KR20230002300U - Cloud Server and Method for providing customized showhost reflecting the user's preference - Google Patents

Abstract

Currently, the market is developing a show host marketing strategy that maximizes marketing effectiveness by discovering show hosts on live commerce and promoting products through them.
However, since this is based only on the input information of show hosts with the same tendencies, it has the problem of not being able to objectively identify the show hosts' tendencies and not being able to effectively match advertisers and freelancers with similar tendencies.
To solve this problem, the purpose is to provide a matching management device and method between advertisers and show hosts that can match show hosts suitable for advertisers' marketing goals and efficiently manage the status of products in which the show host participates and the effects after participation. Do it as We aim to provide a method and server for matching show hosts and advertisers using deep learning, which uses deep learning to determine the show host's tendencies and matches show hosts suitable for advertisers.

Description

Live commerce show host search service providing method, device, and cloud server {Cloud Server and Method for providing customized showhost reflecting the user's preference}

The present invention relates to a method of matching advertisers and show hosts for online marketing using deep learning, and more specifically, to a method of providing solutions through viral marketing and consumer analysis for advertising targets.

The show host management department extracts the optimal show host for the advertiser by calculating the show host score for each show host according to the show host information and show host search conditions, and sends an advertisement proposal to the selected show host to confirm the advertisement production process. In this case, the present invention relates to a matching management device and method between an advertiser and a show host that includes an advertisement production management unit that manages advertisements produced by the selected show host.

As Internet technology develops, technology for providing content in the form of text, images, and videos through the Internet is rapidly developing.

Platforms such as video platforms, Internet broadcasting platforms, portal site platforms, etc. that are provided through the Internet and allow users to view and enjoy a variety of content are increasing.

In line with this trend, show hosts active on various platforms have begun to appear, and many platforms are starting a new form of home shopping by combining one-person streaming functions and show hosts.

A show host, also called a shopping host, is a person who introduces and sells products on home shopping broadcasts. To be more specific, a show host refers to a presenter who introduces and directly demonstrates products to consumers in a product sales program through television or video media.

With the recent development of the Internet, the influence of show hosts on home shopping is growing. Meanwhile, there is also a movement to attempt marketing activities using show hosts. In other words, by discovering show hosts on live commerce and promoting products through them,

Show host marketing strategies that maximize marketing effectiveness are being developed.

However, since this is based only on the input information of show hosts with the same tendencies, it has the problem of not being able to objectively identify the show hosts' tendencies and not being able to effectively match advertisers and freelancers with similar tendencies.

As Internet technology develops, technology that provides content in the form of text, images, and videos through the Internet is rapidly developing.

Platforms such as video platforms, Internet broadcasting platforms, portal site platforms, etc. that are provided through the Internet and allow users to view and enjoy a variety of content are increasing.

In line with this trend, show hosts active on various platforms have begun to appear, and many platforms are starting a new form of home shopping by combining one-person streaming functions and show hosts.

A show host, also called a shopping host, is a person who introduces and sells products on home shopping broadcasts.

To be more specific, a show host refers to a presenter who introduces and directly demonstrates products to consumers in a product sales program through television or video media.

With the recent development of the Internet, the influence of show hosts on home shopping is increasing.

Meanwhile, there is also a movement to attempt marketing activities using show hosts like this. In other words, by discovering show hosts on live commerce and promoting products through them,

Show host marketing strategies that maximize marketing effectiveness are being developed.

However, since this is based only on the input information of show hosts with the same tendencies, it has the problem of not being able to objectively identify the show hosts' tendencies and not being able to effectively match advertisers and freelancers with similar tendencies.

In the matching server between a show host and an advertiser using deep learning according to an embodiment of the present invention, a storage unit 240 (put storage part) that stores analysis data, which is data that is the basis for creating an analysis model;

a model formation part 221 (formation part) that forms a show host tendency judgment model through deep learning based on the analysis data;

In order to analyze the tendency of a target show host, which is a show host whose tendency is to be analyzed, a target tendency information receiving part 211 (receiving part) that receives target tendency data, which is data related to media produced by the target show host;

a propensity calculation unit 222 (calculate part) that calculates the target show host propensity by inputting the target propensity data into the show host propensity determination model; It may include a distributed storage server that distributes and stores the calculated propensity, and a target show host selection unit 114 (selection part) that selects the target show host with the same propensity as the advertiser's product.

