WO2019240322A1 - 소셜 네트워크를 이용한 영향력 측정 방법 및 장치 - Google Patents
소셜 네트워크를 이용한 영향력 측정 방법 및 장치 Download PDFInfo
- Publication number
- WO2019240322A1 WO2019240322A1 PCT/KR2018/007925 KR2018007925W WO2019240322A1 WO 2019240322 A1 WO2019240322 A1 WO 2019240322A1 KR 2018007925 W KR2018007925 W KR 2018007925W WO 2019240322 A1 WO2019240322 A1 WO 2019240322A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- attribute
- product
- user
- influence value
- influence
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000013507 mapping Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 10
- 239000000284 extract Substances 0.000 description 8
- 238000010606 normalization Methods 0.000 description 5
- 238000005259 measurement Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000000691 measurement method Methods 0.000 description 2
- 125000002066 L-histidyl group Chemical group [H]N1C([H])=NC(C([H])([H])[C@](C(=O)[*])([H])N([H])[H])=C1[H] 0.000 description 1
- 244000240602 cacao Species 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000001151 other effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/52—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail for supporting social networking services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/2866—Architectures; Arrangements
- H04L67/30—Profiles
- H04L67/306—User profiles
Definitions
- the present invention relates to a method and apparatus for measuring influence using a social network.
- SNSs Social network services
- SNS service begins to function as a new purchasing channel, and contents existing on SNS also began to be used for marketing purposes.
- the problem to be solved by the present invention is to provide an impact measuring method and apparatus using a social network.
- An object of the present invention is to provide a method and apparatus for dynamically evaluating the influence of a product based on the influence and image tagging on a social network.
- the problem to be solved by the present invention is to provide a method and apparatus that can recommend products and place advertisements by dynamically reflecting the influence on the social network.
- an impact measuring method performed by an apparatus for measuring influence using a social network may include collecting SNS data from a social network service (SNS), and a user among the SNS data. Measuring a user influence index based on account information and content information related to the user account information, and measuring an attribute influence value for an attribute included in the image information based on image information among the SNS data Measuring a product influence value for the product information on the content including the product information based on the user influence index and the attribute influence value, and the content including the product information based on the product influence value.
- Curation Step It includes.
- the measuring of the attribute influence value may include: obtaining recent image information related to the user account information from the SNS data, applying image tagging to the recent image information, and performing the image information. It may include extracting at least one attribute included in, and measuring the attribute impact value for each of the at least one attribute.
- the extracting of the at least one attribute comprises: deriving at least one influential user based on the user influence index, and user account information of the at least one influential user.
- the method may include extracting the at least one attribute by acquiring recent image information from content information associated with the at least one attribute, and measuring the attribute impact value comprises: a user impact index for each of the at least one influential user Based on the attribute attribute value for each of the at least one attribute can be measured.
- measuring the attribute influence value further comprises: normalizing the attribute influence value for each of the at least one attribute in a corresponding class to which each of the at least one attribute belongs. It may include.
- the measuring of the attribute influence value may further include mapping the attribute influence value for each attribute and storing the attribute influence value in an attribute database.
- the measuring of the product influence value may include obtaining content including the product information from a user, and applying image tagging to the content including the product information. Extracting an attribute, obtaining an attribute influence value corresponding to each of the at least one product attribute from the attribute database, and a product influence value for content including the product information based on the obtained attribute influence value It may include the step of measuring.
- the measuring the product influence value further includes mapping the product influence value for each product and storing the product influence value in a product attribute database, curating the content including the product information.
- the step of detecting may be curated by detecting the content having a product influence value that meets a predetermined condition from the product attribute database.
- the predetermined condition may be set based on a rank of the merchandise influence value, or based on a degree similar to the merchandise information included in the content.
- the collecting of the SNS data may include collecting and updating new SNS data at regular intervals from the social network service.
- an apparatus for measuring influence using a social network includes a data collector configured to collect SNS data from a social network service (SNS), user account information among the SNS data, and the user.
- a user influence index is measured based on content information related to account information
- an attribute influence value of an attribute included in the image information is measured based on image information among the SNS data, and content including product information.
- the influence on the content can be evaluated based on the influence of the influencer on the SNS.
- the influencer on the SNS by continuously monitoring the contents of the influencer on the SNS, it is possible to perform an impact evaluation on the content in real time, thereby providing a timely supply of goods or advertisements related to the content.
- FIG. 1 is a diagram schematically illustrating an impact measuring system using a social network according to an exemplary embodiment of the present invention.
- FIG. 2 is a diagram illustrating a configuration of an impact measuring apparatus using a social network according to an exemplary embodiment of the present invention.
