Method and electronic device for processing product sales registration request
By segmenting product names and calculating similarity scores with brand keywords, the method enhances brand gating detection accuracy, preventing unauthorized sales of protected brand products and counterfeits on e-commerce platforms.
Patent Information
- Application Number
- PCT/KR2023/007580
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-05-15
- Filing Date
- 2023-06-02
- Publication Date
- 2024-11-21
AI Technical Summary
E-commerce platforms face challenges in preventing unauthorized sellers from offering protected brand products or counterfeit items by using brand gating technology, as malicious sellers can bypass detection by using synonyms or obfuscation in product names.
The method involves segmenting product names into keywords, identifying synonyms, and calculating similarity scores with brand keywords to determine if a sales registration request is subject to brand gating, using tokenization and a keyword synonym list to enhance detection accuracy.
This approach effectively prevents malicious sellers from bypassing brand gating by accurately determining if a product sales registration request is related to a protected brand, thereby protecting the brand's image and consumer trust.
Smart Images

Figure KR2023007580_21112024_PF_FP_ABST
Abstract
Description
Method and electronic device for processing product sales registration requests
[0001] The present disclosure relates to a method and electronic device for processing product sales registration requests. More specifically, the present disclosure relates to a brand gating technique for preventing sellers (vendors) on an e-commerce platform from selling products of a protected brand, or their illegal copies or counterfeits, even if they are not authorized to do so.
[0002] In an online store on an e-commerce platform, sellers sell various products, and consumers can purchase them. For example, to list a product on an online store, a seller can submit a product registration request to the e-commerce platform administrator. If the e-commerce platform administrator accepts the request, the seller can then sell the product on the online store.
[0003] Meanwhile, e-commerce platforms can maintain a brand's image and protect consumer trust by restricting or controlling the sale of certain branded products. To this end, e-commerce platforms can use brand gating technology to prevent unauthorized sellers from selling protected branded products or their pirated or counterfeit counterparts.
[0004] As the e-commerce market has grown in recent years, the variety and number of products offered on online stores on e-commerce platforms, as well as the number of sellers, have skyrocketed. Consequently, brand gating has become increasingly important. This allows sellers who are not authorized to sell protected brand products to detect and block attempts to sell protected brand products or products that could be mistaken for them.
[0005] According to brand gating technology, a brand gating system can match a seller's product name with brand keywords set for a protected brand. If the product name includes at least one brand keyword, the brand gating system can determine the seller's sales registration request as eligible for brand gating, as the seller's product is related to the protected brand. For example, if a seller's product name is "2023 Apple AirPods Bluetooth Earphones" and the brand keywords are "Apple," "AirPods," "Bluetooth," and "Earphones," the product name contains at least one brand keyword, so the brand gating system can determine the seller's sales registration request as eligible for brand gating. However, if the seller uses synonyms or obfuscations of brand keywords to construct a product name, the seller's product name will not contain brand keywords, and therefore the brand gating system may determine that the seller's sales registration request is not eligible for brand gating. For example, if a seller changes the brand keyword "earphones" to the synonym "earpiece" or constructs a product name by concatenating words before or after the brand keyword "AirPods," the product name may not contain words identical to the brand keyword, and thus the brand gating system may determine that the seller's sales registration request is not subject to brand gating. Malicious sellers can bypass brand gating in this way and register and sell their products on e-commerce platforms' online stores. To effectively protect a brand, the accuracy of determining whether a seller's product sales registration request is subject to brand gating must be improved to prevent brand gating bypass.
[0006] In order to solve the above-described problem, the present disclosure provides a technology for segmenting a product name requested for sale registration by a seller into one or more keywords, and detecting and processing whether the seller's product sale registration request is subject to brand gating based on the similarity between a keyword group based on synonyms of the keywords and a brand keyword, thereby preventing malicious sellers from bypassing brand gating.
[0007] The technical problems of the present disclosure are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art of the present disclosure from the description below.
[0008] A method for processing a product sale registration request performed by an electronic device according to various embodiments of the present disclosure comprises the steps of: receiving a product sale registration request, wherein the product sale registration request includes information on a product name of the product; generating one or more first keywords for the product name by tokenizing the product name; identifying one or more synonyms for at least some of the one or more first keywords based on a keyword synonym list; generating one or more keyword groups based on combinations between the one or more first keywords and the one or more synonyms, wherein each of the one or more keyword groups includes one or more second keywords; calculating one or more scores based on a similarity between the one or more second keywords and one or more third keywords set for a protected brand, wherein the one or more keyword groups each correspond to the one or more scores; calculating an average score for the one or more keyword groups by averaging the one or more scores; comparing the average score with a preset threshold value; And based on the result of the above comparison, it may include a step of generating information requesting confirmation of whether the sales registration request is accepted.
[0009] Tokenization of the product name according to various embodiments of the present disclosure may be performed based on a dictionary for morphological analysis, and the dictionary for morphological analysis may be generated based on information about one or more products.
[0010] The step of generating the one or more keyword groups according to various embodiments of the present disclosure may include the step of generating the one or more keyword groups including the one or more second keywords by replacing at least a portion of the one or more first keywords with the one or more synonyms.
[0011] The step of generating one or more keyword groups according to various embodiments of the present disclosure may include the step of identifying a first keyword having a synonym among the one or more first keywords based on the keyword synonym list; and the step of replacing the first keyword having a synonym with the one or more synonyms.
[0012] The step of calculating one or more scores according to various embodiments of the present disclosure may include: matching the one or more second keywords with the one or more third keywords such that the one or more second keywords each correspond to the one or more third keywords; calculating one or more similarity values between the one or more second keywords and the one or more third keywords based on the matching; and calculating a score by adding up the one or more similarity values.
[0013] According to various embodiments of the present disclosure, each of the one or more third keywords may be associated with a preset weight, and the step of calculating the one or more scores may include: matching the one or more second keywords with the one or more third keywords such that the one or more second keywords correspond to the one or more third keywords, respectively; calculating one or more similarity values between the one or more second keywords and the one or more third keywords based on the matching; and calculating a score based on the one or more similarity values and the weights for each of the one or more third keywords.
[0014] A method for processing a product sales registration request performed by an electronic device according to various embodiments of the present disclosure may further include a step of obtaining one or more values by multiplying the one or more similarity values and the weights for each of the one or more third keywords; and a step of calculating a score by adding up the one or more values.
[0015] A method for processing a product sales registration request performed by an electronic device according to various embodiments of the present disclosure may further include a step of receiving information about the one or more third keywords, and the information about the one or more third keywords may include information for setting a weight for at least some of the one or more third keywords.
[0016] Among the one or more third keywords according to various embodiments of the present disclosure, the weight of a third keyword for which a weight is not set may be determined as a default value.
[0017] A method for processing a product sales registration request performed by an electronic device according to various embodiments of the present disclosure may further include the steps of transmitting information requesting confirmation of acceptance of the sales registration request to a user's terminal device; and receiving, from the terminal device, selection information of the user for accepting or rejecting the sales registration request.
[0018] A method for processing a product sales registration request performed by an electronic device according to various embodiments of the present disclosure may further include a step of updating the threshold value based on whether the sales registration request is accepted or rejected.
[0019] A method for processing a product sales registration request performed by an electronic device according to various embodiments of the present disclosure may further include a step of updating a weight for each of the one or more third keywords based on whether the sales registration request is accepted or rejected.
[0020] The sales registration request according to various embodiments of the present disclosure may further include at least one of information on the price of the product or information on the seller of the product.
