KR102518637B1 - Method, server and computer program for providing matching service between client and influencer based on artificial intelligence - Google Patents

Abstract

A method for providing an artificial intelligence-based client and influencer matching service, a server, and a computer program are provided. The method for providing an artificial intelligence-based client and influencer matching service according to various embodiments of the present invention, as a method performed by a computing device, includes the steps of: obtaining a matching request between a client wishing to promote a specific promotional target and an influencer; setting matching targets based on the obtained matching request; and performing matching between the set matching targets.

Description

Artificial intelligence-based client and influencer matching service provision method, server and computer program

Various embodiments of the present invention relate to an artificial intelligence-based client and influencer matching service providing method, server, and computer program.

As Internet technology develops, technology for providing content in the form of text, images, and videos over the Internet is rapidly developing, and video platforms (eg YouTube), Internet broadcasting platforms (eg Afreeca TV, Twitch TV and Daumpot) and portal site platforms (eg, Daum, Google, etc.) are provided through the Internet network, and platforms where you can check and enjoy various contents are increasing.

In accordance with this trend, influencers (e.g. creators) who are active on various platforms and have numerous subscribers (or followers) have begun to appear, and influencers produce and develop their own content. It is being produced and embodied as a one-person, small-scale or multi-person broadcasting station.

Recently, it is also common for influencers to directly appear on home shopping or internet shopping, and to conduct advertisements that further maximize the image of the influencer himself. Since each and every action of influencers affects ordinary users who are interested in them, it is obvious that influencers' purchasing power and marketing index increase even more when they advertise.

In accordance with this trend, clients have tried to promote specific products or stores that sell specific products through influencers, but there is a problem in that it is not easy to select an influencer suitable for promoting their own products or stores.

In particular, in the conventional influencer advertising market, the reality is that the influence of an influencer is measured only by the number of followers (fans) of the influencer. Not only are there many cases where publicity effects are not properly seen due to lack of trust in influencers, but there is also a problem that influencers with high content are not recognized for their value.

The problem to be solved by the present invention is to provide an optimal influencer to a client who wants to promote a specific promotion target through a pre-learned artificial intelligence model for the purpose of solving the problems of the conventional influencer advertising market described above. Provides an artificial intelligence-based client and influencer matching service providing method, server, and computer program that can perform optimal matching between a client and an influencer by matching or matching the optimal client to a specific influencer. will be.

The problems to be solved by the present invention 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.

A method for providing an artificial intelligence-based client and influencer matching service according to an embodiment of the present invention for solving the above problems is a method performed by a computing device, a client and an influencer who wants to promote a specific promotion target It may include obtaining a matching request between words, setting a matching target based on the obtained matching request, and performing matching between the set matching targets.

In various embodiments, the step of setting the matching target may include, when obtaining an influencer matching request from a first client, a plurality of those registered in a pre-stored influencer manpower pool based on the obtained influencer matching request. Selecting influencers located within a predetermined range based on the current location of the first client among the influencers of the and matching conditions included in the acquired influencer matching request - the matching conditions include a target for promotion and Setting one or more influencers among the selected influencers as a matching target based on - including information on a promotion method, information on an influencer to be matched, and information on an amount to be paid. can

In various embodiments, the step of setting one or more matching conditions based on the information on the promotion target input from the first client and the information on the promotion method for the promotion target, and pre-stored using the pre-learned artificial intelligence model. Among the plurality of influencers registered in the influencer manpower pool, influencers that satisfy one or more set matching conditions are selected, and the first client-tailored manpower pool containing information on the selected influencers is created. It may further include steps to do.

In various embodiments, the step of selecting one or more influencers may include, when obtaining an influencer matching request from the first client, an influencer located within a predetermined range based on the current location of the first client. The method may include selecting one or more influencers from among the speakers, and preferentially selecting an influencer included in the created first client-tailored manpower pool.

In various embodiments, the performing of the matching may include that at least one influencer among the influencers registered in the manpower pool customized for the first client is within a predetermined range set around the current location of the first client. When entering, providing information about the at least one influencer to the first client, or automatically matching the at least one influencer with the first client.

In various embodiments, the step of performing the matching may include receiving a fee for influencer matching from a first client in advance, and as matching between the first client and a specific influencer is completed, the previously paid fee The cost is paid to the specific influencer, but in response to the specific influencer posting promotional content - the promotional content is content that the first client promotes the promotion target - the cost received in advance It may include paying the specific influencer.

In various embodiments, the step of performing the matching may include monitoring the status of promotional content posted from the specific influencer at predetermined intervals for a predetermined period of time, but posting from the specific influencer within the predetermined period of time. A step of imposing a penalty on the specific influencer may be included when the state of the promotional content is switched from a public state to a private state or is deleted.

In various embodiments, the setting of the matching target may include, when obtaining a client matching request from the first influencer, based on the current location of the first influencer based on the obtained client matching request. The method may further include selecting one or more clients from among a plurality of clients located within a set range and providing map data including information on the selected one or more clients to the first influencer.

In various embodiments, the step of generating an influencer manpower pool including information on each of a plurality of influencers is further included, and the step of generating the influencer manpower pool includes the influence from the first influencer. When receiving a request for registration in the luncer manpower pool, providing the first influencer with a self-authentication process - the self-authentication process includes at least one of mobile phone authentication and SNS account authentication - and the first influencer may include registering the first influencer in the created influencer manpower pool based on a result of performing identity authentication according to the identity authentication process provided above.

In various embodiments, the step of generating an influencer manpower pool including information on each of a plurality of influencers is further included, and the step of generating the influencer manpower pool includes a plurality of first influencers. When a representative of an organization to which is a member is requested to register an influencer manpower pool for a plurality of first influencers included in the organization, the attributes of the organization and the representative - The attributes of the organization and the representative An authentication method is determined based on - including the size of the organization and the awareness of the representative, and based on a result of performing an authentication procedure according to the determined authentication method, the plurality of first influencers are assigned to the generated influencers. The first authentication method, which is registered in the luncer manpower pool, but the authentication method performs identity authentication only for the representative, identity authentication for at least one representative influencer among the representative and the plurality of first influencers It may include a step that includes at least one of a second authentication method performed and a third authentication method performed identity authentication for the representative and all of the plurality of first influencers.

In various embodiments, each of the plurality of influencers is classified by country based on the nationality and active country of each of the plurality of influencers, and a plurality of influencers each including information about the plurality of influencers classified by country Further comprising creating a country-level manpower pool, and setting the matching target, when obtaining an influencer matching request for promotion of the specific promotion target in the first country from the first client, the Select a country-level manpower pool corresponding to the first country from among a plurality of country-level manpower pools, and select one or more first-country influencers from among the plurality of first-country influencers included in the selected country-level manpower pool. steps may be included.

In various embodiments, the step of selecting one or more first nationality influencers may include matching the obtained influencer among a plurality of first country influencers included in a national manpower pool corresponding to the first country. If there is no influencer in the first country that satisfies one or more matching conditions included in the request, one or more influencers satisfying the one or more matching conditions are used by using a country-level manpower pool corresponding to a second country adjacent to the first country. Selecting a second country influencer, asking the selected one or more second country influencers whether or not to participate in the promotion of the specific promotion target in the first country, and the specific promotion target in the first country The method may include determining whether to select the selected one or more second country influencers based on a response of the selected one or more second country influencers to an inquiry about whether or not to participate in public relations.