- FIG. 3 is a flowchart schematically illustrating a method for measuring impact using a social network according to an embodiment of the present invention.
- FIG. 4 is a diagram illustrating an example of applying an impact measurement method using a social network according to an embodiment of the present invention.
- 5 and 6 are diagrams illustrating another example of applying an influence measuring method using a social network according to an embodiment of the present invention.
- FIG. 7 is a diagram illustrating another example of applying an influence measuring method using a social network according to an embodiment of the present invention.
- FIG. 1 is a diagram schematically illustrating an impact measuring system using a social network according to an exemplary embodiment of the present invention.
- an influence measuring system using a social network may be a social network service (SNS) server 100 and a terminal device. 200, and the influence measuring apparatus 300.
- SNS social network service
- the SNS server 100 is a server device of a service provider (eg, Twitter, Facebook, Instagram, Kakao Story, etc.) that provides SNS, and establishes a network and exchanges information with SNS users through the terminal device 200. can do.
- the SNS server 100 allocates an SNS account to a user (eg, an individual user, a content provider, etc.) who wants to use the SNS, and publishes various contents or views contents posted by others through the assigned account. Make various services available.
- a service provider eg, Twitter, Facebook, Instagram, Kakao Story, etc.
- the terminal device 200 is a terminal device of a user using SNS provided through the SNS server 100, and may be, for example, various computing devices such as a smart phone, a tablet PC, a desktop, a notebook, a smart TV, and the like.
- the impact measurement apparatus 300 may collect various SNS data posted on the SNS from the SNS server 100, and may evaluate the influence on various information included in the SNS data through the SNS data. In addition, the impact measurement apparatus 300 may provide curated contents to a user having various purposes based on the impact evaluation of various information included in the SNS data. A detailed operation process of the influence measuring apparatus 300 will be described later.
- FIG. 2 is a diagram illustrating a configuration of an impact measuring apparatus using a social network according to an exemplary embodiment of the present invention.
- an influence measuring apparatus 300 (hereinafter, referred to as an influence measuring apparatus) using a social network according to an embodiment of the present invention may include a data collecting unit 310, an impact measuring unit 320, and content curation. It may include a portion 330.
- the data collector 310 may collect various SNS data posted on the SNS from the SNS server 100.
- the data collector 310 may include an account information collector 311 for collecting account information of an SNS user from the SNS server 100, and a content information collector for collecting content information posted by an SNS user ( 312).
- the impact measuring unit 320 may evaluate the influence of various kinds of information included in the SNS data.
- the impact measuring unit 320 may include a user impact measuring unit 321, an attribute impact measuring unit 322, and a product impact measuring unit 323.
- the user influence measuring unit 321 may measure a user influence index based on the SNS user account information collected by the data collecting unit 310 and related content information.
- the influence measuring apparatus 300 may map each SNS user account information and a user influence index corresponding thereto, and store the same in the user account database 340.
- the attribute impact measuring unit 322 may measure the attribute impact value of the attribute included in the image information based on the image information among the contents collected by the data collecting unit 310.
- the influence measuring apparatus 300 may map the attribute and the attribute influence value corresponding thereto to store the attribute in the attribute database 341.
- the product influence measuring unit 323 may measure the product influence value of the product information on the content including the product information based on the user influence index and the attribute influence value.
- the influence measuring apparatus 300 may store the product information and the product influence value corresponding thereto by mapping the product information to the product attribute database 342.
- the content curation unit 330 may curate the content including the product information based on the product influence value to provide the user with various purposes.
- FIG. 3 is a flowchart schematically illustrating a method for measuring impact using a social network according to an embodiment of the present invention.
- the method of FIG. 3 may be performed by the influence measuring apparatus 300 of FIG. 2.
- the data collector 310 may collect various SNS data posted on the SNS from the SNS server 100 (S400).
- the account information collector 311 may collect account information of the SNS user registered in the SNS server 100.
- the content information collection unit 312 may collect various content data posted on the SNS from the SNS server 100.
- the account information collecting unit 311 and the content information collecting unit 312 may collect and update the user account information and the content information at regular intervals, thereby maintaining the latest SNS data.
- the impact measuring unit 320 may measure a user impact index, an attribute impact value, and a product impact value based on the collected SNS data (S410 ⁇ S430).
- the user impact measuring unit 321 may derive a user impact index based on user account information of the SNS user and content information related thereto (S410).
- the user account information may include a user account, contact information (eg, a follower, following, etc.) associated with the user account.
- Content information related to user account information includes additional information such as the number of content posted through that user account, and interest in content posted through that user account (e.g., rating information such as number of comments, likes, etc.) can do.
