KR102537141B1 - Method, device and system for providing beauty and lifestyle product sales service through micro-influencer linkage - Google Patents

Abstract

The present invention manages stores and shopping malls, and influencers perform sales activities through product reviews and SNS activities for stores and shopping malls located in the region, and use the processing results of keyword extraction and image recognition to analyze age and gender. , fashion, and lifestyle (lifestyle expressed as a data index) are calculated, and according to the sum of the calculated related indexes, influencers who review products and social media are recruited, and central management recruits Distribute the revenue earned by the influencer's sales activities.

Description

Method, device and system for providing beauty and lifestyle product sales service through linkage with micro influencers

The present invention relates to a method, apparatus, and system for providing a sales service for beauty and lifestyle products through linkage with micro-influencers, and more particularly, influencers earn profits related to their activities, and the system operates A method, device, and system for providing beauty and lifestyle product sales services through linkage with micro-influencers that promote product sales by recruiting the right influencers and maintain a win-win relationship between central management and influencers will be.

Prior art related to the present invention includes influencer marketplace, influencer marketing, style classification, and fashion styling. Patent Document 1 Brand-Influencer Marketplace provision method satisfies both the needs of brands that need promotion and the needs of influencers who want to earn income using social network services by mediating brands and influencers. In addition, the influencer marketing service method of Patent Document 2 can provide influencers with opportunities to experience various products or services and generate revenue. In addition, Patent Document 3 method, device, and computer program for classifying the style of a fashion item using a multi-labeling learned artificial intelligence model accurately classifies the style of a fashion item having a plurality of style attributes. In addition, the patent document 4 customer-customized fashion styling consultation purchase system and method enables online communication and purchase with a stylist selected by consumers.

However, the prior art calculates a related index including age group, gender, fashion, and lifestyle (expressing a lifestyle as a data index) using the processing result of keyword extraction and image recognition, and calculates a product according to the sum of the calculated related indexes. There is a problem of not being able to recruit influencers who do reviews and social media activities.

Registered Patent Publication No. 10-1986512 (2019.06.07) Publication No. 10-2021-0128614 (2021.10.27) Publication No. 10-2021-0030240 (2021.03.17) Publication No. 10-2022-0112417 (2022.08.11)

The present invention provides beauty and lifestyle product sales services through linkage with micro-influencers that manage stores and shopping malls, and influencers perform sales activities through product reviews and SNS activities for stores and shopping malls located in the region. It aims to provide methods, devices and systems.

In addition, the present invention calculates a relation index including age group, gender, fashion, and lifestyle (expressing a lifestyle as a data index) using the processing result of keyword extraction and image recognition, and according to the sum of the calculated relation index Another purpose is to provide a method, device, and system for providing beauty and lifestyle product sales services through linkage with micro-influencers that recruit influencers who do product reviews and SNS activities.

In addition, the present invention provides a method, apparatus, and system for providing a beauty and lifestyle product sales service through linkage with micro-influencers in which the central management distributes profits obtained by sales activities of influencers recruited by another. The purpose.

An apparatus for providing beauty and lifestyle product sales services through linkage with micro-influencers according to a preferred embodiment of the present invention collects data of product reviews and SNS (Social Networking Service) activities published by influencers on the Internet, , keyword extraction (31) for processing keyword extraction by determining whether the collected data includes keywords in the DB (9); Image recognition (33) that collects data on face, clothing style, skin tone, color tone, and makeup by recognizing images included in product reviews and SNS activities using neural networks; Using the processing results of the keyword extraction (31) and the image recognition (33), a correlation index including age group, gender, fashion, and lifestyle (lifestyle expressed as a data index) is calculated, and Analysis (32) of recruiting influencers (55) who do product reviews and SNS activities according to the sum; Settlement (34) for distributing profits obtained by sales activities of the influencer (55) recruited by the central management (51); and a controller 5 that performs the keyword extraction (31), the analysis (32), the image recognition (33), and the settlement (34).

