WO2020130369A1

WO2020130369A1 - Artificial intelligence analysis system for establishing online marketing strategy

Info

Publication number: WO2020130369A1
Application number: PCT/KR2019/015766
Authority: WO
Inventors: 김윤희
Original assignee: 주식회사 리틀페이지
Priority date: 2018-12-17
Filing date: 2019-11-18
Publication date: 2020-06-25
Also published as: KR102018888B1

Abstract

An artificial intelligence analysis system according to an embodiment of the present invention comprises: a server; a user device for sending, to the server, information about a request to enter into a partnership and a purchaser's request for purchase of goods generated on the basis of SNS, as a user inputs same; and a partner company device for uploading information about goods to be sold to the server, wherein the server comprises: a communication unit for collecting information required to perform data mining on the basis of artificial intelligence; a storage unit for storing result values yielded on the basis of the artificial intelligence and data for performing the data mining collected by the communication unit; and a control unit which enters into a partnership with a specific partner company selected according to the request to enter into a partnership from the user device, provides information about goods to be sold, provided by the partner company, to the user device, upon confirming a goods purchase request event and a sales amount payment event of a purchaser from the user device, determines that a purchase has occurred and requests delivery of purchased goods to the partner company device, and controls a certain percentage of the sales amount to be allocated as a commission to the user device.

Description

Artificial intelligence analysis system for establishing online marketing strategy

The present invention relates to an artificial intelligence analysis system for establishing an online marketing strategy.

Recently, marketing and sales activities on the web including SNS have been actively conducted. According to this trend, interest in entrepreneurship using the Internet and marketing activities using SNS is also increasing.

The present invention was designed to provide artificial intelligence-based feedback information on the sale of goods made on the web including SNS.

In addition, the present invention is designed to provide personalized advertisements in response to each type of information based on the calculated type information of customers for the sale of goods made on the web.

An artificial intelligence analysis system according to an embodiment of the present invention includes a communication unit that collects information required to perform data mining based on artificial intelligence; A storage unit for storing the result value calculated based on artificial intelligence and data for performing data mining collected by the communication unit; According to a request to enter a partnership from a user device, a partnership with a specific partner company selected is provided, and information on a sale item provided from the partner company is provided to the user device side, and a purchase request event of a buyer's product and a payment settlement event are confirmed from the user device. The server includes a control unit, a request to conclude a partnership, and a SNS-based control unit that determines that a purchase has occurred, and requests delivery of purchased items to a partner company's device, and controls a certain percentage of the sales amount to be allocated as a commission to the user device side. It includes a user device that transmits information about the purchase request of the purchaser generated by the user to the server and a partner company device that uploads information about the product to be sold to the server, and the control unit includes the number of views and comments Based on at least one of the criteria, we collect public SNS information that is determined to have a degree of topicality higher than or equal to a predetermined value, and sample only the information related to the field of sales goods of the registered partner companies among the collected SNS information, Performs a data transformation operation that assigns codes according to data characteristics to the sampled data, and performs correlation analysis on SNS information that performs the data transformation operation to derive the result values for purchase trends and issue keywords Artificial intelligence analysis unit; characterized in that it comprises a.

According to an embodiment of the present invention, feedback information on sales using SNS can be calculated based on artificial intelligence, and accordingly, there is an effect of providing information on establishing a marketing strategy to users and sellers in a more convenient manner. .

An embodiment of the present invention classifies interests of major customers by type and calculates interest type information of each customer based on information obtained through the user's SNS account of the user's main customer, so that promotional activities according to customer characteristics can be performed. It works.

1 is a view showing the configuration of an artificial intelligence analysis system according to an embodiment of the present invention.

2 is a view showing the configuration of the server according to an embodiment of the present invention.

3 is a flowchart illustrating an overall operation sequence of an artificial intelligence analysis system according to an embodiment of the present invention.

4 is a flowchart illustrating a procedure related to a partnership according to an embodiment of the present invention.

5 is a flowchart illustrating a sequence of an article sales and feedback operation by the AI analysis system according to an embodiment of the present invention.

The present invention can be applied to various changes and can have various embodiments, and specific embodiments will be illustrated in the drawings and described in detail.

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 drawing, similar reference numerals are used for similar components.

When a component is said to be'connected' or'connected' to another component, it is understood that other components may be directly connected or connected to the other component, but other components may exist in the middle. It should be. On the other hand, when a component is said to be'directly connected' or'directly connected' to another component, it should be understood that no other component exists in the middle.

The terms used in this application are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this application, terms such as'include' or'have' are intended to indicate that a feature, number, step, action, component, part, or combination thereof described in the specification exists, one or more other features. It should be understood that the existence or addition possibilities of fields or numbers, steps, operations, components, parts or combinations thereof are not excluded in advance.

As illustrated in FIG. 1, the artificial intelligence analysis system according to an embodiment of the present invention may include a server 100, a user device 200, and a partner company device 300.

