KR-102963474-B1 - INFLUENCER ACTIVITY INFORMATION-BASED ITEM RECOMMENDATION METHOD FOR RECOMMENDING TARGET ITEMS AND RELATED ACTIVITY HISTORIES, EXTRACTED FROM MULTIPLE ITEMS BASED ON INFLUENCER ACTIVITIES IN USER-CORRESPONDING COUNTRIES

Abstract

An item recommendation method is disclosed. For example, the item recommendation method may include, in response to receiving an item recommendation request from a user through an item sales interface using a communication interface, an operation of identifying a target country corresponding to the user based on the user's identification information; an operation of extracting a group of influencers belonging to the target country from among a plurality of influencers; an operation of identifying at least one target influencer among the target country influencers included in the influencer group, wherein the activity history according to the characteristic information of the target country influencer satisfies a predetermined condition; an operation of identifying at least one target item among a plurality of items registered in the item sales interface using the activity history of the at least one target influencer; and an operation of providing recommendation information to a user terminal corresponding to the user, the recommendation information including a sales page of the at least one target item and a target activity history associated with the at least one target item among the activity history.

Inventors

• 최춘연

Assignees

• 주식회사원링크

Dates

Publication Date

20260513

Application Date

20250814

Claims (5)

1. In an influencer activity information-based item recommendation method performed by an electronic device including a processor, which recommends to a user a target item extracted based on activity information of an influencer active in a country corresponding to the user among a plurality of items and an activity history associated with the target item, The above processor performs the operation of identifying a target country corresponding to the user based on the user's identification information in response to receiving an item recommendation request from the user through an item sales interface; The above processor performs the operation of extracting a group of influencers belonging to the target country from among a plurality of influencers; The above processor identifies at least one target influencer among the target country influencers included in the influencer group, wherein the activity history according to the characteristic information of the target country influencer satisfies a predetermined condition; The above processor identifies at least one target item among a plurality of items registered in the item sales interface by utilizing the activity history of at least one target influencer; and The above processor provides recommendation information to a user terminal corresponding to the user, the recommendation information including a sales page of the at least one target item and a target activity history associated with the at least one target item among the activity history; and The above-mentioned item recommendation method based on influencer activity information is, The above processor performs the operation of requesting the above characteristic information of the above target country influencer belonging to the above target country from the influencer platform API; and The above processor further includes the operation of extracting at least one target influencer among the target country influencers based on the characteristic information; The above characteristic information is, Profile information including the name, stage name, country of affiliation, place of residence, area of activity, age group, and type of language spoken for each of the above-mentioned multiple influencers; Platform information including the main activity platform of each of the above-mentioned plurality of influencers, the number of followers per platform, and the average number of content posts per day; and The activity history including the main field of activity of each of the plurality of influencers, the number and list of affiliate brands, the type and price range of items for sale, and the click-through rate, purchase conversion rate, number of shares, and number of comments per campaign for selling items; The above-mentioned item recommendation method based on influencer activity information is, The above processor performs the operation of identifying recommended items among the plurality of items based on the user's past purchase history; and The processor further includes the operation of determining as at least one target influencer an influencer in which there are two or more target contents associated with the recommended item in the activity history and the ratio of the target contents associated with the recommended item to the total content is 10% or more. The above-mentioned item recommendation method based on influencer activity information is, The operation of the processor to calculate the degree of association between the plurality of contents and the recommended item based on a comparison result between the plurality of content information, including hashtags, text, and images of the plurality of contents according to the activity history, and the item characteristics of the recommended item; and The above processor further includes the operation of determining as the target content the correlation degree between the plurality of contents and the recommendation item exceeds a predetermined correlation degree. The above-mentioned item recommendation method based on influencer activity information is, The above processor calculates an influence score for each of the above target country influencers based on the following mathematical formula; The processor further includes the operation of identifying an influencer among the target country influencers whose influence score is greater than or equal to a predetermined value as the at least one target influencer. I corresponds to the above influence score, V corresponds to the total number of views of the influencer's posted content during a specific period, C corresponds to the number of comments on the influencer's posted content during a specific period, S corresponds to the number of shares of the influencer's posted content during a specific period, F corresponds to the number of followers of the influencer, and a, b, and c correspond to the weights for the total number of views, comments, and shares of the posted content, respectively. Item recommendation method based on influencer activity information.
2. In paragraph 1, The above-mentioned item recommendation method based on influencer activity information is, The above processor further includes an operation in which it calculates the influence score by further considering the increase in followers, the click-through rate per campaign, and the purchase conversion rate during the specific period, wherein the influence score is calculated to be proportional to the increase in followers, the click-through rate per campaign, and the purchase conversion rate. The above influence score is calculated by assigning the greatest weight to the purchase conversion rate by campaign among the above follower growth, the above campaign click-through rate, and the above campaign purchase conversion rate, Item recommendation method based on influencer activity information.
3. delete
4. delete
5. delete