In addition, the control unit 5 includes a data input step (S201) of collecting product reviews and SNS activity data published by the influencer on the Internet; A keyword extraction step (S202) of processing keyword extraction by determining whether the collected data includes keywords of the DB 9; a relation index analysis step (S203) of calculating a relation index using the processing result of the keyword extraction (31); and an influencer recruiting step (S204) of recruiting the influencer 55 according to the sum of the calculated association indices.

In addition, the control unit 5 includes a data input step (S201) of collecting product reviews and SNS activity data published by the influencer on the Internet; An image recognition step (S302) of collecting data on face, clothing style, skin tone, color tone, and makeup by recognizing images included in product reviews and SNS activities using a neural network; A face and clothing style analysis step of assigning a recognition index based on the collected data (S303); It is characterized in that it includes; an influencer recruiting step (S204) of recruiting the influencer 55 according to the sum of the indices.

In addition, the control unit 5 includes a state machine 20, and the state machine 20 includes event processing 21 for processing events according to key, mouse, and touch inputs; a state transition 22 for transitioning a state corresponding to an event; state processing (23) for processing routines for the transitioned state; the state includes the keyword extraction (31), the analysis (32), the image recognition (33), and the settlement (34); , The routine includes a keyword extraction routine, an analysis routine, an image recognition routine, and a settlement routine, and the controller 5 performs the event processing 21 corresponding to user manipulation and data input, the state transition 22, the The state machine 20 of the state processing 23 is executed, the event processing 21 processes events according to manipulation and input, and the state processing 23 performs calculations, displays, vibrations, alarms, , User manipulation, data input, and range, time, and level inputs for random input are verified, and system verification is performed according to state probabilities for user manipulation, data input, and random input.

In addition, the controller 5 inputs the keyword extraction (31), the analysis (32), the image recognition (33), and the settlement (34) as time-series data, and uses an artificial intelligence model (47) to The processing of the settlement (34) is performed, and the artificial intelligence model (47) is model selected (45) through repeated trial and error (46) of learning (43) and performance verification (44), and the settlement (34) is output. , and the control unit 5 uses the artificial intelligence model 47 to optimize the assignment of a related index, recruitment of influencers, and settlement, and the recruitment of influencers is related to the assignment of a related index and settlement, Depending on whether the settlement (34) between the central management (51) and the influencer (55) is made efficiently, influencer recruiting is processed, and the settlement (34) is the product of the influencer (55). It is related to review, SNS activity, association index, and activity index, and the control unit 5 applies these variables to the artificial intelligence model 47 to process influencer recruitment.

The present invention manages stores and shopping malls, and influencers perform sales activities through product reviews and SNS activities for stores and shopping malls located in the region, so influencers can have the effect of earning profits linked to their activities. can

In addition, the present invention calculates a relation index including age group, gender, fashion, and lifestyle (expressing a lifestyle as a data index) using the processing result of keyword extraction and image recognition, and according to the sum of the calculated relation index By recruiting influencers who do product reviews and SNS activities, the system can have the effect of promoting product sales by recruiting influencers suitable for the field in which it operates.

In addition, the present invention can have the effect of maintaining a win-win relationship between the central management and the influencers by distributing the profits obtained by the sales activities of the influencers recruited by the central management.

1 is a block diagram showing the configuration of an apparatus for providing a sales service for beauty and lifestyle products through linkage with a micro-influencer according to the present invention.
2 is an exemplary view showing the logistics configuration of the system for providing sales services for beauty and lifestyle products through linkage with micro-influencers according to the present invention.
3 is a flowchart showing a keyword analysis operation of the method of providing a sales service for beauty and lifestyle products through linkage with a micro-influencer according to the present invention.
4 is a flowchart showing an image analysis operation of the method of providing a sales service for beauty and lifestyle products through linkage with a micro-influencer according to the present invention.
5 is an exemplary diagram showing a state machine of the beauty and lifestyle product sales service providing device through linkage with the micro-influencer of the present invention.
6 is an exemplary view showing application of a neural network to explain the present invention.
7 is an exemplary view illustrating a configuration for verifying data errors to explain the present invention.
FIG. 8 is an exemplary diagram illustrating a system authentication configuration for granting authority to execute hardware resources, an operating system, an operation of a control unit, which is a core, and an operation of a control unit for explaining the present invention.

