KR102674273B1 - Apparatus and method for providing bidirectional affiliate matching service based on artificial intelligence - Google Patents

Abstract

This disclosure relates to an artificial intelligence-based two-way affiliate matching service providing device and method, which includes a communication module that communicates with an external device; A storage module that stores at least one process for providing a two-way affiliate matching service based on artificial intelligence; and a control module that provides the two-way affiliate matching service based on the at least one process, wherein the control module includes company data including sales information on items provided by at least one company and tendencies of at least one organization. and group data including information on the tendencies of members belonging to the group, and generate a promotional plan for companies and organizations that can be matched based on the collected company data and the collected group data. The group data used to create the promotion plan is the number of members who have commented on the items of the matched company on an Internet community comprised of members of the matched group, and the number of members who have commented on the item of the matched company, derived through analysis of the context of the comment. It includes preference for items of the matched company and the number of members of the matched group who already own the item of the matched company.

Description

Apparatus and method for providing artificial intelligence-based two-way affiliate matching service {APPARATUS AND METHOD FOR PROVIDING BIDIRECTIONAL AFFILIATE MATCHING SERVICE BASED ON ARTIFICIAL INTELLIGENCE}

This disclosure relates to an apparatus and method for providing an affiliate matching service. More specifically, the present disclosure relates to an apparatus and method for providing an artificial intelligence-based two-way affiliate matching service between affiliates.

With the rapid development and expansion of wired and wireless communication network technology, various online marketing activities are being conducted based on these wired and wireless communication networks.

Marketing refers to activities related to distributing products or services to consumers and can include various activities such as market research, demand forecasting, product development, setting up sales channels, advertising to promote sales, and publicity. there is.

There are countless marketing partnerships around us. In particular, online marketing services take the form of sending advertisements, promoting events, and generating coupons to promote sales through various platforms, and are sent to each individual based on a messaging service or email service, or are launched as banner advertisements and are sent to unspecified people. Allows advertising pages to be linked to users. However, since these online marketing services are provided unilaterally by companies, there is a problem in that they are exposed to individuals who are not suitable for or do not need the advertising or promotion.

In addition, when a specific company searches for an organization (group) with similar characteristics to the product/service it wants to sell or promote and proposes an alliance, and the organization confirms the proposal and accepts the proposal, mutual matching is performed. Partnerships are taking place in this way. In this case, if the company's proposal is not one that the organization actually needs, not only is it difficult to conclude a match, but even if it is concluded, it is extremely rare for the company to actually benefit from the partnership.

Therefore, there is a need to develop technology that allows organizations and companies to set their own partnership conditions through separate platforms or web pages, and to facilitate matching between organizations and companies that mutually satisfy each partnership condition.

Korean Patent Publication No. 10-2023-0040976 (Publication Date: March 23, 2023)

This disclosure enables partnerships to be easily concluded through matching between organizations and companies through a separate platform or web page, and at the same time, organizations and companies each set partnership conditions, so that organizations and companies that mutually satisfy each partnership condition The aim is to provide a device and method for providing an artificial intelligence-based two-way partnership matching service that increases the probability of partnership by suggesting matching between companies and activates the use of benefits resulting from partnership.

The problems to be solved by the present disclosure are not limited to the problems mentioned above, and other problems not mentioned can be clearly understood by those skilled in the art from the description below.

An affiliate matching service providing device according to one aspect of the present disclosure for achieving the above-described technical problem includes a communication module that communicates with an external device; A storage module that stores at least one process for providing a two-way affiliate matching service based on artificial intelligence; and a control module that provides the two-way affiliate matching service based on the at least one process, wherein the control module stores corporate data including sales information on items provided by at least one company and at least one organization. Collect group data including information on the tendencies and tendencies of members belonging to the organization, and create a promotional plan for companies and organizations that can be matched based on the collected corporate data and group data. , the promotion plan is the number of members who wrote comments on the items of the matched company on an Internet community made up of members of the matched organization, and the items of the matched company derived through analysis of the context of the comments. It is generated based on the preference for and the number of members of the matched group that already own items of the matched company.

In addition, the control module controls the comment to be analyzed using a predetermined language model, and from the analysis results of the comment, the topic of debate of members of the matched group regarding the item is determined by at least one of the selling price and the specifications of the item. One is selected, and the promotion plan may be created by additionally considering the selected controversial topic.

In addition, the specifications as the selected topic of debate include size or color, and the control module uses a predetermined generative artificial intelligence model to determine the size or color preferred by the members even though it is not available as an item of the matched company. The color can be controlled to be derived, and the derived size or color can be controlled to be reflected in the promotion.

In addition, the number of members who already own the items of the matched company refers to the fact that members of the matched group purchased each item as a result of image analysis of a photo taken by at least one of the members of the matched group. It may be derived based on at least one of the analysis results of comments and the analysis results of comments mentioning the history of members of the matched organizations purchasing each item and selling it to others through second-hand transactions or discarding it. there is.

In addition, the control module sorts a plurality of posts on the Internet community according to the relative preference for the corresponding item based on comments written about the item of the matched company, and the preference among the plurality of sorted posts is It is possible to control the promotion plan to be posted in the comments of a predetermined number of posts selected in high order.

Additionally, the control module can control the promotion plan posted in the comment to be deleted when more than a predetermined number of items from the matched company are purchased.

Meanwhile, in the method of providing an artificial intelligence-based two-way affiliate matching service performed by a device, corporate data including sales information on items provided by at least one company and the tendencies of at least one organization and members belonging to the organization Collecting group data including information on the tendencies of each group; and generating a predetermined promotion plan for companies and organizations that can be mutually matched based on the collected company data and the collected group data, wherein the promotion plan is created on an Internet community composed of members of the matched group, The number of members who wrote comments on items of the matched company, preferences for the items of the matched company derived through context analysis of the comments, and items of the matched company among members of the matched organization It is created based on the number of members who already have it.

In addition to this, a computer-readable recording medium recording a computer program for executing a method for implementing the present disclosure may be further provided.