According to the method and server for matching a show host and an advertiser using deep learning according to the present invention, the tendency of the show host can be accurately determined, and based on this, the show host desired by the advertiser can be matched.

In addition, by providing a matching service between the show host and the advertiser (e.g. messaging service, etc.) so that advertisers can easily match with the show host, a separate operation (e.g. matching service) is required to contact a show host suitable for promoting a specific product. There is an advantage that there is no need to use a separate service to run .

In addition, according to the above-described means for solving the problem of the present invention, when marketing activities are carried out through show hosts who have influence on social media, predictions are made regarding the results.

Through this, it is possible to allocate efficient show hosts depending on the type of marketing, predict the performance of the marketing campaign based on the target performance, and calculate budget operation.

1 is a relationship diagram between a show host matching server, an advertiser, and a show host according to an embodiment of the present invention.
Figure 2 is a block diagram of the configuration of a show host according to an embodiment of the present invention.
Figure 3 is a flowchart illustrating a method of matching show hosts using a show host matching server according to an embodiment of the present invention.
FIG. 4 is a diagram illustrating a process in which a propensity calculation unit of a show host matching server calculates a propensity according to an embodiment of the present invention.
Figure 5 is a diagram showing information about a show host according to an embodiment of the present invention.
Figure 6 is a diagram illustrating a show host and matching request according to an embodiment of the present invention.

Hereinafter, specific embodiments of the present invention will be described in detail with reference to the drawings. However, the idea of the present invention is not limited to the presented embodiments,

A person skilled in the art who understands the spirit of the present invention can easily suggest other regressive inventions or other embodiments included within the scope of the present invention by adding, changing, or deleting other components within the scope of the same spirit. However, this will also be said to be included within the scope of the present invention.

In this specification, if it is determined that a detailed description of the configuration or function of the server related to the present invention may obscure the gist of the present invention, the detailed description thereof will be omitted.

Figure 1 is a diagram illustrating the relationship between a show host matching server, an advertiser, and a show host according to an embodiment of the present invention.

Referring to FIG. 1, the show host matching server according to an embodiment of the present invention may be communicatively connected to the advertiser's terminal to transmit and receive predetermined data.

Additionally, the show host matching server may be communicatively connected to the show host terminal to transmit and receive predetermined data.

Here, the advertiser terminal may include a mobile terminal including a smartphone and a fixed terminal including a desktop computer, a smart TV, and a certain server, and the present invention is not limited thereto.

Communication includes Internet, LAN, Ethernet, WIFI (Wireless Fiedlity), TCP/IP, IPX, Firewire, IEEE1394, iLink, CDMA, TDMA, BT (BlueTooth), and HDMI-CEC (High Definition Multimedia Interface). and/or Wireless HDMI-CEC, RF (Radio Frequency), etc. may be included, but the present invention is not limited thereto, and the show host search service providing device may provide a control signal (e.g., a control signal for providing a show host search service). : Among the information and performance analysis information on multiple show hosts corresponding to the search term entered by the user, only information on the show host and content corresponding to the transmission request is extracted (crawled) and provided to the show host search service provider. can do.

Figure 2 is a block diagram of the configuration of a show host according to an embodiment of the present invention.

Referring to FIG. 2, the show host matching server according to an embodiment of the present invention includes a calculation unit 220 that calculates predetermined information and a reception unit 230 that receives predetermined information, and predetermined data. It may be provided with a transmission unit that transmits the information to another device and a storage unit 240 that stores predetermined information.

The transmitting unit 210, the receiving unit 230, the calculating unit 220, and the storage unit 240 can transmit or receive certain information to each other and can be connected wired or wirelessly.

The calculation unit 220 may include a model forming unit 221, a tendency calculation unit 222, a target show host selection unit 114, a product classification unit 224, and a tendency calculation unit 225, which will be described later. .

The receiving unit 230 may include a target tendency information receiving unit 211, a product information receiving unit 212, a sample data receiving unit 213, and a link receiving unit 214, which will be described later.

The transmitting unit 210 may include a list transmitting unit 210 and a personal information transmitting unit 232, which will be described later.

