing an SNS-based marketing recommendation service to which an artificial intelligence algorithm is applied.

As information and communication technology advances, many types of social network services (SNS) are being developed and distributed, and users can freely use the SNS to share their daily lives with others and receive information about others.

In addition, SNS is not simply used for daily sharing between users, but is also widely used as a comprehensive platform for advertising various products and services. In other words, when products and services are advertised effectively through SNS, there is an advantage in that it can create a greater effect compared to other types of marketing with the same labor costs and expenses.

Patent Publication No. 10-2393278, April 27, 2022.

The present disclosure has been made to solve the above-described problems, and the purpose of the present disclosure is to provide a method and device for providing a SNS-based marketing recommendation service to which an artificial intelligence algorithm is applied.

In addition, the purpose of the present disclosure is to provide a method and device for automatically classifying marketing channels by industry in order to efficiently perform online SNS-based marketing.

In addition, the purpose of the present disclosure is to provide a method and device for calculating weights for each SNS channel based on search volumes and views collected for each SNS channel and uploading marketing materials to each SNS channel according to the calculated weights.

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 description below.

In one embodiment of the present disclosure, a method for providing a marketing recommendation service based on an SNS (social network service) performed by a device includes the steps of: receiving information related to a plurality of types of businesses operated by a specific company and information related to a plurality of types of SNS channels managed by the specific company from a terminal device used by a specific company; identifying an inflow keyword for each of the plurality of types of SNS channels and a number of visits based on the inflow keyword through the information related to the plurality of types of SNS channels; obtaining recommendation information related to marketing content to be uploaded to each of the plurality of types of SNS channels based on the inflow keyword for each of the plurality of types of SNS channels, the number of visits, and the information related to the plurality of types of businesses; and transmitting the obtained recommendation information to the terminal device, wherein the recommendation information may include information related to a ratio of marketing content for each of the plurality of types of businesses to be uploaded to each of the plurality of types of SNS channels, a weight for each of the plurality of types of SNS channels, and information recommending a composition of marketing content to be uploaded to each of the plurality of types of SNS channels.

And, the step of obtaining the recommendation information includes the step of inputting the inflow keywords for each of the plurality of types of SNS channels, the number of visits, and information related to the plurality of types of businesses into a first AI model to obtain the recommendation information, and the first AI model may be trained to obtain a correlation between the inflow keywords for each of the plurality of types of SNS channels and the plurality of types of businesses, classify the inflow keywords for each of the plurality of types of SNS channels by the plurality of types of businesses based on the obtained correlation, and calculate a ratio of marketing content for each of the plurality of types of businesses to be uploaded to each of the plurality of types of SNS channels based on one or more of the inflow keywords classified by the plurality of types of businesses.

And, the first AI model is trained to output information recommending a composition of marketing content to be uploaded to each of the plurality of types of SNS channels based on a distribution of one or more inflow keywords classified by the plurality of types of businesses, and the information recommending a composition of marketing content to be uploaded to each of the plurality of types of SNS channels may include an image related to the one or more inflow keywords, information related to a business corresponding to the one or more inflow keywords, and information about content related to the one or more inflow keywords among content whose exposure amount is greater than a threshold value in each of the plurality of types of SNS channels.

And, the first AI model is trained to output information related to weights for each of the plurality of types of SNS channels based on the number of contents whose exposure amount is greater than a threshold value and the number of visits based on the inflow keyword in each of the plurality of types of SNS channels, and the information related to weights for each of the plurality of types of SNS channels may include information on marketing costs to be invested for each of the plurality of types of SNS channels out of the total marketing costs of the specific company and information on the number of marketing contents to be uploaded for each of the plurality of types of SNS channels.

And, the method may further include a step of inputting information recommending a composition of marketing content to be uploaded for each of the plurality of types of SNS channels into a second AI model to obtain marketing content to be uploaded for each of the plurality of types of SNS channels; and a step of uploading the obtained marketing content to each of the plurality of types of SNS channels based on the marketing content to be uploaded for each of the plurality of types of SNS channels being approved by the specific company.

