KR102455296B1 - method for recommending knitted clothing products and a device supporting the same - Google Patents

Abstract

The present invention relates to a method for recommending a knitted clothing product and a device supporting the same. An electronic device comprises: a memory; and a processor connected to the memory. Therefore, according to various embodiments, viral marketing may be activated.

Description

{method for recommending knitted clothing products and a device supporting the same}

The present invention relates to a method for recommending a clothing product and a device supporting the same.

Specifically, an embodiment of the present invention relates to a method of recommending a knitted clothing product.

Clothing products are more than just daily necessities, they are a means of expressing individual personality and style, and their functions and uses are changing. Accordingly, a technology capable of predicting consumer tastes and recommending clothing products suitable for them is required.

Domestic Patent Publication 10-2020-0024404 A (2020.03.09) Domestic Patent Publication 10-2020-0058799 A (2020.05.28) Domestic Patent Publication 10-2007-0077908 A (2007.07.30)

Various embodiments may provide a clothing product recommendation method and an apparatus supporting the same.

Technical problems to be achieved in various embodiments are not limited to those mentioned above, and other technical problems not mentioned are considered by those of ordinary skill in the art from various embodiments to be described below. can be

According to various embodiments, a method performed by an electronic device may be provided.

According to various embodiments, the method includes: receiving request information including user information and clothing type information; From the output of a preset recommendation model according to the input of the user information, the second plurality of clothing products corresponding to the user information among the plurality of available clothing products, the second plurality of clothing products corresponding to the type corresponding to the clothing type information obtaining a recommended clothing product list including a plurality of recommended clothing products predicted to be preferred by the user; and providing information on the recommended clothing product list; may include doing

According to various embodiments, in obtaining the recommended clothing product list, a preference score related to the predicted preference of the user may be given to each of the second plurality of clothing products by the preset recommendation model.

According to various embodiments, the plurality of recommended clothing products may be M plurality of clothing products having the highest M preference score among the second plurality of clothing products, and M may be a natural number.

According to various embodiments, the plurality of recommended clothing products may be arranged in a descending order of the preference score in the recommended clothing product list.

According to various embodiments, when the preference score is given: (i) a first additional point is given to an apparel product with a history of purchase by the user, and (ii) a sales price within the maximum budget available to the user A second additional point may be given to the in-apparel product.

According to various embodiments, the first addition point may be a negative number, and the second addition point may be a positive number.

According to various embodiments, when the preference score is given: (iii) a third additional point is given to the clothing products being discounted, and (iv) the discounted clothing products exceeding the maximum budget available to the user. A fourth additional point may be given to an apparel product having an original selling price.

According to various embodiments, the third addition point may be a positive number, and the fourth addition point may be a positive number.

According to various embodiments, the third additional point may be set based on a discount rate of a discounted clothing product.

According to various embodiments, the fourth additional point may be set based on a difference between the original selling price and the discounted selling price of the clothing product, which is an original selling price that exceeds the maximum budget available to the user.

According to various embodiments, the preference score may be assigned based on Equation (1).

[Equation 1]

According to various embodiments, in Equation 1, S _k is a value corresponding to the preference score for a specific clothing product k, and X _i is the first plus point, the second plus point, the third plus point, and the A plurality of addition points including a fourth addition point may be an i-th addition point, and ω _i may be an i-th weight factor assigned to the i-th addition point among weight factors assigned to each of the plurality of addition points.

According to various embodiments, the weight factor may be a real number of 0 or more and 1 or less.

According to various embodiments, the clothing product with a history of purchase by the user is a clothing product provided in a single color, or purchased in a color different from the clothing product with a history of purchase by the user according to the preset recommendation model. When at least one of the clothing products predicted not to be available or the clothing products not provided with the user's preferred color predicted by the preset recommendation model is satisfied, the weighting factor assigned to the first additional point is the Among the plurality of additional points, the weight factor may be set to be greater than a weight factor assigned to the remaining additional points except for the first additional points.

According to various embodiments, the preset recommendation model may be preset based on application of machine learning to an artificial intelligence (AI) engine for obtaining the preset recommendation model.

According to various embodiments, the machine learning comprises: - (a1) learning the AI engine based on training data for obtaining the preset recommendation model; - (b1) acquiring first feedback information about the processed data output in response to the input of test data for verification of the learned AI engine into the AI engine; - (c1) updating the AI engine based on the first feedback information; and - (d1) the above (a1) to (c1) are repeated, but whenever (a1) to (c1) are repeated, the count value having the initial value of 0 is increased by 1, and the count value is a preset count threshold exit based on matching a value; It can be performed based on

According to various embodiments, the training data and the test data may be acquired based on training data for acquiring the preset recommendation model.

According to various embodiments, the learning data may include product characteristic information including types, materials, colors, sizes, and costs of the first plurality of clothing products, and age, gender, and occupation of a plurality of users including the user. , profile information including social network service (SNS) account information, purchase history information of the plurality of users, return history information of the plurality of users, types and materials of one or more clothing products obtained based on the return history information , may include returned product characteristic information, including color, size, and cost.

According to various embodiments, the method may include: performing evaluation on the accuracy of the preset recommendation model based on second feedback information on the recommended clothing product list; may further include

According to various embodiments, the second feedback information may include an evaluation score.

According to various embodiments, (a2) when the user requests to purchase a recommended clothing product having the highest preference score among the plurality of recommended clothing products, the evaluation score may be set to a positive number.

According to various embodiments, (b2) when the user requests to purchase a recommended clothing product other than the recommended clothing product having the highest preference score among the plurality of recommended clothing products, the evaluation score is the other recommended clothing product The product may be set to a negative number based on a ranking in the recommended clothing product list.

According to various embodiments, (c2) when the user requests to purchase a clothing product that is not included in the plurality of second plurality of clothing products and the plurality of recommended clothing products, the evaluation score may be set to a negative number. have.