[0021] A method for processing a product sales registration request performed by an electronic device according to various embodiments of the present disclosure may further include, in response to a step of generating information requesting confirmation of acceptance of the sales registration request, a step of determining whether to accept or reject the sales registration request based on at least one of the price of the product or the sales history of the seller of the product.
[0022] A method for processing a product sales registration request performed by an electronic device according to various embodiments of the present disclosure may further include a step of updating the threshold value based on whether the sales registration request is accepted or rejected.
[0023] A method for processing a product sales registration request performed by an electronic device according to various embodiments of the present disclosure may further include a step of updating a weight for each of the one or more third keywords based on whether the sales registration request is accepted or rejected.
[0024] An electronic device for processing a product sales registration request according to various embodiments of the present disclosure comprises: a processor; And it may include a memory storing instructions configured to be executed by the processor, wherein the instructions, when executed by the processor, cause the processor to receive a sales registration request for a product, wherein the sales registration request includes information on a product name of the product, perform tokenization on the product name to generate one or more first keywords for the product name, and, based on a keyword synonym list, identify one or more synonyms for at least some of the one or more first keywords, and, based on a combination between the one or more first keywords and the one or more synonyms, generate one or more keyword groups, each of the one or more keyword groups including one or more second keywords, calculate one or more scores based on a similarity between the one or more second keywords and one or more third keywords set for a protected brand, wherein the one or more keyword groups each correspond to the one or more scores, calculate an average score for the one or more keyword groups by averaging the one or more scores, and compare the average score with a preset threshold value, and, based on a result of the comparison, generate information requesting confirmation of whether the sales registration request is accepted. You can do it.
[0025] According to various embodiments of the present disclosure, a technology is provided for dividing a product name into one or more keywords, and detecting and processing whether a seller's product sales registration request is subject to brand gating based on the similarity between a keyword group based on synonyms of the keywords and a brand keyword, thereby preventing malicious sellers from bypassing brand gating.
[0026] The effects that can be obtained from the present disclosure are not limited to the effects mentioned above, and other effects that are not mentioned can be clearly understood by a person having ordinary skill in the art to which the present disclosure belongs from the description below.
[0027] To more clearly illustrate the various embodiments proposed in this disclosure, drawings of the embodiments are briefly introduced. The drawings below are merely for reference to various embodiments of the present disclosure and are not intended to limit the present disclosure.
[0028] FIG. 1 is a diagram illustrating a system according to various embodiments of the present disclosure.
[0029] FIG. 2 is a block diagram of an electronic device and a terminal device according to various embodiments of the present disclosure.
[0030] FIG. 3 is a diagram illustrating an operation flow diagram of an electronic device for brand gating according to various embodiments of the present disclosure.
[0031] FIG. 4 is a diagram illustrating an example of a brand keyword list according to various embodiments of the present disclosure.
[0032] FIG. 5 is a diagram illustrating an example of a ticket list according to various embodiments of the present disclosure.
[0033] FIG. 6 is a diagram illustrating an example of a ticket according to various embodiments of the present disclosure.
[0034] FIG. 7 is a diagram illustrating an operation flow diagram of an electronic device for brand gating according to various embodiments of the present disclosure.
[0035] The embodiments of this disclosure are provided for the purpose of illustrating the technical concepts of this disclosure. The scope of rights under this disclosure is not limited to the embodiments presented below or the specific descriptions of these embodiments.
[0036] All technical and scientific terms used in this disclosure, unless otherwise defined, have the meanings commonly understood by those of ordinary skill in the art to which this disclosure pertains. All terms used in this disclosure have been selected for the purpose of more clearly explaining this disclosure and are not intended to limit the scope of rights under this disclosure.
[0037] Expressions such as “including,” “comprising,” “having,” and the like used in this disclosure should be understood as open-ended terms that imply the possibility of including other embodiments, unless otherwise stated in the phrase or sentence in which the expression is included.
[0038] The singular forms described in this disclosure may include plural meanings unless otherwise stated, and the same applies to the singular forms described in the claims.
[0039] The expressions “first,” “second,” etc. used in this disclosure are used to distinguish between multiple components, and do not limit the order or importance of the components.
[0040] The term "unit" as used herein refers to software or hardware components such as field-programmable gate arrays (FPGAs) and application specific integrated circuits (ASICs). However, "units" are not limited to hardware and software. "Units" may be configured to reside on an addressable storage medium, and may be configured to execute one or more processors. Thus, by way of example, "units" include components such as software components, object-oriented software components, class components, and task components, as well as processors, functions, properties, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functionality provided within a component and "unit" may be combined into a smaller number of components and "units" or further separated into additional components and "units."
[0041] The expression "based on" as used in this disclosure is used to describe one or more factors that influence the decision, act of judgment, or action described in the phrase or sentence containing the expression, and this expression does not exclude additional factors that influence the decision, act of judgment, or action.
[0042] In this disclosure, when a component is referred to as being "connected" or "connected" to another component, it should be understood that the component can be directly connected or connected to the other component, or can be connected or connected via a new other component.
[0043] Hereinafter, embodiments of the present disclosure will be described with reference to the attached drawings. In the attached drawings, identical or corresponding components are assigned the same reference numerals. Furthermore, in the description of the embodiments below, redundant descriptions of identical or corresponding components may be omitted. However, even if a description of a component is omitted, it is not intended that such component is not included in any embodiment.
[0044] FIG. 1 is a diagram illustrating a system (10) according to various embodiments of the present disclosure.
[0045] The system (10) of the present disclosure may include an electronic device (110) and a terminal device (120).
[0046] The electronic device (110) of the present disclosure may be a server operating a brand gating system. The electronic device (110) may receive a sales registration request for a product from a seller's terminal device (120) and perform the brand gating procedure described below.
[0047] The terminal device (120) of the present disclosure may, depending on the context, refer to a terminal device of a brand seller authorized to sell products of a protected brand, a terminal device of a brand gate manager, or a terminal device of a seller wishing to sell products. The brand seller transmits a brand certificate to an electronic device (110) via the terminal device (120) to perform an authentication procedure, and upon completion of the authentication, the brand seller may register and sell products of the protected brand in an online store of an e-commerce platform. Furthermore, the brand seller may transmit information regarding keywords (brand keywords) related to the protected brand to the electronic device (110) via the terminal device (120). The seller may be different from the brand seller. For example, unlike a brand seller authorized to sell products of a protected brand, the seller may not have the authority to sell products of the protected brand. The seller may transmit a sales registration request (including the price and / or product name) for products to be sold (e.g., products of the protected brand) to the electronic device (110) via the terminal device (120). The brand gating manager can transmit information (e.g., selection information of the brand gating manager) indicating whether the seller accepts or rejects the product sales registration request to the electronic device (110) via the terminal device (120).
[0048] Meanwhile, the terminal device (120) of the present disclosure may be a device that can connect to the Internet, and may be, for example, a mobile phone, a smart phone, a laptop, a computer, a wearable device, or an HMD. However, the type of the terminal device (120) is not limited thereto, and the terminal device (120) may be any device that includes an input / output interface capable of receiving information from a user or outputting information to a user, and that can communicate with the electronic device (110) or other devices via a network. The terminal device (120) may provide information received from the electronic device (110) to a user (e.g., a seller or a brand gate manager), and may receive input from the user and transmit it to the electronic device (110). For example, the terminal device (120) may receive a page from the electronic device (110), receive a user input from the page, and transmit information about the user input to the electronic device (110). In the present disclosure, a page may refer to a screen that includes an area that displays (provides) information or functions necessary for a user to achieve a specific purpose, as an interface for interacting with a user on the web or an application. Accordingly, the electronic device (110) providing a page to a terminal device (120) may mean that the electronic device (110) provides an interface that can receive user input to the terminal device (120). In this case, the input obtained from the user may include various forms of input, such as a click using a mouse, a touch using a touchpad or touch screen, voice recognition, or other electronic input.