An artificial intelligence-based client and influencer matching service providing server according to another embodiment of the present invention for solving the above problems is loaded into a processor, a network interface, a memory, and the memory, and is executed by the processor. A computer program comprising: an instruction for obtaining a matching request between a client who wants to promote a specific promotion target and an influencer, an instruction for setting a matching target based on the obtained matching request, and It may include an instruction for performing matching between the set matching targets.

A computer program recorded on a computer-readable recording medium according to another embodiment of the present invention for solving the above problems is combined with a computing device, and a matching request between a client and an influencer who wants to promote a specific promotion target In order to execute an artificial intelligence-based client and influencer matching service providing method including obtaining a matching request, setting a matching target based on the obtained matching request, and performing matching between the set matching targets. It can be stored on a computer-readable recording medium.

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

According to various embodiments of the present invention, by matching the optimal influencer to a client who wants to promote a specific promotion target through a pre-learned artificial intelligence model or by matching the optimal client to a specific influencer, the client and the influencer There is an advantage in that optimal matching between Luancers can be performed.

The effects of the present invention 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.

1 is a diagram illustrating an AI-based client and influencer matching service providing system according to an embodiment of the present invention.
2 is a hardware configuration diagram of an artificial intelligence-based client and influencer matching service providing server according to another embodiment of the present invention.
3 is a flow chart of a method of providing an artificial intelligence-based client and influencer matching service on the client side, in various embodiments.
4 is a flowchart of a method for creating and storing an influencer manpower pool, in various embodiments.
5 is a flow chart of a method for providing an artificial intelligence-based client and influencer matching service in terms of an influencer, in various embodiments.
6 is a diagram illustrating a user interface (UI) provided by an artificial intelligence-based client and an influencer matching service providing server in various embodiments.

Advantages and features of the present invention, and methods of achieving them, will become clear with reference to the detailed description of the following embodiments taken in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, only these embodiments are intended to complete the disclosure of the present invention, and are common in the art to which the present invention belongs. It is provided to fully inform the person skilled in the art of the scope of the invention, and the invention is only defined by the scope of the claims.

Terminology used herein is for describing the embodiments and is not intended to limit the present invention. In this specification, singular forms also include plural forms unless specifically stated otherwise in a phrase. As used herein, "comprises" and/or "comprising" does not exclude the presence or addition of one or more other elements other than the recited elements. Like reference numerals throughout the specification refer to like elements, and “and/or” includes each and every combination of one or more of the recited elements. Although "first", "second", etc. are used to describe various components, these components 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 element mentioned below may also be the second element within the technical spirit of the present invention.

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

The term "unit" or "module" used in the specification means a hardware component such as software, FPGA or ASIC, and "unit" or "module" performs certain roles. However, "unit" or "module" is not meant to be limited to software or hardware. A “unit” or “module” may be configured to reside in an addressable storage medium and may be configured to reproduce one or more processors. Thus, as an example, a “unit” or “module” may refer to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays and variables. Functions provided within components and "units" or "modules" may be combined into smaller numbers of components and "units" or "modules" or may be combined into additional components and "units" or "modules". can be further separated.

The spatially relative terms "below", "beneath", "lower", "above", "upper", etc. It can be used to easily describe a component's correlation with other components. Spatially relative terms should be understood as including different orientations of elements in use or operation in addition to the orientations shown in the drawings. For example, if you flip a component that is shown in a drawing, a component described as "below" or "beneath" another component will be placed "above" the other component. can Thus, the exemplary term “below” may include directions of both below and above. Components may also be oriented in other orientations, and thus spatially relative terms may be interpreted according to orientation.

In this specification, a computer means any kind of hardware device including at least one processor, and may be understood as encompassing a software configuration operating in a corresponding hardware device according to an embodiment. For example, a computer may be understood as including a smartphone, a tablet PC, a desktop computer, a laptop computer, and user clients and applications running on each device, but is not limited thereto.

In addition, this specification describes a method for providing an artificial intelligence-based client and influencer matching service targeting influencers, but is not limited thereto, and influencers as well as influencer hopefuls, celebrities and aspiring celebrities can include all

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

Although each step described in this specification is described as being performed by a computer, the subject of each step is not limited thereto, and at least a part of each step may be performed in different devices according to embodiments.

1 is a diagram illustrating an AI-based client and influencer matching service providing system according to an embodiment of the present invention.

1, an artificial intelligence-based client and influencer matching service providing system according to an embodiment of the present invention includes a client and influencer matching service providing server 100, a user terminal 200, an external server ( 300) and a network 400.

Here, the artificial intelligence-based client and influencer matching service providing system shown in FIG. 1 is according to an embodiment, and its components are not limited to the embodiment shown in FIG. 1, and additional, if necessary, may be changed or deleted.

In one embodiment, the client and influencer matching service providing server 100 (hereinafter referred to as “server 100”) may provide a matching service between clients and influencers.

In various embodiments, when obtaining an influencer matching request from a client, the server 100 may select an optimal influencer using a previously learned artificial intelligence model and match the selected influencer with the client. there is.

In addition, when obtaining a client matching request from an influencer, the server 100 may select an optimal client using a pre-learned artificial intelligence model and match the selected client with the influencer.

Here, the pre-learned artificial intelligence model is information about each of a plurality of influencers (e.g. personal information of each influencer, information about SNS account (e.g. SNS type, number of followers), information about promotion method (e.g., type of promotional content, posting method, etc.)), information about the target of promotion (e.g., type of target, etc.) and the resulting public relations effect are learned according to a machine learning-based learning method. It may be a model that calculates a promotion effect (eg, a score in the range of 0 to 100) as result data by using information about a promotion target and information about an influencer as input data.

An artificial intelligence model (or computational model, neural network, network function, neural network) is composed of one or more network functions, which are generally a set of interconnected computational units that can be referred to as 'nodes'. may consist of These 'nodes' may also be referred to as 'neurons'. One or more network functions include at least one or more nodes. Nodes (or neurons) that make up one or more network functions can be interconnected by one or more 'links'.

In an artificial intelligence model, one or more nodes connected through a link may form a relative relationship of an input node and an output node. The concept of an input node and an output node is relative, and any node in an output node relationship with one node may have an input node relationship with another node, and vice versa. As described above, the input node to output node relationship can be created around the link. More than one output node can be connected to one input node through a link, and vice versa.

In a relationship between an input node and an output node connected through one link, the value of the output node may be determined based on data input to the input node. Here, a node interconnecting an input node and an output node may have a weight. The weight may be variable, and may be variable by a user or an algorithm in order to perform a function desired by the artificial intelligence model. For example, when one or more input nodes are interconnected by respective links to one output node, the output node is set to a link corresponding to values input to input nodes connected to the output node and respective input nodes. An output node value may be determined based on the weight.

As described above, in the AI model, one or more nodes are interconnected through one or more links to form an input node and output node relationship in the AI model. Characteristics of the artificial intelligence model may be determined according to the number of nodes and links in the artificial intelligence model, the relationship between the nodes and links, and the value of weight assigned to each link. For example, when there are two artificial intelligence models having the same number of nodes and links and different weight values between the links, the two artificial intelligence models may be recognized as different from each other.