According to various embodiments, (d2) when the user does not request a purchase for a clothing product for a preset time period from the time when the information on the recommended clothing product list is received, the evaluation score may be set to 0 can

According to various embodiments, an accuracy score for the accuracy of the recommendation model may be obtained based on the evaluation score.

According to various embodiments, when the accuracy score is less than or equal to a preset threshold, the recommendation model may be retrained based on big data obtained from the second feedback information.

According to various embodiments, the absolute value of the evaluation score set in (b2) may be smaller than the absolute value of the evaluation score set in (c2).

According to various embodiments, the method includes: providing the user with an interface enabling the user to write a purchase review on a clothing product; providing, in response to the user's request, information related to the user recommending a clothing sales service platform operated by the electronic device to the user; and when one or more of the following is satisfied: the purchase review is written based on the interface or the third party who has received information related to recommending the clothing sales service platform is identified as a new subscription based on the interface accumulating at least one of mileage usable for purchasing a plurality of clothing items or coupons usable for purchase of the first plurality of clothing items to the user; may further include

According to various embodiments, an electronic device may be provided.

According to various embodiments, the electronic device may include: a memory; and one or more processors coupled to the memory; may include.

According to various embodiments, the one or more processors are configured to: receive request information including user information and clothing type information; From the output of a preset recommendation model according to the input of the user information, the second plurality of clothing products corresponding to the user information among the plurality of available clothing products, the second plurality of clothing products corresponding to the type corresponding to the clothing type information obtaining a recommended clothing product list including a plurality of recommended clothing products predicted to be preferred by the user; and providing information on the recommended clothing product list; can be set to

According to various embodiments, in obtaining the recommended clothing product list, a preference score related to the predicted preference of the user may be given to each of the second plurality of clothing products by the preset recommendation model.

According to various embodiments, the plurality of recommended clothing products may be M plurality of clothing products having the highest M preference score among the second plurality of clothing products, and M may be a natural number.

According to various embodiments, the plurality of recommended clothing products may be arranged in a descending order of the preference score in the recommended clothing product list.

According to various embodiments, when the preference score is given: (i) a first additional point is given to an apparel product with a history of purchase by the user, and (ii) a sales price within the maximum budget available to the user A second additional point may be given to the in-apparel product.

According to various embodiments, the first addition point may be a negative number, and the second addition point may be a positive number.

According to various embodiments, when the preference score is given: (iii) a third additional point is given to the clothing products being discounted, and (iv) the discounted clothing products exceeding the maximum budget available to the user. A fourth additional point may be given to an apparel product having an original selling price.

According to various embodiments, the third addition point may be a positive number, and the fourth addition point may be a positive number.

According to various embodiments, the third additional point may be set based on a discount rate of a discounted clothing product.

According to various embodiments, the fourth additional point may be set based on a difference between the original selling price and the discounted selling price of the clothing product, which is an original selling price that exceeds the maximum budget available to the user.

According to various embodiments, the preference score may be assigned based on Equation (1).

[Equation 1]

According to various embodiments, in Equation 1, S _k is a value corresponding to the preference score for a specific clothing product k, and X _i is the first plus point, the second plus point, the third plus point, and the A plurality of addition points including a fourth addition point may be an i-th addition point, and ω _i may be an i-th weight factor assigned to the i-th addition point among weight factors assigned to each of the plurality of addition points.

According to various embodiments, the weight factor may be a real number of 0 or more and 1 or less.

According to various embodiments, the clothing product with a history of purchase by the user is a clothing product provided in a single color, or purchased in a color different from the clothing product with a history of purchase by the user according to the preset recommendation model. When at least one of the clothing products predicted not to be available or the clothing products not provided with the user's preferred color predicted by the preset recommendation model is satisfied, the weighting factor assigned to the first additional point is the Among the plurality of additional points, the weight factor may be set to be greater than a weight factor assigned to the remaining additional points except for the first additional points.

According to various embodiments, the preset recommendation model may be preset based on application of machine learning to an artificial intelligence (AI) engine for obtaining the preset recommendation model.

According to various embodiments, the machine learning comprises: - (a1) learning the AI engine based on training data for obtaining the preset recommendation model; - (b1) acquiring first feedback information about the processed data output in response to the input of test data for verification of the learned AI engine into the AI engine; - (c1) updating the AI engine based on the first feedback information; and - (d1) the above (a1) to (c1) are repeated, but whenever (a1) to (c1) are repeated, the count value having the initial value of 0 is increased by 1, and the count value is a preset count threshold exit based on matching a value; It can be performed based on

According to various embodiments, the training data and the test data may be acquired based on training data for acquiring the preset recommendation model.

According to various embodiments, the learning data may include product characteristic information including types, materials, colors, sizes, and costs of the first plurality of clothing products, and age, gender, and occupation of a plurality of users including the user. , profile information including social network service (SNS) account information, purchase history information of the plurality of users, return history information of the plurality of users, types and materials of one or more clothing products obtained based on the return history information , may include returned product characteristic information, including color, size, and cost.

According to various embodiments, the one or more processors are configured to: evaluate the accuracy of the preset recommendation model based on second feedback information for the recommended clothing product list; can be set to

According to various embodiments, the second feedback information may include an evaluation score.

According to various embodiments, (a2) when the user requests to purchase a recommended clothing product having the highest preference score among the plurality of recommended clothing products, the evaluation score may be set to a positive number.

According to various embodiments, (b2) when the user requests to purchase a recommended clothing product other than the recommended clothing product having the highest preference score among the plurality of recommended clothing products, the evaluation score is the other recommended clothing product The product may be set to a negative number based on a ranking in the recommended clothing product list.

According to various embodiments, (c2) when the user requests to purchase a clothing product that is not included in the plurality of second plurality of clothing products and the plurality of recommended clothing products, the evaluation score may be set to a negative number. have.