According to the means for solving the above-described problem of the present disclosure, it is possible to easily conclude an alliance through matching between an organization and a company through a separate platform or web page, and at the same time, the organization and the company each set partnership conditions to By proposing matching between organizations and companies that mutually satisfy the terms of partnership, the probability of partnership is increased and the use of benefits resulting from partnership is activated.

The effects of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned may be clearly understood by those skilled in the art from the description below.

1 is a diagram showing the network structure of an artificial intelligence-based two-way affiliate matching service provision system according to an embodiment of the present disclosure.
Figure 2 is a flowchart showing the operation of an artificial intelligence-based two-way affiliate matching service providing system according to an embodiment of the present disclosure.
Figure 3 is a diagram showing the configuration of an artificial intelligence-based two-way affiliate matching service providing device according to an embodiment of the present disclosure.
Figure 4 is a diagram showing a method of providing an artificial intelligence-based two-way affiliate matching service according to an embodiment of the present disclosure.
5 is a diagram illustrating in detail the operation of completing a contract based on a promotion plan/promotion information in a method of providing an artificial intelligence-based two-way affiliate matching service according to an embodiment of the present disclosure.
FIG. 6 is a diagram illustrating in detail the operation of generating a promotion plan in a method of providing an artificial intelligence-based two-way affiliate matching service according to an embodiment of the present disclosure.
FIG. 7 is a diagram illustrating in detail the operation of updating corporate data and group data in the method of providing an artificial intelligence-based two-way affiliate matching service according to an embodiment of the present disclosure.
Figure 8 is a diagram for specifically explaining the operation of building an artificial intelligence-based dictionary learning model according to an embodiment of the present disclosure.
Figure 9 is a diagram showing an example of a user interface displayed on the display module of a group terminal according to an embodiment of the present disclosure.

The advantages and features of the present disclosure and methods for achieving them will become clear by referring to the embodiments described in detail below along with the accompanying drawings. However, the present disclosure is not limited to the embodiments disclosed below and may be implemented in various different forms. The present embodiments are merely provided to ensure that the present disclosure is complete and to those skilled in the art to which the present disclosure pertains. It is provided to fully convey the scope of the present disclosure, and the present disclosure is defined only by the scope of the claims.

The terminology used herein is for the purpose of describing embodiments and is not intended to limit the disclosure. As used herein, singular forms also include plural forms, unless specifically stated otherwise in the context. As used in the specification, “comprises” and/or “comprising” does not exclude the presence or addition of one or more other elements in addition to the mentioned elements. Like reference numerals refer to like elements throughout the specification, and “and/or” includes each and all combinations of one or more of the referenced elements. Although “first”, “second”, etc. are used to describe various components, these components are of course not limited by these terms. These terms are merely used to distinguish one component from another. Therefore, it goes without saying that the first component mentioned below may also be the second component within the technical spirit of the present disclosure.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used with meanings that can be commonly understood by those skilled in the art to which this disclosure pertains. Additionally, terms defined in commonly used dictionaries are not to be interpreted ideally or excessively unless clearly specifically defined.

Like reference numerals refer to like elements throughout this disclosure. The present disclosure does not describe all elements of the embodiments, and general content or overlapping content between the embodiments in the technical field to which the present disclosure pertains is omitted. As used in the specification, the term “unit” or “module” refers to a hardware component such as software, FPGA, or ASIC, and the “unit” or “module” performs certain roles. However, “part” or “module” is not limited to software or hardware. A “unit” or “module” may be configured to reside on an addressable storage medium and may be configured to run on one or more processors. Thus, as an example, a “part” or “module” refers to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, Includes procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functionality provided within components and “parts” or “modules” can be combined into smaller components and “parts” or “modules” or into additional components and “parts” or “modules”. Could be further separated.

Throughout the specification, when a part is said to be “connected” to another part, this includes not only direct connection but also indirect connection, and indirect connection includes connection through a wireless communication network. do.

Additionally, when a part is said to “include” a certain component, this does not mean excluding other components, but may include other components, unless specifically stated to the contrary.

Throughout the specification, when a member is said to be located “on” another member, this includes not only cases where a member is in contact with another member, but also cases where another member exists between the two members.

Terms such as first and second are used to distinguish one component from another component, and the components are not limited by the above-mentioned terms.

Singular expressions include plural expressions unless the context clearly makes an exception.

The identification code for each step is used for convenience of explanation. The identification code does not explain the order of each step, and each step may be performed differently from the specified order unless a specific order is clearly stated in the context. there is.

The terms used in the following description are defined as follows.

Although the description is limited to 'service server' in this specification, it is a terminal of a service provider that seeks to provide a two-way affiliate matching service between companies and organizations based on a separate platform and/or web page, and is capable of performing computational processing. It can include a variety of devices. That is, the service server 100 may further include various devices such as computers, servers, and/or portable terminals, or may take the form of any one of them, but is not limited thereto.

Here, the computer may include, for example, a laptop, desktop, laptop, tablet PC, slate PC, etc. equipped with a web browser.

The server is a server that processes information by communicating with external devices, and may include an application server, computing server, database server, file server, game server, mail server, proxy server, and web server.

The portable terminal is, for example, a wireless communication device that guarantees portability and mobility, such as PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), and PDA. (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), WiBro (Wireless Broadband Internet) terminal, smart phone ), all types of handheld wireless communication devices, and wearable devices such as watches, rings, bracelets, anklets, necklaces, glasses, contact lenses, or head-mounted-device (HMD). may include.

Hereinafter, the operating principle and embodiments of the present disclosure will be described with reference to the attached drawings.

1 is a diagram showing the network structure of a two-way affiliate matching service providing system according to an embodiment of the present disclosure.

Referring to Figure 1, the two-way affiliate matching service provision system 10 (hereinafter referred to as 'service provision system') according to an embodiment of the present disclosure includes a service server 100, at least one enterprise terminal 200, and It may be configured to include at least one group terminal 300.

First, as described above, the service server 100 is a device (terminal) of a service provider that seeks to provide a two-way affiliate matching service between companies and organizations based on a separate platform and/or web page, and is a company capable of mutual matching. and organizations are detected and an environment is provided in which an alliance can be concluded.