Hereinafter, a method, apparatus, and system for providing a sales service for beauty and lifestyle products through linkage with micro-influencers according to embodiments of the present invention will be described in detail with reference to the drawings. Hereinafter, descriptions of conventionally known matters are omitted or simplified to clarify the gist of the present invention. The configurations included in the description of the present invention operate in individual or complex combination configurations.

1 is a block diagram showing the configuration of an apparatus for providing a sales service for beauty and lifestyle products through linkage with a micro-influencer according to the present invention.

Referring to FIG. 1 , the terminal 6 includes keyword extraction 31 , analysis 32 , image recognition 33 , and settlement 34 .

The terminal 6 operates as a device for providing sales services for beauty and lifestyle products through linkage with micro-influencers. Unlike mega-influencers, micro-influencers are product reviewers and SNS (Social Networking Service) activists who engage in small-scale activities, and beauty and lifestyle represent a user class with various lifestyles.

The controller 5 performs keyword extraction (31), analysis (32), image recognition (33), and settlement (34).

Keyword extraction (31) collects product reviews and SNS activity data released by influencers on the Internet, and processes keyword extraction by determining whether the collected data includes keywords in DB (9). The controller 5 updates the keywords of the DB 9 using the crawling module, and the keyword extraction 31 adjusts the number of included keywords.

Analysis (32) uses the processing results of keyword extraction (31) and image recognition (33) to calculate association indices including age group, gender, fashion, and lifestyle (lifestyle expressed as data indices), Influencers (55) who do product reviews and SNS activities are recruited according to the sum of the relevant indexes.

Image recognition (33) uses a neural network to recognize images included in product reviews and SNS activities, and collects data on face, clothing style, skin tone, color tone, and makeup, and analysis (32) is based on the collected data An index is given, and an influencer (55) is recruited according to the sum of the index.

The settlement 34 distributes the profits obtained by the sales activities of the influencer 55 recruited by the central management 51. Settlement (34) manages administrator accounts and user accounts, and grants user accounts to influencers to access settlement data.

2 is an exemplary view showing the logistics configuration of the system for providing sales services for beauty and lifestyle products through linkage with micro-influencers according to the present invention.

Referring to FIG. 2 , distribution 52 includes a central management 51 , a store 53 , a shopping mall 54 , and an influencer 55 .

The central management (51) manages the store (53) and shopping mall (54), and the influencer (55) conducts sales activities through product reviews and SNS activities for the store (53) and shopping mall (54) located in the region. Do it.

3 is a flowchart showing a keyword analysis operation of the method of providing a sales service for beauty and lifestyle products through linkage with a micro-influencer according to the present invention.

Referring to FIG. 3 , the keyword analysis operation includes a data input step (S201), a keyword extraction step (S202), a correlation index analysis step (S203), and an influencer recruiting step (S204).

The data input step (S201) collects product reviews and SNS activity data released by the influencer on the Internet, and the keyword extraction step (S202) determines whether the collected data includes the keywords of DB (9) Keyword extraction is processed, the relevance index analysis step (S203) calculates the relevance index using the processing result of the keyword extraction (31), and the influencer recruitment step (S204) calculates the influence according to the sum of the calculated relevance index Recruit Unseo (55).

4 is a flowchart showing an image analysis operation of the method of providing a sales service for beauty and lifestyle products through linkage with a micro-influencer according to the present invention.

Referring to FIG. 4 , the image analysis operation includes a data input step (S201), an image recognition step (S302), a face and clothing style analysis step (S303), and an influencer recruiting step (S204).

The data input step (S201) collects product reviews and SNS activity data released by the influencer on the Internet, and the image recognition step (S302) recognizes the image included in the product review and SNS activity using a neural network and recognizes the face. , Clothing style, skin tone, color tone, and makeup data are collected, the face and clothing style analysis step (S303) assigns a recognition index based on the collected data, and the influencer recruiting step (S204) is based on the sum of the index Recruit influencer (55).