[0049] The electronic device (110) and terminal device (120) of the present disclosure can be connected to each other via a network and transmit and receive various data. The network can be implemented as any type of wired or wireless network, such as, for example, a local area network (LAN), a wide area network (WAN), a mobile radio communication network, or Wibro (Wireless Broadband Internet).
[0050] FIG. 2 is a block diagram of an electronic device (110) and a terminal device (120) according to various embodiments of the present disclosure.
[0051] Referring to FIG. 2, an electronic device (110) according to various embodiments may include a processor (111), a memory (113), and a communication circuit (115). At least one of the components included in the electronic device (110) may be omitted, or another component may be added to the electronic device (110). Additionally or alternatively, some of the components may be implemented in an integrated manner, or may be implemented as a single or multiple entities. At least some of the components within the electronic device (110) may be connected to each other via a bus, a general purpose input / output (GPIO), a serial peripheral interface (SPI), or a mobile industry processor interface (MIPI), and may exchange data and / or signals.
[0052] According to various embodiments, the processor (111) of the electronic device (110) may be a configuration capable of performing operations or data processing related to control and / or communication of each component (e.g., memory (113)) of the electronic device (110). The processor (111) may be operatively connected to, for example, components of the electronic device (110). The processor (111) may load commands or data received from other components of the electronic device (110) into the memory (113), process commands or data stored in the memory (113), and store result data. The processor (111) disclosed in this document may also mean a set of one or more processors (111).
[0053] According to various embodiments, the memory (113) of the electronic device (110) may store instructions (or commands) for the operation of the processor (111). According to various embodiments, the memory (113) may store instructions for the operation of the processor (111). According to various embodiments, the memory (113) may store one or more brand keywords for each brand. According to various embodiments, the memory (113) may store a keyword synonym list (dictionary) including one or more synonyms for each keyword. The electronic device (110) may receive the keyword synonym list from an entity that manages the keyword synonym list or obtain the keyword synonym list from an application programming interface (API) and store it in the memory (113).
[0054] According to various embodiments, the communication circuit (115) of the electronic device (110) can establish a wired or wireless communication channel with an external device (e.g., a terminal device (120)) and transmit and receive various data with the external device. According to various embodiments, the communication circuit (115) can include at least one port for connecting to the external device via a wired cable in order to communicate with the external device via a wire. In the above case, the communication circuit (115) can perform communication with the external device connected via a wire through the at least one port. According to various embodiments, the communication circuit (115) can be configured to include a cellular communication module and be connected to a cellular network (e.g., 3G, LTE, 5G, Wibro, or Wimax). According to various embodiments, the communication circuit (115) can include a short-range communication module and transmit and receive data with the external device using short-range communication (e.g., Wi-Fi, Bluetooth, Bluetooth Low Energy (BLE), UWB), but is not limited thereto. According to various embodiments, the communication circuit (115) may include a contactless communication module for contactless communication. The contactless communication may include at least one contactless proximity communication technology, such as, for example, near field communication (NFC), radio frequency identification (RFID), or magnetic secure transmission (MST).
[0055] A terminal device (120) according to various embodiments may include a controller (121), a memory (123), a display (125), and a communication circuit (127). Even if some of the components illustrated in FIG. 2 are omitted or replaced, there will be no problem in implementing the various embodiments disclosed in this document.
[0056] The controller (121) of the terminal device (120) according to various embodiments is a configuration capable of performing operations or data processing related to control and / or communication of each component of the terminal device (120). The controller (121) may be operatively connected to, for example, components of the terminal device (120). The controller (121) may load commands or data received from other components of the terminal device (120) into the memory (123) of the terminal device (120), process commands or data stored in the memory (123), and store result data.
[0057] The memory (123) according to various embodiments can store instructions (or commands) for the operation of the controller (121).
[0058] The display (125) of the terminal device (120) according to various embodiments can display various screens based on the control of the controller (121). The display (125) can be implemented in the form of a touch sensor panel (TSP) that can recognize the contact or proximity of various external objects (e.g., fingers). The touch sensor panel can have various structures and types, and the present disclosure can be applied to all of them regardless of the structure and type of the touch sensor panel. The display (125) can include an electrostatic capacity sensor to recognize the contact or proximity of various external objects. The electrostatic capacity sensor can be composed of a plurality of capacitors, and the electrostatic capacity sensor can apply an electric signal to the capacitor. The capacitor can charge and discharge an electric charge in response to the application of the electric signal. When an electric signal is applied to the capacitor, an electric charge can be charged in the capacitor depending on the magnitude of the voltage of the electric signal. The display (125) can receive touch input based on signals collected from the electrostatic capacitance sensor. For example, the display (125) can receive a user's tap touch, double tap touch, sliding touch, drag & drop touch, and long touch.
[0059] The controller (121) according to various embodiments can display a page provided from an electronic device (110) through a display (125) and receive user input through the display (125).
[0060] The operations described herein as being performed by an electronic device may be understood as being performed by a processor (111) of the electronic device (110). The operations described herein as being performed by a user's terminal may be understood as being performed by a controller (121) of the terminal device (120).
[0061] E-commerce platforms can maintain a brand's image and protect consumer trust by restricting or controlling the sale of certain branded products. To this end, e-commerce platforms can utilize brand gating technology to prevent unauthorized sellers from selling protected branded products or their illegal copies or counterfeit counterparts. This will be described in detail below with reference to Figure 3.
[0062] FIG. 3 is a diagram illustrating an operation flow diagram of an electronic device (110) for brand gating according to various embodiments of the present disclosure.
[0063] Referring to the operation flowchart of FIG. 3, in operation 310, the electronic device (110) may receive a certificate from a terminal device (120) of a brand seller (e.g., the owner or manufacturer of the brand) to obtain the authority to sell the brand's products on an e-commerce platform as a legal trademark owner of the brand. Here, the certificate is issued in the country where the product is to be sold, and may include at least one of a certification number, a product name, a model name, a manufacturer name, and / or an importer name. For example, the certificate may be for one of Korea's KC (Korea certification), the European Union's CE (conformity to European), Japan's PS (product safety) or JIS (Japanese industrial standards), China's CCC (China compulsory certification), or Taiwan's BSMI (bureau of standards, metrology and inspection). At this time, a certificate for the country where the product is to be sold on the e-commerce platform may be transmitted to the electronic device (110). For example, when selling a product in Korea, the brand seller's terminal device (120) may transmit a certificate for KC to the electronic device (110). Alternatively, when selling a product in Taiwan, the brand seller's terminal device (120) may transmit a certificate for BSMI to the electronic device (110). The types of certificates described above are merely examples, and the present disclosure is not limited thereto. The electronic device (110) may perform an authentication procedure for the certificate by determining the validity of the certificate based on the certificate's serial number (e.g., authentication number), etc.
[0064] If the certificate is valid, the electronic device (110) may store the brand keyword and / or the serial number of the certificate in operation 320. In the present disclosure, the brand keyword is a word related to the brand's products, and may include a brand name, a model name, and / or a series name. When the brand keyword is stored in the electronic device (110) and registered in the brand gating system operated by the electronic device (110), the electronic device (110) operating the brand gating system may detect and block attempts by sellers who are not authorized to sell the brand's products to sell products using the brand keyword.
[0065] According to one embodiment, the electronic device (110) may receive a keyword of the brand along with the certificate in operation 310, and if the certificate is valid, store the keyword of the brand and / or the serial number of the certificate.