According to various embodiments of the present disclosure, a method and device for providing a SNS-based marketing recommendation service to which an artificial intelligence algorithm is applied can be provided.

In addition, by various embodiments of the present disclosure, a method and device for automatically classifying industry-specific marketing channels to efficiently perform online SNS-based marketing can be provided.

In addition, according to various embodiments of the present disclosure, a method and device for calculating weights for each SNS channel based on search volumes and views collected for each SNS channel and uploading marketing materials to each SNS channel according to the calculated weights can be provided.

In addition, through various embodiments of the present disclosure, unnecessary marketing costs can be reduced and more efficient marketing effects can be produced.

The 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 description below.

FIG. 1 is a schematic diagram of a system for providing a SNS-based marketing recommendation service using an artificial intelligence algorithm according to one embodiment of the present disclosure.
FIG. 2 is a block diagram briefly illustrating the configuration of a device that provides a SNS-based marketing recommendation service to which an artificial intelligence algorithm is applied according to one embodiment of the present disclosure.
FIG. 3 is a flowchart illustrating a method for providing an SNS-based marketing recommendation service to which an artificial intelligence algorithm is applied according to one embodiment of the present disclosure.

The advantages and features of the present disclosure, and the methods for achieving them, will become apparent by referring to the embodiments described in detail below together with the accompanying drawings. However, the present disclosure is not limited to the embodiments disclosed below and may be implemented in various different forms, and these embodiments are provided only to make the disclosure of the present disclosure complete and to fully inform a person skilled in the art of the scope of the present disclosure, and the present disclosure is defined only by the scope of the claims.

The terminology used herein is for the purpose of describing embodiments only and is not intended to be limiting of the present disclosure. In this specification, the singular also includes the plural unless specifically stated otherwise. The terms "comprises" and/or "comprising" as used herein do not exclude the presence or addition of one or more other components other than the mentioned components.

Throughout the specification, the same reference numerals refer to the same elements, and "and/or" includes each and every combination of one or more of the elements mentioned. Although "first", "second", etc. are used to describe various elements, it is to be understood that these elements are not limited by these terms. These terms are merely used to distinguish one element from another. Accordingly, it should be understood that a first element mentioned below may also be a second element within the technical spirit of the present disclosure.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used with the meaning commonly understood by those skilled in the art to which this disclosure belongs. In addition, terms defined in commonly used dictionaries shall not be ideally or excessively interpreted unless explicitly specifically defined.

The spatially relative terms "below," "beneath," "lower," "above," "upper," and the like can be used to easily describe the relationship of one component to another, as illustrated in the drawings. The spatially relative terms should be understood to include different orientations of the components when used or operated, in addition to the orientations illustrated in the drawings.

For example, when a component depicted in a drawing is flipped, a component described as "below" or "beneath" another component may be placed "above" the other component. Thus, the exemplary term "below" may include both the above and below directions. Components may also be oriented in other directions, and thus spatially relative terms may be interpreted according to the orientation.

Below, a method, device, and system for providing a SNS-based marketing recommendation service using an artificial intelligence algorithm are described with reference to drawings.

FIG. 1 is a diagram briefly illustrating a system (1000) that implements a method for providing an SNS-based marketing recommendation service using an artificial intelligence algorithm according to one embodiment of the present disclosure.

As illustrated in FIG. 1, a system (1000) implementing a method for providing a SNS-based marketing recommendation service using an artificial intelligence algorithm may include a device (100) and terminal devices (200-1, 200-2, ... 200-N) used by multiple companies (N is a natural number greater than or equal to 2).

In explaining the present disclosure, each company may mean a business entity conducting various types of business. However, this is only an example, and the company of the present disclosure may mean an individual user conducting a personal business. That is, the terminal device (200-1) used by the first company may mean a specific user who manages the first company. And, the terminal device (200-N) used by the Nth company may mean a specific user who manages the Nth company.

FIG. 1 illustrates a case where terminal devices (200-1, 200-2, ... 200-N) used by multiple companies are implemented in the form of a single smart phone, but is not limited thereto.