5 is an exemplary diagram showing a state machine of the beauty and lifestyle product sales service providing device through linkage with the micro-influencer of the present invention.

Referring to FIG. 5 , the state machine 20 includes event processing 21 , state transition 22 , and state processing 23 .

The state machine 20 includes event processing 21 for processing events according to key, mouse, and touch inputs; a state transition 22 for transitioning a state corresponding to an event; State processing 23, which processes routines for transitioned states; is performed. The states include keyword extraction (31), analysis (32), image recognition (33), and settlement (34), and routines include keyword extraction routines, analysis routines, image recognition routines, and settlement routines.

The controller 5 executes the state machine 20 of event processing 21, state transition 22, and state processing 23 corresponding to user manipulation and data input. Event processing 21 processes events according to manipulation and input, and state processing 23 performs calculation, display, vibration, and alarm, and inputs range, time, and level for user manipulation, data input, and random input. and performs system verification according to state probabilities for user manipulation, data input, and random input. System verification includes state machine verification based on sampling data.

6 is an exemplary view showing application of a neural network to explain the present invention.

Referring to FIG. 6, neural network learning selects a model through feature selection and algorithm selection from time-series data collected from various sensors such as temperature, altitude, and fingerprints, cameras such as images, infrared rays, and input devices such as lidar, learning, Model selection is repeated through repeated trial and error through the performance verification process. After performance verification is complete, an artificial intelligence model is selected.

The control unit 5 performs a deep learning algorithm using a neural network to determine the sensor value, uses training data to learn the neural network, and verifies the performance of the neural network with test data.

The control unit 5 inputs keyword extraction (31), analysis (32), image recognition (33), and settlement (34) as time-series data, and performs optimization of settlement (34) using an artificial intelligence model (47). do. The artificial intelligence model (47) is selected (45) through repeated trial and error (46) of learning (43) and performance verification (44), and the output of settlement (34) is optimized.

In addition, the control unit 5 may use the artificial intelligence model 47 to optimize the assignment of a correlation index, recruitment of influencers, and settlement. Recruitment of influencers is related to the assignment and settlement of the relevant index, and the recruitment of influencers is optimized depending on whether the settlement (34) between the central management (51) and the influencer (55) is efficiently performed. The settlement (34) is related to the influencer's (55) product review, SNS activity, association index, and activity index, and the control unit (5) applies these variables to the artificial intelligence model (47) to optimize influencer recruitment do.

7 is an exemplary view illustrating a configuration for verifying data errors to explain the present invention.

Referring to FIG. 7 , the control unit 5 stores sampling data, calculates a probability distribution by accumulating the number of occurrences for each size of the sampling data for a predetermined time, calculates a probability distribution for another predetermined time, and calculates two probabilities. By calculating the distribution difference, area difference, and difference distance accumulation (S101), sampling circuit abnormalities, data errors, and data changes can be predicted and responded to (S102). The control unit 5 may respond to the user by notifying the user of the prediction result, or the control unit 5 may respond to hardware failure, data error, or data change.

The sampling data includes keyword extraction (31), analysis (32), image recognition (33), and settlement (34) data, and the controller 5 responds to hardware failure, data error, and data change based on the sampling data. do.

The controller 5 looks at the trend of each probability distribution for a certain period of time, predicts an abnormal phenomenon among the probability distribution, responds to an abnormal accident, and informs the outside of normal operation if the data change is constant with respect to the probability distribution. In addition, the control unit 5 feeds back the data change rate in order to adjust the predetermined time interval. For example, if the data change rate is large, the certain time interval is increased, and if the data change rate is small, the certain time interval is decreased.

FIG. 8 is an exemplary diagram illustrating a system authentication configuration for granting authority to execute hardware resources, an operating system, an operation of a control unit, which is a core, and an operation of a control unit for explaining the present invention.

Referring to FIG. 8 , the present invention includes a processor 1 , a memory 2 , an input/output device 3 , an operating system 4 , and a control unit 5 .

The processor 1 is a CPU (Central Processing Units), a GPU (Graphic Processing Unit), an FPGA (Field Programmable Gate Array), and an NPU (Neural Processing Unit). ) executes the executable code.