The server 100 may serve as an intermediary so that a partnership between a user and a partner company is concluded. To this end, the server 100 may receive information on a sale item that the user wants to sell and promote through SNS, and the server 100 may present a list of companies corresponding to the sale item input by the user. For example, assuming that the user has requested'children's clothing' as an item to be sold, the server 100 may present a list of partner companies responsible for selling children's clothing.

In addition, the server 100 may perform a partnership agreement with a selected partner company according to a user's partner company selection, and the server 100 may support a user to receive information on merchandise available for sale from a partner company after the partnership is concluded. The user may perform sales and promotion activities by processing information on the sale items provided by the partner companies on the user device 200 and uploading them on a personal SNS.

Subsequently, when the user uploads photos and articles for promotion and sales based on the information on the goods sold by the partner company through the server 100 to his SNS, he/she can check customer inquiries and purchase requests generated through this. . According to various embodiments of the present disclosure, when it is determined that a query and a purchase request received through the SNS of the user account are generated, the user may provide the generated purchase related information to the server 100. Accordingly, the server 100 may collect purchase-related information in a manner such as monitoring while the user checks his SNS.

In addition, the server 100 collects purchase-related information in a manner monitored by the user through the user device 200, and the server 100 directly inputs purchase-related information through an app or web supported by the server 100 through the user device 200. Related information can be collected through actions. In addition, the server 100 may analyze a user's purchase pattern and preferred item-related information based on artificial intelligence based on the collected purchase-related information. The information calculated based on the artificial intelligence may be provided for feedback to the user device 200 and the device 300 of the partner company, and accordingly, the user and partner company can refer to the information for feedback when establishing a promotional strategy and a product purchase plan. There will be.

In addition, when the purchase request event delivered by the user is confirmed, the server 100 may transmit the product to the corresponding partner company and request the partner company to deliver the corresponding product. In addition, the server 100 may control to allocate a commission, which is calculated as a certain percentage of the sales amount (or a certain amount per sale, etc.) to the user's side every time an item is sold.

According to various embodiments of the present disclosure, when the user becomes a'recommender', the server 100 may allocate a predetermined commission to the user who becomes the recommender. According to an embodiment of the present invention, a user who has completed the entrepreneurship and marketer education provided by the server 100 can be completely sold through a SNS account operated by himself/herself to a specific person (entrepreneurship and marketer education provided by the server 100). If so, there may be a right to receive a commission accordingly. In this case, a user who has the right to receive the commission may be referred to as a'recommender'. Accordingly, the server 100 may distinguish commissions to be paid in response to the sale of goods to a user, and commissions to be paid as set as a'recommended person', and perform commission payment.

2 is a diagram showing the configuration of the server 100 according to an embodiment of the present invention.

As illustrated in FIG. 2, the server 100 according to an embodiment of the present invention may include a communication unit 110, a storage unit 120, and a control unit 130. In addition, the control unit 130 may include a user education management unit 131, a partnership conclusion unit 132, a sales item information processing unit 133, a purchase information processing unit 134, an artificial intelligence analysis unit 135, and a commission management unit 136.

First, the communication unit 110 may use a network to transmit and receive data between a user device and a server, and the type of the network is not particularly limited. The network may be, for example, an Internet Protocol (IP) network that provides a large data transmission/reception service through an Internet Protocol (IP) or an All IP network that integrates different IP networks. In addition, the network is a wired network, a Wibro (Wireless Broadband) network, a mobile communication network including WCDMA, a High Speed Downlink Packet Access (HSDPA) network and a mobile communication network including a Long Term Evolution (LTE) network, LTE advanced (LTE-A) ), 5G (Five Generation), one of the mobile communication network, satellite communication network and Wi-Fi (Wi-Fi) network, or may be made by combining at least one of them.

The communication unit 110 according to an embodiment of the present invention may receive information related to a sale item from a partner company. The communication unit 110 may receive information about a purchase request generated through the SNS from the user side and other information monitored through the user SNS through wireless communication.

In addition, the communication unit 110 may receive various data required to perform data mining based on artificial intelligence. For example, data required for AI-based analysis may include a user's (member's) SNS post, a comment, and a conversation history with a buyer. Data required for AI-based analysis may include SNS account or SNS post information having a topicality (eg, it can be determined based on the number of views, number of comments, number of followers, etc.) above a predetermined reference value. In addition, data required for artificial intelligence-based analysis may include information such as real-time search words of portal sites, news articles, and broadcast clips. In addition, data required for artificial intelligence-based analysis may include information such as sales items and reviews of internet shopping malls.