The device (100) and terminal devices (200-1, 200-2, ... 200-N) used by multiple companies may mean various types of electronic devices (e.g., smartphones, desktops, laptops, tablet PCs, server devices, wearable devices, etc.) or a group of devices to which one or more types of electronic devices are connected, as described above.

Devices (100) included in the system (1000) and terminal devices (200-1, 200-2, ... 200-N) used by multiple companies can communicate via a network (W).

Here, the network (W) may include a wired network and a wireless network. For example, the network may include various networks such as a local area network (LAN), a metropolitan area network (MAN), and a wide area network (WAN).

Additionally, the network (W) may include the well-known World Wide Web (WWW). However, the network (W) according to the embodiment of the present disclosure is not limited to the networks listed above, and may include at least a portion of a well-known wireless data network, a well-known telephone network, or a well-known wired/wireless television network.

The device (100) can perform a method of providing a SNS-based marketing recommendation service using an artificial intelligence algorithm. For example, the device (100) can provide an application or/and a web-based UI capable of providing a SNS-based marketing recommendation service using an algorithm to terminal devices (200-1, 200-2, ... 200-N) used by multiple companies.

Accordingly, terminal devices (200-1, 200-2, ... 200-N) used by multiple companies can receive SNS-based marketing recommendation services using artificial intelligence algorithms through the application or/and web-based UI.

The device (100) can obtain recommendation information related to marketing content to be uploaded to each of the plurality of types of SNS channels based on information related to multiple types of businesses operated by a specific company and multiple types of SNS channels managed by the specific company. The device (100) can provide recommendation information related to marketing content to be uploaded to each of the multiple types of SNS channels obtained to a terminal device used by the specific company.

Here, the marketing content to be uploaded to each of the multiple types of SNS channels may refer to marketing content scheduled to be uploaded to each of the multiple types of SNS channels.

Additionally or alternatively, the device (100) can generate marketing content to be uploaded to multiple types of SNS channels based on the recommendation information. Accordingly, a specific company can upload marketing content on SNS more efficiently.

The method by which the device (100) provides a SNS-based marketing recommendation service to which an artificial intelligence algorithm is applied will be specifically described with reference to FIG. 3.

FIG. 2 is a block diagram briefly illustrating the configuration of a device that provides an SNS-based marketing recommendation service to which an artificial intelligence algorithm is applied according to one embodiment of the present disclosure.

As illustrated in FIG. 2, the device (100) may include a memory (110), a communication module (120), a display (130), an input module (140), and a processor (150). However, the present invention is not limited thereto, and the device (100) may have software and hardware configurations modified/added/omitted within a range apparent to those skilled in the art according to a required operation.

The memory (110) can store data supporting various functions of the device and a program for the operation of the control unit, can store input/output data (for example, information related to multiple types of businesses operated by a specific company, etc.), and can store a plurality of application programs (or applications) run on the device, data for the operation of the device, and commands. At least some of these application programs can be downloaded from an external server via wireless communication.

The memory (110) may include at least one type of storage medium among a flash memory type, a hard disk type, an SSD (Solid State Disk type), an SDD (Silicon Disk Drive) type, a multimedia card micro type, a card type memory (for example, an SD or XD memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, and an optical disk. In addition, the memory (110) may be a database that is separate from the device (100) but connected by wire or wirelessly.

The communication module (120) may include one or more components that enable communication with an external device, and may include, for example, at least one of a wireless communication module or a location information module.

Here, the wireless communication module may include a wireless communication module that supports various wireless communication methods such as GSM (global System for Mobile Communication), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), UMTS (universal mobile telecommunications system), TDMA (Time Division Multiple Access), LTE (Long Term Evolution), 4G, 5G, and 6G, in addition to a WiFi module and a Wireless broadband module.

The wireless communication module may include a wireless communication interface including an antenna and a transmitter for transmitting various signals (e.g., information related to multiple types of businesses operated by a specific company). In addition, the wireless communication module may further include a signal conversion module for modulating a digital control signal output from a control unit through the wireless communication interface into an analog wireless signal under the control of the control unit.