[0066] According to another embodiment, the electronic device (110) may transmit information indicating that the certificate is valid and authentication has been completed to the brand seller's terminal device (120), and subsequently provide a brand keyword edit page to the brand seller's terminal device (120). On the brand keyword edit page displayed on the display of the brand seller's terminal device (120), the brand seller may input (select) a brand keyword. In this case, the brand seller's terminal device (120) may transmit the brand seller's input information regarding the brand keyword to the electronic device (110). The electronic device (110) may confirm the brand keyword based on the brand seller's input information, store it, and generate (update) a brand keyword list. Hereinafter, the brand keyword list will be described in detail with reference to FIG. 4.
[0067] FIG. 4 is a diagram illustrating an example of a brand keyword list (400) according to various embodiments of the present disclosure.
[0068] According to operation 320 of FIG. 3, a brand keyword list (400) of FIG. 4 is generated, and the electronic device (120) can perform a brand gating procedure for each brand based on the brand keyword list. Referring to FIG. 4, the brand keyword list (400) includes one or more rows, and each row can include at least one of a brand ID, a brand name, a brand keyword, an exclude keyword, and / or whether brand gating is enabled (410). Here, an exclude keyword may refer to a word that is excluded from detection of a brand gating target. For example, when a seller who is not authorized to sell a brand's product attempts to sell a product whose product name includes a brand keyword and the product name also includes an exclude keyword, the seller's attempt to sell the product may be excluded from the brand gating target. Taking brand A in FIG. 4 as an example, the brand keywords of brand A are X, X' (partially different from X), X'' (partially different from X and X'), Y, Y' (partially different from Y), Y'' (partially different from Y and Y'), Z, Z' (partially different from Z), Z'' (partially different from Z and Z'), and the exception keyword is U. If the product name for which the seller has requested sale registration includes at least one brand keyword of brand A, the sale registration request for the corresponding product may be subject to brand gating. Alternatively, if the product name for which the seller has requested sale registration includes at least one brand keyword of brand A, but also includes an exception keyword, the sale registration request for the corresponding product may be excluded from brand gating. Meanwhile, the brand keyword list (400) in FIG. 4 is merely an example for the convenience of explanation, and the present disclosure is not limited thereto.
[0069] The electronic device (110) can transmit a brand keyword list (400) to the terminal device (120) of the brand gating manager. For example, the electronic device (110) can provide a page including the brand keyword list (400) to the terminal device (120) of the brand gating manager. The brand gating manager can select whether to activate brand gating (410) for a specific brand on the page including the brand keyword list (400) displayed on the display of the terminal device (120). For example, if the brand gating manager selects to activate brand gating for a specific brand for which brand gating is disabled, the terminal device (120) of the brand gating manager can transmit information indicating that brand gating activation has been selected for the specific brand to the electronic device (110). In this case, the electronic device (110) can perform a brand gating procedure according to operations 330 and 340 described below for the brand for which brand gating activation has been selected. As another example, if the brand gating manager selects to disable brand gating for a specific brand for which brand gating is enabled, the terminal device (120) may transmit information indicating that brand gating disablement has been selected for the specific brand to the electronic device (110). In this case, the electronic device (110) may not perform the brand gating procedure according to operations 330 and 340 described below for the brand for which brand gating disablement has been selected.
[0070] Returning to FIG. 3, the electronic device (110) may, at operation 330, receive a sales registration request for a product from a seller other than a brand seller. The seller's sales registration request for the product may include at least one of the product's price and / or product name. Meanwhile, whether the seller is a brand seller may be determined based on the seller's vendor ID and / or vendor inventory ID.
[0071] The electronic device (110) may perform a brand gating procedure based on at least one of the stored brand keywords and / or serial numbers in operation 340. For example, the electronic device (110) may determine whether the product name for which the seller has requested sale registration matches the brand keyword. If the product name for which the seller has requested sale registration includes at least one brand keyword, the electronic device (110) may determine that the product name and the brand keyword match and determine that the seller's sale registration request for the product is subject to brand gating. Alternatively, if the product name for which the seller has requested sale registration does not include a brand keyword, the electronic device (110) may determine that the product name and the brand keyword do not match and determine that the seller's sale registration request for the product is not subject to brand gating. For example, if the product name for which a seller has requested a sales registration is composed of keywords such as “2023 Apple AirPod Bluetooth earphones” and the brand keywords are “Apple”, “AirPods”, “Bluetooth” and “earphones”, and since the product name includes at least one of the brand keywords, the electronic device (110) may determine that the product name and the brand keyword match and determine the seller’s sales registration request for the product as a target of brand gating.
[0072] If a seller's product sales registration request is determined to be subject to brand gating, the electronic device (110) may generate a ticket, which is information for requesting confirmation of acceptance of the seller's product sales registration request, and transmit the ticket to the terminal device (120) of the brand gating manager. For example, the electronic device (110) may provide a page including the ticket to the terminal device (120) of the brand gating manager. Through this, the brand gating manager may verify the ticket and decide whether to accept or reject the seller's product sales registration request. At this time, the electronic device (110) may determine whether the certificate for the product for which the seller has requested sales registration is valid and transmit information regarding the validity of the certificate to the terminal device (120) of the brand gating manager. For example, the electronic device (110) may transmit a message to the terminal device (120) of the seller requesting the certificate or the serial number of the certificate for the product for which sales registration has been requested. In this case, the electronic device (110) may receive a certificate or a serial number of the certificate for the product for which sales registration has been requested from the seller's terminal device (120). The electronic device (110) may determine whether the serial number of the stored brand certificate matches the serial number of the certificate for the product for which sales registration has been requested. If the serial number of the stored brand certificate matches the serial number of the certificate for the product for which sales registration has been requested, the electronic device (110) may transmit information indicating that the certificate for the product for which sales registration has been requested is valid to the terminal device (120) of the brand gating manager. Alternatively, if the serial number of the stored brand certificate does not match the serial number of the certificate for the product for which sales registration has been requested, the electronic device (110) may transmit information indicating that the certificate for the product for which sales registration has been requested is invalid to the terminal device (120) of the brand gating manager.The brand gating manager can decide whether to accept or reject a sales registration request for a product based on the validity of the certificate for which the seller has requested sales registration. For example, if the certificate for the product requested by the seller is valid, the brand gating manager can accept the sales registration request for that product. Alternatively, if the certificate for the product requested by the seller is invalid, the brand gating manager can reject the sales registration request for that product.
[0073] Hereinafter, the ticket will be described in detail with reference to Figures 5 and 6.
[0074] FIG. 5 is a diagram illustrating an example of a ticket list (500) according to various embodiments of the present disclosure.