The storage unit 120 may include an internal memory or an external memory. The internal memory includes, for example, volatile memory (eg, dynamic RAM (DRAM), static RAM (SRAM), or synchronous dynamic RAM (SDRAM)), non-volatile memory (eg, OTPROM (one time programmable ROM (PROM), programmable ROM (PROM), erasable and programmable ROM (EPROM), electrically erasable and programmable ROM (EEPROM), mask ROM, flash ROM, flash memory (e.g. NAND flash or NOR flash, etc.), hard drives, Or it may include at least one of a solid state drive (SSD).

The external memory may be a flash drive, such as compact flash (CF), secure digital (SD), micro secure digital (Micro-SD), mini secure digital (SD-SD), extreme digital (XD), It may further include a multi-media card (MMC) or a memory stick. The external memory may be functionally and/or physically connected to the electronic device through various interfaces.

The storage unit 120 according to an embodiment of the present invention may store a result value calculated based on artificial intelligence. In addition, the storage unit 120 may store information collected from various portals and SNS for data mining.

In addition, the storage unit 120 may store educational content related to a user selling items through SNS.

The storage unit 120 may store information related to a sale item received from a partner company.

The controller 130 may also be referred to as a processor, a controller, a microcontroller, a microprocessor, or a microcomputer. Meanwhile, the control unit may be implemented by hardware or firmware, software, or a combination thereof.

In the case of implementation by firmware or software, an embodiment of the present invention may be implemented in the form of a module, procedure, function, etc. that performs the functions or operations described above. The software code can be stored in the memory and driven by the control unit. The memory may be located inside or outside the user terminal and the server, and may exchange data with the control unit by various means already known.

The control unit 130 according to an embodiment of the present invention may include a user education management unit 131, a partnership conclusion unit 132, a sales item information processing unit 133, a purchase information processing unit 134, an artificial intelligence analysis unit 135, and a commission management unit 136.

First, the user education management unit 131 may perform a series of operations for matching the educationable mentors 1:1 by responding to the user's education request. The user education management unit 131 may receive information on a sales area of interest, a type of main use SNS, and the like, and may match an appropriate education program and an educator (mentor) from the user. In addition, if the user wants to set a specific member he or she has discovered through SNS as an educator, the user can enter the educator ID or identification number he or she wants in the server 100, and the user education management unit 131 requests such You can connect mentor and mentee by combining.

Thereafter, the user education management unit 131 may manage the progress of the education after the mentor and the mentee are connected 1:1, and the education content may be related to starting a business, operating a mall through SNS, and the like. Information related to education can be made using an instant messenger, telephone, etc., and the user education management unit 131 checks the number of times the education was conducted by these means, the type of content delivered from the mentor to the mentee, and determines whether the education is completed. can do. In addition, according to various embodiments, the user education management unit 131 may educate users who want to be directly trained based on educational contents uploaded by mentors who have completed training provided by the server 100, and check the number of attendance, content play time, and assignments Mentees that satisfy the evaluation criteria such as can be treated as having completed training. The user education management unit 131 may grant the authority to educate another user when the user who has completed the training provided by the server 100 satisfies an immediate or additional predetermined criterion (eg, a product sales history). .

The above education may be provided for a fee, and a part of the education expenses obtained from the user who wants to complete the education may be paid as a commission for implementing the education to the mentor who conducted the education and the recommender who invited the mentee. According to various embodiments, the mentor and the recommender may or may not be the same person, and if they are not the same person, commissions for the mentor and the recommender may be set to different amounts.

On the other hand, if the user training management unit 131 grants the user who has completed training to the other user to perform training, the user may perform an activity for recruiting other users who will act as marketers in order to receive a commission. According to various embodiments, when a specific user inputs a training request to the server 100 to complete training, recommender information may also be registered, and at the same time, the recommender may be designated as a mentor. The user education management unit 131 can monitor the mentor's mentee education activities as soon as the mentee-mentor relationship is established in this way, or the mentor can report their education activities to the server 100 side. The user education management unit 131 may perform an operation such as checking the reported education activity, evaluating mentee's weaknesses and strengths, and recommending additional education materials to compensate for the vulnerability.

When confirming that the user has completed the training course, the user education management unit 131 may grant qualification to perform a partnership with an arbitrary company.

The partnership fastening unit 132 may provide a list of merchandise sellers corresponding to information related to a user's sales item field, and may transmit a partnership fastening request to a device of a corresponding company as a user selects a specific company. The partnership fastening unit 132 may confirm that both the user and the company agree to the partnership fastening, and may perform an operation for bilateral partnership fastening in response thereto. For example, the partnership fastening unit 132 may provide sales-related information to the user device side as soon as the sales-related information such as photos, size information, and shipping information for the sales goods provided by the partner company is uploaded or requested by the user. Can.

In addition, the partnership conclusion unit 132 may determine the main visitor type of the user account based on comments of other accounts registered in the SNS of the user account, pre-registered posting content, etc., according to various embodiments. The matching suitable selling product and the suitable partner type may be calculated and based on this, recommendation partner company information may be provided.