- the user influence index may be derived as shown in Equation 1, which may be used as a criterion for evaluating how much influence the user has on the SNS.
- Equation 1 represents (the number of followers of the user compared to the average number of followers of the total user) * (the root mean square root of interest (RMS) per post).
- the user influence indexes for the user A and the user B may be calculated as follows by applying Equation 1.
- the user impact measuring unit 321 may map the user account information derived as described above and a user impact index corresponding thereto and store the same in the user account database 340.
- the attribute impact measuring unit 322 may derive the attribute influence value for the attribute included in the image information based on the image information among the content data (S420).
- the attribute impact measurement unit 322 may obtain the latest content data associated with the user account information from the content information collector 312. According to an embodiment, the attribute impact measuring unit 322 may search for, derive, and derive at least one influential user (influencer) from the user account database 340 based on the user impact index. The latest content data posted through the user account of the influential user can be obtained.
- the image processor 324 may obtain image information from the recent content data, and apply at least one attribute included in the image information by applying an image tagging technique to the obtained image information.
- the image processor 324 forms a trained model using deep learning, a neural network, and the like on the image information, and applies image tagging to the trained model of the image and includes it in the image information. At least one attribute can be extracted.
- the attribute impact measuring unit 322 may derive the attribute impact value for each of the at least one attribute.
- the attribute influence value may be derived as shown in Equation 2, which may be used as a criterion for evaluating how frequently the attribute appears in the content of an influential user and has a high impact. .
- the attribute influence measuring unit 322 calculates an attribute influence value based on a frequency of each attribute included in the image of the at least one influential user and the at least one influential user. To derive.
- the User Impact Index is 1652.1
- the attribute of influence index is 451.8
- the attribute influence value for each of the attributes based on the influential users A and B may be calculated as follows according to Equation 2.
- the attribute impact measuring unit 322 may normalize the attribute impact value based on the class to which the attribute belongs.
- the process of normalizing an attribute influence value may be derived as shown in Equation 3, which adjusts the influence value of the attribute in the class to which the attribute belongs. It can be measured to have a degree of influence.
- the attribute impact measuring unit 322 normalizes the attribute impact value by the ratio of the attribute in the class to which the attribute belongs.
- the attribute value of the coat attribute is 3304.2
- the attribute value of the skirt attribute is 2103.9
- the attribute attribute value of the long padding attribute is 451.8 in the class of items
- the attribute attribute value of the gray attribute in the color class is Suppose that the attribute influence value of 3304.2, Beige attributes is 2555.7. Normalizing the attribute influence value for each attribute according to Equation 3 can be calculated as follows.
- the attribute impact measuring unit 322 may map the attribute derived as described above, the attribute impact value corresponding thereto, and the normalized value of the attribute to be stored in the attribute database 341.
- the product influence measuring unit 323 may derive the product influence value for the product included in the content based on the user influence index and the attribute influence value for the content including the product information (S430).
- the product impact measuring unit 323 may obtain the content including the product information from the user.
- the product influence measuring unit 323 may obtain content including product information from a user who sells a product online, a user who wants a product advertisement, or the like through an online shopping mall.
- the user may separately construct and use a database 343 for storing his / her product information.
- the influence measuring apparatus 300 may obtain product information from the database 343 of each user.
- the image processor 324 may obtain image information from content including product information, and extract at least one product attribute from the image information by applying image tagging through deep learning or neural networks to the obtained image information. .
- the product influence measuring unit 323 may measure the product influence value for the content including the product information on the basis of the attribute influence value for each of the extracted at least one product attribute. In this case, the product influence measuring unit 323 may derive the product influence value by obtaining an attribute influence value corresponding to the product attribute from the attribute database 341. In one embodiment, the product influence value may be derived as shown in Equation 4, which may be used as a criterion for evaluating how influential the content including the product is and reflecting the trend.
- the product impact measuring unit 323 is based on the normalized value of the attribute influence value for each product attribute included in one content, the weight (for example, the degree of interest, importance of the class to which the product attribute belongs) The value of the product, etc.) is derived.
- the weight may be variably changed through empirical data.
- the normalization value of the attribute influence value for the coat is 0.9433
- the normalization value of the attribute influence value for the skirt is 0.1051
- the normalization value of the attribute influence value for the long padding is -1.0484, and the normalization of the attribute influence value for the gray.
- the value is 0.7071
- the normalization value of the attribute influence value for beige is -0.7071
- the weight of the item class is 1
- the weight of the color class is 0.5
- the product influence value for the products included in the first content and the second content may be calculated as follows according to Equation 4.
- the merchandise impact measuring unit 323 may map the merchandise attribute derived as described above and the merchandise influence value corresponding thereto to store the merchandise attribute database 342.