Specifically, the service server 100 collects, stores, and manages corporate data of at least one company and group data of at least one organization.

At this time, corporate data can be collected by entering answers to question information (including question trees) provided according to a preset template by the corporate terminal corresponding to each company, and similarly, group data can be collected by the corporate terminal corresponding to each company. The terminal can be collected by entering answers to question information (including question trees) provided according to a preset template. At this time, the corporate terminal is a terminal of a company that provides affiliate benefits, and the group terminal is a terminal of an organization that wishes to receive affiliate benefits, so the question information provided to the corporate terminal and group terminal are different from each other. In addition, the question information provided to each company may be provided differently depending on the characteristics of each company, or the question information provided to each organization may be provided differently depending on the characteristics of each organization.

In addition, the service server 100 collects change data by checking whether there are changes to the corporate data of each company and the group data of each organization at preset intervals, and uses the change data to collect the previously stored corporate data of the company and/ Or update the previously stored group data of the group.

Additionally, in another embodiment, corporate data of each company and group data of each organization may be automatically collected by the service server 100 based on big data, and the collection method is not limited to a specific method. Here, the group data of each organization may be obtained by crawling from each organization's homepage or Internet community. At this time, the target of crawling is not only posts posted on the organization's homepage or Internet community, but also comments or comments for each post, replies to these comments or comments, and emoticons for each post or comment. Recommended information shown may be included. In some cases, these posts, comments, comments, etc. may include controversial topics about a specific company's items, i.e., products or services, and these controversial topics may be related to the selling price or specifications of the item (e.g., color, size, or material, etc.). It may be about. Alternatively, the above-mentioned posts, comments, comments, etc. may include a history of members of the relevant organization purchasing the item and selling it to others through second-hand transactions, or discarding it after no longer using it, or providing proof of this. Information such as photos or videos may also be posted and crawled.

Meanwhile, the service server 100 may be equipped with at least one pre-learning model to conclude mutual matching between specific companies and specific organizations based on the stored corporate data of each company and group data of each organization. For example, through this at least one pre-learning model, mutually matching companies and simplified characters can be detected, or a promotion plan for conclusion can be created and provided. This pre-learning model will be described in detail below based on FIG. 8.

Meanwhile, at least one corporate terminal (200-1, ...200-n) is one of the terminals to receive a two-way affiliate matching service through a separate platform or web page provided by the service server 100, and is provided by at least one organization This is a terminal owned by the manager or person in charge of a company that wishes to provide affiliate benefits through a terminal.

Specifically, at least one enterprise terminal (200-1, ...200-n) may subscribe to the corresponding service by transmitting a service provision request to the service server 100. At this time, when signing up, you can receive question information from the service server 100 and enter an answer so that corporate data corresponding to you is collected.

Thereafter, when at least one corporate terminal (200-1, ...200-n) receives a promotion plan generated based on the company data from the service server 100, it can determine whether to approve the promotion plan and proceed with the conclusion. . If at least one piece of promotional information is included in the promotion plan, one piece of promotional information can be selected and the selection information (selected promotional information) can be transmitted to the service server 100. In addition, if you wish to partially modify the promotion plan or at least one promotional information included therein, you can edit the promotion plan or promotion information and transmit the revised information (modified promotion information) to the service server 100. there is.

Meanwhile, at least one group terminal (300-1, ...300-n) is one of the terminals that wishes to be provided with a two-way affiliate matching service through a separate platform or web page provided by the service server 100, and at least one group terminal (300-1, ...300-n) This is a terminal owned by the manager or person in charge of an organization that wishes to receive affiliate benefits from a corporate terminal.

Specifically, at least one group terminal (300-1, ...300-n) may subscribe to the corresponding service by transmitting a service provision request to the service server 100. At this time, when signing up, you can receive question information from the service server 100 and enter an answer to generate group data corresponding to yourself.

Thereafter, when a promotion plan or promotion information is received from the service server 100, it is determined whether to approve the promotion plan or promotion information, and the approval information is transmitted to the service server 100 to proceed with the conclusion.

Here, at least one enterprise terminal 200 and/or at least one group terminal 300 is a computer, UMPC (Ultra PC) capable of installing and executing a plurality of applications (i.e., applications) desired by each administrator (person in charge). Mobile PC, workstation, net-book, PDA (Personal Digital Assistants), portable computer, web tablet, wireless phone, mobile phone, smart phone Smart phone, Pad, smart watch, wearable terminal, e-book, PMP (portable multimedia player), portable game console, navigation device, black It may be a black box, a digital camera, or other mobile communication terminal. That is, each of the at least one enterprise terminal 200 and/or the at least one group terminal 300 may be provided in various forms, and the number, type, and form thereof are not limited.

Figure 2 is a flowchart showing the operation of an artificial intelligence-based two-way affiliate matching service providing system according to an embodiment of the present disclosure. For convenience of explanation, one corporate terminal and one group terminal are shown, but as described above, at least one or more It may be composed of, and the number and type are not limited. In addition, one or more of each step shown in FIG. 2 may not be executed depending on the embodiment, or one or more steps not shown in FIG. 2 may be additionally executed, and may be executed in a different order from that shown in FIG. 2. there is.

Referring to FIG. 2, the enterprise terminal 200 installs and executes a separate application provided by the service server 100 (S101), and sends information to the service server 100 through the application to subscribe to the two-way affiliate matching service. A service provision request is transmitted (S103).

Next, the service server 100 collects corporate data corresponding to the corporate terminal 200 through the service provision request received in step S103 (S105). At this time, the corporate data may include sales information about products or services provided by at least one company.

In addition, the group terminal 300 installs and runs a separate application provided by the service server 100 (S107), and sends a service provision request to the service server 100 through the application to subscribe to the two-way affiliate matching service. Transmit (S109).

Next, the service server 100 collects group data corresponding to the group terminal 300 through the service provision request received in step S109 (S111). At this time, the group data may include information about the tendencies of each of at least one organization and the tendencies of members belonging to the organization.