Hereinafter, a method of matching a show host using the show host matching server will be described in detail.

Figure 3 is a flowchart illustrating a method of matching show hosts using a show host matching server according to an embodiment of the present invention.

Referring to FIG. 3, in the show host matching method, target tendency data, which is data related to media produced by the target show host, is transmitted to the show host matching server to analyze the tendency of the target show host. receiving target propensity information, a link upload 320 step in which the Internet address where the media produced by the target show host is uploaded is uploaded to the show host matching server, and the target propensity data is used to model the show host propensity determination model. A propensity calculation step, which is a step of calculating the propensity of the target show host by inputting into A target show host selection step, which is a step of selecting the target show host with a tendency, a list sending step, which is a step of transmitting information related to the information of the selected show host, which is the selected target show host, to the advertiser terminal, among the selected show hosts. A sample data generation step in which sample data, which is information related to the fact that the advertiser sends a sample of the advertiser's product to a sample show host, which is a show host that the advertiser wishes to provide the sample, is generated in the advertiser's terminal, the sample data is It may include a sample data receiving step, which is a step of receiving sample data from a show host matching server, and a re-propensity calculation step, which is a step of recalculating the target show host's propensity when a predetermined condition is satisfied based on the sample data.

In addition, the show host matching method may further include a personal information sending step of transmitting personal data, which is data related to personal information, which is information related to personal information of the sample show host, to the advertiser terminal when the sample information is received. You can.

In the show host matching server that matches show hosts, who are active through social network services (SNS), and advertisers, the show host matching server is the analysis data that is the basis for creating an analysis model - the analysis data is the analysis show A storage unit 240 that stores analysis media data, which is data related to the media produced by the host, and analysis tendency data, which is data related to the tendency of the analysis show host, through deep learning based on the analysis data. It may include a model forming unit 221 that forms a show host tendency judgment model.

Media may include any video, photo, and/or audio produced by the show host.

A large amount of the analysis information may be stored in the storage unit 240.

The model forming unit 221 may generate a show host tendency determination model capable of determining the show host tendency using deep learning based on the analysis information stored in the storage unit 240.

Here, deep learning may use a back-propagation algorithm, which is an algorithm that updates the weights of the neural network using labeled information of the output layer, but is not limited to this.

FIG. 4 is a diagram illustrating a process by which the tendency calculation unit 222 of the show host matching server calculates a tendency according to an embodiment of the present invention.

The show host matching server according to an embodiment of the present invention receives target tendency data, which is information related to media produced by the target show host, in order to analyze the tendency of the target show host, which is a show host whose tendency is to be analyzed. It may further include a propensity information receiving unit 211 and a propensity calculation unit 222 that inputs the target propensity data into the show host propensity determination model to calculate the target show host propensity.

Additionally, the show host matching server may further include a link receiving unit 214 that receives the Internet address where the media produced by the target show host is uploaded.

Referring to FIG. 4, in the step of receiving target tendency information, the target tendency information may be transmitted from the show host terminal to the target tendency information receiving unit 211.

The propensity calculation unit 222 may input the target propensity data received from the target propensity information receiver 211 into the show host propensity determination model.

Based on this, the tendency calculation unit 222 can calculate the tendency of the target show host.

The propensity calculation unit 222 may classify the propensity of the target show host into target groups based on the second age propensity, the second gender propensity, and the second product product propensity.

Referring to FIG. 5, in various embodiments, it is a diagram showing information about a show host stored in a show host search service providing device.

Referring to this drawing, advertisers can check the personal information of the show host registered in the present invention and the live commerce platform information, field, pay, and job type in which the show host is active.

Referring to FIG. 6, the computer device may obtain a request for matching one of the show hosts among the plurality of show hosts included in the show host labeled list from the user terminal.

The present description sets forth the best mode of the invention and provides examples to illustrate the invention and to enable any person skilled in the art to make or use the invention. The specification prepared in this way does not limit the present invention to the specific terms presented.

Accordingly, although the present invention has been described in detail with reference to the above-described examples, those skilled in the art may make modifications, changes, and variations to the examples without departing from the scope of the present invention.