The sales article information processing unit 133 may perform an operation of confirming that information on a sale article is uploaded to the server 100 side from a plurality of partner companies. At this time, the information on the sales items provided by partner companies may be in a form in which only essential information (eg, size, price, color, etc.) is described, not processed to satisfy the purchase needs of actual buyers. Accordingly, the user can perform the publicity and sales promotion activities by receiving the information on the sale goods by the information delivery operation performed by the sales goods information processing unit 133 and then processing them appropriately and uploading them on their SNS. .

Subsequently, after the promotion and sales promotion activities are performed on the user's SNS, a purchase request for a specific product may be generated. Accordingly, the user may check the purchase request made on his SNS (eg, receive a purchase request message through an SNS messenger), and input the purchase request to the server. In this case, the purchase information processing unit 134 may confirm that information on a purchase request input by the user is input, and may perform a subsequent operation corresponding thereto. For example, the purchase information processing unit 134 may check information (eg, size, quantity, etc.) of a product requested to be purchased, a vendor of the product requested to be purchased, based on the purchase request information input by the user. In addition, the purchase information processing unit 134 may support payment for a product requested to be purchased. For example, it may support virtual account information for each company and a payment link. Accordingly, the user can provide payment information so that the sales amount corresponding to the product to be purchased can be settled to customers who have requested the purchase through their SNS.

According to various embodiments of the present disclosure, the purchase information processing unit 134 may check inquiry information such as messages and comments received through the user's SNS at the user's request, collect the contents of the received inquiry information, and collect the collected contents in natural language. It can be classified into items such as purchase requests and product inquiries. In order to perform the monitoring and information collection function, the purchase information processing unit 134 may activate the monitoring function as the monitoring function is selected on an app or web supported by the server 100 according to a user request. When the monitoring function is activated and the user performs an operation for checking SNS comments and messages, the purchase information processing unit 134 automatically checks the contents of the comments and messages to extract only inquiry information (messages or comments) related to the purchase request. can do. Further, the purchase information processing unit 134 may analyze the contents of the inquiry information related to the purchase request, and extract detailed information such as the product information, quantity, and delivery time of the purchase request based on the result. The purchase information processing unit 134, after re-confirming the extracted detailed information to the user according to various embodiments and when the user processes the approval, may be immediately delivered to the partner company's device 300 and request delivery.

In general, an alarm signal may be provided in response to an event such as a chat message and comment registration received in conjunction with a user's SNS. According to various embodiments of the present disclosure, the purchase information processing unit 134 may automatically provide an answer to the inquiry information when an alarm event for the inquiry information is confirmed. For example, the purchase information processing unit 134 is automatically linked to the user's SNS account at the user's request and automatically selects the corresponding notification information as soon as a notification notifying that a new comment registration and message reception event has occurred is generated. Message, etc.) on the screen. Accordingly, the purchase information processing unit 134 may check the content displayed on the screen for the inquiry information delivered to the user SNS account in real time, and collect and analyze the contents of the inquiry information. Subsequently, the purchase information processing unit 134 may input and provide an answer content corresponding to the analyzed inquiry content.

In addition, the purchase information processing unit 134 may classify a case in which an answer content corresponding to an inquiry content is automatically input and a case in which it is not, according to a word inclusion state. For example, the user can set a direct response to a comment that includes the word'price', and accordingly, the purchase information processing unit 134 responds to a comment that includes the word'price' and asks'price is a message. Please enter a pre-set phrase such as'Please.' On the other hand, the purchase information processing unit 134 can confirm that the customer has entered a comment such as'How long is the L size' for a specific product image uploaded to the user's SNS (eg, Instagram), in response to this Of the pre-registered total size information (eg, S, M, L, XL, etc.), only size information corresponding to L can be automatically entered as a comment.

The purchase information processing unit 134 analyzes the monitored comments and message information according to various embodiments, and when it is determined that it is a purchase request, automatically transmits a message to the purchased user account, but payment related information (eg, payment link information, (Passbook deposit information). In addition, the purchase information processing unit 134 may check whether payment is completed. The purchase information processing unit 134 may automatically send a completion message to the contacting user account when payment request and payment are completed by a user message, comment, or the like. In addition, when the payment is completed, the purchase information processing unit 134 may transmit purchase related information to a partner company. Accordingly, when the partner company receives the purchase-related information by the purchase information processing unit 134, it is possible to proceed with subsequent procedures such as purchase of goods and delivery of goods.

The order and sales process through SNS may be generally performed by the purchase information processing unit 134 as described above. However, the server 100 according to an embodiment of the present invention may perform the operation of calculating feedback information using artificial intelligence through the artificial intelligence analysis unit 135 as well.