Some of the nodes constituting the artificial intelligence model may constitute one layer based on distances from the first input node. For example, a set of nodes having a distance of n from the first input node may constitute n layers. The distance from the first input node may be defined by the minimum number of links that must be passed through to reach the corresponding node from the first input node. However, the definition of such a layer is arbitrary for explanation, and the order of a layer in an artificial intelligence model may be defined in a different way from the above. For example, a layer of nodes may be defined by a distance from a final output node.

An initial input node may refer to one or more nodes to which data is directly input without going through a link in relation to other nodes among nodes in the artificial intelligence model. Alternatively, in an artificial intelligence model network, in a relationship between nodes based on a link, it may mean nodes that do not have other input nodes connected by a link. Similarly, the final output node may refer to one or more nodes that do not have an output node in relation to other nodes among nodes in the artificial intelligence model. Also, the hidden node may refer to nodes constituting an artificial intelligence model other than the first input node and the last output node. An artificial intelligence model according to an embodiment of the present disclosure may have more nodes of an input layer than nodes of a hidden layer close to an output layer, and may be an artificial intelligence model in which the number of nodes decreases as the number of nodes increases from the input layer to the hidden layer. can

AI models can include one or more hidden layers. A hidden node of a hidden layer may use outputs of previous layers and outputs of neighboring hidden nodes as inputs. The number of hidden nodes for each hidden layer may be the same or different. The number of nodes of the input layer may be determined based on the number of data fields of the input data and may be the same as or different from the number of hidden nodes. Input data input to the input layer may be operated by a hidden node of the hidden layer and may be output by a fully connected layer (FCL) that is an output layer.

In various embodiments, the server 100 may build learning data for training the artificial intelligence model, and use the built learning data to perform supervised learning, unsupervised learning, and class teacher learning. The artificial intelligence model may be trained using at least one method of semi-supervised learning.

Training of AI models is aimed at minimizing errors in the output. In the learning of the artificial intelligence model, the training data is repeatedly input into the artificial intelligence model, the output of the artificial intelligence model for the training data and the error of the target are calculated, and the error of the artificial intelligence model is converted into the artificial intelligence model in the direction of reducing the error. This is the process of backpropagating from the output layer to the input layer to update the weight of each node of the AI model.

In the case of teacher learning, the learning data in which the correct answer is labeled is used for each learning data (ie, the labeled learning data), and in the case of comparative teacher learning, the correct answer may not be labeled in each learning data. That is, for example, learning data in the case of teacher learning regarding data classification may be data in which each learning data is labeled with a category. Labeled training data is input to the artificial intelligence model, and an error can be calculated by comparing the output (category) of the artificial intelligence model with the label of the training data.

As another example, in the case of comparative history learning for data classification, an error may be calculated by comparing input learning data with an artificial intelligence model output. The calculated error is back-propagated in the reverse direction (ie, from the output layer to the input layer) in the AI model, and the connection weight of each node in each layer of the AI model can be updated according to the back-propagation. The amount of change in the connection weight of each updated node may be determined according to a learning rate.

The computation of an AI model on input data and backpropagation of errors can constitute a learning cycle (epoch). The learning rate may be applied differently according to the number of iterations of the learning cycle of the artificial intelligence model. For example, a high learning rate can be used in the early stage of AI model training to increase efficiency by enabling the AI model to quickly achieve a certain level of performance, and a low learning rate can be used in the late stage to increase accuracy.

In learning artificial intelligence models, generally, training data can be a subset of real data (ie, data to be processed using the trained artificial intelligence model), and therefore, errors for training data are reduced, but for real data There may be learning cycles with increasing errors. Overfitting is a phenomenon in which errors for actual data increase due to excessive learning on training data. For example, a phenomenon in which an artificial intelligence model that learned a cat by showing a yellow cat does not recognize that it is a cat when it sees a cat other than yellow may be a type of overfitting.

Overfitting can act as a cause of increasing the error of machine learning algorithms. Various optimization methods can be used to prevent such overfitting. In order to prevent overfitting, methods such as increasing training data, regularization, and omitting some nodes of a network in the process of learning may be applied.

In various embodiments, the artificial intelligence-based client and influencer matching service provided by the server 100 may be implemented in the form of a web or application and provided to users (clients or influencers). , but not limited thereto.

In one embodiment, the user terminal 200 (eg, a client terminal or an influencer terminal) may be connected to the server 100 through the network 400, and the artificial intelligence-based client and influencer terminal from the server 100 Unseo matching service can be provided.

Here, the user terminal 200 includes an artificial intelligence-based client implemented in the form of a web or application and an operating system for executing an influencer matching service, and a smartphone having a display in a predetermined area for UI output ( Smart-phone), but is not limited thereto, and the user terminal 200 is a wireless communication device that ensures portability and mobility, and includes navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC ( Personal Digital Cellular), Personal Handyphone System (PHS), Personal Digital Assistant (PDA), International Mobile Telecommunication (IMT)-2000, Code Division Multiple Access (CDMA)-2000, W-Code Division Multiple Access (W-CDMA), It may include all types of handheld-based wireless communication devices such as Wibro (Wireless Broadband Internet) terminals, smart pads, tablet PCs, and the like.

In addition, here, the network 400 refers to a connection structure capable of exchanging information between nodes such as a plurality of terminals and servers, and examples of such networks include a local area network (LAN) and a wide area network. A wide area network (WAN), a World Wide Web (WWW), a wired/wireless data communication network, a telephone network, a wired/wireless television communication network, and the like may be included.

In addition, wireless data communication networks include 3G, 4G, 5G, 3GPP (3rd Generation Partnership Project), 5GPP (5th Generation Partnership Project), LTE (Long Term Evolution), WIMAX (World Interoperability for Microwave Access), Wi-Fi (Wi-Fi) , Internet (Internet), LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), RF (Radio Frequency), Bluetooth (Bluetooth) network, NFC ( A Near-Field Communication) network, a satellite broadcasting network, an analog broadcasting network, a Digital Multimedia Broadcasting (DMB) network, and the like may be included, but are not limited thereto.

In one embodiment, the external server 300 may be connected to the server 100 through the network 400, and various information and information necessary for the server 100 to provide an artificial intelligence-based client and influencer matching service. Data (e.g. influencer manpower pool containing information on multiple influencers) can be stored and managed.

In addition, the external server 300 stores and manages various information and data (eg, matching result data according to matching conditions, etc.) generated as the server 100 provides an AI-based client and influencer matching service. can do.

In various embodiments, the external server 300 may be a storage server provided separately outside the server 100, but is not limited thereto. Hereinafter, with reference to FIG. 2, the hardware configuration of the server 100 performing the AI-based client and influencer matching service providing method will be described.

2 is a hardware configuration diagram of an artificial intelligence-based client and influencer matching service providing server according to another embodiment of the present invention.

Referring to FIG. 2 , in various embodiments, the server 100 includes one or more processors 110, a memory 120 that loads a computer program 151 executed by the processor 110, and a bus 130. ), a communication interface 140 and a storage 150 for storing the computer program 151. Here, in FIG. 2, only components related to the embodiment of the present invention are shown. Therefore, those skilled in the art to which the present invention pertains can know that other general-purpose components may be further included in addition to the components shown in FIG. 2 .