As described above, steps S101 to S105 are operations performed for a company (corporate terminal), and steps S107 to S111 are operations performed for an organization (group terminal), so they are performed individually for the company and organization. As a step, the order in which it is performed is not limited. In other words, these are steps that multiple companies and multiple organizations can perform individually.

Next, the service server 100 performs matching by detecting companies and organizations that can be mutually matched based on the previously collected corporate data and organization data (S113), and detects the detected organizations based on the tendency information of the detected organizations (S113). Create a promotion plan for the company's product or service (S115).

Next, the service server 100 transmits the promotion plan generated in step S115 to the corporate terminal 200 of the company detected in step S113 (S117), and when the corporate terminal 200 approves the promotion plan, Accordingly, when approval information is generated (S119), it is transmitted to the service server 100 (S121).

Next, the service server 100 transmits the promotion plan to the group terminal 300 of the group detected in step S113 (S123), and when the group terminal 300 approves the promotion plan, approval information is generated. (S125), and transmits this to the service server 100 (S127).

Next, the service server 100 proceeds with the conclusion as it receives approval information from both the enterprise terminal 200 and the group terminal 300 (S129).

Although not shown in FIG. 2, in order to proceed with the conclusion in step S129, a contract for conclusion may be written and transmitted to the enterprise terminal 200 and the group terminal 300, respectively. The conclusion can be completed as the contract is completed.

Below, we will look at the specific configuration and operation of the service server 100.

Figure 3 is a diagram showing the configuration of an artificial intelligence-based two-way affiliate matching service providing device according to an embodiment of the present disclosure.

Referring to FIG. 3, the artificial intelligence-based two-way affiliate matching service providing device according to an embodiment of the present disclosure, that is, the service server 100, includes a communication module 110, a storage module 130, and a control module 150. It can be configured to include.

The communication module 110 transmits and receives at least one information or data with at least one device/terminal. Here, the at least one device/terminal may be a device/terminal that wishes to use (or receive) a two-way affiliate matching service in addition to the at least one corporate terminal 200 and at least one group terminal 300 described above, and the type thereof. and the form is not limited.

In addition, this communication module 110 can perform communication with other devices and transmits and receives wireless signals in a communication network based on wireless Internet technologies.

Wireless Internet technologies include, for example, WLAN (Wireless LAN), Wi-Fi (Wireless-Fidelity), Wi-Fi (Wireless Fidelity) Direct, DLNA (Digital Living Network Alliance), WiBro (Wireless Broadband), and WiMAX (Worldwide). Interoperability for Microwave Access), HSDPA (High Speed Downlink Packet Access), HSUPA (High Speed Uplink Packet Access), LTE (Long Term Evolution), LTE-A (Long Term Evolution-Advanced), etc. Service server (100) transmits and receives data according to at least one wireless Internet technology, including Internet technologies not listed above.

For short range communication, Bluetooth™, RFID (Radio Frequency Identification), Infrared Data Association (IrDA), UWB (Ultra Wideband), ZigBee, NFC (Near Field Communication), Wi -Short-distance communication can be supported using at least one of Fi (Wireless-Fidelity), Wi-Fi Direct, and Wireless USB (Wireless Universal Serial Bus) technologies. These wireless area networks can support wireless communication between the service server 100 and at least one enterprise terminal 200 and/or at least one organization terminal 300. At this time, the short-range wireless communication network may be a short-range wireless personal area network.

Meanwhile, the storage module 130 may store data about at least one process (algorithm) for providing a two-way affiliate matching service or a program that reproduces the process. In addition, the storage module 130 may further store processes for performing other operations, but this is not limited.

Additionally, the storage module 130 may store a plurality of application programs or applications running on the service server 100, data for operation of the production device 100, and commands. At least some of these applications may be downloaded from an external server via wireless communication. Meanwhile, the application program is stored in at least one memory provided in the storage module 130, installed on the service server 100, and stored in the storage module 130 through the control module 150. It can be driven to perform an operation (or function) by.

Meanwhile, at least one memory is a flash memory type, hard disk type, multimedia card micro type, or card type memory (e.g., SD or XD memory, etc.). , RAM (Random Access Memory), SRAM (Static Random Access Memory), ROM (Read-Only Memory, ROM), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory) magnetic memory, It may include at least one type of storage medium among magnetic disks and optical disks. In addition, memory can store information temporarily, permanently, or semi-permanently, and can be provided as a built-in or removable type.

Additionally, the storage module 130 may be further linked with a separate external server (including a cloud server).

In addition to operations related to the application program, the control module 150 controls all components within the service server 100 based on at least one processor to process input or output signals, data, information, etc., or stores information in at least one memory. Various processes are performed by executing stored commands, algorithms, and applications, and appropriate information or functions to provide a two-way affiliate matching service can be provided or processed.

Specifically, the control module 150 includes corporate data including sales information about products or services provided by at least one company, and disposition information about the dispositions of at least one organization and the dispositions of members belonging to the organization. Each group data is collected, and companies and organizations that can be matched with each other are detected based on the collected company data and the collected group data.

Here, corporate data includes the company's size, purpose, region, operating tendency, products produced, services provided, past partnership history, and benefit provision conditions (conditions of the organization wishing to provide benefits, i.e., the organization wishing to enter into an alliance must meet the conditions). conditions), and group data includes the size, purpose, region, inclination, activity history, past partnership history, and benefit request conditions of the organization (conditions of the company seeking to receive benefits, i.e., wishing to enter into an alliance). It may include at least one of the conditions that a company must meet. In addition, the past partnership history included in each of the corporate data and group data includes at least one of the evaluations from each organization and company with which it has entered into an alliance in the past, as well as the partnership benefits provided by each company and the performance (performance/sales) through the conclusion. Information about may be included. Here, the evaluation may be recorded through scores, levels, text, etc., but is not limited thereto. Additionally, this corporate data includes information on the lowest selling price at which the company can make a profit when selling a specific item, i.e., a product or service, and the lowest selling quantity at which it can make a profit when selling at this minimum selling price. It may be included, but is not limited to this.