The AI analysis unit 135 serves to provide users with information to sell and promote goods to be sold through their SNS, and to provide users with information on goods to be sold, to purchase and manage goods, and to deliver goods requested to be purchased. Feedback information calculated based on artificial intelligence can be provided to all partners. In addition, the AI analysis unit 135 may present a decision related to the establishment of a sales strategy, selection of main sales items, etc. to the user and partner companies in response to feedback information analyzed based on the AI. For example, the AI analysis unit 135 may check conversation data in text form between the user 200 and the purchaser provided from the user device, and perform AI-based analysis on the conversation data on the SNS.

The AI analysis unit 135 is a content mainly asked by customers who have purchased a specific product based on AI, the age range of the specific product, the reason for purchasing the specific product (gift, group order, etc.), the product of interest of a specific customer. Information such as information on types, inquiry keywords (e.g., radon) increased above the reference value, major complaint types, major return or exchange request types can be calculated. And accordingly, the AI analysis unit 135 may present a sales strategy based on the calculated feedback information. If it is determined that the inquiry keyword increased by a preset percentage or more is a'fluorescent substance', the'fluorescent substance' is included. It is possible to analyze the main question breakdown and determine that the question of whether or not a fluorescent substance has been detected has increased. In addition, the artificial intelligence analysis unit 135 may calculate a strategy for uploading inspection results for detection of fluorescent substances in a specific sales item, and may present it as feedback to a partner company. In addition, the artificial intelligence analysis unit 135 may calculate a sales strategy to emphasize that a fluorescent material has not been detected for a specific sales item, and may provide feedback to the user.

Specifically, the AI analysis unit 135 may operate based on data mining when analyzing data and calculating feedback information. The AI analysis unit 135 not only receives inquiries and complaints received through the SNS accounts of members already registered in the server 100, but also inquiries and complaints by product type for other public users' SNS and shopping mall web pages. Information can be collected. In addition, the artificial intelligence analysis unit 135 may collect content such as posts and comments, celebrity SNS account posts and comments based on the number of views and reactions (eg, number of likes, number of comments, etc.) on the SNS. Through this, the AI analysis unit 135 may perform data mining and AI-based analysis operations to calculate result values of real-time SNS users' main interests and purchase trends.

First, the artificial intelligence analysis unit 135 may collect SNS information that is determined to have a topical degree greater than or equal to a preset value (eg, based on a number of views and comments) among a plurality of published SNS information. Thereafter, the artificial intelligence analysis unit 135 may perform an operation of sampling information to be used for data mining among the collected SNS information. Sampling may be, for example, an operation of extracting only SNS information (eg, children's clothing photos, children's photos, etc.) that are determined to be related to the user's sales field or the sales item field of the pre-registered partner company (eg, children's clothes). .

Thereafter, the artificial intelligence analysis unit 135 may perform a data conversion operation of the extracted data. At this time, the artificial intelligence analysis unit 135 may perform operations such as deleting duplicate SNS information, and code according to the characteristics of the collected information. For example, the artificial intelligence analysis unit 135 may assign codes according to the color of children's clothes, tag keywords, etc. to the sampled children's clothes images.

The artificial intelligence analysis unit 135 may perform a modeling operation to perform association analysis and cluster analysis on SNS information that has undergone the process of data collection, sampling, and data conversion according to the topic. Similarly, the AI analysis unit 135 may collect posts (eg, broadcast, news articles, etc.) that are determined to be topical from general web pages other than SNS, and perform sampling, data conversion, and modeling processes through them. Can.

The artificial intelligence analysis unit 135 may perform an artificial intelligence analysis operation as described above, thereby deriving a result value for a purchase trend, an issue keyword, and the like. The AI analysis unit 135 responds to, for example, when a'fluorescent material' is derived from a keyword related to children's clothing that has increased topicality over a predetermined period of time, the AI analysis unit 135 increases the buyer's interest in the'fluorescent material'. It can be determined and information about it can be posted on the app and the web supported by the server 100. Accordingly, the AI analysis unit 135 may help users and partner companies to check issue information related to their products and establish a sales strategy.

According to various embodiments of the present disclosure, the AI analysis unit 135 may calculate consumer's main curiosity about a specific product and additional information required based on information collected about user inquiries and complaints. For example, if the AI analysis unit 135 determines that a material inquiry for a specific product occurs more than a preset number of times based on real-time input comment information monitored by the purchase information processing unit 134, the material information for the product is missing or insufficient. You can judge it as not. In addition, the AI analysis unit 135 may request a partner company to provide additional material-related information for the corresponding product. At this time, the request for providing additional information may be made through push notifications.

In addition, according to various embodiments of the present disclosure, the AI analysis unit 135 may perform various procedures for providing user-customized advertisements.

For example, the artificial intelligence analysis unit 135 may extract the SNS account list of the main question customer, the account list registered as a friend (eg, following list, follow list, etc.), the SNS account list of the main purchasing customer, and the like. Based on this, posts previously uploaded to the SNS account of the main customer can be collected. At this time, the collected information may be provided from a user device. Alternatively, the collected information (eg, comments) may be obtained by accessing a user's SNS account registered in the server. Specifically, the artificial intelligence analysis unit 135 according to an embodiment of the present invention may collect the contact information of a customer who sent a question about a product and a purchase request customer as a contact information of a user (member), and based on this, link with the corresponding contact information SNS account of an old customer.

