KR-20260063548-A - SYSTEM AND METHOD FOR RECOMMENING KEYWORD FOR SALES PRODUCTS

Abstract

The present invention relates to a keyword recommendation system and method for a product for sale that can recommend keywords with a high probability of sale to a seller based on seller product information and product information from an open market. According to the present invention, a method for providing keyword information of a product for sale to a product seller may include: a seller information collection step of collecting seller product information from an external source; a big data collection step of collecting open market product information from an external source; a product name input step of inputting a product name of a product that the seller intends to register; a text embedding step of vectorizing the input product name; a category prediction step of predicting the product category most advantageous for product sales among a plurality of product categories using the product name; a keyword extraction step of searching for and extracting a plurality of related keywords based on the predicted category; and a keyword analysis and recommendation step of analyzing the demand and competition rate of the extracted keywords and recommending one or more more suitable keywords.

Inventors

• 황인범
• 김세진

Assignees

• 황인범

Dates

Publication Date

20260507

Application Date

20241030

Claims (4)

1. In a method for providing keyword information for products to be sold to product sellers, Seller information collection step for collecting seller product information from external sources; Big data collection stage for collecting open market product information from external sources; A product name input step in which the seller enters the product name of the product they wish to register; Text embedding step for vectorizing the input product name; A category prediction step for predicting the product category most advantageous for product sales among multiple product categories using the above product name; A keyword extraction step for searching and extracting a plurality of associated keywords based on the predicted above categories; and Keyword analysis and recommendation stage that analyzes the demand and competition rates of the extracted keywords to recommend one or more more suitable keywords. A keyword recommendation method for products for sale characterized by including
2. In paragraph 1, The above seller product information includes one or more of the following: product name, product price, category to which the product belongs, product sales volume, number of views for the product, product rating, review information, and product category information. The above open market product information includes one or more of the following: product name, product price, category to which the product belongs, product sales volume, number of views for the product, product rating, review information, product list, and product category information. In the text embedding step above, product names are vectorized using one of the natural language processing models Word2Vec, BERT, or KoBERT, and In the above category prediction step, the category is predicted using CNN, LSTM, and Transformer models with the vector transformed through text embeddings as input, and A keyword recommendation method for products for sale, characterized in that, in the above keyword analysis and extraction step, keywords with high search volume relative to the number of products and high sales performance relative to the search volume are selected preferentially.
3. In paragraph 2, In the keyword analysis and recommendation stage, A keyword recommendation method for a product for sale, characterized by applying the final score calculation formula of the following mathematical formula 1 to evaluate the marketing competitiveness of the product when deriving optimal keywords. [Mathematical Formula 1] Here, am.
4. In paragraph 3, In the keyword analysis and recommendation stage, A keyword recommendation method for a product for sale, characterized in that the search formula adjustment function formula of the following mathematical formula 2 is used in the above mathematical formula 1. [Mathematical Formula 2]

Description

System and Method for Recommending Keyword for Sales Products The present invention is intended to provide a keyword recommendation method for products for sale, and more specifically, to a keyword recommendation method for products for sale that can recommend keywords to a seller that can increase the likelihood of sale in relation to products that the seller intends to sell online. Traditionally, when selling products in online markets, online sellers faced the difficulty of having to personally identify products that are currently selling well or are likely to sell well. Therefore, methods are being developed to improve this problem and increase the sales potential of online sellers by providing information on selected products that are advantageous to the seller. However, despite this, it is very difficult to increase sales potential amidst a multitude of other sellers and products. Therefore, if sellers can select product keywords that are advantageous for maximizing exposure of their items on online sales platforms, it can be of great help in increasing their revenue. FIG. 1 is a block diagram schematically illustrating the configuration of a system according to one embodiment, FIG. 2 is a flowchart illustrating the steps of operation of a device according to one embodiment, and FIG. 3 is a diagram illustrating an example in which a device according to one embodiment provides sales product keyword information. The advantages and features of the present disclosure and the methods for achieving them will become clear from the embodiments described below in detail together with the accompanying drawings. However, the present disclosure is not limited to the embodiments disclosed below and may be implemented in various different forms; the embodiments provided are merely to make the disclosure complete and to fully inform those skilled in the art of the scope of the present disclosure. The terms used in this specification are for describing embodiments and are not intended to limit the disclosure. In this specification, the singular form includes the plural form unless specifically stated otherwise in the text. The terms “comprises” and/or “comprising” as used in this specification do not exclude the presence or addition of one or more other components in addition to the components mentioned. Throughout the specification, the same reference numerals refer to the same components, and “and/or” includes each of the mentioned components and all combinations of one or more. Although terms such as “first,” “second,” etc., are used to describe various components, these components are not limited by these terms. These terms are used merely to distinguish one component from another. Accordingly, the first component mentioned below may be the second component within the technical scope of this disclosure. Unless otherwise defined, all terms used herein (including technical and scientific terms) may be used in a meaning commonly understood by a person skilled in the art. Additionally, terms defined in commonly used dictionaries are not to be interpreted ideally or excessively unless explicitly and specifically defined otherwise. Spatially relative terms such as "below," "beneath," "lower," "above," and "upper" may be used to facilitate the description of the relationship between one component and other components as illustrated in the drawings. Spatially relative terms should be understood as terms that include different orientations of components during use or operation, in addition to the orientations illustrated in the drawings. For example, if a component illustrated in the drawing is flipped, a component described as "below" or "beneath" of another component may be placed "above" of that other component. Therefore, the exemplary term "below" may include both the lower and upper directions. Components may also be oriented in other directions, and accordingly, spatially relative terms may be interpreted according to the orientation. Various embodiments are described in detail below with reference to the drawings. FIG. 1 is a block diagram schematically illustrating the configuration of a system according to one embodiment. Referring to FIG. 1, the device (100) includes a seller information collection unit (110), a big data collection unit (120), and a keyword provision unit (130). The seller information collection unit (110) can collect seller product information, and the big data collection unit (120) can collect open market product information. In addition, the keyword provision (130) analyzes and recommends optimal keywords related to products for sale by the seller based on the collected product information, which can be based on artificial intelligence such as deep learning and machine learning. Here, the device (100) can communicate with the seller terminal (190). It should be noted that the device (100) can communicate via various combinations of conventional networks, such as the Internet network or mobil