The processor 110 controls the overall operation of each component of the server 100. The processor 110 includes a Central Processing Unit (CPU), a Micro Processor Unit (MPU), a Micro Controller Unit (MCU), a Graphic Processing Unit (GPU), or any type of processor well known in the art of the present invention. It can be.

Also, the processor 110 may perform an operation for at least one application or program for executing a method according to embodiments of the present invention, and the server 100 may include one or more processors.

In various embodiments, the processor 110 may temporarily and/or permanently store signals (or data) processed in the processor 110 (RAM: Random Access Memory, not shown) and ROM (ROM: Read -Only Memory, not shown) may be further included. In addition, the processor 110 may be implemented in the form of a system on chip (SoC) including at least one of a graphics processing unit, RAM, and ROM.

Memory 120 stores various data, commands and/or information. Memory 120 may load computer program 151 from storage 150 to execute methods/operations according to various embodiments of the present invention. When the computer program 151 is loaded into the memory 120, the processor 110 may perform the method/operation by executing one or more instructions constituting the computer program 151. The memory 120 may be implemented as a volatile memory such as RAM, but the technical scope of the present disclosure is not limited thereto.

The bus 130 provides a communication function between components of the server 100 . The bus 130 may be implemented in various types of buses such as an address bus, a data bus, and a control bus.

The communication interface 140 supports wired and wireless Internet communication of the server 100 . Also, the communication interface 140 may support various communication methods other than Internet communication. To this end, the communication interface 140 may include a communication module well known in the art. In some embodiments, communication interface 140 may be omitted.

The storage 150 may non-temporarily store the computer program 151 . When performing the AI-based client and influencer matching service providing process through the server 100, the storage 150 stores various information necessary to provide the AI-based client and influencer matching service providing process. can be saved

The storage 150 may be a non-volatile memory such as read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, or the like, a hard disk, a removable disk, or a device well known in the art. It may be configured to include any known type of computer-readable recording medium.

Computer program 151 may include one or more instructions that when loaded into memory 120 cause processor 110 to perform methods/operations in accordance with various embodiments of the invention. That is, the processor 110 may perform the method/operation according to various embodiments of the present disclosure by executing the one or more instructions.

In one embodiment, the computer program 151 may include obtaining a matching request between a client who wants to promote a specific promotion target and an influencer, setting a matching target based on the obtained matching request, and matching between the set matching targets. It may include one or more instructions for performing an artificial intelligence-based client and influencer matching service providing method comprising the step of performing.

Steps of a method or algorithm described in connection with an embodiment of the present invention may be implemented directly in hardware, implemented in a software module executed by hardware, or implemented 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 form of computer readable recording medium well known in the art to which the present invention pertains.

Components of the present invention may be implemented as a program (or application) to be executed in combination with a computer, which is hardware, and stored in a medium. Components of the present invention may be implemented as software programming or software elements, and similarly, embodiments may include various algorithms implemented as data structures, processes, routines, or combinations of other programming constructs, such as C, C++ , Java (Java), can be implemented in a programming or scripting language such as assembler (assembler). Functional aspects may be implemented in an algorithm running on one or more processors. Hereinafter, with reference to FIGS. 3 to 6, a method for providing an artificial intelligence-based client and influencer matching service provided by the server 100 will be described.

3 is a flow chart of a method of providing an artificial intelligence-based client and influencer matching service on the client side, in various embodiments.

Referring to FIG. 3 , in step S110, the server 100 may obtain an influencer matching request from the first client. For example, the server 100 may provide an artificial intelligence-based client and influencer matching service web or application to the client terminal of the first client, and as the first client executes the web or application, the artificial intelligence-based The user interface (UI) of the client and influencer matching service can be output, and influencer matching requests can be received through the AI-based client and influencer matching service UI.

Here, the influencer matching request is information on the target to be promoted (e.g., type of target to be promoted, etc.), matching condition information (e.g., the number of influencers to be matched with, age, gender, personality, body type, image, compensation, etc.) ), but is not limited thereto.

In step S120, the server 100 matches one or more influencers among a plurality of influencers registered in the pre-stored influencer manpower pool based on the influencer matching request acquired through step S110. can be selected as a target. To this end, the server 100 may build an influencer manpower pool in advance before providing an artificial intelligence-based client and influencer matching service. Hereinafter, it will be described with reference to FIG. 4 .

4 is a flowchart of a method for creating and storing an influencer manpower pool, in various embodiments.

Referring to FIG. 4 , in step S210, the server 100 may create an influencer manpower pool using information on each of a plurality of influencers.

Here, the influencer manpower pool is a pool of influencers suitable for producing promotional content suitable for various promotional targets and each target in order to produce promotional content for promoting a specific product or a store that sells a specific product. It may mean a group secured in advance.

In addition, here, the information about the influencer registered in the influencer manpower pool is all information about the influencer, including age, place of birth, place of residence, nationality, and body information (eg height, weight, blood type, foot size, etc.) ), occupation, family information (e.g. parents, siblings, spouse, children, etc.), education information, religion information, military service information, agency information, MBTI information, image or reputation information, SNS account information, appearance fee information and profile picture However, it is not limited thereto, and the information about influencers registered in the influencer manpower pool may further include matching condition information (eg, payment of more than a certain amount of advertisement fee, exclusion of certain types of products, etc.).

In various embodiments, the server 100 classifies each of the plurality of influencers by country based on the nationality and active country of each of the plurality of influencers, and provides information on the plurality of influencers classified by country, respectively. Multiple national manpower pools can be created. That is, the server 100 may classify a plurality of influencers registered in the influencer manpower pool by country according to their nationality and activity country and individually manage them.

At this time, when a specific influencer is active in multiple countries, the server 100 registers all information about the specific influencer in each country-level manpower pool corresponding to the multiple countries, so that later, the country-level manpower pool When selecting an influencer to match using , you can set it so that the influencer can be searched and selected in multiple countries.

In addition, the server 100 grants a specific influencer the right to register in a specific country-level manpower pool or cancel registration of a specific country-level manpower pool, so that a specific influencer can more freely receive matching proposals in a specific country or You can set it not to accept.

In various embodiments, the server 100 may group information on a plurality of influencers registered in the influencer manpower pool by agency of each of the plurality of influencers.

That is, the server 100 first classifies a plurality of influencers by country according to the nationality and activity country of each of the plurality of influencers, and influences the influencers based on the companies to which each of the firstly classified influencers belongs. We can classify the Leuancers in the second order.

In various embodiments, when the server 100 receives a selection of at least one influencer from among a plurality of influencers (a plurality of influencers registered in the influencer manpower pool) from a specific client, the server 100 selects at least one influencer. It is possible to create a client-tailored manpower pool by separately classifying the information on the Luencer.

In various embodiments, the server 100 may set one or more matching conditions based on information about a promotion target input from a client and information on a promotion method for the promotion target, and using a pre-learned artificial intelligence model. Influencers that satisfy one or more matching conditions can be selected from among a plurality of influencers, and a client-tailored manpower pool including information on the selected influencers can be created.

In other words, clients build a manpower pool in advance consisting of influencers they are interested in or influencers suitable for promoting the promotion target they want to promote, and provide information about the influencers they manage. can be managed more conveniently, and matching can be made within their own manpower pool in the future.