According to this process, the AI analysis unit 135 may acquire information related to the post uploaded to the SNS from the SNS accounts of the major customers. The post-related information may include, for example, content such as photos and videos uploaded to the customer's SNS account, posts uploaded to the SNS account, tags (hash tags), and comments on the post. have. The artificial intelligence analysis unit 135 may perform an operation of collecting customer-related post information and classifying customer types according to tastes (or interests) based on the information.

First, the AI analysis unit 135 may perform a customer type classification operation according to taste through collected post-related information. In order to classify customer types according to taste, the artificial intelligence analysis unit 135 may collect product model names of products that customers have shown interest in. When marketing using SNS, photos or videos of products are uploaded as posts on SNS. Using this point, the artificial intelligence analysis unit 135 may determine a product name corresponding to a post to which a customer has left a comment as a product that the customer is interested in and perform a subsequent operation. The AI analysis unit 135 may store and store the post image of the SNS account information of the customer who registered the comment when the customer leaves a comment on the post of the user's SNS. Alternatively, the artificial intelligence analysis unit 135 may match the customer SNS account and product model information corresponding to the post image, such as "th_esw (customer SNS account)-M045 (product model name)", and store it as customer-specific interest product information. In addition, data about a product that a specific customer has purchased or showed interest through a plurality of users (members) may be accumulated in the storage unit 120 of the server by the artificial intelligence analysis unit 135. Accordingly, the artificial intelligence analysis unit 135 may determine a company (a partner company) of a product that a particular customer mainly pays attention to, and a type of an item that mainly pays attention.

According to various embodiments of the present disclosure, the AI analysis unit 135 matches the SNS account information of a customer who has registered a comment with a post image with a comment and stores it as product information of interest for each customer. Product type classification can be performed and stored. That is, the product type information of the customer's SNS account and the post image may be matched and stored as product information of interest for each customer. For example, when the selling item is assumed to be clothing through image sensing, the artificial intelligence analysis unit 135 may perform classification by application such as inner, outer, top, and bottom, and classification by design such as material, pattern, and color. The AI analysis unit 135 may calculate a conclusion that a specific customer prefers a black image in the case of bottoms.

Alternatively, the artificial intelligence analysis unit 135 performs a matching operation with image information pre-stored in a server, thereby providing detailed information of a sale product (eg, a partner company selling an actual product, size information of the product, etc.) through the matching operation. ). Accordingly, the artificial intelligence analysis unit 135 may acquire size information of a product that a customer mainly purchases or is interested in, thereby inferring a customer's body size and a customer's family body size (eg, a child's body size). I can do it.

For example, if it is determined that the size of children's clothes that a particular customer has mainly paid attention to for a predetermined period or more is a children's clothes for 2-3 years old, the artificial intelligence analysis unit 135 generates family data in response to the corresponding SNS account information of the corresponding customer. The family data may be set to a plurality of items as many as the expected number of families. The family data may include expected gender, expected relationship, expected age, and expected body size information. In the case of the specific customer, the family data may be generated as "first family data: female, child, 2-3 years, 98cm tall". Similarly, the family data includes: "Second family data: male, spouse, early 40s, height 178~180cm, weight 65kg", "third family data: female, mother, 70s, no information, no information" and Can be created together. The artificial intelligence analysis unit 135 may request to collect and update related information every predetermined period for family data for family members predicted to be minors. In addition, the artificial intelligence analysis unit 135 may invalidate if the height and weight information of a family member predicted as a minor is not calculated by post-related information obtained within a predetermined period.

Thereafter, the artificial intelligence analysis unit 135 may calculate a list of recommended products for each time period in response to information related to a family stored in family data of a specific customer. For example, the AI analysis unit 135 determines the existence of family members related to a specific time, such as Mother's Day, Halloween Day, Christmas, New Year's Day, Children's Day, Adult Day, Vacation Period, Entrance Ceremony, Graduation Ceremony, and related family It is possible to calculate the result of increasing the number of advertisements for products corresponding to each period for customers with members. For example, the artificial intelligence analysis unit 135 promotes parental-related products to users who have an SNS account (an SNS account that has family data corresponding to a parent relationship) that requires advertisement for a product related to Mother's Day as a friend list or more than a preset value. You can request an activity.

Alternatively, the artificial intelligence analysis unit 135 may request the user's device side to perform a promotional activity for the corresponding inventory item when the inventory corresponding to the body size of the family of the specific account or the body size of the customer is held. Accordingly, the user (member) can perform personalized advertisement through activities such as sending event notification information for the corresponding product to specific accounts.