[0075] Referring to FIG. 5 , an electronic device (110) may provide a page including a ticket list (500) to a terminal device (120) of a brand gating manager. The ticket list (500) may include one or more rows, each row including at least one of a ticket ID, a seller (vendor) ID, a brand gating target (brand name), and / or a current status of the corresponding ticket. Here, the current status of the ticket may be set to one of initial (or INIT), approved (approve), and rejected (reject). If the current status of the ticket is "initial," this may indicate that a decision has not been made regarding whether to accept or reject the seller's product sales registration request. If the current status of the ticket is "accepted," this may indicate that the seller's product sales registration request has been granted. If the current status of the ticket is "rejected," this may indicate that the seller's product sales registration request has been rejected. Meanwhile, each row of the ticket list (500) may further include option information (510) that changes the status of the ticket. For example, the option information (510) may include a first option (Request New Ticket) that requests the issuance of a new ticket for the ticket, a second option (Reject) that changes the status of the ticket to "Reject," and a third option (Approve) that changes the status of the ticket to "Accept." The brand gating manager may select one of the first, second, and third options to change the current status of the ticket. For example, the brand gating manager may select the first option that requests the issuance of a new ticket for an existing ticket for a specific reason, such as when the detailed information (e.g., product category, etc.) of the existing ticket does not match the product for which the seller has requested to register for sale, or when the review priority of the existing ticket has changed.If the brand gating manager selects the first option, the terminal device (120) of the brand gating manager may transmit selection information for the first option to the electronic device (110), and the electronic device (110) may create a new ticket for a product sales registration request related to an existing ticket, and provide a page displaying a ticket list (500) including the new ticket to the terminal device (120) of the brand gating manager. As another example, if the brand gating manager selects the second option, the terminal device (120) of the brand gating manager may transmit selection information for the second option to the electronic device (110), and the electronic device (110) may change the current status of the ticket to “rejected”, and provide a page displaying a ticket list (500) including the ticket whose current status has been changed to “rejected” to the terminal device (120) of the brand gating manager. Alternatively, if the brand gating manager selects the third option, the terminal device (120) of the brand gating manager may transmit selection information regarding the third option to the electronic device (110), and the electronic device (110) may change the current status of the ticket to "Accepted" and provide the terminal device (120) of the brand gating manager with a page displaying a ticket list (500) including tickets whose current status has been changed to "Accepted." Taking the first row of FIG. 5 as an example, the ticket in the first row has a ticket ID of "M1K4," a seller (vendor) ID of "MM," a brand gating target (i.e., a brand associated with the product) of "A," and a current status of "Rejected." In this case, this may mean that the seller's sales registration request for the product associated with the ticket in the first row has been rejected.
[0076] Meanwhile, the brand gating manager can select one ticket from the ticket list (500) displayed on the page. In this case, the terminal device (120) of the brand gating manager can transmit selection information for one ticket from the ticket list (500) to the electronic device (110), and the electronic device (110) can provide a page containing detailed information about the selected ticket to the terminal device (120) of the brand gating manager.
[0077] FIG. 6 is a diagram illustrating an example of a ticket according to various embodiments of the present disclosure.
[0078] Detailed information about the ticket illustrated in FIG. 6 can be provided to the terminal device (120) of the brand gating manager by the electronic device (110) as a result of selecting one ticket from the ticket list (500) of FIG. 5.
[0079] Referring to FIG. 6, a ticket may include at least one of a ticket ID, a product category ID, a brand gating target (brand name), a current status, and / or product details. Here, the product details may include at least one of a product ID, a product name (title), a brand, a manufacturer, and / or a category.
[0080] The brand gate manager can review detailed information about a ticket and change the current status of the ticket to "Accepted" or "Rejected," as described in FIG. 5 . If the current status of the ticket changes to "Accepted," the electronic device (110) can transmit information indicating that the seller's product registration request related to the accepted ticket has been accepted to the seller's terminal device (120). Alternatively, if the current status of the ticket changes to "Rejected," the electronic device (110) can transmit information indicating that the seller's product registration request related to the rejected ticket has been rejected to the seller's terminal device (120).
[0081] According to the brand gating procedure described in FIGS. 3 to 6, the electronic device (110) operating the brand gating system may determine whether a product name and a brand keyword match based on whether a product name requested for sale registration by a seller other than the brand seller includes at least one brand keyword, and may determine whether the seller's product's sale registration request is subject to brand gating based on the matching result. Meanwhile, if the seller has constructed a product name using a synonym or obfuscation of the brand keyword, the electronic device (110) may determine that the seller's product's sale registration request is not subject to brand gating because the seller's product name does not include the brand keyword. For example, if the seller changes the brand keyword "earphone" to the synonym "earpiece" or constructs a product name by attaching words before or after the brand keyword "AirPod," the product name does not include words identical to the brand keyword, and thus the electronic device (110) may determine that the seller's sale registration request is not subject to brand gating. Malicious sellers can bypass brand gating in this way, registering and selling products on online stores on e-commerce platforms. To effectively protect a brand, it's necessary to accurately determine whether a seller's product registration request is subject to brand gating, preventing them from bypassing brand gating.
[0082] Accordingly, the electronic device (110) according to various embodiments of the present disclosure segments a product name for which a seller has requested to register for sale into one or more keywords, and detects and processes whether the seller's product registration request for sale is subject to brand gating based on the similarity between a keyword group based on synonyms of the keywords and the brand keyword, thereby preventing malicious sellers from bypassing brand gating. This will be described in detail below with reference to FIG. 7 .
[0083] FIG. 7 is a diagram illustrating an operation flowchart (700) of an electronic device (110) for brand gating according to various embodiments of the present disclosure.
[0084] Referring to the operation flowchart (700), the electronic device (110) may, in operation 710, receive a sales registration request for a product from the seller's terminal device (120). For example, the sales registration request may include the product name. Additionally, the sales registration request may further include at least one of the product price and / or information about the seller (e.g., vendor ID, vendor inventory ID).
[0085] The electronic device (110) may perform tokenization on the product name at operation 720 to generate one or more first keywords for the product name. For example, the electronic device may segment the product name for which the seller has requested to register for sale into one or more first keywords (tokenized product names), as shown in [Table 1] below. [Table 1] below is provided merely as an example for convenience of explanation, and the present disclosure is not limited thereto.
[0086] Product Name: "2023 Apple AirPods Bluetooth Earphones" Keywords: "2023," "Apple," "AirPods," "Bluetooth," "Earphones"
[0087] In the present disclosure, tokenization may include word-level tokenization, subword-level tokenization, or morpheme-level tokenization. Word-level tokenization may refer to segmenting text or a corpus into word-level tokens. Subword-level tokenization may refer to segmenting text or a corpus into subword-level tokens based on the notion that a single word is composed of smaller, meaningful subwords. Morpheme-level tokenization may refer to segmenting text or a corpus into morphemes, which are the smallest units of speech with meaning. The electronic device (110) may determine which tokenization to perform on a product name based on the language in which the product name is composed. For example, if the product name is composed of English words, the electronic device (110) may perform word-level tokenization or subword-level tokenization on the product name to segment the product name into one or more first keywords. Alternatively, if the product name is composed of Korean words, the electronic device (110) may perform morpheme-based tokenization on the product name to segment the product name into one or more first keywords. Alternatively, if the product name is composed of English words and Korean words, the electronic device (110) may perform morpheme-based tokenization on the product name to segment the product name into one or more first keywords. This morpheme-based tokenization may be performed based on a dictionary for morpheme analysis (e.g., a morpheme analysis tokenizer). Here, the dictionary for morpheme analysis may be a dictionary generated based on detailed information (e.g., product name, model name, brand name, manufacturer name, detailed product description, etc.) on one or more products handled on an e-commerce platform. That is, words or morphemes frequently used in relation to the products may be extracted from the detailed information on one or more products, and a dictionary for morpheme analysis may be generated based on the extracted words or morphemes.
[0088] Meanwhile, tokenization in the present disclosure may be performed using an artificial intelligence (AI) or machine learning (ML) model. Various AI or ML models may be used for tokenization, and the present disclosure is not limited thereto.
[0089] The electronic device (110) may, at operation 730, identify one or more synonyms for at least some of one or more first keywords based on a keyword synonym list. In the present disclosure, the keyword synonym list may refer to a list including information on one or more synonyms for each word. For example, the keyword synonym list may include information on one or more synonyms for each word frequently used as a product or product name in an e-commerce platform (online store).