In various embodiments, the server 100 may set a level for each of a plurality of influencers, match the set level with information on each of the plurality of influencers, and store the level. Here, the level may mean an index representing the grade of the influencer. For example, the server 100 includes the activity amount of each of the plurality of influencers (e.g., the number of times the AI-based client and influencer matching service is used), the matching success rate (e.g., the AI-based client and influencer matching service), and the server 100. A level within the range of 1 to 10 can be set for each of the plurality of influencers in consideration of the number of times the user has been matched with the client through the matching service).

Later, as each of the plurality of influencers uses an artificial intelligence-based client and influencer matching service or is matched with a client through an artificial intelligence-based client and influencer matching service, the server 100 provides a plurality of influencers. As a reward, a predetermined amount of experience can be provided to each influencer, and the level of the influencer can be raised as the predetermined level of experience is accumulated to achieve a level increase condition.

In various embodiments, the server 100 updates information on a plurality of pre-registered influencers at predetermined intervals, but when the information on a specific influencer is not updated for a certain period of time, the information on the influencer You can delete or deactivate information about influencers within the influencer manpower pool.

In addition, the server 100 may delete or deactivate information about the influencer in the influencer manpower pool when a specific influencer rejects matching offers more than a predetermined number of times.

In step S220, the server 100 may obtain a request for registration in the influencer manpower pool from the first influencer not registered in the influencer manpower pool.

In step S230, the server 100 may provide a self-authentication process in response to the request for registration in the influencer manpower pool obtained through step S220, and based on the result of self-authentication, the first influencer You can decide whether to register in the influencer manpower pool.

Here, the identity authentication process refers to the process of performing a procedure to prove that the person who requested the registration of the influencer manpower pool is the person and that the person is an influencer. For example, the identity verification process includes mobile phone authentication and SNS It may include, but is not limited to, account authentication.

In various embodiments, when the server 100 obtains a request for registration in the influencer manpower pool from the first influencer, the server 100 may provide the first influencer with a personal authentication process, and as a result of performing the identity authentication, Based on this, it may be determined whether or not to register the first influencer in the influencer manpower pool.

In various embodiments, the server 100 registers an influencer manpower pool for a plurality of first influencers belonging to a plurality of first influencers from a representative of an organization (eg, an agency) to which the plurality of first influencers belong. When requested, the authentication method is determined according to the attributes of the organization and representative (e.g. size, awareness, etc.), and a plurality of first influencers are influenced based on the results of performing the authentication procedure according to the determined authentication method. You can decide whether or not to enroll in the unseo manpower pool.

Here, the authentication method includes a first authentication method that performs identity authentication only for the representative, a second authentication method that performs identity authentication for at least one representative influencer among the representative and a plurality of first influencers, and a representative and multiple first influencers. may include, but is not limited to, at least one of the third authentication methods for self-authentication of all of the first influencers.

For example, in the case of a large agency, there is a problem that it can take a considerable amount of time to authenticate one by one because the number of influencers belonging to the agency is large. In consideration of this, the server 100, as described above, if the size of the agency is higher than the standard (eg, a listed company) or the representative of the agency has high awareness, the representative of the agency through the first authentication method or the second authentication method. It is possible to complete the authentication of all influencers belonging to the agency by performing the identity authentication procedure for only the representative, or by performing the identity authentication procedure for several representative influencers including the representative.

On the other hand, in the case of a rather small agency, in order to prevent fraudulent registration of the influencer manpower pool, a third authentication method can be used to have all influencers included in the agency as well as the representative perform the identity verification process. .

In step S240, the server 100 may reject the registration of the influencer manpower pool of the person who requested the registration of the influencer manpower pool when the identity authentication fails through step S230.

In step S250, the server 100 may register in the influencer manpower pool of the person who made the request for registration in the influencer manpower pool when the identity authentication is successful through step S230.

Again, referring to FIG. 3 , in various embodiments, when the server 100 obtains the influencer matching request from the first client through step S110, the influencer matching request is assigned to the influencer manpower pool based on the influencer matching request. Among a plurality of registered influencers, influencers located within a predetermined range (eg, a radius of 300m) based on the current location of the first client can be selected, and the matching conditions included in the influencer matching request (eg, : You can set one or more influencers among the influencers selected based on the target and method of promotion, information on the influencer you want to match and information on the amount you want to pay, etc.) as a matching target.

More specifically, the server 100 can primarily select influencers whose distance from the client is within a predetermined distance among a plurality of influencers registered in the influencer manpower pool, and the pre-learned artificial intelligence model (Example: 1st artificial intelligence model), by analyzing information on primarily selected influencers, publicity predicted when the primarily selected influencer promotes a specific promotion target (client is a promotion target) The effect can be calculated, and among the influencers selected primarily based on the calculated publicity effect, the top N influencers (the number of influencers to be matched) with high publicity effect can be selected secondarily. there is.

Here, the first artificial intelligence model is information about each of a plurality of influencers (e.g. personal information of each influencer, information about SNS account (e.g. SNS type, number of followers, etc.), information about promotion method ( Ex: type of promotional content, posting method, etc.)), information on promotion target (eg type of promotion target, etc.) , but not limited thereto.

In various embodiments, when the server 100 obtains an influencer matching request including a search word from the first client, the information about each of a plurality of influencers registered in the pre-stored influencer manpower pool and the search word are separated. You can select one or more influencers from among multiple influencers through keyword matching.

For example, when the server 100 receives a search word including one or more keywords (eg, age, body type, gender, etc.) related to matching conditions as an influencer matching request from a first client, multiple keyword matching is performed. Among the influencers, you can select an influencer that includes all of the keywords entered by the client.

At this time, if there is no influencer including all of the keywords input from the first client, the server 100 sequentially starts with the influencer having the largest number of keywords input from the first client among the plurality of influencers. You can select N influencers with However, it is not limited thereto.

In addition, when a plurality of influencers are selected through keyword matching, the server 100 selects only influencers whose distance from the client is within a predetermined distance (eg, 300m) among the plurality of influencers, or 1 Influencers with a short distance from the client are sorted in order, and only the top N influencers (the number of influencers you want to match) can be selected according to the sorted order.

In various embodiments, when the server 100 obtains an influencer matching request including video data from the first client, the server 100 analyzes the video data through a pre-learned artificial intelligence model (eg, a second artificial intelligence model). It is possible to extract one or more keywords, and one or more influencers among the plurality of influencers can be extracted through keyword matching between information about each of the plurality of influencers registered in the pre-stored influencer manpower pool and one or more extracted keywords. You can choose your language.

For example, when the server 100 receives a photo image of a specific person as an influencer matching request from a first client, the server 100 analyzes the photo image of the specific person using a second artificial intelligence model to determine the identity of the specific person. One or more keywords (e.g., warm image, cool image, double eyelids, egg-shaped face, exotic, etc.) indicating attributes can be extracted, and through keyword matching, influencers who include all keywords extracted from photo images among multiple influencers You can choose Luancer.

At this time, if there is no influencer including all keywords extracted from the photo image, the server 100 sequentially N You can choose one influencer. However, it is not limited thereto.