- the content curation unit 330 may curate the content including the product information based on the product influence value (S440).
- the content curation unit 330 may detect a product content having a product influence value that meets a predetermined condition from the product attribute database 342, and may provide it to a user who wants to utilize the content. For example, when the ranking of the product influence value is set as a condition, the content curation unit 330 obtains a product attribute having a high product influence value from the product attribute database 342 among various contents provided by the user. Content can be curated product attributes. Alternatively, when the similarity of the product is set as a condition, the content curation unit 330 obtains a product attribute similar to the product included in the content provided by the user from the product attribute database 342 and compares the obtained product attribute with the obtained product attribute. Similarity can be calculated and used for content curation.
- FIG. 4 is a diagram illustrating an example of applying an impact measurement method using a social network according to an embodiment of the present invention.
- the data collector 310 may collect new SNS data at predetermined intervals (S500). According to an embodiment, the data collector 310 may detect an influential user from the user account database 340 based on the user influence index, and periodically collect the SNS data of the detected user.
- the impact measuring unit 320 may obtain an image from the collected SNS data and extract at least one attribute included in each image (S510). According to an exemplary embodiment, the impact measuring unit 320 may extract an attribute only from the newly collected image from the SNS data of the influential user.
- the impact measuring unit 320 may measure an attribute impact value of an attribute included in each image by using a user impact index for each influential user (S520).
- the impact measurer 320 extracts the coat, beige, and belt attributes from the first image 501 of the first user, and the second image 502 of the second user. You can extract the lap skirt, grey, and destroyed attributes from it.
- the impact measuring unit 320 may calculate the value of each attribute influence by using the user impact index of the first and second users for each extracted attribute.
- the influence measuring unit 320 may store each attribute and the attribute influence value corresponding thereto in the attribute database 341 (S530).
- the impact measurer 320 may derive the product influence value using the updated attribute and attribute influence value in the attribute database 341, and accordingly the product attribute database 342. It may be updated (S540).
- the impact measurement unit 320 may measure the product impact value for the product included in the user's content by using the attribute and attribute influence value stored in the attribute database 341. There is (S550).
- 5 and 6 are diagrams illustrating another example of applying an influence measuring method using a social network according to an embodiment of the present invention.
- the impact measuring unit 320 may obtain content including product information from the user product database 343 (S600). In an embodiment, the impact measuring unit 320 may obtain the content in units of stock keeping units (SKUs) from the user product database 343.
- SKUs stock keeping units
- the impact measuring unit 320 extracts an attribute from each of the acquired contents (S610), measures an attribute influence value for each of the extracted attributes, and then measures a product influence value for each of the contents based on each attribute influence value. There is (S620).
- the content curation unit 330 may determine whether the content influences the predetermined influence value based on the product influence value for each of the acquired content, and filter the content that satisfies the condition according to the determination result (S630). For example, you can select and filter content that has a high impact value ranking.
- the content curation unit 330 may curate the filtered content and provide the filtered content to the user (S640). For example, the most influential product on the social network among the contents possessed by the user may be reflected and provided.
- the attribute influence value and the product influence value may be changed.
- the content curation unit 330 may filter the content by determining whether the predetermined condition is met again based on the updated product influence value from the product attribute database 342. Therefore, it is possible to continuously monitor the trend change on the social network, thereby dynamically updating the content reflecting the trend.
- FIG. 7 is a diagram illustrating another example of applying an influence measuring method using a social network according to an embodiment of the present invention.
- the impact measuring unit 320 may obtain content including new product information from the user (S700).
- the impact measuring unit 320 may extract a product attribute from the content including the new product information (S710), and measure the product influence value of the content including the product information based on the attribute influence value of each extracted product attribute. There is (S720).
- the impact measuring unit 320 may evaluate a product influence value by comparing a similar product with a product included in the content obtained from the user.
- the impact measurer 320 may obtain a product 701 similar to the product attribute in the content obtained from the user, from the product attribute database 342 (S730).
- the impact measuring unit 320 extracts the product attributes 702 and 703 from each of the similar products 701 (S740), and the degree of similarity between each of the extracted product attributes 702 and 703 and the product attributes of the content obtained from the user. It may be compared (704, 705) (S750). Similarity of each of the similar products may be derived according to the degree of similarity (704, 705) between each of these attributes.
- the impact measuring unit 320 may measure the product influence value by reflecting the product similarity for each similar product 701.
- the content curation unit 330 may determine whether the content is similar to the content obtained from the user based on the product influence value reflecting the similarity of the product, and may filter the content including the similar product according to the determination result (S760).