[0090] According to one embodiment, the electronic device (110) can identify one or more synonyms for at least some of the one or more first keywords from a keyword synonym list stored in the memory (113).
[0091] According to another embodiment, the electronic device (110) may receive a keyword synonym list from an external entity that manages synonyms or obtain a keyword synonym list from an API, and then identify one or more synonyms for at least some of one or more first keywords in the keyword synonym list.
[0092] For example, as shown in [Table 2] below, the electronic device (110) can identify “earpiece,” “headphone,” and “headset” as synonyms of “earphone” among one or more first keywords of [Table 1] in the keyword synonym list. Meanwhile, in order to avoid repetition of redundant explanations and to more clearly explain the embodiments of the present disclosure, it is assumed below that only “earphone” among one or more first keywords has synonyms, and only “earpiece,” “headphone,” and “headset” exist as synonyms of “earphone” in the keyword synonym list. This assumption is merely an example for clarifying the explanation, and the present disclosure is not limited thereto.
[0093] Product name: "2023 Apple AirPod Bluetooth Earphones" Keyword #1: "2023", "Apple", "AirPods", "Bluetooth", "Earphones" Synonyms for "Earphones" among the first keywords: "Earpiece", "Headphones", "Headset"
[0094] The electronic device (110), in operation 740, may generate one or more keyword groups including one or more second keywords based on a combination of one or more first keywords and one or more synonyms. For example, the electronic device (110) may generate one or more keyword groups including one or more second keywords as a result of replacing at least a portion of one or more first keywords with one or more synonyms. Specifically, the electronic device (110) may identify a first keyword having a synonym among one or more first keywords based on a keyword synonym list, and generate one or more keyword groups including one or more second keywords as a result of replacing the first keyword having a synonym with the synonym. For example, following [Table 1] and [Table 2], the electronic device (110) may generate one or more keyword groups #1 to #4 as shown in [Table 3] below. [Table 3] below is merely an example for convenience of explanation, and the present disclosure is not limited thereto.
[0095] Product Name: "2023 Apple AirPod Bluetooth Earphones" Keyword #1: "2023", "Apple", "AirPod", "Bluetooth", "Earphone" Synonyms of "Earphone" among the first keywords: "Earpiece", "Headphone", "Headset" Keyword Group #1: "2023", "Apple", "AirPod", "Bluetooth", "Earphone" Keyword Group #2: "2023", "Apple", "AirPod", "Bluetooth", "Earpiece" Keyword Group #3: "2023", "Apple", "AirPod", "Bluetooth", "Headphone" Keyword Group #4: "2023", "Apple", "AirPod", "Bluetooth", "Headset"
[0096] The electronic device (110), in operation 750, may calculate one or more scores for one or more keyword groups based on the similarity between one or more second keywords and one or more third keywords (brand keywords) set for the protected brand for each keyword group. Here, the one or more third keywords set for the protected brand may refer to the brand keywords described in FIGS. 3 to 6. For example, the electronic device (110) may receive information on one or more third keywords set for the protected brand from a terminal device of a brand seller before operation 710 of FIG. 7 and store the information in the memory (113).
[0097] According to one embodiment, the electronic device (110) may perform fuzzy matching between one or more second keywords and one or more third keywords set for the protected brand for each keyword group to determine a similarity between the one or more second keywords and the one or more third keywords. In the present disclosure, fuzzy matching is a method of measuring how similar two words (strings) are to each other, and as a result of fuzzy matching, the similarity between the two words (strings) can be quantified to obtain a similarity value indicating the degree of matching. At this time, the similarity value between the two words (strings) can be any one of the Levenshtein distance, the minimum edit distance, or the ratio of matching characters. The minimum edit distance can mean the minimum number of operations such as insertion, deletion, and substitution required to change one word (string) to another word (string). The ratio of matching characters can mean a value obtained by dividing the number of matching characters between the two words (strings) by the total length of one of the two words (strings). For example, if one of one or more second keywords is "earphone" and one of one or more third keywords is "earpiece," the matching characters are "이" and "어", which are two characters, and the total length of the second keyword, "earphone," is three characters, so the ratio of matching characters is It could be 0.67(≒2 / 3).
[0098] For example, the electronic device (110) may match one or more second keywords with one or more third keywords, such that one or more second keywords correspond to one or more third keywords, for each keyword group. Based on the result of this matching, the electronic device (110) may calculate one or more similarity values between the one or more second keywords and the one or more third keywords. Thereafter, the electronic device (110) may calculate a score for one keyword group by adding up the one or more similarity values. For example, following [Table 3], the electronic device (110) may perform fuzzy matching on one or more second keywords and one or more third keywords to obtain one or more similarity values, as shown in [Table 4] below, and may calculate a score for the keyword group by adding them up. In [Table 4] below, the one or more third keywords are assumed to be “2023”, “Apple”, “AirPods”, “Bluetooth”, and “earphones”. Also, in [Table 4] below, the similarity value between the second and third keywords is the ratio of matching characters ( ) was calculated. According to this, in [Table 4] below, the score of keyword group #1 is 5, the score of keyword group #2 is 4.5, the score of keyword group #3 is 4.33, and the score of keyword group #4 is 4. Meanwhile, [Table 4] below is merely an example for the convenience of explanation, and the present disclosure is not limited thereto.
[0099] Keyword Group #1 Second Keyword "2023" "Apple" "AirPods" "Bluetooth" "Earphones" Third Keyword "2023" "Apple" "AirPods" "Bluetooth" "Earphones" Similarity Value 1 (= )1 (= )1 (= )1 (= )1 (= )Score 5 (=1+1+1+1+1)Keyword group #2Second keyword "2023" "Apple" "AirPods" "Bluetooth" "Earpiece"Third keyword "2023" "Apple" "AirPods" "Bluetooth" "Earphones"Similarity value 1 (= )1 (= )1 (= )1 (= )0.5 (= )Score 4.5 (=1+1+1+1+0.5)Keyword group #3Second keyword "2023" "Apple" "AirPods" "Bluetooth" "Headphones"Third keyword "2023" "Apple" "AirPods" "Bluetooth" "Earphones"Similarity value 1 (= )1 (= )1 (= )1 (= )0.33 (= )Score 4.33 (=1+1+1+1+0.33)Keyword group #4Second keyword "2023" "Apple" "AirPods" "Bluetooth" "Headset"Third keyword "2023" "Apple" "AirPods" "Bluetooth" "Earphones"Similarity value 1 (= )1 (= )1 (= )1 (= )0 (= )Score 4 (=1+1+1+1+0)
[0100] As another example, each of the one or more third keywords set for a protected brand may be associated with a preset weight. The brand gating manager may assign a weight to each keyword to reflect the importance of a specific keyword in brand gating. In this case, the terminal device (120) of the brand gating manager may transmit information about one or more third keywords, including information for setting weights for at least some of the one or more third keywords, to the electronic device (110). The electronic device (110) may determine the weights for at least some of the one or more third keywords and store them in the memory (113). In addition, the electronic device (110) may determine the weights of third keywords for which no weights have been set as a default value (e.g., 1) and store them in the memory (113). The electronic device (110) can match one or more second keywords with one or more third keywords, for each keyword group, such that one or more second keywords correspond to one or more third keywords. Based on the result of this matching, the electronic device (110) can calculate one or more similarity values between the one or more second keywords and the one or more third keywords. The electronic device (110) can obtain one or more values by multiplying one or more similarity values by weights for each of the one or more third keywords. The electronic device (110) can calculate a score for one keyword group by adding up one or more values. For example, following [Table 3], the electronic device (110) can perform fuzzy matching on one or more second keywords and one or more third keywords to obtain one or more similarity values, multiply one or more similarity values by weights for each of the one or more third keywords to obtain one or more values, and add up one or more values to calculate a score for the keyword group.In [Table 5] below, one or more third keywords are assumed to be "2023", "Apple", "AirPods", "Bluetooth", and "earphones". In [Table 5] below, the weight of "2023" is assumed to be 0.1, the weight of "Apple" is assumed to be 0.9, the weight of "AirPods" is assumed to be 0.95, the weight of "Bluetooth" is assumed to be 0.4, and the weight of "earphones" is assumed to be 0.5. In addition, in [Table 5] below, the similarity value between the second and third keywords is the ratio of matching characters (. ) was calculated. According to this, in [Table 5] below, the score of keyword group #1 is 2.85, the score of keyword group #2 is 2.6, the score of keyword group #3 is 2.52, and the score of keyword group #4 is 2.35. Meanwhile, [Table 5] below is merely an example for the convenience of explanation, and the present disclosure is not limited thereto.
