Search

KR-20260063230-A - Method and device for artificial intelligence service based on causal inference reflecting user tendencies using the usage history of computing devices

KR20260063230AKR 20260063230 AKR20260063230 AKR 20260063230AKR-20260063230-A

Abstract

A method and apparatus for an artificial intelligence service based on causal inference that reflects user tendencies using the usage history of a computing device are disclosed. A method for an artificial intelligence service based on causal inference that reflects user tendencies using the usage history of a computing device according to one aspect of the present invention comprises: a step of analyzing usage tendencies based on the usage history of a computing device of a user who has entered a question; a step of selecting one or more query keywords that are the subject of causal inference based on basic information and usage tendencies corresponding to the entered question; a step of selecting a plurality of inference factors corresponding to the query keywords; a step of requesting a user selection for each selected inference factor; and a step of generating a causal inference answer corresponding to the question by first using the inference factor selected by the user.

Inventors

  • 송광헌
  • 이금탁
  • 양승남
  • 김창모
  • 채화종
  • 이진웅

Assignees

  • 주식회사 피씨엔

Dates

Publication Date
20260507
Application Date
20241030

Claims (10)

  1. In a causal reasoning-based artificial intelligence service method, A step of analyzing usage patterns based on the computing device usage history of the user who entered the question; A step of selecting one or more query keywords that are the subject of causal inference based on basic information corresponding to the input question and the above usage trends; A step of selecting multiple inference factors corresponding to the above query keywords; A step of requesting user selection for each selected inference factor; and A causal inference-based artificial intelligence service method reflecting user tendencies using the usage history of a computing device, comprising the step of generating a causal inference answer corresponding to the above question by first utilizing inference factors selected by the user.
  2. In paragraph 1, A causal inference-based artificial intelligence service method that reflects user tendencies using the usage history of a computing device, generating the causal inference answer by adding weights to inference factors corresponding to the above usage tendency.
  3. In paragraph 1, A causal inference-based artificial intelligence service method that reflects user tendencies using the usage history of a computing device, generating user questions unrelated to the above-mentioned query keywords and respective answers according to the above-mentioned inference factors to request the above-mentioned user selection.
  4. In paragraph 3, A causal inference-based artificial intelligence service method that reflects user tendencies using the usage history of a computing device, which generates and provides each answer for the above-mentioned user selection as an image.
  5. In paragraph 4, A causal inference-based artificial intelligence service method that reflects user tendencies using the usage history of a computing device, providing information on the selection history of other users who selected each answer for the above-mentioned user selection.
  6. In paragraph 1, A causal inference-based artificial intelligence service method reflecting user tendencies using the usage history of a computing device, which selects the inference factor based on the user inference tendency set using multiple prior questions and answers managed as the user's history information.
  7. In paragraph 1, A causal inference-based artificial intelligence service method that reflects user tendencies using the usage history of a computing device, which prioritizes the use of information according to a storage or data type pre-specified by the user as basic information.
  8. A computer program stored on a computer-readable medium that enables the execution of a causal inference-based artificial intelligence service method reflecting user tendencies using the usage history of a computing device, wherein the computer program enables the computer to perform the following steps, and the steps are, A step of analyzing usage patterns based on the computing device usage history of the user who entered the question; A step of selecting one or more query keywords that are the subject of causal inference based on basic information corresponding to the input question and the above usage trends; A step of selecting multiple inference factors corresponding to the above query keywords; A step of requesting user selection for each selected inference factor; and A computer program stored on a computer-readable medium, comprising the step of generating a causal inference answer corresponding to the above question by first utilizing inference factors selected by the user.
  9. Information search unit that searches for basic information corresponding to the input question; A usage tendency analysis unit that analyzes usage tendencies based on the computing device usage history of the user who entered the above question; An inference factor selection unit that selects one or more query keywords to be the subject of causal inference based on the above basic information and the above usage trends, and selects multiple inference factors corresponding to the above query keywords; A user interface section for receiving a selection from the user for each selected inference factor; and A causal inference-based artificial intelligence service device reflecting user tendencies using the usage history of a computing device, comprising a causal inference unit that generates an answer by performing causal inference corresponding to the above question using inference factors selected by the user first.
  10. In Paragraph 9, The above-mentioned causal inference unit generates the above-mentioned causal inference answer by adding weights to inference factors corresponding to the above-mentioned usage tendency, a causal inference-based artificial intelligence service device reflecting user tendency using the usage history of a computing device.

Description

Method and device for artificial intelligence service based on causal inference reflecting user tendencies using the usage history of computing devices The present invention relates to a causal inference-based artificial intelligence service method and device that reflects user tendencies using the usage history of a computing device. Recently, there has been an explosive increase in interest in conversational artificial intelligence (AI), such as ChatGPT. While advanced AI technology leads us to expect it to surpass the human brain not only in quantitative aspects like processing speed and memory but also in qualitative aspects such as insight and artistic creativity, there are still many areas where it falls short of catching up with the human brain, a system that is remarkably efficient and even elegant. For AI to evolve into a cooperative relationship that assists humans, there is a challenge that must be overcome. This challenge is causal reasoning. In the context of machine learning, causal reasoning can be used to identify the most important factors influencing a specific outcome. However, while it remains difficult to develop artificial intelligence capable of performing human-like causal reasoning, many attempts are being made. Therefore, since perfect causal inference may be virtually impossible, it is necessary to provide users with customized causal inference AI that reflects their tendencies or situations. FIGS. 1 and 2 are configuration diagrams and flowcharts illustrating a causal inference-based artificial intelligence service device and process reflecting user tendencies according to an embodiment of the present invention. FIG. 3 is an exemplary diagram illustrating a user interface screen for selecting inference factors according to an embodiment of the present invention. FIG. 4 is an example diagram illustrating inference tendency information set and managed using user usage history according to an embodiment of the present invention. FIG. 5 is an exemplary diagram illustrating a causal inference-based artificial intelligence service reflecting user tendencies according to an embodiment of the present invention. FIG. 6 is a flowchart illustrating a process for generating a causal inference answer using the usage history of a computing device according to an embodiment of the present invention. FIG. 7 is a table illustrating a user's computing device usage history according to an embodiment of the present invention. The present invention is capable of various modifications and may have various embodiments, and specific embodiments are illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the invention to specific embodiments, and it should be understood that the invention includes all modifications, equivalents, and substitutions that fall within the spirit and scope of the invention. When it is stated that one component is "connected" or "connected" to another component, it should be understood that while it may be directly connected or connected to that other component, there may also be other components in between. On the other hand, when it is stated that one component is "directly connected" or "directly connected" to another component, it should be understood that there are no other components in between. Terms such as "first," "second," etc., may be used to describe various components, but said components should not be limited by said terms. These terms are used solely for the purpose of distinguishing one component from another. For example, terms such as "first threshold," "second threshold," etc., to be described later may be pre-designated as thresholds that are substantially different or partially identical; however, since there is a possibility of confusion when expressed using the same word "threshold," the terms "first," "second," etc., will be used together for the convenience of distinction. The terms used herein are merely for describing specific embodiments and are not intended to limit the invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this specification, terms such as “comprising” or “having” are intended to indicate the presence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof. Furthermore, the components of the embodiments described with reference to each drawing are not limited to the respective embodiments and may be implemented to be included in other embodiments within the scope of maintaining the technical spirit of the present invention; it is also obvious that multiple embodiments may be re-implemented as a single embodiment that integrates multiple embodiments, even if a separate description is omitte