In addition, the artificial intelligence analysis unit 135 may infer the interest of the corresponding customer and classify the type according to the information of the post, tag (hash tag, etc.) uploaded to the customer's SNS account. The AI analysis unit 135 may organize customer interests into parenting, sports, games, travel, restaurants, animals, and the like, and set a priority order for a specific customer. In addition, the artificial intelligence analysis unit 135 may set a customer's interest ranking in proportion to the number of accumulated tag keywords collected within a preset period, for example.

As described above, the artificial intelligence analysis unit 135 may perform an operation of setting a priority ranking for a specific customer and classifying the type of the customer based on the priority order. In addition, the artificial intelligence analysis unit 135 classifies customers corresponding to accounts connected to the user's (member's) SNS, accounts that leave comments, accounts that send product inquiry messages, and accounts included in the friend list by type, and customers by type You can calculate the distribution status of. For example, the artificial intelligence analysis unit 135 calculates the information of 50% of the customers who give product inquiries by accessing the SNS of a specific user (member), 30% is the restaurant type, and 20% is the animal type. It can be provided to users (members).

Furthermore, the artificial intelligence analysis unit 135 can further segment the types of interests of customers, derive a sales strategy using them, and present them to users (members).

The commission management unit 136 may pay a commission of a certain percentage of the sales amount to the user 200 on the case where the purchase is completed. In addition, the commission management unit 136 may perform an operation of calculating and paying a commission to be allocated to a mentor and recommender who trained the specific user when payment and training completion for a specific user are completed in the user education management unit 131.

As illustrated in FIG. 3, after the step 305 of performing the SNS marketing education of the user, the artificial intelligence analysis system may proceed to step 310 of signing a partnership of a user who has completed education with a partner company. Thereafter, the artificial intelligence analysis system may proceed to step 315 in which the user obtains product information from the partner company. Thereafter, the user goes through step 320 of promoting and selling the goods on his SNS based on the obtained goods information. When the product is sold by the user, the artificial intelligence analysis system performs step 325 in which the user is paid a certain commission for the sales revenue of the partner company.

The artificial intelligence analysis system according to an embodiment of the present invention may include a server 100, a user device 200, and a partner company device 300.

First, the user 200 may access the server 100 and perform operation 405 for requesting paid education. Accordingly, the server 100 may perform operation 410 for providing educational material. At this time, the operation 410 includes an operation of providing training materials, an operation of confirming whether 1:1 training with a mentor has been performed, an operation of confirming whether a report that training of a specific item has been performed by a set mentor, etc. It can contain.

Thereafter, the user 200 may perform operation 415 to complete the training process, which may include, for example, an operation of confirming completion of an operation, such as viewing and reproducing educational contents provided by the user device. Accordingly, the user device 200 may perform operation 420 to transmit the completion of the education to the server 100 side. When confirming that the user has completed the training, the server 100 may perform operation 425 requesting partner company information to the partner company 300 accordingly. In response, the partner company 300 may perform operation 430 of providing their company information to the server 100. Thereafter, the server 100 may perform operation 435 of providing the received partner company information to the user 200 side.

The operations 425 to 435 may be replaced by providing the pre-registered partner company information to the user 200 in the server 100.

Subsequently, the user may perform operation 440 of selecting a feature company that wants to enter a partnership among the provided partner company information, and when the selection information is transmitted from the user 200 to the server 100, the server 100 performs 450 operations of signing the partnership. Operation 455 may be performed and the partnership conclusion information is transmitted to the 300 partner companies.

According to various embodiments of the present disclosure, the server 100 may analyze a user's SNS activity type and recommend suitable sales items and partner companies in response to the analyzed type information. For example, the server 100 may calculate seller-related information such as a user's main visitor type and interest based on a user's age group, main tag items of an SNS post, SNS post content classification, and comment content. In addition, the server 100 may recommend suitable sales items and partner companies based on the calculated seller-related information.

The server 100 of the artificial intelligence analysis system according to an embodiment of the present invention may perform operation 505 of signing a partnership between a user and a company at a user request. In this case, the company may actually be a subject who purchases goods to be sold to consumers from wholesalers, factories, and the like, and receives sales payments paid by consumers. In addition, through the partnership with the above-mentioned companies, the user promotes goods that are not directly purchased by the user, and recruits buyers through customer response activities such as product guidance and answers to inquiries to buyers, and elicits actual purchases. If the sale of goods is made in accordance with these activities, commissions on the sales can be paid.

After the operation 505, the server 100 may perform operation 510 for confirming a request for product information from the user. Accordingly, the server 100 may perform operation 515 of providing product information provided by a partner company to a user. The product information provided by the partner company may be stored and managed on the storage side of the server 100, and the server 100 may provide the product information of the partner company only to the user who has entered into the partnership.