- the content curation unit 330 may curate the filtered content and provide the filtered content to the user (S770).
- the influence can be evaluated by reflecting the similarity of the product, it can be effectively used when recommending similar products or matching similar products, for example, when the advertisement is posted.
- the steps of a method or algorithm described in connection with an embodiment of the present invention may be implemented directly in hardware, in a software module executed by hardware, or by a combination thereof.
- the software module may be a 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.
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Description
Claims (10)
- 소셜 네트워크를 이용한 영향력 측정 장치에 의해 수행되는 영향력 측정 방법에 있어서,소셜 네트워크 서비스(SNS)로부터 SNS 데이터를 수집하는 단계;상기 SNS 데이터 중 사용자 계정 정보 및 상기 사용자 계정 정보와 관련된 콘텐츠 정보를 기반으로 사용자 영향력 지수를 측정하는 단계;상기 SNS 데이터 중 이미지 정보를 기반으로 상기 이미지 정보에 포함된 어트리뷰트(attribute)에 대한 어트리뷰트 영향력 가치를 측정하는 단계;상품 정보를 포함하는 콘텐츠에 대해서 상기 사용자 영향력 지수 및 상기 어트리뷰트 영향력 가치를 기반으로 상기 상품 정보에 대한 상품 영향력 가치를 측정하는 단계; 및상기 상품 영향력 가치에 기초하여 상기 상품 정보를 포함하는 콘텐츠를 큐레이션(curation)하는 단계를 포함하는 것을 특징으로 하는 영향력 측정 방법.
- 제1항에 있어서,상기 어트리뷰트 영향력 가치를 측정하는 단계는,상기 SNS 데이터로부터 상기 사용자 계정 정보와 관련된 최근 이미지 정보를 획득하는 단계;상기 최근 이미지 정보에 이미지 태깅을 적용하여 상기 이미지 정보에 포함된 적어도 하나의 어트리뷰트를 추출하는 단계; 및상기 적어도 하나의 어트리뷰트 각각에 대한 어트리뷰트 영향력 가치를 측정하는 단계를 포함하는 것을 특징으로 하는 영향력 측정 방법.
- 제2항에 있어서,상기 적어도 하나의 어트리뷰트를 추출하는 단계는,상기 사용자 영향력 지수를 기반으로 적어도 하나의 영향력 있는 사용자를 도출하는 단계; 및상기 적어도 하나의 영향력 있는 사용자의 사용자 계정 정보와 관련된 콘텐츠 정보로부터 최근 이미지 정보를 획득하여, 상기 적어도 하나의 어트리뷰트를 추출하는 단계를 포함하며,상기 어트리뷰트 영향력 가치를 측정하는 단계는,상기 적어도 하나의 영향력 있는 사용자 각각에 대한 사용자 영향력 지수를 기반으로 상기 적어도 하나의 어트리뷰트 각각에 대한 어트리뷰트 영향력 가치를 측정하는 것을 특징으로 하는 영향력 측정 방법.
- 제3항에 있어서,상기 어트리뷰트 영향력 가치를 측정하는 단계는,상기 적어도 하나의 어트리뷰트 각각이 속해 있는 해당 클래스 내에서의 상기 적어도 하나의 어트리뷰트 각각에 대한 어트리뷰트 영향력 가치를 정규화하는 단계를 더 포함하는 것을 특징으로 하는 영향력 측정 방법.
- 제3항에 있어서,상기 어트리뷰트 영향력 가치를 측정하는 단계는,어트리뷰트별로 상기 어트리뷰트 영향력 가치를 맵핑하여 어트리뷰트 데이터베이스에 저장하는 단계를 더 포함하는 것을 특징으로 하는 영향력 측정 방법.
- 제5항에 있어서,상기 상품 영향력 가치를 측정하는 단계는,사용자로부터 상기 상품 정보를 포함하는 콘텐츠를 획득하는 단계;상기 상품 정보를 포함하는 콘텐츠에 이미지 태깅을 적용하여 적어도 하나의 상품 어트리뷰트를 추출하는 단계;상기 어트리뷰트 데이터베이스로부터 상기 적어도 하나의 상품 어트리뷰트 각각에 대응하는 어트리뷰트 영향력 가치를 획득하는 단계; 및상기 획득한 어트리뷰트 영향력 가치를 기반으로 상기 상품 정보를 포함하는 콘텐츠에 대한 상품 영향력 가치를 측정하는 단계를 포함하는 것을 특징으로 하는 영향력 측정 방법.
