KR102453535B1 - Method and apparatus for providing an online shopping platform - Google Patents

Abstract

According to various embodiments, an online shopping platform providing server which promotes and sells products of a seller through an influencer may comprise: a big data management unit which categorizes products of a seller according to the characteristics of the products and collects activity information of a plurality of influencers; a candidate influencer determination unit which determines first candidate influencers to be matched with the seller based on the product characteristics and the activity information; a final influencer determination unit which determines final influencers based on a predefined growth index and a good index among the determined first candidate influencers; a schedule management unit which provides group purchase schedule information on the products of each of the determined final influencers to a user terminal; and a feedback reflection unit which calculates the sales contribution for the products sold by each of the determined final influencers and provides a sales contribution table generated according to the calculated sales contribution to a seller terminal of the seller. According to the present invention, the online shopping platform providing server can recommend the best influencer who can sell and promote products well according to the characteristics of the products.

Description

METHOD AND APPARATUS FOR PROVIDING AN ONLINE SHOPPING PLATFORM

The present invention relates to a method and apparatus for providing an online shopping platform, and more particularly, to match sellers and influencers based on big data, and to allow the matched influencers to be recommended to users among the seller's products. It relates to a method and apparatus for promoting or selling customized products, collecting schedules of influencers, and providing the collected schedules to users.

With the opening of the Internet era, technology for forming and providing posts through text information, image information, video information, and multimedia information is rapidly developing. Recently, video platforms such as Youtube, Internet broadcasting platforms such as Afreeca TV, Twitch TV, TV Daumpot, etc., portal site platforms such as Naver, Google, Daum, and Yahoo, social media platforms such as facebook, Instagram, twitter, cacao story, etc. The number of users who check and use various information through blog platforms such as Daum Blog, Naver Blog, Tistory Blog, and Blog Spot is increasing explosively.

As the media has diversified as above, the marketing channels have also diversified. Therefore, in the past, promotion of only a few mass media was effective, but now there are various promotion channels such as search channels, blogs, social media channels such as Facebook and Instagram. With the explosive increase in the number of users, influencers began to appear among users using various platforms. Influencers refer to users with high influence within the platform. Examples of influencers are users who have a large number of followers on social media platforms, users who run blogs with many visitors, and YouTube users who run channels with a large number of subscribers. etc.

Influencers produce, produce and post their own posts, and the posts are exposed to a large number of users on the platform. With the increase in exposure frequency, other users' interest in things related to influencers, such as products used by influencers, places to enjoy, hobbies, and special skills, is increasing. Influencers can use this influence to obtain various benefits. For example, a product seller may request an advertisement for a product from influencers, and the influencer may obtain financial or material benefits in return for product sales and advertisement request. That is, the influencer is used as a single distribution channel or advertisement channel for sellers.

However, in the case of the existing advertisement method through an influencer, there is a problem in that a lot of time and money is consumed for the seller because the seller has to contact the influencer individually to request a product promotion or advertisement. In addition, it is difficult for sellers to obtain information about influencers who will promote products or request advertisements, and it is difficult to predict the advertisement effects that can be obtained when requesting advertisements from the influencers. In addition, in the case of an influencer with a large influence, it has an advantage over the seller and enters into an exclusive contract. There may be risks to product B.

Also, in many cases, broadcast information on product sales broadcasts is displayed in chronological order through media such as home shopping malls and internet online malls, but social media platforms still collect information according to the schedules of the influencers to users. Therefore, it may be inconvenient because it is not provided in an easy-to-understand manner.

Registered Patent No. 10-2289098 (Aug. 11, 2021, published) Publication No. 10-2018-0120571 (2018.11.06., published) Registered Patent No. 10-2246387 (August 28, 2021, published) Patent Publication No. 10-2014-0062651 (2014.05.26., published)

An object of the present invention for solving the above problems is to provide a method and apparatus for determining optimal influencers who can sell or promote a product well according to the product characteristics of the seller.

Another object of the present invention to solve the above problems is to provide a method and apparatus for collecting schedule information including purchase schedules of influencers and providing them to users.

Another object of the present invention for solving the above problems is to provide a method and apparatus capable of maximizing the effect of promoting or selling a seller's product through feedback to influencers.