In addition, when a plurality of influencers are selected through image search, the server 100 selects only influencers whose distance from the first client is within a predetermined distance (eg, 300m) among the plurality of influencers, or , Influencers with a short distance from the first client are sorted sequentially, and only the top N influencers (the number of influencers to be matched) can be selected according to the sorted order.

Here, the second artificial intelligence model is a model learned according to the supervised learning method using each of a plurality of portrait images labeled with one or more keywords as learning data, and one or more keywords using portrait images as input It may be a model to be extracted, but is not limited thereto.

In various embodiments, when obtaining an influencer matching request including information on a promotion target from the first client, the server 100 may set one or more matching conditions based on the information on the promotion target. Through the learned artificial intelligence model (e.g., the third artificial intelligence model), the profile pictures of each of the plurality of influencers registered in the pre-stored influencer manpower pool are analyzed, indicating the attributes of each of the plurality of influencers. One or more keywords may be extracted, and one or more influencers may be selected from among a plurality of influencers based on the extracted one or more keywords and one or more matching conditions.

More specifically, first, when the server 100 receives input of the type of promotion target as information on the promotion target from the first client, one or more matching conditions are set to select an influencer suitable for promoting the corresponding promotion target. can For example, when the promotional target input from the first client is women's cosmetics, the server 100 may set women, innocence, clean, clear, etc. as one or more matching conditions.

Thereafter, the server 100 analyzes the profile pictures of each of the plurality of influencers registered in the pre-stored influencer manpower pool using the third artificial intelligence model, thereby indicating one or more attributes of each of the plurality of influencers. Keywords can be extracted, and one or more influencers can be selected from among a plurality of influencers by matching one or more extracted keywords with one or more matching conditions set according to the above method.

At this time, if there is no influencer that satisfies all of the one or more matching conditions set according to the above method, the server 100 sequentially selects N influencers from among the plurality of influencers who satisfy the largest number of matching conditions. You can choose an influencer. However, it is not limited thereto.

Here, the third artificial intelligence model may be a model learned according to a supervised learning method using each of a plurality of portrait images labeled with one or more keywords as learning data, similarly to the second artificial intelligence model, but is not limited thereto.

In various embodiments, when the server 100 obtains an influencer matching request for a promotion request in the first country from a first client, the country-level manpower pool corresponding to the first country among a plurality of country-level manpower pools. , and one or more first country influencers may be selected from among a plurality of first country influencers included in the selected country-level manpower pool.

At this time, the server 100, when there is no first country influencer that satisfies one or more matching conditions among a plurality of first country influencers included in the country-level manpower pool corresponding to the first country, You can select one or more second country influencers using the country-level manpower pool corresponding to the neighboring second country, and ask whether the selected one or more second country influencers can be promoted in the first country. Based on the response of the one or more influencers in the second country to the inquiry about whether or not promotion is possible in the first country, it may be determined whether to select one or more selected influencers in the second country.

That is, when the first client wants to produce promotional content for publicity in a specific country, the server 100 selects one or more influencers from the pool of influencers corresponding to the specific country. , If there is no influencer that meets the matching conditions in the influencer manpower pool corresponding to a specific country, cross-country matching is also possible by requesting collaboration from influencers registered in the influencer manpower pool of neighboring countries as needed. make it possible

In various embodiments, the server 100 selects N influencers from among a plurality of influencers based on the influencer matching request obtained from the first client, but sets the matching conditions included in the influencer matching request. If the number of satisfied influencers is M (where M is greater than N), N influencers can be sequentially selected from influencers with higher levels based on the level of each of the M influencers. .

In various embodiments, the server 100 may generate and post recruitment notification content for selecting one or more influencers based on the influencer matching request obtained from the client, and guide the posted recruitment notification content. It can be provided to a plurality of influencers in the form of data (e.g. Fig. 6), and support requests can be obtained from influencers through map data and provided to clients, and influencers who have requested support from clients You can choose any one of the influencers.

At this time, when the recruitment announcement content is posted, the server 100 bases on one or more matching conditions (eg, category setting, etc.) included in the matching request obtained from the client, and plural numbers registered in the pre-stored influencer manpower pool. It is possible to select at least one influencer that most satisfies one or more matching conditions among the influencers of , recommend the selected at least one influencer to a client, or provide recruitment notification content suitable for the selected at least one influencer. You can provide a notification to inform you that it has been posted.

In various embodiments, the server 100 may include a plurality of influencers (influencers located within a predetermined distance from the first client) registered in the influencer manpower pool based on the influencer request obtained from the first client. ), but if the first client-tailored manpower pool is built in advance, the first client-tailored manpower pool is considered first and the influencer satisfies the matching conditions included in the influencer matching request. can be selected, and if there is no influencer that satisfies the matching condition within the first client-customized manpower pool, an influencer that satisfies the matching condition can be selected from the entire influencer manpower pool. That is, when the server 100 obtains an influencer matching request from the first client when a manpower pool tailored to the first client is established, the server 100 may select the influencers included in the manpower pool tailored to the first client with the highest priority. .

In step S130, the server 100 may match the first client with one or more influencers selected as matching targets through step S120. For example, the server 100 may provide information on an influencer as a matching target to a first client, and when receiving a matching request for the corresponding influencer from the first client, the influencer's Matching suggestion information (eg, location information, promotion target information, cost information, etc.) of the first client may be provided to the terminal. Thereafter, when the server 100 receives a matching acceptance input from the influencer in response to providing the matching suggestion information to the influencer, the server 100 may complete the matching between the influencer and the first client.

In various embodiments, the server 100 may mediate a contract between the influencer whose match is finally determined and the first client.

In various embodiments, the server 100 may charge a predetermined fee in response to matching the influencer and the first client. At this time, the size of the fee may be determined according to the level of the matched influencer. For example, if the influencer level is 1, the server 100 may charge 10% of the down payment as a fee, and if the influencer level is 5, it may charge a 5% fee. If the level of the Luencer is 10, you may not charge a fee.

In various embodiments, the server 100 may receive from the first client a cost for matching a specific influencer as a deposit in advance, and as the matching between the specific influencer and the first client is completed, the first client Pay the expenses paid in advance from ) in response to posting certain influencers. For example, the server 100 may pay a fee to a specific influencer when authentication of promotional content posted by a specific influencer (eg, URL authentication of a promotional content posting, etc.) is completed.

In various embodiments, the server 100 monitors the status of promotional content posted from a specific influencer at predetermined intervals for a predetermined period of time, but discloses the status of the promotional content posted from the specific influencer within the predetermined period. If the status is changed to private or deleted, a penalty (e.g., influencer level down, service use restriction for a certain period of time, or service use limit permanently) can be imposed on a specific influencer.

Here, as shown in FIG. 3, the server 100 may select an influencer as a matching target according to obtaining an influencer matching request from a specific client and arrange a matching with the client, but is not limited thereto, If a client-tailored manpower pool is built in advance, matching with the influencer to be matched can be arranged based on the client-tailored manpower pool built in advance regardless of the influencer matching request.

More specifically, the server 100 builds a client-customized manpower pool that includes information on influencers who satisfy the information on the promotion target and the method of promoting the promotion target as input from the client. , and detects that at least one influencer among the influencers registered in the client-tailored manpower pool enters a predetermined range centered on the client's current location to promote the target of the client's promotion. Information on the influencer may be provided to the client along with a notification indicating that the influencer has been detected.