The memory 2 includes a permanent mass storage device such as random access memory (RAM), read only memory (ROM), disk drive, solid state drive (SSD), flash memory, etc. can do.

The input/output device 3 is an input device, such as a camera, keyboard, microphone, mouse, etc., including an audio sensor and/or an image sensor, and an output device, such as a display, speaker, haptic feedback device, etc. device may be included.

The operating system 4 may include Windows, Linux, IOS, a virtual machine, a web browser, and an interpreter, and supports tasks, threads, timer execution, scheduling, resource management, graphics, font processing, communication, and the like.

The control unit 5 determines the state of the input/output device 3 by sensor, key, touch, and mouse input under the support of the operating system 4, and performs an operation according to the determined state. The control unit 5 performs task scheduling using a timer and thread as a parallel execution routine.

The control unit 5 determines a state using the sensor value of the input/output device 3 and performs an algorithm according to the determined state.

Referring to FIG. 8 , the system authentication configuration includes a terminal 6 including a control unit 5 and an authentication server 7 .

The terminal 6 duplicates the data channels, receives the key value and biometric information of the terminal 6, and requests user authentication from the authentication server 7 through the first data channel. It is displayed on the display and transmitted to the authentication server (7).

The terminal 6 inputs the kit value displayed on the display of the terminal 6 and transmits it to the authentication server 7 through the second data channel along with user information. The terminal 6 requests the authentication server 7 to authenticate the system installed in the terminal 6 using the kit value and user information. The kit value of the terminal 6 can be generated from computer-specific information such as the CPU manufacturing number and the address of the Ethernet chip. The terminal 6 may obtain user information through face recognition using a camera, voice recognition using a microphone, and handwriting recognition using a display, and may use it for authentication.

The authentication server 7 receives the kit value from the terminal 6, receives the kit value and user information from the terminal 6 through a duplicated data channel, compares the kit value of the terminal 6 with the user information, and returns the user information Correspondingly, authentication for system use of the terminal 6 is processed. The authentication server 7 transmits the authentication result to the terminal 6 to allow the user to use the system. Due to the duplicated data channel of the terminal 6, loss of kit value can be minimized.

The authentication server 7 performs a history analysis of user information, and compares and determines consistency and change of user information over time. In the history analysis, if the user information shows consistency, the user's use is permitted, and if it shows change, the user's use is not permitted. When the user information shows consistency, the user's use of the system is permitted, thereby strengthening security to prevent a user whose user information has been altered from accessing the system.

The authentication server 7 assigns weights to consistency, change, frequency, frequency trend, and high frequency, and blocks access by untrusted users with a combination of weights. For example, if the frequency threshold is exceeded, access by untrusted users is blocked in proportion to the excess cumulative number, and users attempting access over a long period of time can be authenticated. At this time, additional authentication is requested for untrusted users.

The terminal 6, which is a means of authenticating the use of the system, does not directly connect to the system, but forms a detour through the authentication server 7, so that the network constituting the Internet network is composed of an internal network and an external network, and the IP address setting process When this is cumbersome, there is an advantage in that the authentication process using the terminal 6 is smoothly performed. At this time, the system is mounted on the terminal 6, the terminal 6 serves as an authentication terminal means, and the authentication server 7 serves as an authentication server means.

The cloud 12 is modularized by the container 7 under the support of the operating system 4 that manages the processor 1, memory 2, input/output device 3, and communication unit 6, and the web 8, DB ( 9), protocol 10, and library 11 services are provided, and the control unit 5 executes a cloud application using the container 7 service. A standard software package, called a container 7, bundles the application's code along with relevant configuration files, libraries 11 and the dependencies required to run the app.

The cloud 12 performs integrated control of a plurality of terminals 6, stores sensor values received from the terminals 6, monitors them over time, processes operation errors of the terminals 6, and transmits error messages to other terminals. The terminal 6 is notified, and the control target terminal 6 is switched and controlled.