According to various embodiments, the online shopping platform providing server that promotes and sells the seller's product through an influencer classifies the category of the product according to the product characteristic of the seller's product, and a plurality of influencers a big data management unit that collects activity information of unspeakers; a candidate influencer determining unit that determines first candidate influencers to be matched with the seller based on the product characteristics and the activity information; a final influencer determining unit that determines final influencers based on a predefined growth index and an excellent index among the determined first candidate influencers; a schedule management unit for providing the determined group purchase schedule information on the product of each of the final influencers to the user terminal; and a feedback reflecting unit that calculates the sales contribution for the product sold by each of the determined final influencers, and provides a sales contribution table generated according to the calculated sales contribution to the seller terminal of the seller. have.

According to various embodiments, the growth index may be calculated based on at least one of a follower increase rate, a post upload cycle, an influencer's upload propensity, and the sum of the average number of likes per post and the average number of comments for the last month. can The goodness index may be calculated based on at least one of the number of followers, the number of posts, the post upload cycle, the influencer's upload propensity, the average number of likes per post, and the average number of comments per post have.

According to various embodiments, the final influencer determiner may calculate the growth index for each of the first candidate influencers whose number of followers is greater than or equal to a first threshold and less than or equal to a second threshold, and the calculated growth index determines the first candidate influencers having a predetermined threshold growth index or higher as growth-type influencers, and calculates the good index for each of the first candidate influencers whose number of followers exceeds the second threshold value and the first candidate influencers having the calculated goodness index equal to or greater than a predefined critical goodness index may be determined as high quality influencers.

According to various embodiments, the final influencer determiner generates a map for the first candidate influencers, and the high quality influencer having the highest quality index among the first candidate influencers. is determined as a reference influencer, the reference influencer is placed in the center of the map, a second candidate influencer is placed on the map according to a similarity distance with the reference influencer, and the reference influencer is placed on the map. The second candidate influencer and the reference influencer having a similarity distance with the influencer equal to or greater than a threshold distance may be determined as the final influencer.

According to various embodiments, the online platform providing server includes the number of followers overlapping between the second candidate influencer and the reference influencer, the post uploaded by the second candidate influencer, and the reference influencer The method may further include a similarity distance calculator configured to calculate the similarity distance between the second candidate influencer and the reference influencer based on overlapping upload dates between posts uploaded by .

According to various embodiments, the growth index is calculated according to the following equation,

In the above formula, G is the growth index, R is the follower growth rate (%) during the last month, X is the post upload cycle (days), M is the number of followers, K is the average number of likes and average comments per post It may be a sum of numbers.

According to various embodiments, the goodness index is calculated according to the following equation,

In the above formula, E is the quality index, M is the number of followers, X is the post upload cycle (days), R is the follower growth rate (%) during the last month, K ₁ is the average number of likes per post, K ₂ may be the average number of comments per post.

According to various embodiments, the similarity distance is calculated based on the following equation,

In the above equation, D is a similarity distance between the reference influencer and the second candidate influencer, F is the number of followers of the second candidate influencer, N _f is the reference influencer and the second candidate influencer The number of overlapping followers among the influencers, I _-f is the number of influencers whose followers are equal to or greater than the first threshold among the overlapping followers, C is the number of times the second candidate influencer uploaded a post in the last month, S _p may be the number of times the reference influencer and the second candidate influencer uploaded a post on the same date during the last month.

According to various embodiments disclosed in this document, time and money can be saved because the seller does not need to visit the influencer directly.

Also, according to various embodiments, it is possible to recommend an optimal influencer who can sell or promote a product well according to the product characteristics of the seller.

In addition, according to various embodiments, it is possible to maximize the effect of promoting or selling the seller's product by competing with influencers.

Also, according to various embodiments, it is possible to provide convenience to users by sharing schedules of influencers with users.

In addition, various effects directly or indirectly identified through this document may be provided.

1 is a diagram illustrating an online shopping platform providing system according to an exemplary embodiment.
2 is a view showing a screen in which a unique link is set in an influencer's account.
3 is a view showing a screen for collecting and viewing a group purchase schedule of each influencer for a specific product and a screen for viewing a group purchase schedule of a specific influencer.
FIG. 4 is a diagram illustrating configurations of an online shopping platform providing server according to FIG. 1 .
5 is a diagram related to determining candidate influencers to match with a seller.
6 is a diagram for determining final influencers satisfying a specific condition from among candidate influencers.
FIG. 7 is a diagram illustrating a hardware configuration of the online shopping platform providing server according to FIG. 1 .