The wireless communication module may include a wireless communication interface including an antenna and a receiver for receiving various signals. In addition, the wireless communication module may further include a signal conversion module for demodulating an analog wireless signal received through the wireless communication interface into a digital control signal.

The display (130) displays (outputs) information processed in the device (100) (e.g., information related to multiple types of businesses operated by a specific company, etc.). For example, the display may display execution screen information of an application program (e.g., an application) running in the device (100), or UI (User Interface) or GUI (Graphical User Interface) information according to such execution screen information.

The input unit (140) is for inputting image information (or signal), audio information (or signal), data, or information input from a user, and may include a user input unit, etc.

Specifically, the user input unit is for receiving information from a user, and when information is input through the user input unit, the control unit can control the operation of the device to correspond to the input information. The user input unit may include a hardware physical key (e.g., a button located on at least one of the front, rear, and side of the device, a dome switch, a jog wheel, a jog switch, etc.) and a software touch key.

As an example, the touch key may be formed as a virtual key, a soft key, or a visual key that is displayed on a display unit of a touch screen type through software processing, or may be formed as a touch key that is placed on a part other than the touch screen. Meanwhile, the virtual key or visual key may be displayed on the touch screen in various forms, and may be formed as, for example, a graphic, text, an icon, a video, or a combination thereof.

The processor (150) may be implemented as a memory storing data for an algorithm for controlling the operation of components within the device or a program reproducing the algorithm, and at least one processor (not shown) performing the above-described operation using the data stored in the memory. In this case, the memory and the processor may be implemented as separate chips. Alternatively, the memory and the processor may be implemented as a single chip.

Additionally, the processor may control any one or a combination of the components described above to implement various embodiments according to the present disclosure, as illustrated in FIG. 3 below, on the device.

FIG. 3 is a flowchart illustrating a method for providing an SNS-based marketing recommendation service to which an artificial intelligence algorithm is applied according to one embodiment of the present disclosure.

The device can receive information related to multiple types of businesses operated by a specific company and information related to multiple types of SNS channels managed by the specific company from terminal devices used by the specific company (S310).

And, the device can identify/obtain the number of visits based on the inflow keywords and the number of visits based on the inflow keywords for each of the multiple types of SNS channels through information related to the multiple types of SNS channels (S320).

Here, the fact that the device receives information related to multiple types of businesses operated by a specific company and information related to multiple types of SNS channels managed by the specific company from a terminal device used by the specific company may mean that the terminal device has entered information related to multiple types of businesses operated by the specific company and information related to multiple types of SNS channels managed by the specific company onto an application UI screen managed/controlled by the device.

That is, a terminal device used by a specific company can input information related to multiple types of businesses operated by the specific company and information related to multiple types of SNS channels managed by the specific company from the terminal device used by the specific company on the UI screen of the application after the terminal device installs an application managed/controlled by the device.

For example, information relating to multiple types of businesses may include the types of businesses a particular company operates, information on products and/or services sold by each business, and/or the types of events being held by each business.

Information related to multiple types of SNS channels managed by a specific company may include the types of SNS channels managed by the specific company, the number of subscribers (or/and followers) for each SNS channel, the cost (or/and budget) used to manage each SNS channel (i.e., the total marketing cost of the specific company), information about content uploaded to each SNS channel, and information about permissions for accessing content uploaded to each SNS channel.

Based on the information about access rights to the content uploaded to each SNS channel being received from a terminal device used by a specific company, the device can extract metadata of the content uploaded to each SNS channel (e.g., inflow keywords for each content, playback length for each content, images included in the content, text written with each content, comments registered for each content, etc.).

Here, content-specific inflow keywords may include keywords searched by other users to access the content, hashtags set for the content, and/or core keywords of the content.

Specifically, the device can access a management page capable of managing each SNS channel using the above authority information. The device can extract metadata of content uploaded to each SNS channel from the management page capable of managing each SNS channel.

Additionally or alternatively, the device may input content uploaded to each SNS channel into a separate AI model (e.g., a third AI model) to obtain core keywords of the content. The core keywords may include keywords indicating the subject matter of the content, keywords indicating goods or/and services promoted/advertised in the content, etc. In other words, the third AI model may be trained to output core keywords of the input content.