At this time, the control module 150 may perform an operation to detect companies and organizations that can be mutually matched by a matching request from a specific corporate terminal or a specific group terminal, and may be used to detect companies and organizations registered to receive the corresponding service (two-way affiliate matching service). By monitoring the matching between terminals and group terminals based on a preset period, an operation to detect companies and organizations that can be matched with each other may be performed. This may be set/changed by the administrator (person in charge) of the service server 100, and corresponds to a condition that can be set/changed by at least one corporate terminal 200 and/or at least one group terminal 300. and is not limited to this.

Meanwhile, the control module 150 generates a promotion plan for the product or service of the detected company based on the detected organization's tendency information, recommends it to the corresponding corporate terminal (corporate terminal corresponding to the detected company), and recommends the recommended product or service to the corporate terminal (corporate terminal corresponding to the detected company). If the promotion plan is approved by the corporate terminal, it is sent to the group terminal (group terminal corresponding to the detected group) to perform a mutual partnership agreement.

Meanwhile, promotional proposals can be created in a variety of ways, one of which can be created based on an artificial intelligence-based model, more specifically, a generative artificial intelligence model such as a generative language model.

Accordingly, the corporate terminal can request to proceed with the conclusion by selecting the promotional information it wishes to proceed among at least one piece of promotional information. Alternatively, the enterprise terminal may request modification of the promotion plan or promotion information and request that a conclusion be concluded using the modified promotion information.

Additionally, when approval information is received from both the enterprise terminal 200 and the group terminal 300, the control module 150 performs or controls an alliance conclusion to be performed. At this time, the control module 150 reflects the corresponding promotional information in the pre-stored template, creates a contract targeting the detected company and organization, and transmits it to the corporate terminal 200 and the group terminal 300.

Accordingly, when the contract writing is completed by each of the corporate terminal 200 and the group terminal 300, the alliance conclusion is completed.

However, this is only one embodiment, and the promotion plan is not sent directly to the corporate terminal 200 and the group terminal 300, but rather sends a notification through an application, and each manager of the company or organization executes the application to receive the notification. You can also check the corresponding promotion plan.

In order to perform all of the operations described above, the control module 150 may be equipped with at least one artificial intelligence-based dictionary learning model. For example, corporate data corresponding to each of at least one corporate terminal 200 is generated through a pre-learning model created by learning the original model using the corporate information and organization information of each previously matched company and organization as learning data. By inputting group data corresponding to each of and at least one group terminal 300, a promotion plan can be generated as an output.

Meanwhile, the control module 150 collects change data for each company and/or each organization at preset intervals rather than collecting and using company data and group data one-time, and analyzes the collected change data. You can update corporate information and/or group information. At this time, change data is collected by checking whether changes have occurred in the previously stored corporate data of the company and the group data of the organization based on the data for each company and/or each organization collected based on big data. Updates can be made by reflecting the changed data in the relevant corporate data and/or group data. However, this is only one embodiment, and change data may be input and collected by each enterprise terminal 200 and group terminal 300 at preset intervals, and the collection method is not limited.

As an example, the control module 150 guides the corporate terminal 200 and the group terminal 300 to pay the subscription fee when they sign up for the service, or establishes an alliance between the corporate terminal 200 and the group terminal 300. When concluding, you may be instructed to pay the execution fee.

In addition, specific operations of the control module 150 will be described below based on each drawing.

Figure 4 is a diagram showing a method of providing an artificial intelligence-based two-way affiliate matching service according to an embodiment of the present disclosure.

Referring to FIG. 4, the service server 100 provides corporate data including sales information on products or services provided by at least one company, the tendencies of at least one organization, and the tendencies of members belonging to the organization. Group data containing information is collected respectively (S210). At this time, each company data and each group data may be stored in the storage module 130 and/or a separate database. In addition, since the collected corporate data and group data have been described above, further explanation regarding this will be omitted.

Next, the service server 100 detects companies and organizations that can be mutually matched based on the company data and organization data collected in step S210 (S220), and identifies the companies and organizations detected based on the tendency information in the detected step. A promotion plan for a product or service is created and recommended to the corporate terminal corresponding to the detected company (S230).

Next, if the recommended promotion plan is approved by the corporate terminal, the service server 100 transmits the promotion plan to the group terminal corresponding to the detected group (S240).

FIG. 5 is a diagram illustrating in detail the operation of completing a contract based on a promotion plan/promotion information in a method of providing an artificial intelligence-based two-way affiliate matching service according to an embodiment of the present disclosure.

Referring to FIG. 5, after step S240, when the selected promotional information or modified promotional information is received from the enterprise terminal 200 (S250), the service server 100 sends the selected promotional information or modified promotional information to the group terminal 300. Transmit promotional information (S260).

Next, when approval information for the selected promotional information or modified promotional information is received from the group terminal 300 (S270), an alliance is concluded between the corporate terminal 200 and the group terminal 300 (S280). .

However, Figure 4 shows an operation that can be performed when the enterprise terminal 200 selects one piece of promotion information or performs modifications to the promotion plan transmitted in step S240, and the promotion plan includes one promotion information. Therefore, if approval is made without specific selection or modification, the promotion plan can also be transmitted as is to the group terminal 300.

FIG. 6 is a diagram for specifically explaining the operation of generating a promotion plan in the method of providing an artificial intelligence-based two-way affiliate matching service according to an embodiment of the present disclosure, and is a diagram for specifically explaining step S230 of FIG. 4.

Referring to FIG. 6, the service server 100 checks the affiliation history information of the organization detected in step S220 (S231), and enters the affiliation history information of the organization detected in step S220 into an artificial intelligence-based dictionary learning model. Enter partnership history information (232).

Next, the service server 100 generates a promotion plan based on at least one promotion information that the company can proceed with detected in step S220 (S233).

Here, the promotion plan may be created in a different way. For example, the service server 100 creates a promotion plan using the above-mentioned group data and company data through the control module 150, but the group data used at this time includes the Internet consisting of members of an organization to be matched with a specific company. In the community, the number of members who have commented on the item of the matched company, the preference for the item of the matched company derived through context analysis of the comment, and the matching among members of the matched organization. The number of members who already own items from the company may be included.

