KR-20260063552-A - Method And Apparatus for Providing Answer Including Advertisement

Abstract

A method and apparatus for providing an answer including an advertisement are disclosed. According to one aspect of the present disclosure, a computer-implemented method for providing an answer including an advertisement in response to a user's question is provided, comprising: a step of obtaining an advertisement material associated with the question obtained from the user; a step of generating one or more prompts based on one or more of the question and the advertisement material; and a step of generating an answer based on the prompts.

Inventors

• 김형은

Assignees

• 에스케이텔레콤 주식회사

Dates

Publication Date

20260507

Application Date

20241030

Claims (7)

1. A computer implementation method for providing an answer including an advertisement in response to a user's question, A process of obtaining advertising materials related to the above question obtained from the above user; A process of generating one or more prompts based on one or more of the above questions and the above advertising materials; and A computer implementation method comprising a process of generating an answer based on the above prompt.
2. In paragraph 1, Before obtaining the advertising materials related to the above question, The process of determining the type of the above question; and A computer implementation method further comprising a process of requesting the above advertising material from a user based on the type of the above question.
3. In paragraph 2, The advertising material associated with the above question is a computer implementation method that is an advertising material of the same type as the type of the above question.
4. In paragraph 1, The above one or more prompts include user prompts and system prompts, and The process of generating one or more of the above prompts is, A process of generating the above user prompt based on the above question; and A computer implementation method comprising the process of generating the system prompt based on the above advertising material.
5. In paragraph 1, After generating the above answer, A process for determining whether the above-mentioned advertising material is included in the above-mentioned answer; and A computer implementation method further comprising a process of delivering the above-mentioned judgment result to a user.
6. As a device for providing an answer including an advertisement in response to a user's question, Memory for storing instructions; and at least one processor, comprising The above at least one processor executes the above instructions, Obtaining advertising materials related to the above question obtained from the above user, and Based on one or more of the above questions and the above advertising materials, generate one or more prompts, and A device comprising a process for generating an answer based on the above prompt.
7. A computer program stored on a computer-readable recording medium to execute each process included in the method according to any one of paragraphs 1 through 5.

Description

Method and Apparatus for Providing Answer Including Advertisement The present disclosure relates to a method and apparatus for providing a response including an advertisement. The following description merely provides background information related to the present embodiment and does not constitute prior art. With the emergence of Large Language Models (LLMs) such as GPT-3.5 and GPT-4, the method of users asking questions in natural language and receiving immediate answers is becoming commonplace. Consequently, there is an increasing number of instances where users utilize LLMs rather than traditional search portals when searching for desired information. Traditional search portals exposed advertisements to users through a listing ad method that placed ads on web pages or search results. However, LLM is not suitable for applying this advertising method. Therefore, a method and mechanism are needed for LLM to generate and provide answers containing advertisements to users. FIG. 1 is a drawing referenced to explain the basic operation of an LLM agent according to one embodiment of the present disclosure. FIG. 2 is a block diagram schematically showing the configuration of an LLM agent according to one embodiment of the present disclosure. FIG. 3 is a drawing referenced to explain the detailed operation of an LLM agent according to one embodiment of the present disclosure. FIG. 4 is a flowchart schematically illustrating the process of an LLM agent providing an answer including an advertisement according to one embodiment of the present disclosure. FIG. 5 is a schematic block diagram of an exemplary computing device that can be used to implement the devices and methods described in the present disclosure. Some embodiments of the present disclosure are described in detail below with reference to exemplary drawings. It should be noted that in assigning reference numerals to the components of each drawing, the same components are given the same reference numeral whenever possible, even if they are shown in different drawings. Furthermore, in describing the present disclosure, if it is determined that a detailed description of related known components or functions could obscure the essence of the present disclosure, such detailed description is omitted. In describing the components of the embodiments according to the present disclosure, symbols such as first, second, i), ii), a), b), etc., may be used. These symbols are intended only to distinguish the components from other components, and the essence, order, or sequence of the components is not limited by the symbols. When a part in the specification is described as 'comprising' or 'having' a component, this means that, unless explicitly stated otherwise, it does not exclude other components but may include additional components. The detailed description set forth below, together with the accompanying drawings, is intended to describe exemplary embodiments of the present disclosure and is not intended to represent the only embodiment in which the present disclosure can be practiced. FIG. 1 is a drawing referenced to explain the basic operation of an LLM agent according to one embodiment of the present disclosure. Referring to FIG. 1, an LLM agent (10) can obtain a question from a user (S100). In the present disclosure, the device for providing an answer including an advertisement may be an LLM agent (10). In the present disclosure, the method for providing an answer including an advertisement may be a set of operations performed by the LLM agent (10). The LLM agent (10) can understand the user's question and generate an answer to the question using a Large Language Model (LM) called a large language model. The LLM agent (10) can provide an answer to the user (S102). The LLM agent (10) can provide an answer generated using LLM as a response to the user's question. The answer generated by the LLM agent (10) using LLM may include an advertisement. The process of the LLM agent (10) generating an answer including an advertisement using LLM will be explained in detail below with reference to FIG. 3. FIG. 2 is a block diagram schematically showing the configuration of an LLM agent according to one embodiment of the present disclosure. Referring to FIG. 2, the LLM agent (10) may include a UI module (100), a prompt generation module (102), a question type analysis module (104), an ad creative request/reception module (106), and an LLM (108). The LLM agent (10) can be implemented using an on-device device or a server. The on-device device may be a user's terminal. The server may be in the form of a cloud server, a web server, a database server (DB server), and an application server, or a combination thereof. The LLM agent (10) may be implemented using one or more computing devices (50). The UI module (100) may provide an interface for interaction between the LLM agent (10) and the user. More specifically, the UI module (100) may provide an input interface for obtaining the