Description

An influencer activity information-based item recommendation method that recommends target items and related activity histories to a user, extracted from multiple items based on the activity information of influencers active in the user's country. The present invention relates to an influencer activity information-based item recommendation method that recommends to a user a target item and an activity history associated with the target item, extracted based on the activity information of an influencer active in a country corresponding to the user among a plurality of items. With the proliferation of e-commerce platforms, technology for recommending personalized items to users has continuously evolved. Existing recommendation systems primarily constructed algorithms based on users' past purchase history, search logs, and click data. While this approach offers strengths in terms of personalization because it is based on direct user behavioral data, it has limitations in reflecting new trends. Furthermore, social media and influencer marketing have recently been playing a significant role in consumer purchasing decisions, and content generated by influencers often directly influences consumer behavior. Consequently, there is a growing need for recommendation systems based on influencer activity information and content data. However, even when utilizing influencer data, the technologies proposed to date are based on limited metrics such as the number of followers or posts, and there is a lack of sophisticated recommendation mechanisms that reflect influencer information from countries culturally or geographically connected to the user. FIG. 1 is a block diagram showing the components of an electronic device according to one embodiment of the present invention. FIG. 2 is a block diagram showing the components of an item recommendation system including an electronic device according to one embodiment of the present invention. FIG. 3 is a flowchart of an item recommendation method according to one embodiment of the present invention. FIG. 4 is a flowchart of an item recommendation method according to one embodiment of the present invention. FIG. 5 is a flowchart of an item recommendation method according to one embodiment of the present invention. In relation to the description of the drawings, the same or similar reference numerals may be used for identical or similar components. Hereinafter, some embodiments of the present invention will be described in detail with reference to exemplary drawings. It should be noted that in assigning reference numerals to the components of each drawing, the same components are given the same reference numeral whenever possible, even if they are shown in different drawings. Furthermore, in describing the embodiments of the present invention, if it is determined that a detailed description of related known components or functions would hinder understanding of the embodiments of the present invention, such detailed description is omitted. In describing the components of the embodiments of the present invention, terms such as first, second, A, B, (a), (b), etc., may be used. These terms are intended merely to distinguish the components from other components, and the essence, order, or sequence of the components is not limited by the terms. Furthermore, unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which the present invention pertains. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this application. Hereinafter, embodiments of the present invention will be described in detail with reference to FIGS. 1 to 5. FIG. 1 is a block diagram showing the components of an electronic device according to one embodiment of the present invention. According to one embodiment, the electronic device (100) may include a memory (110), a processor (120), a communication interface (130), and/or a display device (140). The configuration of the electronic device (100) shown in FIG. 1 is exemplary and the embodiments of the present invention are not limited thereto. For example, the electronic device (100) may further include components not shown in FIG. 1 (e.g., a web crawler, a user interface, an input device, a notification unit, a sensor unit, or at least one of any combination thereof). According to one embodiment, the memory (110) may store instructions or data. For example, the memory (110) may store one or more instructions that cause the electronic device (100) to perform various operations when executed by the processor (120). For example, the memory (110) may be implemented as a single chipset with the processor (120). The processor (120) may include at least one