- 제6항에 있어서,상기 상품 영향력 가치를 측정하는 단계는,상품별로 상기 상품 영향력 가치를 맵핑하여 상품 어트리뷰트 데이터베이스에 저장하는 단계를 더 포함하며,상기 상품 정보를 포함하는 콘텐츠를 큐레이션하는 단계는,상기 상품 어트리뷰트 데이터베이스로부터 기설정된 조건에 부합하는 상품 영향력 가치를 가지는 콘텐츠를 검출하여 큐레이션하는 것을 특징으로 하는 영향력 측정 방법.
- 제7항에 있어서,상기 기설정된 조건은,상기 상품 영향력 가치의 순위를 기준으로 설정되거나, 상기 콘텐츠에 포함된 상품 정보와 유사한 정도를 기준으로 설정되는 것을 특징으로 하는 영향력 측정 방법.
- 제1항에 있어서,상기 SNS 데이터를 수집하는 단계는,상기 소셜 네트워크 서비스로부터 일정 주기마다 신규 SNS 데이터를 수집하여 갱신하는 것을 특징으로 하는 영향력 측정 방법.
- 소셜 네트워크를 이용한 영향력 측정 장치에 있어서,소셜 네트워크 서비스(SNS)로부터 SNS 데이터를 수집하는 데이터 수집부;상기 SNS 데이터 중 사용자 계정 정보 및 상기 사용자 계정 정보와 관련된 콘텐츠 정보를 기반으로 사용자 영향력 지수를 측정하고, 상기 SNS 데이터 중 이미지 정보를 기반으로 상기 이미지 정보에 포함된 어트리뷰트(attribute)에 대한 어트리뷰트 영향력 가치를 측정하고, 상품 정보를 포함하는 콘텐츠에 대해서 상기 사용자 영향력 지수 및 상기 어트리뷰트 영향력 가치를 기반으로 상기 상품 정보에 대한 상품 영향력 가치를 측정하는 영향력 측정부; 및상기 상품 영향력 가치에 기초하여 상기 상품 정보를 포함하는 콘텐츠를 큐레이션(curation)하는 콘텐츠 큐레이션부를 포함하는 것을 특징으로 하는 영향력 측정 장치.
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2020569959A JP7082216B2 (ja) | 2018-06-11 | 2018-07-12 | ソーシャルネットワークを利用した影響力測定方法および装置 |
CN201880094553.4A CN112313687B (zh) | 2018-06-11 | 2018-07-12 | 利用社交网络的影响力测量方法及装置 |
US16/684,318 US11232525B2 (en) | 2018-06-11 | 2019-11-14 | Method and apparatus for measuring influence on social network |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020180066604A KR102052344B1 (ko) | 2018-06-11 | 2018-06-11 | 소셜 네트워크를 이용한 영향력 측정 방법 및 장치 |
KR10-2018-0066604 | 2018-06-11 |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/684,318 Continuation US11232525B2 (en) | 2018-06-11 | 2019-11-14 | Method and apparatus for measuring influence on social network |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2019240322A1 true WO2019240322A1 (ko) | 2019-12-19 |
Family
ID=68842296
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/KR2018/007925 WO2019240322A1 (ko) | 2018-06-11 | 2018-07-12 | 소셜 네트워크를 이용한 영향력 측정 방법 및 장치 |
Country Status (5)
Country | Link |
---|---|
US (1) | US11232525B2 (ko) |
JP (1) | JP7082216B2 (ko) |
KR (1) | KR102052344B1 (ko) |
CN (1) | CN112313687B (ko) |
WO (1) | WO2019240322A1 (ko) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20210077949A (ko) | 2019-12-18 | 2021-06-28 | 주식회사 화성 | 소셜 웹서비스에서의 사용자 영향력 지수 산출 방법 및 시스템 |
KR102264034B1 (ko) * | 2020-04-10 | 2021-06-11 | 주식회사 민팅 | 사용자의 sns 계정과 상품 정보를 매칭하는 서버 및 그 운영 방법 |
KR102407057B1 (ko) * | 2020-06-01 | 2022-06-10 | 주식회사 피처링 | Sns 사용자 채널에 대한 공개 데이터를 분석하여 영향력 리포트를 제공하는 시스템 및 방법 |
KR102407056B1 (ko) * | 2020-06-01 | 2022-06-10 | 주식회사 피처링 | Sns 사용자 채널에 대한 공개 데이터를 수집하고, 수집된 공개 데이터를 기반으로 영향력을 측정하는 시스템 및 방법 |
KR102468220B1 (ko) * | 2020-09-14 | 2022-11-18 | 선문대학교 산학협력단 | 외부 온라인 계정에 대한 활동가치 평가를 기반으로 하는 주식 거래 시스템 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20130089778A (ko) * | 2011-12-30 | 2013-08-13 | 주식회사 네오위즈인터넷 | 인터넷 정보에 기초하여 콘텐츠 서비스를 제공하는 방법, 콘텐츠 서비스 서버, 단말기, 기록매체 |
KR101302507B1 (ko) * | 2011-04-11 | 2013-09-03 | 에스케이씨앤씨 주식회사 | Sns를 이용한 마케팅 서비스 방법 및 장치 |
KR20140078008A (ko) * | 2012-12-13 | 2014-06-25 | 에스케이플래닛 주식회사 | 소셜네트워크 이용자의 영향력정보 결정 시스템 및 방법 |