Here, the number of members who wrote comments can be obtained by counting the number of members who wrote posts in the relevant Internet community or the number of members who wrote comments or comments on a specific post. Here, the number of such members can be confirmed from the ID of each member who wrote a post, comment, or comment, but is not limited to this. Here, since the technology itself for verifying the ID of each member is a known technology, a detailed description thereof will be omitted.

In addition, members' preferences for items of a specific company, derived through context analysis of each comment, can be derived from the results of the language model analysis of these comments. Here, the language model is a language model learned by transfer learning, such as BERT, a model pre-trained through a large amount of corpora for a specific purpose, such as positive or negative for a given query. It may have been prepared by fine-tuning to derive the degree. More specifically, when a comment about a specific item is entered into this language model, context analysis for the comment can be performed by the language model, and the result is whether the comment is positive or negative for the specific item. can be derived. The result derived at this time may be in the form of binary classification. The closer it is to 0, the closer it may be to a negative, and the closer it is to 1, the closer it may be to a positive, but it is not limited to this.

Additionally, among the members of the matched organization, the number of members who already own items of the matched company can also be derived from the analysis results of the above-described language model. In the case of the above-mentioned language model, it is possible to understand the context of the comment, so by analyzing the comments of each member of the organization, binary classification can be performed on whether each member holds the item, and as a result, if If it is close to 0, it can be interpreted as a high possibility of not owning the item, and if it is close to 1, it can be interpreted as a high possibility of owning the item. In addition, by refining the results derived for each member in this way, whether or not each member of the group possesses the item can be derived, and by adding them up, the number of members who possess the item among all members can be derived. Of course, the derivation process is not limited to this.

Meanwhile, in addition to the above-mentioned language model, according to one embodiment, an artificial intelligence model is prepared and implemented to analyze posts, comments or comments written by members of the relevant organization and select which part is the topic of controversy. It can be used. Specifically, this artificial intelligence model may also be similar to the language model described above. That is, by fine-tuning the pre-trained model, when a post, comment, or comment is input, the context thereof is analyzed, and the probability for each of a plurality of options can be derived from the analyzed results. The plurality of options here may be several pre-set topics of debate, and may include, for example, selling price or specifications. More specifically, when posts, comments, or comments written by multiple people are entered into this artificial intelligence model, the probability of the sales price is 0.1, the probability of the color of the specifications is 0.3, and the probability of the size of the specifications is 0.6. You can. In this case, the topic of debate may be determined to be size among the specifications.

Here, let's look at how the topic of debate is decided. First, by analyzing the context of sentences written by each of multiple people, it can be analyzed whether each of the multiple people has the same or conflicting opinions on a specific topic, and if so, how much they are opposed to each other. The specific topic may be, for example, the controversial topic discussed earlier, such as selling price or various types of specifications. Here, the relatively greater the degree of conflict, the more likely it is that it will be decided as a topic of debate.

Then, the control module 150 may generate the above-described promotion plan by additionally considering the determined topic of controversy. For example, information about items that a company can provide may be obtained from company data. When creating the above-mentioned promotion, the control module 150 may set the price of the item to the company's price if price is included in the controversial topic. Promotions can be created to match the lowest available price or to be within 10% of that minimum available price. At this time, the creation of this promotion plan can be performed by a generative artificial intelligence model. As you know, a generative artificial intelligence model is an artificial intelligence model that can generate data or information for a given query, and currently, models such as chatGPT are emerging. For example, a generative artificial intelligence model such as chatGPT may say, 'The current selling price of this clothes is 300 USD, but prospective buyers are arguing about the price. If you ask a query such as 'Recommend an appropriate price by understanding the content of comments on the Internet,' you can receive a price proposal that matches the price. That is, in one embodiment, in the creation of a promotion plan, various information such as company data and group data are taken into consideration, and in particular, comments from those wishing to purchase a specific item among the group data or the company's margin rate are taken into consideration to generate artificial intelligence. Intelligent models can ensure that the optimal price is suggested.

At this time, the price or specifications proposed in this way may be for items that the above-mentioned purchasers mentioned in posts, comments, etc., but which are not yet available from the company's standpoint. Nevertheless, the proposal is possible because the generative artificial intelligence model enables context analysis of posts written by prospective buyers and the creation of new content based on the results of this analysis.

Meanwhile, the above-mentioned promotion plan created for a specific item may be posted on the above-mentioned Internet community. At this time, according to one embodiment, such a promotion plan may be posted in the comments of a post in which the item has been discussed in an Internet community, and information that a predetermined number or more purchases of the item have been made may be used to provide the service according to one embodiment. Once acquired on the device, such promotions may be deleted from the comment. Here, advertisements for items may be posted on bulletin boards of Internet communities, but it may be more effective to place advertisements on posts where discussions about the item occur. However, from the member's point of view, they may not want excessive advertisements, such as promotional proposals, to be displayed in posts or comments they have written. First, in one embodiment, among such posts, posts with a preference for the item above a certain level may not be desired. For example, when sorting based on preference, a promotional plan can be posted only for a certain number of posts selected in high order. Additionally, secondly, in one embodiment, if a purchase is made for the corresponding item after such a promotion plan is posted, the promotion plan may no longer be needed, and in this case, the promotion plan may be deleted from the comments of the post.

Figure 7 is a diagram for specifically explaining the operation of updating company data and group data in the method of providing an artificial intelligence-based two-way affiliate matching service according to an embodiment of the present disclosure. This operation can be performed after the company information and group information is initially created and stored, and can be performed repeatedly while subscription to the service is maintained.

Referring to FIG. 7, the service server 100 collects change data for each of at least one company and at least one organization (S310), and analyzes the collected change data to update company information or organization information. Determine whether there is (S320).

As a result of the determination, when it is determined that the corporate data and/or group data require updating, the service server 100 updates the personal data and/or group data based on the analysis result of the change data in step S320 (S330 ).