Since the present invention can have various changes and can have various embodiments, specific embodiments are illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the present invention to specific embodiments, and should be understood to include all modifications, equivalents and substitutes included in the spirit and scope of the present invention. In describing each figure, like reference numerals have been used for like elements.

Terms such as first, second, A, and B may be used to describe various elements, but the elements should not be limited by the terms. The above terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, a first component may be referred to as a second component, and similarly, a second component may also be referred to as a first component. and/or includes a combination of a plurality of related listed items or any of a plurality of related listed items.

When a component is referred to as being “connected” or “connected” to another component, it may be directly connected or connected to the other component, but it is understood that other components may exist in between. it should be On the other hand, when it is said that a certain element is "directly connected" or "directly connected" to another element, it should be understood that the other element does not exist in the middle.

The terms used in the present application are only used to describe specific embodiments, and are not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly dictates otherwise. In the present application, terms such as “comprise” or “have” are intended to designate that a feature, number, step, operation, component, part, or combination thereof described in the specification exists, but one or more other features It is to be understood that this does not preclude the possibility of the presence or addition of numbers, steps, operations, components, parts, or combinations thereof.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in a commonly used dictionary should be interpreted as having a meaning consistent with the meaning in the context of the related art, and should not be interpreted in an ideal or excessively formal meaning unless explicitly defined in the present application. does not

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

1 is a diagram illustrating an online shopping platform providing system 10 according to an exemplary embodiment. Referring to FIG. 1 , the online shopping platform providing system 10 may include an online shopping platform providing server 100 , a user terminal 200 , a seller terminal 300 , and an influencer terminal 400 . The operations described below may be performed through an online shopping platform (eg, a web page and/or a kind of application) controlled by the online shopping platform providing server 100 .

The online shopping platform providing server 100 may match the seller and the influencer using the online shopping platform service, and allow the influencer to sell and/or promote the products of the matched seller. The online shopping platform providing server 100 may determine an influencer to be matched with the seller based on the product sold by the seller and the characteristics of the influencer.

The online shopping platform providing server 100 may provide a unique link for purchasing the seller's product to the influencer or influencer terminal 400 determined to match the seller. The influencer who has signed a contract with the seller may display the unique link provided from the online shopping platform providing server 100 on his/her social media platform in his/her account or channel so that users can view or click. The unique link may be a link for accessing a product sales server operated by the seller. To help understand this, a diagram for displaying a unique link in an account or a channel is shown in FIG. 2 below.

The online shopping platform providing server 100 may collect schedules of influencers and provide information on the collected schedules to the user terminal 200 . For example, the schedule of influencers may include a group purchase schedule for jointly purchasing the seller's product.

The online shopping platform providing server 100 may list schedules of influencers according to preset conditions, and may provide information regarding schedules of the listed influencers to the user terminal 200 . For example, the online shopping platform providing server 100 may list schedules of influencers in chronological order and provide information about schedules of influencers listed in chronological order to the user terminal 200 . The online shopping platform providing server 100 may control to display a series of screens on which schedules of influencers are displayed on the user terminal 200 . The online shopping platform providing server 100 may provide an alarm about the schedule to the user terminal 200 before a predetermined period of time before the schedule of the influencers.

The online shopping platform providing server 100 may calculate the sales contribution of each of the influencers for the seller's product, and generate a sales contribution table according to the calculated sales contribution. The online shopping platform providing server 100 may provide the generated sales contribution table to the seller terminal 300 , and allow the seller to refer to the sales contribution of each of the influencers shown in the sales contribution table, so that the influencer We can help you manage them. For example, the sales contribution may be calculated based on a ratio accessed through a unique link set in each account of the influencers while the seller's product is sold. For example, when 100 products of the seller are sold, when 15 products are purchased by accessing through a unique link set in influencer A's account, the sales contribution may be 15%.