When the device acquires/extracts keywords for each type of SNS channel, the device can identify the number of visits based on the keywords for each inflow. For example, the device can identify the number of visits based on keywords for each content by using metadata of the content uploaded to each SNS channel.

As an example of the present disclosure, it is assumed that first content and second content are uploaded by a specific company on a first type of SNS channel and a second type of SNS channel among a plurality of types of SNS channels. Then, the device can receive information related to a business (e.g., fashion product sales business) operated by the specific company and information related to the first/second type of SNS channels from a terminal device used by the specific company.

The device can identify one or more search terms (i.e., inflow keywords) entered by other users to access each of the first content and the second content uploaded on the first type of SNS channel, and the number of visits based on the one or more search terms. At this time, the device can identify/obtain the above-described information based on metadata for the first content and the second content uploaded on the first type of SNS channel.

In addition, the device can identify one or more search terms (i.e., inflow keywords) entered by other users to access each of the first content and the second content uploaded on the second type of SNS channel, and the number of visits based on the one or more search terms. At this time, the device can identify/obtain the above-described information based on metadata for the first content and the second content uploaded on the second type of SNS channel.

The device can obtain recommendation information related to marketing content to be uploaded to each of the multiple types of SNS channels based on keywords for each of the multiple types of SNS channels, the number of visits based on the keywords for each of the multiple types of SNS channels, and information related to the multiple types of businesses (S330). Then, the device can transmit the obtained recommendation information to a terminal device used by a specific company (S340).

Here, the recommendation information related to the marketing content to be uploaded to each of the plurality of types of SNS channels may include information related to the ratio of the plurality of types of business-specific marketing content to be uploaded to each of the plurality of types of SNS channels, information related to the weights of the plurality of types of SNS channels, and information recommending the composition of the marketing content to be uploaded to each of the plurality of types of SNS channels.

Specifically, the device can input keywords for each of multiple types of SNS channels, the number of visits based on the keywords for inflow, and information related to multiple types of businesses into the first AI model to obtain recommendation information related to marketing content to be uploaded to each of the multiple types of SNS channels.

Here, the first AI model can be trained to obtain/produce the correlation between the keywords for inflow by multiple types of SNS channels and the correlation between the multiple types of businesses. And, the first AI model can classify the keywords for inflow by multiple types of SNS channels by multiple types of businesses based on the obtained correlation.

Specifically, the first AI model can be trained to calculate the similarity or correlation between the keywords for inflow by multiple types of SNS channels and the multiple types of businesses, and output the calculated similarity or correlation as the correlation between the keywords for inflow by multiple types of SNS channels and the multiple types of businesses.

For example, let's assume that the keywords for the first type of SNS channel are "spring new knitwear" and "tablet PC", and the multiple types of businesses include "fashion product sales" and "electronic product sales". The first AI model can be trained to output a high correlation between "spring new knitwear" and "fashion product sales" and a high correlation between "spring new knitwear" and "electronic product sales". In addition, the first AI model can be trained to output a high correlation between "tablet PC" and "electronic product sales" and a high correlation between "tablet PC" and "fashion product sales".

And, the first AI model can classify “spring new knitwear” as a keyword that brings in daily traffic for “fashion product sales” and “tablet PC” as a keyword that brings in daily traffic for “electronic product sales.”

The first AI model can be trained to calculate the ratio of multiple types of business-specific marketing content to be uploaded to each of multiple types of SNS channels based on one or more inflow keywords classified by multiple types of businesses.

Specifically, the ratio of marketing content for each of the multiple types of businesses to be uploaded to each of the multiple types of SNS channels can be calculated based on the number of one or more inflow keywords classified by each of the multiple types of businesses. When the number of inflow keywords classified as the first type of business is N and the number of inflow keywords classified as the second type of business is M, the ratio of content corresponding to the first type of business and content corresponding to the second type of business to be uploaded to each of the multiple types of SNS channels can be determined by the first AI model as N:M.