Figure 8 is a diagram for specifically explaining the operation of building an artificial intelligence-based dictionary learning model according to an embodiment of the present disclosure.

Referring to FIG. 8, the service server 100 checks the company data and group data of each company and organization that has already been matched (with a history of mutual agreement completed) based on past matching history, and matches each confirmed company. Construct learning data using data and group data (S410).

Next, the service server 100 performs learning by inputting the learning data constructed in step S410 into the original model (S420). As a result, a pre-learning model for generating a promotion plan can be implemented.

Meanwhile, when performing step S410, an operation of preprocessing each company data and group data and converting them into learnable data can be additionally performed.

FIG. 9 is a diagram illustrating an example of a user interface displayed on a display module of a group terminal according to an embodiment of the present disclosure.

Referring to FIG. 9, a specific group terminal 300 can access a separate web page to receive the corresponding service. At this time, a user interface implemented to enable use of the corresponding service may be displayed on the display module 310 of the specific group terminal 300.

Meanwhile, the present disclosure may perform inference for a predetermined purpose using a model implemented in an artificial neural network method.

Below, we will look at artificial neural networks. A model in this specification may refer to any type of computer program that operates based on a network function, artificial neural network, and/or neural network. Throughout this specification, model, neural network, network function, and neural network may be used interchangeably. In a neural network, one or more nodes are interconnected through one or more links to form an input node and output node relationship within the neural network. The characteristics of the neural network can be determined according to the number of nodes and links within the neural network, the correlation between the nodes and links, and the value of the weight assigned to each link. A neural network may consist of a set of one or more nodes. A subset of nodes that make up a neural network can constitute a layer.

A deep neural network (DNN) may refer to a neural network that includes multiple hidden layers in addition to the input layer and output layer. In a deep neural network, there is at least one hidden layer, preferably two. It consists of the above.

These deep neural networks include convolutional neural network (CNN), vision transformer, recurrent neural network (RNN), Long Short Term Memory (LSTM) network, and Generative Pre-trained (GPT). Transformer, auto encoder, GAN (Generative Adversarial Networks), restricted Boltzmann machine (RBM), deep belief network (DBN), Q network, U network, Siamese network, adversarial generation. It may include a network (GAN: Generative Adversarial Network), a transformer, etc.

Alternatively, depending on the embodiment, the deep neural network may be a model learned using transfer learning. Here, transfer learning pre-trains a large amount of unlabeled learning data using a semi-supervised learning or self-learning method to create a pre-trained model (or base unit) with the first task. A learning method that implements a target model by learning labeled learning data using a supervised learning method in order to obtain it through various techniques (MLM, NSP, etc.) and fine-tune the pre-trained model to be suitable for the second task. represents. One of the models learned using this transfer learning method is BERT (Bidirectional Encoder Representations from Transformers), but it is not limited to this.

The description of the deep neural network described above is only an example and the present disclosure is not limited thereto. In the case of the convolutional neural network described above, it consists of a feature extraction unit (feature learning) that extracts features from the image, and a classification unit that performs classification using the extracted features. The feature extraction unit may include, but is not limited to, a convolution layer in which features are extracted from the image using a kernel, a ReLU layer as one of the activation functions, and a pooling layer to reduce the dimensionality of the data. In addition, the classification unit may include, but is not limited to, a flatten layer that lines up the features extracted from the feature extraction unit, a fully connected layer where classification is actually performed, and a softmax function.

A neural network can be learned in at least one of supervised learning, unsupervised learning, semi-supervised learning, self-supervised learning, or reinforcement learning. You can. Learning of a neural network may be a process of applying knowledge for the neural network to perform a specific operation to the neural network.

Neural networks can be trained to minimize output errors. In neural network learning, learning data is repeatedly input into the neural network, the output of the neural network and the error of the target for the learning data are calculated, and the error of the neural network is transferred from the output layer of the neural network to the input layer in the direction of reducing the error. This is the process of updating the weight of each node in the neural network through backpropagation. In the case of supervised learning, data in which the correct answer is labeled (labeled data) can be used in each learning data, and in the case of unsupervised learning, data in which the correct answer is not labeled in each learning data (unlabeled data) can be used. The amount of change in the connection weight of each updated node may be determined according to the learning rate. The neural network's calculation of input data and backpropagation of errors can constitute a learning cycle (epoch). The learning rate may be applied differently depending on the number of repetitions of the learning cycle of the neural network. Additionally, to prevent overfitting, methods such as increasing learning data, regularization, dropout to disable some nodes, and batch normalization layer can be applied.

Meanwhile, the model disclosed in one embodiment may borrow at least part of a transformer. The transformer may be composed of an encoder that encodes embedded data and a decoder that decodes the encoded data. A transformer may have a structure that receives a series of data, goes through encoding and decoding steps, and outputs a series of data of different types. In one embodiment, a series of data can be processed into a form that can be operated by a transformer. The process of processing a series of data into a form that can be operated by a transformer may include an embedding process. Expressions such as data token, embedding vector, embedding token, etc. may refer to data embedded in a form that a transformer can process.

In order for the transformer to encode and decode a series of data, the encoders and decoders within the transformer can be processed using an attention algorithm. The attention algorithm calculates the similarity of one or more keys for a given query, reflects the given similarity to the value corresponding to each key, and returns the reflected similarity value ( It may refer to an algorithm that calculates the attention value by weighting the values.

Depending on how queries, keys, and values are set, various types of attention algorithms can be classified. For example, if attention is obtained by setting the query, key, and value all the same, this may mean a self-attention algorithm. In order to process a series of input data in parallel, when the dimension of the embedding vector is reduced and attention is obtained by obtaining individual attention heads for each divided embedding vector, this refers to a multi-head attention algorithm. can do.

In one embodiment, the transformer may be composed of modules that perform a plurality of multi-head self-attention algorithms or a multi-head encoder-decoder algorithm. In one embodiment, the transformer may also include additional components other than the attention algorithm, such as embedding, normalization, and softmax. A method of configuring a transformer using an attention algorithm may include the method disclosed in Vaswani et al., Attention Is All You Need, 2017 NIPS, which is incorporated herein by reference.