KR20140094052A (ko) * | 2013-01-15 | 2014-07-30 | 에스케이플래닛 주식회사 | 관심대상 분석 시스템 및 그 방법, 그리고 이에 적용되는 장치 |
KR20180049591A (ko) * | 2016-11-03 | 2018-05-11 | 신철호 | 소셜인플루언서를 이용한 포스팅 방법 |
Family Cites Families (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090307057A1 (en) * | 2008-06-06 | 2009-12-10 | Albert Azout | Associative memory operators, methods and computer program products for using a social network for predictive marketing analysis |
CN102385601B (zh) * | 2010-09-03 | 2015-11-25 | 阿里巴巴集团控股有限公司 | 一种产品信息的推荐方法及系统 |
US20120209786A1 (en) * | 2011-02-15 | 2012-08-16 | Shesha Shah | Social Net Advocacy Business Applications |
JP2013161116A (ja) | 2012-02-01 | 2013-08-19 | Nec Corp | レコメンドシステム、レコメンド方法及びレコメンドプログラム |
JP5848199B2 (ja) | 2012-06-15 | 2016-01-27 | 日本電信電話株式会社 | 影響力予測装置、影響力予測方法、及びプログラム |
US20140095307A1 (en) | 2012-09-28 | 2014-04-03 | Sony Computer Entertainment America Llc | Spotting trends by identifying influential consumers |
JP5940955B2 (ja) | 2012-10-18 | 2016-06-29 | 株式会社日立製作所 | トレンド分析装置、方法及びプログラム |
US20140143013A1 (en) * | 2012-11-19 | 2014-05-22 | Wal-Mart Stores, Inc. | System and method for analyzing social media trends |
US9213996B2 (en) | 2012-11-19 | 2015-12-15 | Wal-Mart Stores, Inc. | System and method for analyzing social media trends |
US9224174B2 (en) | 2012-11-28 | 2015-12-29 | Facebook, Inc. | Determining influence in a social networking system |
US9489699B2 (en) * | 2013-07-10 | 2016-11-08 | Excalibur Ip, Llc | Influence maximization with viral product design |
US20170132688A1 (en) | 2013-09-13 | 2017-05-11 | Google Inc. | Pricing product recommendations in a social network |
CN104408648A (zh) * | 2014-12-09 | 2015-03-11 | 北京博雅立方科技有限公司 | 一种挑选商品的方法及装置 |
US20160246896A1 (en) * | 2015-02-20 | 2016-08-25 | Xerox Corporation | Methods and systems for identifying target users of content |
KR101801846B1 (ko) * | 2015-08-26 | 2017-11-27 | 옴니어스 주식회사 | 상품 영상 검색 및 시스템 |
JP6341899B2 (ja) | 2015-11-13 | 2018-06-13 | Necパーソナルコンピュータ株式会社 | 広告システム及び広告配信方法 |
CN105809558A (zh) * | 2016-03-15 | 2016-07-27 | 平安科技(深圳)有限公司 | 基于社交网络的推荐方法和装置 |
CN105913159A (zh) * | 2016-04-29 | 2016-08-31 | 北京邮电大学 | 基于社交网络事件的用户影响力预测方法 |
US10684738B1 (en) * | 2016-11-01 | 2020-06-16 | Target Brands, Inc. | Social retail platform and system with graphical user interfaces for presenting multiple content types |
CN107730343A (zh) * | 2017-09-15 | 2018-02-23 | 广州唯品会研究院有限公司 | 一种基于图片属性提取的用户商品信息推送方法及设备 |
CN108009896A (zh) * | 2017-12-22 | 2018-05-08 | 广州爱美互动网络科技有限公司 | 基于微博平台商品推广方法、电子设备、存储介质及系统 |
US11915288B2 (en) * | 2018-04-20 | 2024-02-27 | Noww, Inc. | Useful and novel shopping application |
-
2018
- 2018-06-11 KR KR1020180066604A patent/KR102052344B1/ko active IP Right Grant
- 2018-07-12 JP JP2020569959A patent/JP7082216B2/ja active Active
- 2018-07-12 CN CN201880094553.4A patent/CN112313687B/zh active Active