Additionally or alternatively, the first AI model may be trained to output information recommending the composition of marketing content to be uploaded to each of the plurality of types of SNS channels based on the distribution of one or more inflow keywords classified by the plurality of types of businesses and/or information related to the one or more inflow keywords.

Here, information recommending the composition of marketing content to be uploaded to each of a plurality of types of SNS channels may include images related to one or more inflow keywords, business-related information corresponding to one or more inflow keywords, and information about content related to one or more inflow keywords among the content whose exposure volume exceeds a threshold value on each of a plurality of types of SNS channels.

Additionally, information related to one or more inflow keywords may include images matching one or more inflow keywords, information related to the business, etc.

In addition, the distribution of inflow keywords classified by multiple types of business may include the number of inflow keywords classified by multiple types of business, the number of searches for the corresponding inflow keywords, etc.

Information about content whose exposure amount is greater than a threshold value in each of a plurality of types of SNS channels may be provided from each of a plurality of types of SNS channels for a specific time period. The device may build a database with content whose exposure amount is greater than a threshold value in each of a plurality of types of SNS channels. The device may learn to output information recommending a composition of marketing content to be uploaded to each of a plurality of types of SNS channels based on database-based learning data to the first AI model.

Additionally or alternatively, the first AI model may be trained to output information related to weights for each of the plurality of types of SNS channels based on the number of contents with an exposure volume greater than a threshold value and the number of visits based on inflow keywords in each of the plurality of types of SNS channels.

Here, information related to weights for each of the multiple types of SNS channels may include information on marketing costs to be invested for each of the multiple types of SNS channels out of the total marketing costs of a specific company and information on the number of marketing contents to be uploaded for each of the multiple types of SNS channels.

That is, if the weight of the first SNS channel is 1 and the weight of the second SNS channel is 2, the device can identify that there is 1 marketing content to be uploaded to the first SNS channel and 2 marketing contents to be uploaded to the second SNS channel.

Additionally or alternatively, if the weight of the first SNS channel is 1 and the weight of the second SNS channel is 2, 1/3 of the total marketing cost may be invested in marketing costs for the first SNS channel, and 2/3 may be invested in marketing costs for the second SNS channel.

A specific company can configure the content to be uploaded to each SNS using information related to the weights of each type of SNS channel and information recommending the composition of marketing content to be uploaded to each type of SNS channel.

Additionally or alternatively, the device may input information recommending a composition of marketing content to be uploaded for each of a plurality of types of SNS channels into the second AI model to obtain marketing content to be uploaded for each of a plurality of types of SNS channels.

That is, the device can generate marketing content to be uploaded to each of multiple types of SNS channels managed by a specific company by inputting information about content related to one or more inflow keywords, information related to a business corresponding to one or more inflow keywords, and content with an exposure volume exceeding a threshold value on each of multiple types of SNS channels into the second AI model.

Based on the marketing content to be uploaded to each of the multiple types of SNS channels being approved by a specific company, the device can upload the acquired marketing content to each of the multiple types of SNS channels. At this time, the device can upload the acquired marketing content to each of the multiple types of SNS channels based on the authorization information received from the specific company.

Here, the first AI model and the second AI model can be implemented as a single AI model. That is, when the input data described above is input into the first AI model, the device can obtain recommendation information related to marketing content to be uploaded to each of the plurality of types of SNS channels and marketing content to be uploaded to each of the plurality of types of SNS channels.

However, this is only one embodiment, and the device can obtain recommendation information related to marketing content to be uploaded to each of the plurality of types of SNS channels based on inputting the input data described above into the first AI model. In addition, the device can input information recommending a composition of marketing content to be uploaded for each of the plurality of types of SNS channels among the recommendation information related to marketing content to be uploaded for each of the plurality of types of SNS channels into the second AI model, thereby obtaining marketing content to be uploaded for each of the plurality of types of SNS channels.