According to various embodiments, (d2) when the user does not request a purchase for a clothing product for a preset time period from the time when the information on the recommended clothing product list is received, the evaluation score may be set to 0 can

According to various embodiments, an accuracy score for the accuracy of the recommendation model may be obtained based on the evaluation score.

According to various embodiments, when the accuracy score is less than or equal to a preset threshold, the recommendation model may be retrained based on big data obtained from the second feedback information.

According to various embodiments, the absolute value of the evaluation score set in (b2) may be smaller than the absolute value of the evaluation score set in (c2).

According to various embodiments, the one or more processors may be configured to: provide the user with an interface enabling the user to write a purchase review on clothing products; providing, in response to the user's request, information related to the user recommending a clothing sales service platform operated by the electronic device to the user; and when one or more of the following is satisfied: the purchase review is written based on the interface or the third party who has received information related to recommending the clothing sales service platform is identified as a new subscription based on the interface accumulating at least one of mileage usable for purchasing a plurality of clothing items or coupons usable for purchase of the first plurality of clothing items to the user; can be set to

According to various embodiments, a non-transitory processor-readable medium storing one or more instructions to cause one or more processors to perform an operation will be provided. can

According to various embodiments, the operation may include: receiving request information including user information and clothing type information; From the output of a preset recommendation model according to the input of the user information, the second plurality of clothing products corresponding to the user information among the plurality of available clothing products, the second plurality of clothing products corresponding to the type corresponding to the clothing type information obtaining a recommended clothing product list including a plurality of recommended clothing products predicted to be preferred by the user; and providing information on the recommended clothing product list; may include doing

According to various embodiments, in obtaining the recommended clothing product list, a preference score related to the predicted preference of the user may be given to each of the second plurality of clothing products by the preset recommendation model.

According to various embodiments, the plurality of recommended clothing products may be M plurality of clothing products having the highest M preference score among the second plurality of clothing products, and M may be a natural number.

According to various embodiments, the plurality of recommended clothing products may be arranged in a descending order of the preference score in the recommended clothing product list.

According to various embodiments, when the preference score is given: (i) a first additional point is given to an apparel product with a history of purchase by the user, and (ii) a sales price within the maximum budget available to the user A second additional point may be given to the in-apparel product.

According to various embodiments, the first addition point may be a negative number, and the second addition point may be a positive number.

The various embodiments described above are only some of the various embodiments, and various embodiments in which the technical features of the various embodiments of the present disclosure are reflected are detailed descriptions to be described below by those of ordinary skill in the art. It can be derived and understood based on

According to various embodiments, a clothing product recommendation method and an apparatus supporting the same may be provided.

According to various embodiments, a user-customized clothing product may be recommended based on artificial intelligence.

According to various embodiments, viral marketing may be activated.

The effects obtainable from the various embodiments are not limited to the above-mentioned effects, and other effects not mentioned are clearly derived to those of ordinary skill in the art based on the detailed description below. can be understood

BRIEF DESCRIPTION OF THE DRAWINGS The accompanying drawings, which are included as part of the detailed description to aid understanding of the various embodiments, provide various embodiments and, together with the detailed description, explain the technical features of the present disclosure.
1 is a diagram for describing a system in which a method of operating an apparatus for providing a service according to various embodiments of the present disclosure may be implemented.
2 is a diagram illustrating a configuration of a first device and/or a second device according to various embodiments of the present disclosure;
3 is a diagram illustrating an example of operations of a user device and a server according to various embodiments of the present disclosure;
4 is a diagram illustrating an example of an operation of a user device according to various embodiments of the present disclosure;
5 is a diagram illustrating an example of an operation of a server according to various embodiments.
6 is a diagram illustrating an example of obtaining a list of recommended clothing products according to various embodiments of the present disclosure;
7 is a diagram illustrating a process of acquiring a recommendation model according to various embodiments.
8 is a diagram illustrating a method of operating an electronic device for obtaining a recommendation model according to various embodiments of the present disclosure;

The following embodiments combine elements and features of various embodiments in a predetermined form. Each component or feature may be considered optional unless explicitly stated otherwise. Each component or feature may be implemented in a form that is not combined with other components or features. In addition, various embodiments may be configured by combining some components and/or features. The order of operations described in various embodiments may be changed. Some features or features of one embodiment may be included in another embodiment, or may be replaced with corresponding features or features of another embodiment.

In the description of the drawings, procedures or steps that may obscure the gist of various embodiments are not described, and procedures or steps that can be understood at the level of those of ordinary skill in the art are also not described. did.

Throughout the specification, when a part is said to "comprising or including" a certain component, it does not exclude other components unless otherwise stated, meaning that other components may be further included. do. In addition, terms such as "... unit", "... group", and "module" described in the specification mean a unit that processes at least one function or operation, which is hardware or software or a combination of hardware and software. can be implemented as Also, "a or an", "one", "the" and like related terms are used herein in the context of describing various embodiments (especially in the context of the claims that follow). Unless otherwise indicated or clearly contradicted by context, it may be used in a sense including both the singular and the plural.

Hereinafter, preferred embodiments according to various embodiments will be described in detail with reference to the accompanying drawings. DETAILED DESCRIPTION The detailed description set forth below in conjunction with the appended drawings is intended to describe exemplary embodiments of various embodiments, and is not intended to represent the only embodiments.

In addition, specific terms used in various embodiments are provided to help the understanding of various embodiments, and the use of these specific terms may be changed to other forms without departing from the technical spirit of various embodiments. .

1. System Implementation

1 is a diagram for describing a system in which a method of operating an apparatus for providing a service according to various embodiments of the present disclosure may be implemented.

Referring to FIG. 1 , a system according to various embodiments may be implemented in various types of devices. In the description of various embodiments, a system according to various embodiments may be implemented by an electronic device. For example, the system may be implemented in the first device 100 and/or the second device 200 . In other words, the first device 100 and/or the second device 200 may perform operations according to various embodiments based on a system implemented in each device. Meanwhile, the system according to various embodiments is not limited to that shown in FIG. 1 , and may be implemented in more various devices and/or servers.