- 2018-07-12 WO PCT/KR2018/007925 patent/WO2019240322A1/ko active Application Filing
-
2019
- 2019-11-14 US US16/684,318 patent/US11232525B2/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101302507B1 (ko) * | 2011-04-11 | 2013-09-03 | 에스케이씨앤씨 주식회사 | Sns를 이용한 마케팅 서비스 방법 및 장치 |
KR20130089778A (ko) * | 2011-12-30 | 2013-08-13 | 주식회사 네오위즈인터넷 | 인터넷 정보에 기초하여 콘텐츠 서비스를 제공하는 방법, 콘텐츠 서비스 서버, 단말기, 기록매체 |
KR20140078008A (ko) * | 2012-12-13 | 2014-06-25 | 에스케이플래닛 주식회사 | 소셜네트워크 이용자의 영향력정보 결정 시스템 및 방법 |
KR20140094052A (ko) * | 2013-01-15 | 2014-07-30 | 에스케이플래닛 주식회사 | 관심대상 분석 시스템 및 그 방법, 그리고 이에 적용되는 장치 |
KR20180049591A (ko) * | 2016-11-03 | 2018-05-11 | 신철호 | 소셜인플루언서를 이용한 포스팅 방법 |
Also Published As
Publication number | Publication date |
---|---|
CN112313687A (zh) | 2021-02-02 |
US20200082476A1 (en) | 2020-03-12 |
KR102052344B1 (ko) | 2019-12-04 |
CN112313687B (zh) | 2024-05-07 |
JP2021527883A (ja) | 2021-10-14 |
JP7082216B2 (ja) | 2022-06-07 |
US11232525B2 (en) | 2022-01-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2019240322A1 (ko) | 소셜 네트워크를 이용한 영향력 측정 방법 및 장치 | |
CN108876526B (zh) | 商品推荐方法、装置和计算机可读存储介质 | |
WO2017200234A1 (ko) | 유동인구 패턴정보 기반의 미래입점객수 예측방법 및 장치 | |
CN107203897A (zh) | 一种产品推荐度的评价方法、装置及系统 | |
WO2012165859A2 (ko) | 사용자 심리지수에 기초한 조언 추천 시스템 | |
CN108022152A (zh) | 基于图像识别的用户商品自动推荐系统及推荐方法 | |
KR20190142500A (ko) | 화장품 추천 서비스 제공 방법 및 이를 실행하기 위한 시스템 | |
WO2016208932A1 (ko) | 휴대용 피부상태 측정장치, 피부상태 분석방법 및 이를 이용한 프로그램 | |
Kuo et al. | Automatic machine embroidery image color analysis system. Part I: Using Gustafson-Kessel clustering algorithm in embroidery fabric color separation | |
WO2020218651A1 (ko) | 소셜네트워크의 분석을 통해 사용자를 평가하는 서버, 소셜네트워크의 분석을 통해 사용자를 평가하는 방법 및 시스템 | |
WO2021137539A1 (ko) | 유전자 정보 개인 맞춤형 소셜 컨텐츠 정보 제공 시스템 및 그 방법 | |
CN112700307A (zh) | 一种基于数据分析的商品推荐方法 | |
CN108198631A (zh) | 循证医疗结果生成方法与装置 | |
Song et al. | Eye-tracking and social behavior preference-based recommendation system | |
CN103854206B (zh) | 一种分析人群特征的方法和设备 | |
CN107944761A (zh) | 基于人工智能消费维权指数企业投诉预警监测分析方法 | |
KR20190136337A (ko) | 소셜미디어 컨텐츠 기반 감정 분석 방법, 시스템 및 컴퓨터-판독가능 매체 | |
CN103366308A (zh) | 信息处理设备、信息处理方法和程序 | |
Prasad et al. | An effective assessment of cluster tendency through sampling based multi-viewpoints visual method | |
WO2017086710A1 (ko) | 창업을 위한 사업성 평가 지원 서비스 제공 시스템 및 그 방법 | |
WO2018117327A1 (ko) | 라이프스타일 분석 방법 및 그 시스템 | |
TWI629654B (zh) | Wisdom door city welcome product recommendation system and method thereof | |
KR102230255B1 (ko) | 소셜 네트워크를 이용한 영향력 측정 방법 및 장치 | |
WO2016169404A1 (zh) | 有价文件识别装置自修正识别方法及装置 | |
WO2011145766A1 (ko) | 이벤트 데이터 통합 변환 모듈 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 18922127 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2020569959 Country of ref document: JP Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 17/06/2021) |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 18922127 Country of ref document: EP Kind code of ref document: A1 |