And, the AI model can be a deep neural network. Throughout this specification, neural network, network function, and neural network can be used with the same meaning. A deep neural network (DNN) can mean a neural network that includes multiple hidden layers in addition to an input layer and an output layer. Using a deep neural network, latent structures of data can be identified. That is, latent structures of photos, text, videos, voices, and music can be identified (for example, what objects are in the photo, what the content and emotion of the text are, what the content and emotion of the voice are, etc.). A deep neural network can include a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a Q network, a U network, a Siamese network, etc.

Meanwhile, the disclosed embodiments may be implemented in the form of a recording medium storing instructions executable by a computer. The instructions may be stored in the form of program codes, and when executed by a processor, may generate program modules to perform the operations of the disclosed embodiments. The recording medium may be implemented as a computer-readable recording medium.

Computer-readable storage media include all types of storage media that store instructions that can be deciphered by a computer. Examples include ROM (Read Only Memory), RAM (Random Access Memory), magnetic tape, magnetic disk, flash memory, and optical data storage devices.

As described above, the disclosed embodiments have been described with reference to the attached drawings. Those skilled in the art to which the present disclosure pertains will understand that the present disclosure can be implemented in forms other than the disclosed embodiments without changing the technical idea or essential features of the present disclosure. The disclosed embodiments are exemplary and should not be construed as limiting.

110: Memory
120: Communication Module
130: Display
140: Input module
150: Processor

Claims (5)

A method for providing a social network service (SNS)-based marketing recommendation service performed by a device, the method comprising:
A step of receiving information related to multiple types of businesses operated by a specific company and information related to multiple types of SNS channels managed by the specific company from a terminal device used by the specific company;
A step of identifying keywords for each of the plurality of types of SNS channels and the number of visits based on the keywords for each of the plurality of types of SNS channels through information related to the plurality of types of SNS channels;
A step of obtaining recommendation information related to marketing content to be uploaded to each of the plurality of types of SNS channels based on the keywords for inflow by each of the plurality of types of SNS channels, the number of visits, and information related to the plurality of types of businesses; and
A step of transmitting the obtained recommendation information to the terminal device is included.
A method wherein the above recommendation information includes information related to weights for each of the plurality of types of SNS channels, and information recommending the composition of marketing content to be uploaded for each of the plurality of types of SNS channels.
In the first paragraph,
The steps for obtaining the above recommended information are:
It includes a step of obtaining the recommendation information by inputting the keywords for each of the above multiple types of SNS channels, the number of visits, and information related to the above multiple types of businesses into the first AI model,
The above first AI model is,
Obtain the correlation between the keywords for the above multiple types of SNS channels and the above multiple types of businesses,
A method for learning to classify keywords for each of the above multiple types of SNS channels by the above multiple types of businesses based on the acquired relevance.
In the second paragraph,
The above first AI model is,
It is learned to output information recommending the composition of marketing content to be uploaded to each of the plurality of types of SNS channels based on the distribution of one or more inflow keywords classified by the plurality of types of businesses,
A method wherein information for recommending a composition of marketing content to be uploaded to each of the plurality of types of SNS channels includes images related to the one or more inflow keywords, information related to a business corresponding to the one or more inflow keywords, and information about content related to the one or more inflow keywords among the content whose exposure volume is greater than a threshold value on each of the plurality of types of SNS channels.
In the third paragraph,
The above first AI model is,
It is learned to output information related to the weight of each of the plurality of types of SNS channels based on the number of contents whose exposure amount is greater than a threshold value and the number of visits based on the inflow keyword in each of the plurality of types of SNS channels,
Information related to the weights of each of the above multiple types of SNS channels,
A method including information on marketing costs to be invested in each of the plurality of types of SNS channels among the total marketing costs of the specific company and information on the number of marketing contents to be uploaded in each of the plurality of types of SNS channels.
In paragraph 4,
A step of inputting information recommending the composition of marketing content to be uploaded for each of the plurality of types of SNS channels into a second AI model to obtain marketing content to be uploaded for each of the plurality of types of SNS channels;
A method further comprising the step of uploading the acquired marketing content to each of the plurality of types of SNS channels based on the approval by the specific company of the marketing content to be uploaded to each of the plurality of types of SNS channels.