[0101] Keyword Group #1 Second Keyword "2023" "Apple" "AirPods" "Bluetooth" "Earphones" Third Keyword (Weight) "2023" (0.1) "Apple" (0.9) "AirPods" (0.95) "Bluetooth" (0.4) "Earphones" (0.5) Similarity Value 1 (= )1 (= )1 (= )1 (= )1 (= )Score 2.85 (=(1 0.1)+(1 0.9)+(1 0.95)+(1 0.4)+(1 0.5))Keyword group #2Second keyword "2023" "Apple" "AirPods" "Bluetooth" "Earpiece"Third keyword (weight)"2023"(0.1)"Apple"(0.9)"AirPods"(0.95)"Bluetooth"(0.4)"Earphones"(0.5)Similarity value 1 (= )1 (= )1 (= )1 (= )0.5 (= )Score 2.6 (=(1 0.1)+(1 0.9)+(1 0.95)+(1 0.4)+(0.5 0.5))Keyword group #3Second keyword "2023" "Apple" "AirPods" "Bluetooth" "Headphones"Third keyword (weight)"2023"(0.1)"Apple"(0.9)"AirPods"(0.95)"Bluetooth"(0.4)"Earphones"(0.5)Similarity value 1 (= )1 (= )1 (= )1 (= )0.33 (≒ )Score 2.52 (≒(1·0.1)+(1·0.9)+(1·0.95)+(1·0.4)+(0.33·0.5))Keyword group #4Second keyword "2023" "Apple" "AirPods" "Bluetooth" "Headset"Third keyword (weight)"2023"(0.1)"Apple"(0.9)"AirPods"(0.95)"Bluetooth"(0.4)"Earphones"(0.5)Similarity value 1 (= )1 (= )1 (= )1 (= )0 (= )Score 2.35 (= (1·0.1)+(1·0.9)+(1·0.95)+(1·0.4)+(0·0.5))
[0102] The electronic device (110) may, in operation 760, calculate an average score for one or more keyword groups by averaging the scores for one or more keyword groups. For example, according to the example of [Table 4], the average score for one or more keyword groups is 4.46 ( ) may be. Or, according to the example in [Table 5], the average score for one or more keyword groups may be 2.58 ( ) may be. The electronic device (110) may, in operation 770, compare the average score for one or more keyword groups with a preset threshold value. Here, the threshold value may be set for each brand. For example, the threshold value may be set to a different value for each brand.
[0103] In operation 780, the electronic device (110) may generate a ticket, which is information for requesting confirmation of acceptance of a seller's sales registration request for a product, based on the comparison of the average score for one or more keyword groups with a preset threshold value. For example, if the average score for one or more keyword groups exceeds the threshold value, the electronic device (110) may generate the ticket described in FIGS. 3 to 6 .
[0104] According to one embodiment, as described in FIGS. 3 to 6 , the electronic device (110) may provide a page including a ticket, which is information for requesting confirmation of acceptance of a seller's sales registration request for a product, to the terminal device (120) of the brand gating manager. The brand gating manager may select whether to accept or reject the seller's sales registration request for the product on the provided page. In this case, the terminal device (120) of the brand gating manager may transmit selection information of the brand gating manager for accepting or rejecting the seller's sales registration request to the electronic device (110). If the seller's sales registration request for the product is accepted, the electronic device (110) may transmit information indicating that the sales registration request for the product has been accepted to the terminal device (120) of the seller. If the seller's sales registration request for the product is rejected, the electronic device (110) may transmit information indicating that the sales registration request for the product has been rejected to the terminal device (120) of the seller.
[0105] According to another embodiment, the electronic device (120) may generate a ticket, which is information for requesting confirmation of whether to accept a seller's request for registration of a product for sale, at operation 780, and may determine whether to accept or reject the seller's request for registration of a product for sale based on the product's price and / or the seller's sales history. If the price of the product is significantly lower than the market price or the list price, the electronic device (120) may decide to reject the request for registration of a product for sale. For example, if the price of the product is lower by a predetermined amount than the market price or the list price, the electronic device (120) may decide to reject the request for registration of a product for sale. Alternatively, the electronic device (120) may determine the seller's risk based on the seller's sales history, and if the risk is determined to be high, the electronic device (120) may decide to reject the request for registration of a product for a seller whose seller history risk score is high or higher than a predetermined value. For example, the electronic device (120) may decide to reject the request for registration of a product for a seller whose seller history risk score is high or higher than a predetermined value. Sellers who attempt to sell branded products, counterfeit copies, or counterfeit versions of a branded product, even though they are not authorized to do so, may have a high seller history risk score. Sellers with a high seller history risk score are more likely to repeatedly submit sales registration requests for branded products with malicious intent, and therefore need to be monitored with priority over other sellers. Therefore, the electronic device (120) may decide to reject sales registration requests for products from sellers with high seller history risk scores. In this way, by allowing the electronic device (110) to decide whether to accept or reject a seller's sales registration request, the brand gate manager can minimize the labor and time required compared to manually reviewing sales registration requests.Meanwhile, if the seller's request for product sales registration is accepted, the electronic device (110) may transmit information indicating that the product sales registration request has been accepted to the seller's terminal device (120). If the seller's request for product sales registration is rejected, the electronic device (110) may transmit information indicating that the product sales registration request has been rejected to the seller's terminal device (120).
[0106] Additionally, the electronic device (110) may update a threshold value compared to the average score for one or more keyword groups based on whether a sales registration request for a product has been accepted or rejected. For example, the electronic device (110) may update the threshold value so that the probability of a sales registration request being rejected increases when a ticket, which is information for requesting confirmation of acceptance of a sales registration request for a seller's product, is generated. Alternatively, the electronic device (110) may optimize the threshold value using an AI or ML model. In this case, the electronic device (110) may train an AI or ML model using a backpropagation algorithm so that the probability of a sales registration request being rejected increases when a ticket, which is information for requesting confirmation of acceptance of a sales registration request for a seller's product, is generated, and may obtain an optimal value for the threshold value using the trained AI or ML model.