The user terminal 200 may be a terminal used by a purchaser using the online shopping platform provided by the online shopping platform providing server 100 . The seller terminal 300 may be a terminal used by a seller using an online shopping platform provided by the online shopping platform providing server 100 . The influencer terminal 400 is a terminal used by influencers to share purchase-related schedules (eg, joint purchase schedule) with users, promote products, and contract with sellers to promote or sell products. can A seller may include an entity that manufactures, distributes, and/or sells a particular product. The seller terminal 300 may subscribe to the online shopping platform service by transmitting information related to the seller to the online shopping platform providing server 100 . Information related to the seller includes the products manufactured and/or sold by the seller, whether the product has intellectual property rights, whether the product is in the store, whether the product is certified, whether or not the price of the product can be adjusted, the age of main use of the product, and the It may include information on at least one of the main use gender, the season of use of the product (seasonality), whether the product is epidemic, the number of mass production for the product, the presence or absence of a production plant for the product, and the amount of funds available for the product . The seller may be matched with an influencer using an online shopping platform service to allow the influencer to sell and/or promote the seller's product.

The user terminal 200, the seller terminal 300 and the influencer terminal 400 are a communicable desktop computer, a laptop computer, a notebook, a smart phone, a tablet PC. (tablet PC), mobile phone, smart watch, smart glass, e-book reader, PMP (portable multimedia player), portable game console, navigation device, digital camera ( digital camera), digital multimedia broadcasting (DMB) player, digital audio recorder, digital audio player, digital video recorder, digital video player, and PDA (Personal Digital Assistant) or the like.

2 is a view showing a screen in which a unique link is set in an influencer's account. 3 is a view showing a screen for collecting and viewing a group purchase schedule of each influencer for a specific product and a screen for viewing a group purchase schedule of a specific influencer.

Referring to FIG. 2 , in an embodiment, a screen in which a unique link 210 is set in an influencer's account is shown. The screen on which the unique link 210 is set may be displayed through the user terminal 200 , the seller terminal 300 , and the influencer terminal 400 .

When the user clicks the unique link 210 , the user terminal 200 may access a web page through which the seller's product can be purchased. The web page may include a purchase link for accessing a purchase page, a schedule link for accessing a schedule arrangement page, and the like. The schedule may refer to a group purchase schedule.

Referring to reference number 310 of FIG. 3 , the online shopping platform providing server 100 may arrange the group purchase schedule of the final influencers matched with the seller in chronological order. The group purchase schedule may change in real time over time. The online shopping platform providing server 100 may arrange the group purchase schedule of the final influencers according to the sales contribution of each of the final influencers, rather than chronologically. For example, the online shopping platform providing server 100 may place the group purchase schedule at the top of the influencer with a high sales contribution.

Referring to reference number 320 of FIG. 3 , the online shopping platform providing server 100 may arrange a group purchase schedule for a plurality of products of the final influencer matched with the seller in chronological order. The plurality of products may be products contracted by one seller or products contracted by a plurality of sellers.

FIG. 4 is a diagram showing the main configuration of the online shopping platform providing server 100 according to FIG. 1 .

Referring to FIG. 4 , the online shopping platform providing server 100 includes a big data manager 101 , a candidate influencer determiner 102 , a final influencer determiner 103 , a similarity distance calculator 104 , It may include a recommended product determination unit 105 and a feedback reflecting unit 106 and the like.

The big data management unit 101 may crawl posts posted by a plurality of influencers for each platform based on big data, and obtain activity information of the plurality of influencers. For example, the big data management unit 101 may crawl posts uploaded by a plurality of influencers for each platform such as Instagram, YouTube, Facebook, Twitter, Naver blog, and Tistory. For example, the activity information may include the number of posts uploaded by the influencer per platform, the amount of activity per platform, post category, post content, post format, activity period, feedback, and the like. The big data management unit 101 may acquire information about the upload tendency of the plurality of influencers.

The candidate influencer determiner 102 may determine candidate influencers to match the seller among the plurality of influencers. The candidate influencer determining unit 102 determines candidate influencers based on the product group to which the seller's product belongs, the post upload cycle of each of the plurality of influencers, the type of uploaded post, the number of followers, the follower increase/decrease trend, and the like. can

The final influencer determiner 103 may determine final influencers to be matched with the seller among the candidate influencers. The final influencer determining unit 103 determines one of the candidate influencers as the reference influencer to determine the final influencer, and the determined reference influencer and the candidate distinguished from the reference influencer. Based on the similarity distance between each of the influencers, the final influencers may be determined. The similarity distance calculator 104 may calculate the similarity distance.