Transformers can be applied to various data domains such as embedded natural language, segmented image data, and audio waveforms to convert a series of input data into a series of output data. In order to convert data with various data domains into a series of data that can be input to the transformer, the transformer can embed the data. Transformers can process additional data expressing relative positional or phase relationships between a series of input data. Alternatively, a series of input data may be embedded by additionally reflecting vectors expressing relative positional relationships or phase relationships between the input data. In one example, the relative positional relationship between a series of input data may include, but is not limited to, word order within a natural language sentence, relative positional relationship of each segmented image, temporal order of segmented audio waveforms, etc. . The process of adding information expressing relative positional or phase relationships between a series of input data may be referred to as positional encoding.

The above-mentioned program is C, C++, JAVA, machine language, etc. that the processor (CPU) of the computer can read through the device interface of the computer in order for the computer to read the program and execute the methods implemented as a program. It may include code coded in a computer language. These codes may include functional codes related to functions that define the necessary functions for executing the methods, and include control codes related to execution procedures necessary for the computer's processor to execute the functions according to predetermined procedures. can do. In addition, these codes may further include memory reference-related codes that indicate at which location (address address) in the computer's internal or external memory additional information or media required for the computer's processor to execute the above functions should be referenced. there is. In addition, if the computer's processor needs to communicate with any other remote computer or server to execute the above functions, the code uses the computer's communication module to determine how to communicate with any other remote computer or server. It may further include communication-related codes regarding whether communication should be performed and what information or media should be transmitted and received during communication.

The storage medium refers to a medium that stores data semi-permanently and can be read by a device, rather than a medium that stores data for a short period of time, such as a register, cache, or memory. Specifically, examples of the storage medium include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc., but are not limited thereto. That is, the program may be stored in various recording media on various servers that the computer can access or on various recording media on the user's computer. Additionally, the medium may be distributed to computer systems connected to a network, and computer-readable code may be stored in a distributed manner.

The steps of the method or algorithm described in connection with the embodiments of the present disclosure may be implemented directly in hardware, implemented as a software module executed by hardware, or a combination thereof. The software module may be RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), Flash Memory, hard disk, removable disk, CD-ROM, or It may reside on any type of computer-readable recording medium well known in the art to which this disclosure pertains.

Above, embodiments of the present disclosure have been described with reference to the attached drawings, but those skilled in the art will understand that the present disclosure can be implemented in other specific forms without changing its technical idea or essential features. You will be able to understand it. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive.

10: Service provision system 100: Service server
200: At least one corporate terminal 300: At least one group terminal
110: communication module 130: storage module
150: control module 310: display module

Claims (7)

A communication module that communicates with an external device;
A storage module that stores at least one process for providing a two-way affiliate matching service based on artificial intelligence; and
It includes a control module that provides the two-way affiliate matching service based on the at least one process,
The control module is,
Collect corporate data containing sales information on items provided by at least one company and group data containing tendency information on the tendencies of at least one organization and the tendencies of members belonging to the organization, and collect the collected companies. Based on the data and collected group data, create a promotional plan for companies and organizations that can be matched with each other,
The group data used to create the above promotion plan is:
On the Internet community comprised of members of the matched organization, the number of members who wrote comments on the items of the matched company, preferences for the items of the matched company derived through analysis of the context of the comments, and Among the members of the matched organization, it includes the number of members who already own items of the matched company derived through context analysis of the comment,
The number of members who already own items from the matched company is,
As a result of image analysis of a photo in which at least one of the members of the matched group is taken, as a result of analysis of comments mentioning that members of the matched group purchased each item, and as a result of analysis of comments mentioning that members of the matched group purchased each item It was derived based on at least one of the analysis results of comments mentioning the history of purchasing and selling to others through second-hand transactions or discarding.
An artificial intelligence-based two-way affiliate matching service provider. According to paragraph 1,
The control module is,
Controlling the comment to be analyzed using a predetermined language model, and selecting at least one of the sales price and the specifications of the item as a topic of debate among members of the matched group for the item from the analysis results of the comment,
The above promotion plan is:
It was created with additional consideration of the controversial topics selected above.
An artificial intelligence-based two-way affiliate matching service provider. According to paragraph 2,
Specifications as topics of debate selected above include size or color,
The control module is,
Using a predetermined generative artificial intelligence model, it is controlled so that the size or color preferred by the members is derived even though it is not available as an item of the matched company, and the derived size or color is controlled to be reflected in the promotion.
An artificial intelligence-based two-way affiliate matching service provider. delete According to paragraph 1,
The control module is,
Sorting a plurality of posts on the Internet community according to relative preference for the item based on comments written about the item of the matched company,
Controlling the promotion plan to be posted in the comments of a predetermined number of posts selected in order of preference among the plurality of sorted posts.
An artificial intelligence-based two-way affiliate matching service provider. According to clause 5,
The control module is,
When more than a certain number of items from the matched company are purchased, the promotion plan posted in the comment is controlled to be deleted.
An artificial intelligence-based two-way affiliate matching service provider. In a method of providing an artificial intelligence-based two-way affiliate matching service performed by a device,
Collecting corporate data including sales information about items provided by at least one company and group data including disposition information about the dispositions of at least one organization and the dispositions of members belonging to the organization; and
It includes the step of generating a certain promotion plan for companies and organizations that can be matched with each other based on the collected corporate data and collected group data,
The group data used to create the above promotion plan is:
On the Internet community comprised of members of the matched organization, the number of members who wrote comments on the items of the matched company, preferences for the items of the matched company derived through analysis of the context of the comments, and Among the members of the matched organization, it includes the number of members who already own the items of the matched company,
The number of members who already own items from the matched company is,
As a result of image analysis of a photo in which at least one of the members of the matched group is taken, as a result of analysis of comments mentioning that members of the matched group purchased each item, and as a result of analysis of comments mentioning that members of the matched group purchased each item It was derived based on at least one of the analysis results of comments mentioning the history of purchasing and selling to others through second-hand transactions or discarding.
Method of providing artificial intelligence-based two-way affiliate matching service.