The first device 100 according to various embodiments may be a system and/or a smart device owned by a customer who wants to use a service platform operated by the system, etc. The operation according to various embodiments to be implemented may be implemented in the form of an application operable on a smart device. However, the first device 100 according to various embodiments is not limited thereto.

The second device 200 according to various embodiments may be an apparatus that performs wireless and/or wired communication with the first devices 100 and includes a database having a large storage capacity. For example, the second device 200 may interwork with the plurality of first devices 100 . Although not shown, a separate device for controlling/managing the second device may be provided.

A system according to various embodiments may include various modules for operation. Modules included in the system are implemented so that a physical device (eg, the first device 100 and/or the second device 200) on which the system is implemented (or included in the physical device) can perform a specified operation. It may be computer code or one or more instructions. In other words, the physical device in which the system is implemented stores a plurality of modules in the form of computer code in the memory, and when the plurality of modules stored in the memory are executed, the plurality of modules perform specified operations corresponding to the plurality of modules by the physical device. can make it work.

2 is a diagram illustrating a configuration of a first device and/or a second device according to various embodiments of the present disclosure;

Referring to FIG. 2 , the first device and/or the second device may include an input/output unit 210 , a communication unit 220 , a database 230 , and a processor 240 .

The input/output unit 210 may be various interfaces or connection ports that receive user input or output information to the user. The input/output unit 210 may be divided into an input module and an output module, and the input module receives a user input from a user. The user input may be made in various forms including a key input, a touch input, and a voice input. Examples of input modules that can receive such user input include a traditional keypad, keyboard, and mouse, as well as a touch sensor that detects a user's touch, a microphone that receives a voice signal, a camera that recognizes gestures through image recognition, and the like; A proximity sensor composed of an illuminance sensor or infrared sensor that detects user approach, a motion sensor that recognizes a user's motion through an acceleration sensor or a gyro sensor, and various other input means for sensing or receiving various types of user input It is a comprehensive concept that includes all Here, the touch sensor may be implemented as a piezoelectric or capacitive touch sensor for detecting a touch through a touch panel or a touch film attached to the display panel, an optical touch sensor for detecting a touch by an optical method, and the like. In addition, the input module may be implemented in the form of an input interface (USB port, PS/2 port, etc.) for connecting an external input device that receives a user input instead of a device that detects a user input by itself. In addition, the output module can output various information and provide it to the user. The output module is a comprehensive concept including a display that outputs an image, a speaker that outputs a sound, a haptic device that generates vibration, and other various types of output means. In addition, the output module may be implemented in the form of a port-type output interface for connecting the above-described individual output means.

For example, the display-type output module may display text, still images, and moving images. The display includes a liquid crystal display (LCD), a light emitting diode (LED) display, an organic light emitting diode (OLED) display, a flat panel display (FPD), and a transparent display. display), a curved display, a flexible display, a three-dimensional display, a holographic display, a projector, and various types of devices capable of performing other image output functions. It is a concept meaning an image display device in a broad sense that includes all of them. Such a display may be in the form of a touch display integrally formed with the touch sensor of the input module.

The communication unit 220 may communicate with an external device. Accordingly, the first device and/or the second device may transmit/receive information to and from an external device through the communication unit. For example, the first device and/or the second device may communicate with an external device to share information stored and generated in the system using the communication unit.

Here, communication, that is, transmission and reception of data may be performed by wire or wirelessly. To this end, the communication unit includes a wired communication module that accesses the Internet through a local area network (LAN), a mobile communication module that accesses a mobile communication network through a mobile communication base station and transmits and receives data, and a wireless local area network (WLAN) such as Wi-Fi. A short-distance communication module using an area network communication method or a wireless personal area network (WPAN) communication method such as Bluetooth or Zigbee, or a global navigation satellite system (GNSS) such as GPS (Global Positioning System) ) using a satellite communication module or a combination thereof. A wireless communication technology used for communication may include a Narrowband Internet of Things (NB-IoT) for low-power communication. At this time, for example, NB-IoT technology may be an example of LPWAN (Low Power Wide Area Network) technology, and may be implemented in standards such as LTE Cat (category) NB1 and/or LTE Cat NB2, It is not limited. Additionally or alternatively, a wireless communication technology implemented in a wireless device according to various embodiments may perform communication based on LTE-M technology. In this case, as an example, the LTE-M technology may be an example of an LPWAN technology, and may be called by various names such as enhanced machine type communication (eMTC). For example, LTE-M technology is 1) LTE CAT 0, 2) LTE Cat M1, 3) LTE Cat M2, 4) LTE non-BL (non-Bandwidth Limited), 5) LTE-MTC, 6) LTE Machine It may be implemented in at least one of various standards such as Type Communication, and/or 7) LTE M, and is not limited to the above-described name. Additionally or alternatively, the wireless communication technology implemented in the wireless device according to various embodiments may include at least one of ZigBee, Bluetooth, and Low Power Wide Area Network (LPWAN) in consideration of low power communication. may include, but is not limited to the above-mentioned names. For example, the ZigBee technology can create PAN (personal area networks) related to small/low-power digital communication based on various standards such as IEEE 802.15.4, and can be called by various names.

The database 230 may store various types of information. A database can store data temporarily or semi-permanently. For example, in the database, an operating program (OS) for driving the first device and/or the second device, a program or application (eg, a web application) for generating data or Braille for hosting a web site ) may be stored. In addition, the database may store the modules in the form of computer code as described above.

Examples of the database 230 include a hard disk (HDD), a solid state drive (SSD), a flash memory, a read-only memory (ROM), a random access memory (RAM), and the like. This can be. Such a database may be provided in a built-in type or a detachable type.