The recommended product determination unit 105 may analyze the purchase characteristic of the user and determine a recommended product to be recommended to the user based on the purchase characteristic. The recommended product determining unit 105 may determine a recommended product to be recommended to the user based on the user's search information, the user's follow information, and the like. The recommended product determining unit 105 may determine a recommended product to be recommended to the user through the user's search history, search keyword, and the like. The recommended product determining unit 105 may determine a recommended product to be recommended to the user based on the search histories of other users and big data on products corresponding to the search keyword.

The feedback reflecting unit 106 may calculate a sales contribution of each of the final influencers for the product, and generate a sales contribution table according to the calculated sales contribution. The online shopping platform providing server 100 may provide the generated sales contribution table to the seller terminal 300, and by having the seller refer to the sales contribution of each of the final influencers shown in the sales contribution table, the influence We can provide help to manage the publications.

5 is a diagram related to determining candidate influencers to match with a seller.

The candidate influencer determiner 102 may determine the influencer terminal 400 to be matched with the seller terminal 300 . In other words, the candidate influencer determiner 102 may search a plurality of influencers using big data and determine a candidate influencer who promotes or sells the seller's product among the searched influencers. .

The candidate influencer determining unit 102 may determine a candidate influencer based on product characteristics and influencer characteristics for the seller's product. The candidate influencer determining unit 102 determines a candidate influencer based on the product group to which the seller's product belongs, the post upload cycle of each of the plurality of influencers, the type of uploaded post, the number of followers, the follower increase/decrease trend, and the like. can The post may include a video, text, and/or photo.

The final influencer determining unit 103 determines a final influencer among the candidate influencers, and may distinguish between an excellent influencer and a growth type influencer. The final influencer determining unit 103 may include, among the plurality of influencers, the product group to which the seller's product belongs, the post upload period of each of the plurality of influencers, the type of uploaded post, the number of followers, the follower increase/decrease trend, etc. Based on this, a good influencer and a growth type influencer can be determined. When determining the high-quality influencer and the growth-type influencer, the final influencer determiner 103 may determine the high-quality influencer and the growth-type influencer by applying different criteria, respectively.

The final influencer determining unit 103 is related to the follower increase rate, post upload cycle, influencer's upload tendency, seller's product among influencers whose number of followers is greater than or equal to the first threshold and less than or equal to the second threshold. A growth index may be calculated based on at least one of a ratio of posts, an average number of likes per post, and an average number of comments, and a growth-type influencer may be determined based on the calculated growth index. The growth index may be an index for determining how much an influencer's account or channel is growing when the number of followers is greater than or equal to the first threshold and less than or equal to the second threshold.

The final influencer determiner 103 may calculate a growth index through Equation 1 below, and determine a growth-type influencer based on the calculated growth index.

In Equation 1, G is the growth index, R is the follower growth rate (%) for the last month, post upload cycle, X is the post upload cycle (days), M is the number of followers, K is the average likes and average comments per post It may be a combined number.

The final influencer determiner 103 may determine a candidate influencer having a calculated growth index equal to or greater than a critical growth index as the growth-type influencer.

The final influencer determining unit 103 determines the number of followers, the number of posts, the post upload cycle, the influencer's upload tendency, and the seller's product-related posts among the influencers whose number of followers exceeds the second threshold. A good index may be calculated based on at least one of the ratio of , the average number of likes per post, and the average number of comments, and an excellent influencer may be determined based on the calculated good index. The goodness index may be an index for determining how good the number of followers is when the number of followers exceeds the second threshold.

The final influencer determiner 103 may calculate a good index through Equation 2 below, and determine a good influencer based on the calculated good index.

In Equation 2, E is the quality index, M is the number of followers, X is the post upload cycle (days), R is the follower growth rate (%) for the last month, K ₁ is the average number of likes per post, and K ₂ is the number of posts per post. It could be the average number of comments.

The final influencer determiner 103 may determine a candidate influencer having a calculated good index equal to or greater than a critical good index as the good influencer.

6 is a diagram for determining final influencers satisfying a specific condition among several influencers.