The cloud 12 calculates the frequency concentration for the sensor value probability frequency of the terminal 6, increases the system resources allocated to the monitoring operation when the frequency concentration exceeds a certain threshold value, and stops the monitoring operation when the system resources are exhausted. do. The cloud 12 divides the component of the sensor value having a high frequency concentration to distribute the frequency concentration, and repeats the separation and distribution operation until the frequency concentration decreases below a predetermined threshold value.

The present invention is not limited to the specific preferred embodiments described above, and various modifications can be made by anyone skilled in the art without departing from the gist of the present invention claimed in the claims. Of course, such changes are within the scope of the claims.

1: Processor
2: memory
3: I/O device
4: operating system
5: control unit
6: Terminal
7: authentication server
8: web
9: DB
11: Library
12: cloud
14: container
16: Department of Communications
20: State Machine
21: Event Handling
22: state transition
23: State Handling
31: Keyword Extraction
32: analysis
33: image recognition
34: Settlement
41: time series data
42: feature selection
43: Learning
44: Performance Verification
45: select
46: repeated trial and error
47: AI model
51: central management
52: Logistics
53 Store
54: shopping mall
55: Influencer

Claims (3)

Keyword extraction (31 );
Image recognition (33) that collects data on face, clothing style, skin tone, color tone, and makeup by recognizing images included in product reviews and SNS activities using neural networks;
Using the processing results of the keyword extraction (31) and the image recognition (33), a correlation index including age group, gender, fashion, and lifestyle (lifestyle expressed as a data index) is calculated, and Analysis (32) of recruiting influencers (55) who do product reviews and SNS activities according to the sum;
Settlement (34) for distributing profits obtained by sales activities of the influencer (55) recruited by the central management (51); and
A controller 5 performing the keyword extraction 31, the analysis 32, the image recognition 33, and the settlement 34;
The control unit 5,
A data input step (S201) of collecting data on product reviews and SNS activities published by the influencer on the Internet;
A keyword extraction step (S202) of processing keyword extraction by determining whether the collected data includes keywords of the DB 9;
a relation index analysis step (S203) of calculating a relation index using the processing result of the keyword extraction (31); and
Performing an influencer recruiting step (S204) of recruiting the influencer 55 according to the sum of the calculated association indexes;
The control unit 5,
A data input step (S201) of collecting data on product reviews and SNS activities published by the influencer on the Internet;
An image recognition step (S302) of collecting data on face, clothing style, skin tone, color tone, and makeup by recognizing images included in product reviews and SNS activities using a neural network;
A face and clothing style analysis step of assigning a recognition index based on the collected data (S303);
Performing an influencer recruiting step (S204) of recruiting the influencer 55 according to the sum of the indices,
The sampling data includes a setting profile and application operation data, and the control unit 5 stores the sampling data, calculates a probability distribution by accumulating the number of occurrences for each size of the sampling data for a predetermined time, and calculates a probability distribution for another predetermined time. Calculate the probability distribution of and calculate the difference, area difference, and difference distance accumulation of the two probability distributions (S101) to predict sampling circuit abnormality, data error, and data change, and based on the sampling data, hardware failure, data error, data respond to change,
The terminal 6 duplicates the data channels, receives the key value and biometric information of the terminal 6, requests the authentication server 7 for user authentication through the first data channel, and displays the generated key value on the display and transmitted to the authentication server 7,
Enter the kit value displayed on the display of the terminal (6), transmit it to the authentication server (7) through the second data channel along with user information, and use the kit value and user information to load the terminal (6). Requesting authentication of the authentication server 7,
The authentication server 7 receives the kit value from the terminal 6, receives the kit value and user information from the terminal 6 through a duplicated data channel, compares the kit value of the terminal 6 with user information, , processing authentication for system use of the terminal 6 by matching user information,
Consistency, change, frequency, frequency trend, and high frequency are weighted to block access from untrusted users with a weighted combination, and when the frequency threshold is exceeded, access from untrusted users is blocked in proportion to the excess cumulative number. An apparatus for providing a sales service for beauty and lifestyle products through linkage with a micro influencer, characterized in that authentication is processed for a user attempting access over a long period of time. delete delete

Images