The processor 240 controls the overall operation of the first device 100 and/or the second device 200 . To this end, the processor 340 may perform calculation and processing of various types of information and may control operations of components of the first device and/or the second device. For example, the processor 340 may execute a program or application for providing a service. The processor 240 may be implemented as a computer or a similar device according to hardware software or a combination thereof. In hardware, the processor 240 may be provided in the form of an electronic circuit that processes electrical signals to perform a control function, and in software, it may be provided in the form of a program for driving the processor 240 in hardware. Meanwhile, in the following description, unless otherwise specified, the operations of the first device and/or the second device may be interpreted as being performed under the control of the processor 240 . That is, when the modules implemented in the system are executed, the modules may be interpreted as controlling the processor 240 to perform the following operations on the first device and/or the second device.

In summary, various embodiments may be implemented through various means. For example, various embodiments may be implemented by hardware, firmware, software, or a combination thereof.

In the case of implementation by hardware, the method according to various embodiments may include one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), FPGAs (field programmable gate arrays), a processor, a controller, a microcontroller, may be implemented by a microprocessor.

In the case of implementation by firmware or software, the method according to various embodiments may be implemented in the form of a module, procedure, or function that performs the functions or operations described below. For example, the software code may be stored in a memory and driven by a processor. The memory may be located inside or outside the processor, and data may be exchanged with the processor by various known means.

2. Configuration/operation of devices according to various embodiments

Hereinafter, various embodiments will be described in more detail based on the above technical idea. The various embodiments described below may be combined in whole or in part to constitute other various embodiments unless mutually exclusive, which may be clearly understood by those of ordinary skill in the art.

The contents of Section 1 described above may be applied to various embodiments described below. For example, operations, functions, terms, etc. that are not defined in various embodiments described below may be performed and described based on the contents of the first section.

Unless specifically stated otherwise, in the description of various embodiments, A/B/C may mean A and/or B and/or C.

Unless specifically stated otherwise, in the description of various embodiments, more than/above A may be substituted with more than/above A.

Unless specifically stated otherwise, in the description of various embodiments, less than/below B may be replaced with less than/below B.

Hereinafter, a user device according to an implementation example of the first device 100 according to various embodiments will be described, but other devices performing similar functions may also be the first device. For example, the first device may be a terminal, a smart phone, a laptop computer, a tablet PC, an electronic book terminal, a digital broadcasting terminal, a personal digital assistant (PDA), a portable multimedia player (PMP), or a PC. (personal computer), etc. may be present, but is not limited thereto.

Hereinafter, a server according to an implementation example of the second device 200 according to various embodiments will be described, but other devices performing similar functions may also be the second device.

Unless otherwise noted, information used/obtained/output/displayed in the description of various embodiments below is information directly identified/obtained by the first device and/or the second device, or the first device and / or information stored in a database included in the second device, or information received by the first device and/or the second device from a server and/or other external devices.

In the following description of various embodiments, various embodiments are described by taking a clothing sales service platform related to manufacturing and selling clothing products as an example, but the various embodiments are not limited thereto, and various embodiments are different types of products. can also be extended for The clothing product in the present invention may include knit clothing, and the knit may be a generic term for products made by soft ironing a loop formed by a first series of weft or warp yarns. Accordingly, in one embodiment of the present invention, 'clothing product' is 'knitted clothing product', 'clothing sales service platform' is 'knitted clothing sales service platform', and 'recommended clothing product list' is 'recommended knitted clothing' 'Product list', 'Clothing type information' may be replaced with 'Knitted clothing type information'.

Unless specifically stated otherwise, in the description of various embodiments, a user's action may be replaced with an action of a user device used/used by the user.

3 is a diagram illustrating an example of operations of a user device and a server according to various embodiments of the present disclosure;

4 is a diagram illustrating an example of an operation of a user device according to various embodiments of the present disclosure;

5 is a diagram illustrating an example of an operation of a server according to various embodiments.

3 to 5 , in operations 301, 401, and 501 according to various embodiments, the user device may transmit request information, and the server may receive it.

In operations 303 and 503 according to various embodiments, the server may obtain/create a list of recommended clothing products.

In operations 305, 405, and 505 according to various embodiments, the server may transmit information related to a list of recommended clothing products, and the user device may receive it.

For more specific details of each operation according to various embodiments, reference may be made to descriptions of various embodiments to be described later.

6 is a diagram illustrating an example of obtaining a list of recommended clothing products according to various embodiments of the present disclosure;

Referring to FIG. 6 , according to various embodiments, a user (service user) may transmit request information including user information and clothing type information to a server. (One)

According to various embodiments, the user device may transmit request information including user information and clothing type information to the server. (One)

According to various embodiments, from an output of a preset recommendation model according to input of user information, a user among a plurality of second clothing items corresponding to a type corresponding to the clothing type information among a plurality of available clothing products. obtain a recommended clothing product list including a plurality of recommended clothing products predicted to be preferred by the user corresponding to the information, and transmit information related to the recommended clothing product list (information including the recommended clothing product list); The user device may receive it. (2)

According to various embodiments, the request information may be understood as information for requesting the server to recommend clothes suitable for the user from among the types of clothes that the user wants to purchase according to the clothes type information. For example, the user information may include the user's profile information including the user's age, gender, occupation, and social network service (SNS) account information. For example, the clothing type information may be information on a specific type of clothing that the user desires to purchase from among a plurality of types of clothing that can be provided/sold by a service platform operated by the server.

According to various embodiments, the server may input user information into a preset recommendation model. According to various embodiments, the server may obtain a list of recommended clothing products from the output of a preset recommendation model.

According to various embodiments of the present disclosure, the recommended clothing product list may include, among a plurality of second plurality of clothing products corresponding to the type corresponding to the clothing type information among the provided first plurality of clothing products, the user corresponding to the user information may prefer. It may include a plurality of recommended clothing products predicted to be.

According to various embodiments, the server recommends that the user prefers the second plurality of clothing products corresponding to the type requested by the user among the plurality of first clothing products that can be provided/manufactured by the service platform operated by the server. The predicted plurality of recommended clothing products may be provided in the form of a list.