The final influencer determiner 103 may generate a map for influencers. The final influencer determination unit 103 determines one of the candidate influencers as the reference influencer to determine the final influencer, arranges the determined reference influencer in the center of the map, and places the reference influencer in the center of the map. Candidate influencers can be placed on the map according to the similarity distance with the influencer.

The final influencer determining unit 103 may determine an excellent influencer having the highest quality index as the reference influencer. The final influencer determining unit 103 does not determine candidate influencers whose similarity distance to the reference influencer is less than the threshold distance as final influencers, and the candidate influencer whose similarity distance to the reference influencer is equal to or greater than the threshold distance. They can be decided as final influencers. The closer the similarity distance to the reference influencer is, the more similar it is to the reference influencer.

The final influencer determining unit 103 determines one of the high-quality influencers as the reference influencer, thereby determining a growth-type influencer with a high probability of having a low similarity to the reference influencer as the final influencer. The probability is high, and accordingly, it is possible to match a number of growth-type influencers as well as high-quality influencers to the seller. In other words, the online shopping platform providing server 100 has the advantage of minimizing damage due to the exclusive contract from the seller's point of view by uniformly matching the seller with the high-quality influencer and the growth-type influencer.

The similarity distance calculating unit 104 may calculate a similarity distance between the reference influencer and an influencer distinguished from the reference influencer among the candidate influencers. The similarity distance calculating unit 104 may calculate the similarity distance based on the number of duplicated followers in the reference influencer and the candidate influencer, the duplicate upload date of the post, and the like.

The final influencer determiner 103 may determine a final influencer from among the candidate influencers based on the calculated similarity distance. The final influencer determining unit 103 may determine an influencer similar to the reference influencer as the final influencer. In other words, in order to prevent the seller's product promotion and/or sales effect from being limited, the final influencer determining unit 103 determines that the similarity distance is too large according to the similarity between the reference influencer and other candidate influencers. In a close case, the other candidate influencer having a similarity distance equal to or greater than a threshold distance may be determined as the final influencer without determining the other candidate influencer as the final influencer. For example, if the followers of the first influencer and the followers of the second influencer overlap a lot, the effect of promoting and/or selling the seller's product may be limited, and the followers of the first influencer and the followers of the second influencer may be limited. 2 If the influencer's followers rarely overlap, the effect of promoting and/or selling the seller's product can be maximized.

The similarity distance calculator 104 may calculate a similarity distance between each of the reference influencer and the candidate influencers. The similarity distance calculator 104 may calculate a similarity distance based on a follower of a reference influencer and a follower of a candidate influencer.

The similarity distance calculator 104 may calculate the similarity distance through Equation 3 below.

In Equation 3, D is the similarity distance between the reference influencer and the candidate influencer, F is the number of followers of the candidate influencer, N _f is the overlap between the reference influencer and the candidate influencer Number of followers, I _-f is the number of influencers whose followers are greater than or equal to the first threshold among the overlapping followers, C is the number of times the candidate influencer uploaded a post in the last month, and S _p is the above criterion in the last month It may mean the number of times the influencer and the candidate influencer uploaded a post on the same date.

The final influencer determiner 103 may determine, as the final influencer, candidate influencers whose similarity distance with the reference influencer calculated through the similarity distance calculator 104 is equal to or greater than a threshold distance.

The online shopping platform providing server 100 provides information on the determined final influencer to the seller terminal 300 , and the seller refers to the final influencer information obtained from the online shopping platform providing server 100 . The seller can decide which influencer to contract with himself.

The online shopping platform providing server 100 obtains an input for selecting a recommended final influencer from the seller terminal 300 and determines whether or not to contract with the influencer terminal 400 of the final influencer selected according to the input. A question message or a screen may be provided. When the online shopping platform providing server 100 obtains a response signal corresponding to acceptance of the contract, it may transmit a message for completing the contract conclusion to the seller terminal 300 and the influencer terminal 400 .

FIG. 7 is a diagram illustrating a hardware configuration of the online shopping platform providing server 100 according to FIG. 1 .

Referring to FIG. 7 , the online shopping platform providing server 100 provides at least one processor 110 and instructions for instructing the at least one processor 110 to perform at least one operation. It may include a memory (memory) for storing.

The at least one operation may include at least some of the above-described operations or functions of the online shopping platform providing server 100 , and may be implemented in the form of instructions and performed by the processor 110 .