In addition, the server 100, when at least one influencer among the influencers registered in the client-tailored manpower pool enters within a predetermined range centered on the client's current location, at least one influencer and the client can be matched automatically. However, it is not limited thereto.

5 is a flow chart of a method for providing an artificial intelligence-based client and influencer matching service in terms of an influencer, in various embodiments.

Referring to FIG. 5 , in step S310, the server 100 may obtain a client matching request from the first influencer. For example, the server 100 may provide an artificial intelligence-based client and influencer matching service web or application to the influencer terminal of the first influencer, and the first influencer may use the web or application As it is executed, the AI-based client and influencer matching service UI can be output, and influencer matching requests can be received through the AI-based client and influencer matching service UI.

In step S120, the server 100 may select one or more clients from among a plurality of clients located within a preset range based on the current location of the first influencer, based on the client matching request obtained through step S110. . Here, the preset range may be a preset value (eg, 300 m), and may be freely changed within the predetermined range according to the request of the first influencer.

At this time, the predetermined range may be set differently according to the level of each influencer. For example, the server 100 sets the client selection range (preset range) for all influencers to 300m, but allows the client selection range to be adjusted in the range of 250m to 350m for level 1 influencers, , In the case of a level 5 influencer, the client selection range can be adjusted within a 5km range, and in the case of the highest level, level 10 influencer, the client selection range can be adjusted without any restrictions.

In various embodiments, the server 100 performs keyword matching between information about the first influencer and a matching condition input from each of a plurality of clients located within a preset range based on the current location of the first influencer. , it is possible to select only one or more clients that can satisfy the matching condition among a plurality of clients. However, it is not limited thereto, and the range of selected clients may be determined according to the level of the first influencer. For example, if the first influencer is less than level 5, the server 100 may select only one or more clients that can satisfy the matching condition among a plurality of clients, and if the first influencer is level 5 or higher, regardless of whether the matching condition is satisfied or not, the server 100 may select only one or more clients that can satisfy the matching condition. All clients can be selected.

In step S330, the server 100 may match one or more clients selected in step S320 with the first influencer.

More specifically, first, the server 100 transmits map data (eg, FIG. 6) including information (eg, matching conditions (number of people), cost, etc.) of selected clients through step S320 to the first influencer. can provide

Then, when the first influencer selects a specific client from among the clients displayed on the map data and requests support, the server 100 sends information about the first influencer to the specific client selected from the first influencer. can provide.

Thereafter, the server 100 may receive matching approval from the specific client in response to providing information on the first influencer to the specific client, and as matching approval is obtained, the specific client and the first influencer can be matched.

Meanwhile, when a matching rejection is input from a specific client, the server 100 may provide a notification informing the first influencer that matching with the specific client has not been completed. At this time, the server 100 receives information about the reason for refusal of matching from a specific client and provides it to the first influencer, so that the first influencer can supplement the reason for refusal to match.

The aforementioned artificial intelligence-based client and influencer matching service providing method has been described with reference to the flow chart shown in the drawing. For a brief description, the AI-based client and influencer matching service providing method has been illustrated and described as a series of blocks, but the present invention is not limited to the order of the blocks, and some blocks are shown and operated in this specification. may be performed in a different order or concurrently. In addition, new blocks not described in the present specification and drawings may be added, or some blocks may be deleted or changed.

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

100: Server providing client and influencer matching service
200: user terminal
300: external server
400: network

Claims (14)