According to various embodiments, in order to obtain a recommended clothing product list, a preference score related to a predicted preference of a user may be assigned to a preset recommendation model for each of the second plurality of clothing products. According to various embodiments, the preference score is a score obtained by predicting/predicting/evaluating the user's preference level and/or preference possibility, and may be a clothing product expected/predicted to be preferred by the user as the preference score increases.

According to various embodiments, the plurality of recommended clothing products may be M plurality of clothing products having the M highest preference score among the plurality of second clothing products. 6 illustrates an example in which M=5, various embodiments are not limited thereto.

According to various embodiments, the plurality of recommended clothing products may be sorted in descending order of preference scores in the recommended clothing product list. For example, in FIG. 6 , recommended clothing products XX1, XX2, XX3, XX4, and XX5 may be sorted in descending order of their respective preference scores. For example, XX1 may be a clothing product having the highest preference score, and XX5 may be a clothing product having the lowest preference score in the recommended clothing product list.

According to various embodiments, an additional point may be considered when a preference score is given.

According to various embodiments, additional points and weights that are differently given for each specific situation may be used to assign/calculate a preference score.

According to various embodiments, the preference may be calculated based on Equation (1).

[Equation 1]

S _k : Preference score for a specific clothing product k (and/or a corresponding value)

X _i : the i-th addition point among the plurality of addition points

)ω _i : the i-th weight factor (

)

According to various embodiments, the plurality of addition points may include a first addition point, a second addition point, a third addition point, and a fourth addition point:

1) First bonus points: Additional points given to clothing products that have been purchased by the user. negative value.

According to various embodiments, it is considered that the same user rarely purchases the same clothing product, and thus, a first negative addition point may be given to clothing products for which the user has purchased the same clothing product.

2) Second bonus points: Additional points given to clothing products whose selling price is within the maximum budget available to the user. positive value.

3) Third Bonus Points: Bonus points given to clothing products that are being discounted. positive value.

According to various embodiments, the third additional point may be set based on a discount rate of a discounted clothing product. For example, the larger the discount rate, the larger the third plus point may be set, and the smaller the discount rate, the smaller the third plus point may be set.

4) Fourth Bonus Point: Bonus points given to apparel products whose original selling price exceeds the maximum budget available to the user among the discounted apparel products. positive value. According to various embodiments, in this case, it may be considered that there is a merit to the user as an opportunity to purchase an apparel product having an original selling price that exceeds the maximum available budget. According to various embodiments, the fourth additional point may be set based on a difference between the original selling price and the discounted selling price of the clothing product, which is an original selling price that exceeds the maximum budget available to the user. For example, the greater the difference, the greater the fourth addition point may be set, and the smaller the difference, the smaller the fourth addition point may be set.

As described above, according to various embodiments, it is considered that the same user rarely purchases the same clothing product, and thus, a negative first additional point may be given to clothing products for which the user has purchased a history. . However, according to various embodiments, there may be a case where the same user wants to purchase the same clothing product with a different color, which may be considered.

According to various embodiments, it is determined that the clothing product with a history of purchase by the user is a clothing product provided in a single color, or that it will not be purchased in a color different from the clothing product with a history of purchase by the user according to a preset recommendation model. When at least one of the predicted clothing products or the clothing products not provided with the user's preferred color predicted by a preset recommendation model is satisfied, the weighting factor assigned to the first additional point is the second one of the plurality of additional points. It may be set to be larger than the weight factor given to the remaining additional points except for one additional point.

According to various embodiments, a clothing product with a history of purchase by a user is a clothing product provided in a single color, and according to a preset recommendation model, it is determined that a clothing product with a history of purchase by the user will not be purchased in a different color. When both the predicted clothing product and the clothing product not provided with the user's preferred color predicted by the preset recommendation model are not satisfied, the first additional point is not given and/or is higher than one or more additional points among the plurality of additional points. It can be set small.

According to various embodiments, the server may provide the user with an interface through which the user can write a purchase review on the clothing product.

According to various embodiments, in response to the user's request, information related to the user recommending the clothing sales service platform operated by the server may be provided to the user. According to various embodiments, this is related to viral marketing, and when a user recommends a clothing sales service platform to neighbors and/or a third party and gives a reward therefor, the user's voluntary participation is induced and the viral marketing is activated. can

According to various embodiments, when one or more of a purchase review is written based on an interface or a third party who has received information related to recommending the clothing sales service platform is identified as newly subscribed by the user is satisfied , the server may accumulate one or more of mileage usable for the purchase of the first plurality of clothing products (all clothing products that can be manufactured) or coupons that can be used for the purchase of the first plurality of clothing products to the user.

7 is a diagram illustrating a process of acquiring a recommendation model according to various embodiments.

8 is a diagram illustrating a method of operating an electronic device for obtaining a recommendation model according to various embodiments of the present disclosure;

An artificial intelligence system is a computer system that implements human-level intelligence, and unlike the existing rule-based smart system, the machine learns, judges, and becomes smarter by itself. The more the AI system is used, the better the recognition rate and the more accurate understanding of user preferences, and the existing rule-based smart systems are gradually being replaced by deep learning-based AI systems.

Artificial intelligence technology consists of machine learning (deep learning) and elemental technologies using machine learning.

Machine learning is an algorithm technology that categorizes/learns characteristics of input data by itself, and element technology uses machine learning algorithms such as deep learning to simulate functions such as cognition and judgment of the human brain. It consists of technical fields such as understanding, reasoning/prediction, knowledge expression, and motion control.