Thereafter, the server 100 may perform operation 520 to determine whether the purchase of the product has occurred through the user SNS. The user needs to input information about the occurrence of the buyer in the server 100 in order to deliver the goods when the buyer contacted through the SNS has indicated the intention to purchase. For this reason, the server 100 may determine whether a purchase request has been generated by the user through SNS. In addition, the server 100 may determine whether or not the purchase of the product occurs as the payment of the sales price can be checked on the account and payment system managed by the server 100.

If it is determined that the purchase of the product has not occurred, the server 100 may end the process of FIG. 5. On the other hand, when the server 100 determines that the purchase of the product has occurred as the purchase request of the product and payment of the sales amount are confirmed, operation 525 of acquiring purchase related information and requesting delivery of the purchased product to the partner company is performed. can do.

In addition, according to the purchase occurrence, the server 100 may perform operation 530 of analyzing characteristics of the buyer and the purchased item based on the acquired purchase related information. The operation 530 may be performed by the artificial intelligence analysis unit 135, and may be performed based on inquiries prior to purchase by the purchaser, other product information purchased by the purchaser, and the like.

Thereafter, the server 100 may perform operation 535 for calculating analysis information and providing feedback to the company and the user.

Although the present invention has been described in detail with reference to the above-mentioned examples, those skilled in the art can make modifications, alterations and modifications to the examples without departing from the scope of the present invention. In short, in order to achieve the desired effect of the present invention, it is not necessary to separately include all the functional blocks shown in the drawings or to follow all the order shown in the drawings in the order shown, and even if not, any number of technical aspects of the present invention described in the claims Note that it can fall within the scope.

Claims

A communication unit that collects information required to perform data mining based on artificial intelligence;

A storage unit for storing the result value calculated based on artificial intelligence and data for performing data mining collected by the communication unit;

According to a request to enter a partnership from a user device, a partnership is established with a specific partner company selected, and information on a sale item provided from the partner company is provided to the user device side, and a purchase request event of a buyer's product and a payment settlement event are confirmed from the user device. A server comprising a control unit for determining that a purchase has occurred, requesting delivery of purchased goods to a partner company's device, and controlling a certain percentage of the sales amount to be allocated to the user's device as a commission;

A user device that transmits information to the server as a user inputs information on a request to enter a partnership and a purchase request for an item of a buyer generated based on an SNS;

Includes; partner company device for uploading information about the goods to be sold to the server;

The control unit

Based on at least one of the number of views and the number of comments, public SNS information that is determined to have a topical degree of greater than or equal to a preset value is collected, and among the collected SNS information, information related to the field of sales goods of a pre-registered partner company Results for purchase trends and issue keywords by sampling only, performing data transformation operations that assign codes based on data characteristics to the sampled data, and performing correlation analysis on SNS information that performed data transformation operations AI analysis system for deriving a value; AI analysis system comprising a.
According to claim 1,

The control unit

Including a partnership contracting unit for performing a partnership with a specific goods seller in response to a user request;

The partnership fastener

Based on at least one of the comments registered on the user account's SNS and the content registered in the user's account, the visitor type is determined, and a suitable selling product and a suitable partner type matching the visitor type are calculated to recommend a partner company. Artificial intelligence analysis system characterized by providing information
According to claim 1,

The AI analysis unit

Based on at least one of the number of views and the number of comments, public SNS information that is determined to have a topical degree of greater than or equal to a preset value is collected, and among the collected SNS information, information related to the field of sales goods of a pre-registered partner company Results for purchase trends and issue keywords by sampling only, performing data transformation operations that assign codes based on data characteristics to the sampled data, and performing correlation analysis on SNS information that performed data transformation operations Artificial intelligence analysis system characterized by deriving a value.
According to claim 1,

The AI analysis unit

Calculating information including at least one of the main question content of customers who purchased a specific product, the inquiry keyword increased above the threshold, and the main complaint type based on text data recording the conversation with the buyer made on the user's SNS Features artificial intelligence analysis system.
According to claim 1,

The AI analysis unit

Acquiring post-uploaded information in the SNS account of the main purchasing customer, performing customer type classification, calculating the type information of the user's main customer based on the classified customer type information, and calculating the calculated type information of the main customer Provides advertisements corresponding to

The post-related information includes at least one of content, posts, tags, and comments uploaded to the SNS account, an artificial intelligence analysis system.
The method of claim 5,

The AI analysis unit

When a customer enters a comment on a user's SNS post, the product is classified by analyzing the post image with the comment entered, and the product type information of the customer's SNS account and post image is matched to match the product of interest by customer Artificial intelligence analysis system characterized by storing as information.
The method of claim 5,

The AI analysis unit

Based on the customer's purchase history and the user's comment on the SNS post, the customer's body size or the customer's family body size is determined, and the inventory corresponding to the customer's body size or the customer's family body size is determined. An artificial intelligence analysis system that, when held, requests the user's device to send event notification information for inventory items to the customer.