In short, in order to achieve the intended effect of the present invention, it is not necessary to separately include all functional blocks shown in the drawings or to follow all the orders shown in the drawings, and even if not, the technical aspects of the present invention described in the claims may be used. It states that it may fall within the scope.

Claims (6)

Matching server between show hosts and advertisers using deep learning;

A storage unit 240 that stores analysis data, which is the basis for creating an analysis model, and a model formation part 221 that forms a show host tendency judgment model through deep learning based on the analysis data, A target tendency information receiving unit 211 (receiving part) that receives data related to media produced by the target show host in order to analyze the tendency of the target show host, which is the show host whose tendency is to be analyzed.

A propensity calculation unit 222 (calculate part) that calculates the target show host's propensity by inputting the target propensity information into the show host propensity judgment model. A distributed storage server that distributes and stores the calculated propensity and the same as the propensity of the advertiser's product. A target show host selection unit 114 (selection part) that selects the target show host with a tendency.

Matching management device and method of show host and advertiser using deep learning, characterized by including the above data
In clause 1,

A product data receiver 230 that receives product information, which is information related to the advertiser's product category, and based on the product data, a first age propensity associated with the age of the product as a sales target for the product, and a first age propensity associated with the product's sales target. It further includes a product classification part 224 (classification part) that classifies based on the first gender propensity related to the gender and the first product group propensity related to the classification list of the product,

The propensity calculation unit 222 (calculate part) includes a second age propensity associated with the age predicted to be the main viewer of the target show host's medium, and a second gender associated with the gender predicted to be the main viewer of the target show host's medium. Calculate the tendency of the target show host based on the tendency and the tendency of the second product group related to the product group predicted to be handled by the target show host, and the target show host selection unit 114,

Compare the first age propensity and the second age propensity, compare and analyze the first gender propensity and the second gender propensity, compare the first product group propensity and the second product product propensity, and select a target show host. A matching management device between show hosts and advertisers using deep learning, which is characterized by selection.
According to paragraph 2,
A list transmitter 231 (out-going part) that transmits data related to the selected show host data, which is the target show host selected in the target show host selection unit 114, to the advertiser terminal, and

A sample data receiving part 213 (receiving part) that receives sample data, which is data related to the advertiser sending a sample of the advertiser's product to a sample show host that is a show host that the advertiser wishes to provide samples from among the selected show hosts, and

When the sample data is received from the sample data receiving part 213 (receiving part), a personal information transmitting part ( 232) A matching server between a show host and an advertiser using deep learning, which further includes (out-going part).
According to paragraph 3,

If the link receiving part 214 (receiving part) receives the Internet address where the work participated by the target show host is uploaded, and the conditions pre-selected based on the example information above are matched,
It further includes a propensity calculation unit 225 that calculates at least one of the second age propensity, the second gender propensity, and the second product group propensity based on comments left on the work in which the sample show host participated. do,

The list transmitter 210 (out-going part) is,

When the propensity of the example show host calculated by the re-propensity calculation unit 225 and the propensity of the example show host calculated by the propensity calculation unit 222 are the same, information related to the example show host determined to be the same. A matching server between a show host and an advertiser using deep learning, characterized in that it does not transmit to the advertiser terminal.
According to clause 4,

The predetermined conditions are,
A matching server 100 between a show host and an advertiser using deep learning, wherein the example information receiving unit 230 (receiving part) receives the example information related to the example show host a certain number of times or more.
In the case of the portfolio 510 in FIG. 5, the live commerce broadcast conducted by the show host is scraped using the crawling function in the live commerce channel, and the list is called and displayed to the user.

In the case of the SNS channel 520, a list of SNS channels 520 linked to the live commerce channel is registered on the server, and the user calls the SNS channel 520 registered on the server and shows it to the user.

In the case of the performance indicator 530, the performance indicators 530 of the show hosts registered in this development can be registered on the server and displayed upon user request.
The above-mentioned performance indicator 530 can be registered as an indicator of the performance of show hosts before this development.

In the case of matching request (540), information of advertisers and show hosts is registered in this development, and then users can be matched based on deep learning. Matching can be performed through the sample data receiving part 213 (receiving part), which receives sample data that is the matching request 540 data.

In the case of calculating the expected quotation (550), the pay of the show hosts is registered on the server and displayed to the user based on the pay calculated in advance by the show hosts in this development.