The various fields where artificial intelligence technology is applied are as follows. Linguistic understanding is a technology for recognizing and applying/processing human language/text, and includes natural language processing, machine translation, dialogue system, question and answer, and speech recognition/synthesis. Visual understanding is a technology for recognizing and processing objects like human vision, and includes object recognition, object tracking, image search, human recognition, scene understanding, spatial understanding, image improvement, and the like. Inferential prediction is a technology for logically reasoning and predicting by judging information, and includes knowledge/probability-based reasoning, optimization prediction, preference-based planning, and recommendation. Knowledge expression is a technology that automatically processes human experience information into knowledge data, and includes knowledge construction (data generation/classification) and knowledge management (data utilization). Motion control is a technology for controlling autonomous driving of a vehicle and movement of a robot, and includes motion control (navigation, collision, driving), manipulation control (action control), and the like.

In the following description, various embodiments have been described on the premise that the server performs the operation of acquiring the recommended model, but according to various embodiments, another server device outside the server may perform the operation of acquiring the recommended model. Alternatively, according to various embodiments, a plurality of user devices 200 and/or a plurality of servers are provided so that each operation of the operation of obtaining a recommendation model among the plurality of user devices 200 and/or of the plurality of servers is performed. It may be distributed and implemented separately.

Referring to FIG. 8 , according to various embodiments, the server may collect data for learning.

According to various embodiments, the learning data may include product characteristic information including types of the first plurality of clothing products (the types of all clothing products that can be provided), materials, colors, sizes, and costs, and age and gender of a plurality of users. , occupation, profile information including social network service (SNS) account information, purchase history information of multiple users, and return history information of multiple users ), may include returned product characteristic information including the type, material, color, size, and cost of one or more clothing products obtained based on the return history information.

According to various embodiments, the training data may include data for training and data for testing. For example, the server may classify the training data into training data and test data. For example, data for training may be used to train a model, and data for testing may be used to verify and update the trained model.

According to various embodiments, the server may train the AI engine based on the training data. For example, the AI engine may be an artificial intelligence engine that may be learned based on an artificial intelligence algorithm. For example, an AI engine may include a Deep Neural Network (DNN). For example, artificial intelligence engines include Convolutional Neural Network (CNN), Deep Neural Network (DNN), Recurrent Neural Network (RNN), Restricted Boltzmann Machine (RBM), Deep Belief Network (DBN), Bidirectional Recurrent Deep Neural Network (BRDNN). ) or Deep Q-Networks, but is not limited thereto.

According to various embodiments, the server may acquire processed data for data for testing based on the learned model.

According to various embodiments, the server may obtain first feedback information on the processing data.

According to various embodiments, the first feedback information may be input from a server manager.

According to various embodiments, the server may update the learned model based on the first feedback information.

According to various embodiments, the server corrects a characteristic of a learned model (eg, a characteristic of a CNN) based on the first feedback information, and repeats the process of obtaining and updating the feedback based on the modified model. can

According to various embodiments, when the number of iterations reaches a preset threshold value (eg, 7-9 times), the server may terminate the operation and acquire the learned model as a recommended model.

According to various embodiments, the server may evaluate the accuracy of the recommendation model based on the second feedback information on the list of recommended clothing products provided to the user by the recommendation model.

According to various embodiments, the second feedback information may include an evaluation score. According to various embodiments, the evaluation score may be an accuracy score of the recommendation model and/or for evaluating the accuracy of the recommendation model (the higher the accuracy score, the higher the accuracy of the recommendation model).

An example of a method of setting an evaluation score according to various embodiments may be as follows.

1) According to various embodiments, when a user requests to purchase a recommended clothing product having the highest preference score among a plurality of recommended clothing products included in the recommended clothing product list, the evaluation score may be set to a positive number. According to various embodiments, in this case, it is considered that the recommendation model predicts the clothing product that the user will prefer, and that the clothing product actually selected by the user matches the clothing product predicted by the recommendation model to have the highest preference. may be set.

2) According to various embodiments, when a user requests to purchase a recommended clothing product other than the recommended clothing product having the highest preference score among a plurality of recommended clothing products included in the recommended clothing product list, the evaluation score is negative can be set to According to various embodiments, in this case, it is considered that the recommendation model predicts the clothing product that the user will prefer, but the clothing product actually selected by the user is different from the clothing product that the recommendation model predicts to have the highest preference. , a negative evaluation score may be set. According to various embodiments, the evaluation score may be set based on a ranking in the recommended clothing product list of other recommended clothing products selected by the user. For example, the higher the rank, the smaller the absolute value of the evaluation score may be set, and the lower the rank, the larger the absolute value of the evaluation score may be set.

3) According to various embodiments, when a user requests to purchase a clothing product that is not included in the plurality of recommended clothing products of the second plurality of clothing products, the evaluation score may be set to a negative number. According to various embodiments, in this case, since the recommendation model does not predict the clothing product to be preferred by the user, a negative evaluation score may be set. According to various embodiments, the absolute value of the evaluation score set in this case may be greater than the absolute value of the evaluation score set in case 2). That is, the absolute value of the evaluation score set in 3) may be greater than the absolute value of the evaluation score set when the rank is the lowest in 2).

4) According to various embodiments, when the user does not request to purchase the clothing product for a preset time period from the point in time when the information on the recommended clothing product list is received, the evaluation score may be set to 0.

According to various embodiments, an accuracy score for the accuracy of the recommendation model may be obtained based on the evaluation score. For example, an accuracy score may be obtained based on the summation of the evaluation scores. According to various embodiments, when the accuracy score is less than or equal to a preset threshold, the recommendation model may be retrained based on big data obtained from the second feedback information.

Referring to FIG. 9 , for example, in operation 801 , the server may train a model based on training data among training data and test data obtained based on processing the training data.

For example, in operation 803 , the server may acquire first feedback information about the processed data output in response to the test data being input to the learned model.

For example, in operation 805 , the server may update the model based on the first feedback information.

For example, in operation 807, the server may compare the number of times operations 801 to 805 are repeated with a preset threshold value (N_TH).

For example, if the number of repetitions does not match the preset threshold value (ie, the number of repetitions is less than the preset threshold value), the server may return to operation 801 and perform operations 801 to 805 again.