[0107] Additionally, the electronic device (110) can dynamically reflect the importance of specific keywords in brand gating by updating the weights for each of one or more third keywords set for the protected brand based on whether a sales registration request for a product is accepted or rejected. For example, the electronic device (110) can update the weights for each of one or more third keywords so that the probability of a sales registration request being rejected increases when a ticket, which is information requesting confirmation of acceptance of a sales registration request for a seller's product, is generated. If a sales registration request is rejected when a ticket, which is information requesting confirmation of acceptance of a sales registration request, is generated, this may indicate that the brand gating target has been accurately detected. This may indicate that the importance of the third keyword, which matches the second keyword, is high for detecting whether the product is a brand gating target. In this case, the electronic device (110) can increase the weights for at least some of the one or more third keywords by a predetermined value. Alternatively, if the sales registration request is accepted when a ticket, which is information for requesting confirmation of acceptance of the sales registration request, is generated, this may indicate that the brand gating target has not been accurately detected. Furthermore, this may indicate that the importance of the third keyword matched with the second keyword for detecting whether the product is a brand gating target is low. In this case, the electronic device (110) may reduce the weight of at least some of the one or more third keywords by a predetermined value. Alternatively, the electronic device (110) may optimize the weight of each of the one or more third keywords using an AI or ML model.In this case, the electronic device (110) trains an AI or ML model according to a backpropagation algorithm so that the probability of a sales registration request being rejected increases when a ticket, which is information for requesting confirmation of acceptance of a sales registration request, is generated, and obtains an optimal value of a weight for each of one or more third keywords through the trained AI or ML model.
[0108] While this disclosure primarily focuses on examples in which the product name and brand keyword consist of Korean words, the present disclosure can also be applied similarly to cases in which the product name and brand keyword consist of words in other languages. For example, even when the product name and brand keyword consist of English words, the various embodiments of the present disclosure described above can be applied identically or similarly.
[0109] Although the process steps, method steps, and algorithms illustrated in the flowcharts herein are described in a sequential order, such processes, methods, and algorithms may be configured to operate in any suitable order. In other words, the steps of the processes, methods, and algorithms described in various embodiments of the present disclosure need not be performed in the order described herein. Furthermore, even if some steps are described as being performed asynchronously, in other embodiments, such some steps may be performed concurrently. Furthermore, the illustration of a process by depiction in the drawings does not imply that the illustrated process excludes other variations and modifications thereof, nor does it imply that the illustrated process or any of its steps is essential to one or more of the various embodiments of the present disclosure, nor does it imply that the illustrated process is preferred.
[0110] While the method has been described through specific embodiments, the method can also be implemented as computer-readable code on a computer-readable recording medium. The computer-readable recording medium includes any type of recording device that stores data that can be read by a computer system (10). Examples of the computer-readable recording medium may include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage, etc. In addition, the computer-readable recording medium can be distributed across network-connected computer systems (10), so that the computer-readable code can be stored and executed in a distributed manner. In addition, functional programs, codes, and code segments for implementing the above embodiments can be easily inferred by programmers in the technical field to which the present disclosure pertains.
Claims
1. In a method for processing a product sales registration request performed by an electronic device, A step of receiving a sales registration request for a product, wherein the sales registration request includes information on a product name of the product; A step of performing tokenization on the product name to generate one or more first keywords for the product name; A step of identifying one or more synonyms for at least some of the one or more first keywords based on a list of keyword synonyms; A step of generating one or more keyword groups based on a combination of the one or more first keywords and the one or more synonyms, wherein each of the one or more keyword groups includes one or more second keywords; A step of calculating one or more scores based on a similarity between the one or more second keywords and one or more third keywords set for the protected brand, wherein the one or more keyword groups each correspond to the one or more scores; A step of calculating an average score for the one or more keyword groups by averaging the one or more scores; A step of comparing the above average score with a preset threshold value; and A method comprising the step of generating information requesting confirmation of acceptance of the sales registration request based on the result of the above comparison.
2. In paragraph 1, Tokenization of the above product name is performed based on a dictionary for morphological analysis, A method wherein the dictionary for the above morphological analysis is a dictionary created based on information about one or more products.
3. In paragraph 1, The step of creating one or more keyword groups is: A method comprising the step of generating one or more keyword groups including one or more second keywords by replacing at least a portion of one or more first keywords with one or more synonyms.
4. In paragraph 3, The step of creating one or more keyword groups is: A step of checking a first keyword having a synonym among the one or more first keywords based on the list of synonyms of the keyword; and A method comprising the step of replacing a first keyword having a synonym with one or more of the synonyms.
5. In paragraph 1, The step of calculating one or more of the above scores comprises: A step of matching the one or more second keywords with the one or more third keywords so that the one or more second keywords each correspond to the one or more third keywords; A step of calculating one or more similarity values between the one or more second keywords and the one or more third keywords based on the above matching; and A method comprising the step of calculating a score by adding up one or more of the above similarity values.
6. In paragraph 1, Each of the above one or more third keywords is associated with a preset weight, The step of calculating one or more of the above scores comprises: A step of matching the one or more second keywords with the one or more third keywords so that the one or more second keywords each correspond to the one or more third keywords; A step of calculating one or more similarity values between the one or more second keywords and the one or more third keywords based on the above matching; and A method comprising the step of calculating a score based on the one or more similarity values and the weights for each of the one or more third keywords.
7. In paragraph 6, A step of obtaining one or more values by multiplying the one or more similarity values and the weights for each of the one or more third keywords; and A method further comprising the step of calculating a score by adding one or more of the above values.
8. In paragraph 6, Further comprising a step of receiving information about one or more third keywords, A method wherein the information about the one or more third keywords includes information for setting weights for at least some of the one or more third keywords.
9. In paragraph 8, A method in which the weight of a third keyword among the one or more third keywords, for which a weight has not been set, is determined as a default value.
10. In paragraph 1, A step of transmitting information requesting confirmation of acceptance of the above sales registration request to the user's terminal device; and A method further comprising the step of receiving, from the terminal device, the user's selection information for accepting or rejecting the sales registration request.
11. In paragraph 10, A method further comprising the step of updating the threshold value based on whether the sales registration request is accepted or rejected.
12. In paragraph 10, A method further comprising the step of updating a weight for each of the one or more third keywords based on whether the sales registration request is accepted or rejected.
13. In paragraph 1, A method wherein the above sales registration request further includes at least one of information about the price of the product or information about the seller of the product.
14. In paragraph 13, A method further comprising, in response to the step of generating information requesting confirmation of acceptance of the sales registration request, a step of determining whether to accept or reject the sales registration request based on at least one of the price of the product or the sales history of the seller of the product.
15. In paragraph 14, A method further comprising the step of updating the threshold value based on whether the sales registration request is accepted or rejected.
16. In paragraph 14, A method further comprising the step of updating a weight for each of the one or more third keywords based on whether the sales registration request is accepted or rejected.
17. In an electronic device that processes a request for product sales registration, processor; and A memory comprising instructions configured to be executed by the processor is stored, The above instructions, when executed by the processor, cause the processor to: Receive a sales registration request for a product, wherein said sales registration request includes information on the product name of said product, Tokenization is performed on the above product name to generate one or more first keywords for the above product name, Based on a list of keyword synonyms, identify one or more synonyms for at least some of the one or more first keywords, generating one or more keyword groups based on a combination of the one or more first keywords and the one or more synonyms, wherein each of the one or more keyword groups includes one or more second keywords; Calculating one or more scores based on a similarity between the one or more second keywords and one or more third keywords set for the protected brand, wherein the one or more keyword groups each correspond to the one or more scores, By averaging the one or more scores above, an average score for the one or more keyword groups is calculated, Compare the above average score with a preset threshold value, An electronic device that generates information requesting confirmation of acceptance of the sales registration request based on the results of the above comparison.
Citation Information
Patent Citations
Method and system for providing article information and retrieval system
JP2002032408A
Commercial product information production program, commercial product information production method, and information processing device
JP2023065004A
Valve having 3D wave flow type separating trim-stack
KR102253332B1
Plant box with LID infiltration ditch
KR102377744B1
KR20210038496A