Here, the at least one processor 110 may mean a central processing unit (CPU), a graphics processing unit (GPU), or a dedicated processor on which methods according to embodiments of the present invention are performed. can Each of the memory 120 and the storage device 160 may be configured as at least one of a volatile storage medium and a non-volatile storage medium. For example, the memory 120 may be one of a read only memory (ROM) and a random access memory (RAM), and the storage device 160 is a flash-memory. , a hard disk drive (HDD), a solid state drive (SSD), or various memory cards (eg, micro SD card).

Also, the online shopping platform providing server 100 may include a transceiver 130 that performs communication through a wireless network. Also, the online shopping platform providing server 100 may further include an input interface device 140 , an output interface device 150 , a storage device 160 , and the like. Each of the components included in the online shopping platform providing server 100 may be connected by a bus 170 to communicate with each other. In FIG. 7 , the online shopping platform providing server 100 has been described as an example, but the present invention is not limited thereto. For example, a plurality of user terminals may include the component according to FIG. 7 .

The methods according to the present invention may be implemented in the form of program instructions that can be executed by various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like, alone or in combination. The program instructions recorded on the computer readable medium may be specially designed and configured for the present invention, or may be known and available to those skilled in the art of computer software.

Examples of computer-readable media may include hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions may include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware device described above may be configured to operate as at least one software module to perform the operations of the present invention, and vice versa.

In addition, the above-described method or apparatus may be implemented by combining all or part of its configuration or function, or may be implemented separately.

Although the above has been described with reference to preferred embodiments of the present invention, those skilled in the art can variously modify and change the present invention within the scope without departing from the spirit and scope of the present invention as set forth in the claims below. You will understand that it can be done.

100: online shopping platform providing server 200: user terminal
300: seller terminal 400: influencer terminal

Claims (5)

As an online shopping platform providing server that promotes and sells seller's products through influencers,
a big data management unit for classifying the category of the product according to product characteristics of the seller's product and collecting activity information of a plurality of influencers;
a candidate influencer determining unit that determines first candidate influencers to be matched with the seller based on the product characteristics and the activity information;
a final influencer determining unit that determines final influencers based on a predefined growth index and an excellent index among the determined first candidate influencers;
a schedule management unit for providing the determined group purchase schedule information on the product of each of the final influencers to the user terminal; and
A feedback reflecting unit that calculates the sales contribution for the product sold by each of the determined final influencers, and provides a sales contribution table generated according to the calculated sales contribution to the seller terminal of the seller;
The final influencer decision unit,
calculating the growth index for each of the first candidate influencers whose number of followers is greater than or equal to a first threshold and less than or equal to a second threshold;
determining the first candidate influencers whose calculated growth index is greater than or equal to a predefined critical growth index as growth-type influencers;
calculating the goodness index for each of the first candidate influencers whose number of followers exceeds the second threshold,
determining the first candidate influencers whose calculated goodness index is greater than or equal to a predefined critical goodness index as high quality influencers;
The growth index is calculated according to the following formula,

In the above formula, G is the growth index, R is the follower growth rate (%) in the last month, X is the post upload cycle (days), M is the number of followers, and K is the average number of likes and average comments per post. is the sum of values,
The goodness index is calculated according to the following formula,

In the above formula, E is the quality index, M is the number of followers, X is the post upload cycle (days), R is the follower growth rate (%) during the last month, K ₁ is the average number of likes per post, K ₂ is the average number of comments per post, the online shopping platform providing server. delete delete In claim 1,
The final influencer decision unit,
Create a map for the first candidate influencers,
Determining an excellent influencer having the highest quality index among the first candidate influencers as a reference influencer,
Placing the reference influencer in the center of the map,
placing a second candidate influencer on the map according to the similarity distance with the reference influencer;
An online shopping platform providing server that determines the second candidate influencer and the reference influencer as the final influencer, the second candidate influencer having a similarity distance with the reference influencer equal to or greater than a threshold distance. In claim 4,
Based on the number of duplicated followers between the second candidate influencer and the reference influencer, and the overlapping upload date between the post uploaded by the second candidate influencer and the post uploaded by the reference influencer , The online shopping platform providing server, further comprising a similarity distance calculator for calculating the similarity distance between the second candidate influencer and the reference influencer.

Images