For example, the server may terminate the process if the number of iterations matches a preset threshold.

Since examples of the above-described proposed method may also be included as one of various embodiments, it is obvious that they may be regarded as a kind of proposed method. In addition, the above-described proposed methods may be implemented independently, or may be implemented in the form of a combination (or merge) of some of the proposed methods.

Various embodiments may be embodied in other specific forms without departing from the technical idea and essential characteristics thereof. Accordingly, the above detailed description should not be construed as restrictive in all respects but as exemplary. The scope of the various embodiments should be determined by a reasonable interpretation of the appended claims, and all modifications within the equivalent scope of the various embodiments are included in the scope of the various embodiments. In addition, claims that are not explicitly cited in the claims may be combined to form an embodiment or may be included as a new claim by amendment after filing.

Claims (5)

In an electronic device,
Memory; and a processor coupled to the memory. including,
The processor is:
receive request information including user information and clothing type information;
From the output of a preset recommendation model according to the input of the user information, the second plurality of clothing products corresponding to the user information among the plurality of available clothing products, the second plurality of clothing products corresponding to the type corresponding to the clothing type information Obtaining a recommended clothing product list including a plurality of recommended clothing products predicted to be preferred by the user,
providing information on the recommended clothing product list,
In obtaining the recommended clothing product list, a preference score related to the predicted preference of the user is given to each of the second plurality of clothing products by the preset recommendation model;
The plurality of recommended clothing products are M clothing products having the highest preference score among the second plurality of clothing products, M is a natural number,
The plurality of recommended clothing products are arranged in descending order of the preference score in the recommended clothing product list,
In giving the preference score:
(i) A first additional point is given to clothing products that have been purchased by the user;
(ii) a second additional point is given to clothing products whose sales price is within the maximum budget available to the user;
(iii) A third extra point is given to apparel products that are being discounted;
(iv) Among the discounted clothing products, a fourth additional point is given to clothing products whose original selling price exceeds the maximum budget available to the user;
The first addition point is a negative number, the second addition point is a positive number,
the third addition point is a positive number, the fourth addition point is a positive number,
The third additional point is set based on the discount rate of the clothing product being discounted,
The fourth additional point is set based on a difference between the original selling price and the discounted selling price of the clothing product, which is an original selling price that exceeds the maximum budget available to the user;
The preference score is given based on Equation 1,
[Equation 1]

In Equation 1, S _k is a value corresponding to the preference score for a specific clothing product k, and X _i is a plurality of points including the first plus point, the second plus point, the third plus point, and the fourth plus point. is the i-th addition point of the addition points, and ω _i is the i-th weight factor assigned to the i-th addition point among the weight factors assigned to each of the plurality of addition points,
The weighting factor is a real number between 0 and 1,
The clothing product with a history of purchase by the user is a clothing product provided in a single color, or a clothing product predicted not to be purchased in a color different from that of the clothing product purchased by the user according to the preset recommendation model. If one or more of the following conditions are satisfied: , or a clothing product that is not provided in the user's preferred color predicted by the preset recommendation model, the weighting factor assigned to the first additional point is the second one of the plurality of additional points. It is set larger than the weight factor given to the rest of the additional points except for 1 additional point,
The processor is:
providing the user with an interface that allows the user to write a purchase review for the clothing product,
In response to the user's request, providing the user with information related to the user recommending a clothing sales service platform operated by the electronic device,
When one or more of the purchase review is written based on the interface or the third party who has received information related to recommending the clothing sales service platform is identified as newly subscribed by the user is satisfied, the first plurality of and accumulating, to the user, at least one of mileage usable for purchase of clothing products of , or coupons usable for purchase of the first plurality of clothing products. delete delete The method of claim 1,
The preset recommendation model is preset based on machine learning being applied to an artificial intelligence (AI) engine for obtaining the preset recommendation model,
The machine learning is:
- (a1) learning the AI engine based on training data for obtaining the preset recommendation model;
- (b1) acquiring first feedback information about the processed data output in response to the input of test data for verification of the learned AI engine into the AI engine;
- (c1) updating the AI engine based on the first feedback information; and
- (d1) (a1) to (c1) are repeated, but each time (a1) to (c1) is repeated, the count value with the initial value 0 is increased by 1, and the count value is a preset count threshold Terminate based on match;
It is carried out on the basis of being
The training data and the test data are obtained based on the training data for obtaining the preset recommendation model,
The learning data includes product characteristic information including the type, material, color, size, and cost of the first plurality of clothing products, the age, gender, occupation, and social network service (SNS) of a plurality of users including the user. Profile information including account information, purchase history information of the plurality of users, return history information of the plurality of users, and the type, material, color, size, and cost of one or more clothing products obtained based on the return history information An electronic device comprising returned product characteristic information comprising: 5. The method of claim 4,
evaluating the accuracy of the preset recommendation model based on second feedback information on the recommended clothing product list; further including doing
The second feedback information includes an evaluation score,
(a2) when the user requests to purchase a recommended clothing product having the highest preference score among the plurality of recommended clothing products, the evaluation score is set to a positive number;
(b2) when the user requests to purchase a recommended clothing product other than the recommended clothing product having the highest preference score among the plurality of recommended clothing products, the evaluation score is the recommended clothing product list of the other recommended clothing products set to a negative number based on its rank within,
(c2) when the user requests a purchase for a clothing product that is not included in the plurality of second plurality of clothing products and the plurality of recommended clothing products, the evaluation score is set to a negative number;
(d2) when the user does not request a purchase for a clothing product for a preset time period from the time when the information on the recommended clothing product list is received, the evaluation score is set to 0;
An accuracy score for the accuracy of the recommendation model is obtained based on the evaluation score,
When the accuracy score is less than or equal to a preset threshold, the recommendation model is retrained based on the big data obtained from the second feedback information,
The electronic device, wherein the absolute value of the evaluation score set in (b2) is smaller than the absolute value of the evaluation score set in (c2).

Images