KR-20260063891-A - Method for providing a shopping mall automatic response service based on generative artificial intelligence and a computer program stored in a computer-readable recording medium

KR20260063891AKR 20260063891 AKR20260063891 AKR 20260063891AKR-20260063891-A

Abstract

The present invention relates to a method for providing an automatic response service for a shopping mall based on generative artificial intelligence and a computer program stored on a computer-readable recording medium. The method for providing an automatic response service for a shopping mall based on generative artificial intelligence, performed by a management server, comprises: a process of receiving an expected question regarding a product to be sold in a shopping mall; a process of searching for product data regarding the product from a database of a seller terminal based on the expected question; a process of generating an answer to the expected question based on the product data; a process of training an LLM model with the expected question and the answer to generate a dataset; and a process of generating a response to the question based on the dataset when a question is received from the seller terminal. The invention can provide accurate and consistent responses to new questions registered by customers.

Inventors

강익선

Assignees

(주)네피리티

Dates

Publication Date: 20260507
Application Date: 20241031

Claims (8)

As a method for providing a shopping mall automatic response service based on generative artificial intelligence performed by a management server, The process of receiving anticipated questions about products to be sold in a shopping mall; A process of searching for product data for a product from the seller terminal's database based on the above-mentioned expected questions; A process of generating answers to the above-mentioned anticipated questions based on the above-mentioned product data; A process of generating a dataset by training an LLM model with the above-mentioned expected questions and answers; and A method for providing a generative artificial intelligence-based shopping mall automatic response service, comprising: a process of generating a response to a question based on a dataset when a question is received from the seller terminal.
In claim 1, A method for providing a shopping mall automatic response service based on generative artificial intelligence, wherein the process of searching for the above product data includes the process of searching for at least one of product information, Q&A data and review data, shipping policy data and shopping mall information data.
In claim 2, The process of searching for the above product data is, The process of receiving an API key from the above seller terminal; The process of linking with the above seller terminal; and A method for providing a shopping mall automatic response service based on generative artificial intelligence, further comprising the process of searching for at least one of secret post data and order information data of a buyer using the shopping mall from the above database.
In claim 3, A method for providing a shopping mall automatic response service based on generative artificial intelligence, wherein the process of receiving expected questions about products to be sold in the shopping mall and the process of collecting product data about products from the seller terminal database based on the expected questions are performed using a RAG model.
In claim 3, The process of generating the above dataset is, A process of determining the ranking of the predicted questions based on the number of the predicted questions; and A method for providing a shopping mall automatic response service based on generative artificial intelligence, further comprising the process of generating a predetermined number of frequently asked questions and answers (FAQ) lists according to a predetermined ranking.
In claim 5, A method for providing a generative AI-based shopping mall automatic response service that further includes the process of displaying a list of frequently asked questions and answers (FAQ) of the product on the product introduction screen of the shopping mall.
In claim 4, The process of generating the above response is, A process of searching a dataset related to the received question using the above RAG model, and generating an answer to the received question based on the searched dataset; and A method for providing a generative artificial intelligence-based shopping mall automatic response service, comprising: a process of generating a response to the received question based on an answer generated using the above LLM model.
A computer program stored on a computer-readable recording medium that is combined with a computer, which is hardware, to perform the method described in any one of claims 1 to 7.

Description

Method for providing a shopping mall automatic response service based on generative artificial intelligence and a computer program stored in a computer-readable recording medium The present invention relates to a method for providing an automatic response service for a shopping mall based on generative artificial intelligence and a computer program stored on a computer-readable recording medium. More specifically, the invention relates to a method for providing an automatic response service for a shopping mall based on generative artificial intelligence capable of providing accurate responses to various questions registered by customers in an online shopping mall, and a computer program stored on a computer-readable recording medium. Conversational messenger programs, such as chatbots, can provide a conversational messenger service where, when a user who wishes to consult inputs a question using a message transmission method in everyday language as if having a conversation with a person via message, artificial intelligence (AI) provides an answer in general language based on big data analysis, just as if chatting with a person. With the advent of the Fourth Industrial Revolution, these interactive messenger programs are increasingly expanding their scope of application beyond simple consultations, such as product sales and inquiries at online shopping malls, to include remote medical consultations that require specialized knowledge. Generally, interactive messenger programs interpret questions entered by the user, automatically generate response messages, and provide them to the user. However, such programs have a limitation in that they often provide inappropriate responses when they receive questions that are unprepared or cannot be mechanically addressed. Accordingly, at the current level of technology, conversational messenger programs can only be applied to small amounts of data that can be generated in a short period, simple consultation tasks, or simple questions that can be handled by unskilled personnel without product knowledge, such as branch location information or phone number inquiries. Consequently, there is a growing trend requiring technology that enables the establishment of professional consultation knowledge and allows the program to be trained to the level of a human agent based on this foundation. FIG. 1 is a conceptual diagram of a shopping mall automatic response service providing device based on generative artificial intelligence according to an embodiment of the present invention. FIG. 2 is a block diagram of the management server shown in FIG. 1. FIG. 3 is a flowchart showing a method for providing a shopping mall automatic response service based on generative artificial intelligence according to an embodiment of the present invention. FIG. 4 is a flowchart showing the monitoring process in the method for providing a shopping mall automatic response service based on generative artificial intelligence according to an embodiment of the present invention. The advantages and features of the present invention and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below but may be implemented in various different forms. These embodiments are provided merely to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the scope of the present invention, and the present invention is defined only by the scope of the claims. The terms used in this specification are for describing embodiments and are not intended to limit the invention. In this specification, the singular form includes the plural form unless specifically stated otherwise in the text. The terms "comprises" and/or "comprising" 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. Therefore, the first component mentioned below may be the second component within the technical scope of the invention. Unless otherwise defined, all terms used herein (including technical and scientific terms) may be used in a meaning commonly understood by those skilled in the art to which the present invention pertains. Additionally, terms defined in commonly used dictionaries are not to be interpreted ideally or excessively unless explicitly and specifically defined otherwise. Hereinafter, embodiments of the present invention will be described in detail with r