In a method performed by a computing device,
Obtaining a matching request between a client who wants to promote a specific promotion target and an influencer;
setting a matching target based on the obtained matching request;
performing matching between the set matching targets;
setting one or more matching conditions based on information on a promotion target input from a first client and information on a promotion method for the promotion target; and
Select influencers that satisfy one or more set matching conditions among a plurality of influencers registered in the pre-stored influencer manpower pool using a pre-learned artificial intelligence model, and obtain information about the selected influencers. Including the step of generating a first client-tailored manpower pool comprising a,
The step of performing the matching is,
When at least one influencer among the influencers registered in the first client customized manpower pool enters a predetermined range centered on the current location of the first client, the at least one influencer providing information to the first client or automatically matching the at least one influencer with the first client;
The cost for influencer matching is paid in advance from the first client, and as the matching between the first client and a specific influencer is completed, the cost received in advance is paid to the specific influencer, Paying the pre-paid fee to the specific influencer in response to a specific influencer posting promotional content, wherein the promotional content is content for promoting a promotion target by the first client; and
Monitor the status of the promotional content posted from the specific influencer at predetermined intervals for a predetermined period of time, and the status of the promotional content posted from the specific influencer within the predetermined period is switched from public to private status, or In case of deletion, the specific influencer is given a penalty - the penalty includes a level down of the specific influencer, a predetermined period or permanent restriction on use of AI-based clients and influencer matching services contains steps,
Further comprising generating an influencer manpower pool including information on each of a plurality of influencers,
The step of creating the influencer manpower pool,
When a representative of an organization to which a plurality of first influencers belongs is requested to register an influencer manpower pool for the plurality of first influencers included in the organization, attributes of the organization and the representative - the organization and the attributes of the representative include the size of the organization and the awareness of the representative. An authentication method is determined based on the plurality of first people based on a result of performing an authentication procedure according to the determined authentication method. Register the influencer in the created influencer manpower pool,
The authentication method includes a first authentication method for performing identity authentication only for the representative, a second authentication method for performing identity authentication for at least one representative influencer among the representative and the plurality of first influencers, and the above authentication method. Including at least one of the third authentication methods for performing identity authentication for the representative and all of the plurality of first influencers,
The step of setting the matching target,
extracting one or more keywords indicating attributes of the specific person by analyzing the input photo image when receiving a photo image of a specific person from the first client; and
By analyzing the profile pictures of each of the plurality of influencers registered in the pre-stored influencer manpower pool, the extracted keywords are matched with one or more keywords indicating the attributes of the extracted specific person, and among the plurality of influencers Including setting one or more influencers as matching targets,
A method for providing AI-based client and influencer matching services. According to claim 1,
The step of setting the matching target,
When acquiring an influencer matching request from the first client, based on the obtained influencer matching request, the current location of the first client among a plurality of influencers registered in a pre-stored influencer manpower pool is referenced. Selecting influencers located within a predetermined range as; and
Based on the matching conditions included in the acquired influencer matching request - the matching conditions include information on the promotion target and promotion method, information on the influencer to be matched, and information on the amount to be paid - Including the step of setting one or more influencers among the selected influencers as a matching target,
A method for providing AI-based client and influencer matching services. delete According to claim 1,
The step of selecting one or more influencers,
When obtaining an influencer matching request from the first client, select one or more influencers among influencers located within a predetermined range based on the current location of the first client, and Including the step of first selecting the influencer included in the client-tailored manpower pool,
A method for providing AI-based client and influencer matching services. delete delete delete According to claim 1,
The step of setting the matching target,
When obtaining a client matching request from the first influencer, select one or more clients among a plurality of clients located within a preset range based on the current location of the first influencer based on the obtained client matching request. doing; and
Further comprising providing map data including information on the selected one or more clients to the first influencer,
A method for providing AI-based client and influencer matching services. According to claim 1,
Further comprising generating an influencer manpower pool including information on each of a plurality of influencers,
The step of creating the influencer manpower pool,
When receiving a request for registration in the influencer manpower pool from the first influencer, providing the first influencer with a self-authentication process - the identity authentication process includes at least one of mobile phone authentication and SNS account authentication - ; and
Based on the result of the first influencer performing identity authentication according to the identity authentication process provided above, registering the first influencer in the created influencer manpower pool,
A method for providing AI-based client and influencer matching services. delete According to claim 1,
Multiple country-level manpower pools that classify each of the plurality of influencers by country based on the nationality and active country of each of the plurality of influencers, and each includes information on the plurality of influencers classified by country. Further comprising the step of generating,
The step of setting the matching target,
When obtaining an influencer matching request for promotion of the specific promotion target in a first country from a first client, selecting a country-level manpower pool corresponding to the first country from among the plurality of country-level manpower pools, Selecting one or more first country influencers from among a plurality of first country influencers included in the selected country-level manpower pool,
A method for providing AI-based client and influencer matching services. According to claim 11,
The step of selecting one or more first nationality influencers,
When there is no first-country influencer that satisfies one or more matching conditions included in the obtained influencer matching request among the plurality of first-country influencers included in the country-level manpower pool corresponding to the first country , Using the country-level manpower pool corresponding to the second country adjacent to the first country, one or more second country influencers that satisfy the one or more matching conditions are selected, and the selected one or more second country influencers are selected. inquiring whether or not to participate in publicity of the specific publicity target in the first country; and
Based on the response of the selected one or more second country influencers to the query on whether or not to participate in the promotion of the specific promotion target in the first country, whether or not the selected one or more second country influencers are selected including determining
A method for providing AI-based client and influencer matching services. processor;
network interface;
Memory; and
A computer program loaded into the memory and executed by the processor,
The computer program,
An instruction for obtaining a matching request between a client and an influencer who wants to promote a specific promotion target;
an instruction for setting a matching target based on the obtained matching request;
an instruction for performing matching between the set matching targets;
an instruction for setting one or more matching conditions based on information about a promotion target input from a first client and information on a promotion method for the promotion target; and
Select influencers that satisfy one or more set matching conditions among a plurality of influencers registered in the pre-stored influencer manpower pool using a pre-learned artificial intelligence model, and obtain information about the selected influencers. Including instructions for generating a first client-customized manpower pool that includes,
The instruction for performing the matching is,
When at least one influencer among the influencers registered in the first client customized manpower pool enters a predetermined range centered on the current location of the first client, the at least one influencer instructions for providing information to the first client or automatically matching the at least one influencer with the first client;
The cost for influencer matching is paid in advance from the first client, and as the matching between the first client and a specific influencer is completed, the cost received in advance is paid to the specific influencer, an instruction for paying the pre-paid fee to the specific influencer in response to a specific influencer posting promotional content, wherein the promotional content is content for promoting a promotion target by the first client; and
Monitor the status of the promotional content posted from the specific influencer at predetermined intervals for a predetermined period of time, and the status of the promotional content posted from the specific influencer within the predetermined period is switched from public to private status, or In case of deletion, the specific influencer is given a penalty - the penalty includes a level down of the specific influencer, a predetermined period or permanent restriction on use of AI-based clients and influencer matching services contains instructions;
Further comprising instructions for generating an influencer manpower pool including information on each of the plurality of influencers,
The instructions for creating the influencer manpower pool are:
When a representative of an organization to which a plurality of first influencers belongs is requested to register an influencer manpower pool for the plurality of first influencers included in the organization, attributes of the organization and the representative - the organization and the attributes of the representative include the size of the organization and the awareness of the representative. An authentication method is determined based on the plurality of first people based on a result of performing an authentication procedure according to the determined authentication method. Register the influencer in the created influencer manpower pool,
The authentication method includes a first authentication method for performing identity authentication only for the representative, a second authentication method for performing identity authentication for at least one representative influencer among the representative and the plurality of first influencers, and the above authentication method. Including an instruction comprising at least one of a third authentication method for performing identity authentication for the representative and all of the plurality of first influencers,
The instruction for setting the matching target,
an instruction for extracting one or more keywords indicating attributes of the specific person by analyzing the input photo image when receiving a photo image of a specific person from the first client; and
By analyzing the profile pictures of each of the plurality of influencers registered in the pre-stored influencer manpower pool, the extracted keywords are matched with one or more keywords indicating the attributes of the extracted specific person, and among the plurality of influencers Including instructions for setting one or more influencers as matching targets,
AI-based client and influencer matching service provider server. Combined with a computing device,
Obtaining a matching request between a client who wants to promote a specific promotion target and an influencer;
setting a matching target based on the obtained matching request;
performing matching between the set matching targets;
setting one or more matching conditions based on information on a promotion target input from a first client and information on a promotion method for the promotion target; and
Select influencers that satisfy one or more set matching conditions among a plurality of influencers registered in the pre-stored influencer manpower pool using a pre-learned artificial intelligence model, and obtain information about the selected influencers. Including the step of generating a first client-tailored manpower pool comprising a,
The step of performing the matching is,
When at least one influencer among the influencers registered in the first client customized manpower pool enters a predetermined range centered on the current location of the first client, the at least one influencer providing information to the first client or automatically matching the at least one influencer with the first client;
The cost for influencer matching is paid in advance from the first client, and as the matching between the first client and a specific influencer is completed, the cost received in advance is paid to the specific influencer, Paying the pre-paid fee to the specific influencer in response to a specific influencer posting promotional content, wherein the promotional content is content for promoting a promotion target by the first client; and
Monitor the status of the promotional content posted from the specific influencer at predetermined intervals for a predetermined period of time, and the status of the promotional content posted from the specific influencer within the predetermined period is switched from public to private status, or In case of deletion, the specific influencer is given a penalty - the penalty includes a level down of the specific influencer, a predetermined period or permanent restriction on use of AI-based clients and influencer matching services contains steps,
Further comprising generating an influencer manpower pool including information on each of a plurality of influencers,
The step of creating the influencer manpower pool,
When a representative of an organization to which a plurality of first influencers belongs is requested to register an influencer manpower pool for the plurality of first influencers included in the organization, attributes of the organization and the representative - the organization and the attributes of the representative include the size of the organization and the awareness of the representative. An authentication method is determined based on the plurality of first people based on a result of performing an authentication procedure according to the determined authentication method. Register the influencer in the created influencer manpower pool,
The authentication method includes a first authentication method for performing identity authentication only for the representative, a second authentication method for performing identity authentication for at least one representative influencer among the representative and the plurality of first influencers, and the above authentication method. Including at least one of the third authentication methods for performing identity authentication for the representative and all of the plurality of first influencers,
The step of setting the matching target,
extracting one or more keywords indicating attributes of the specific person by analyzing the input photo image when receiving a photo image of a specific person from the first client; and
By analyzing the profile pictures of each of the plurality of influencers registered in the pre-stored influencer manpower pool, the extracted keywords are matched with one or more keywords indicating the attributes of the extracted specific person, and among the plurality of influencers Stored in a computer-readable recording medium to execute an artificial intelligence-based client and influencer matching service providing method that includes setting one or more influencers as matching targets,
A computer program recorded on a computer-readable recording medium.

Images