KR-20260063008-A - METHOD FOR GENERATIING AI RESPONSE USING PERSONAL DATA AND APPARATUS THEREFOR

KR20260063008AKR 20260063008 AKR20260063008 AKR 20260063008AKR-20260063008-A

Abstract

The present disclosure relates to a method and apparatus for generating an AI response using personal data. Specifically, it relates to a method and apparatus for generating a work-related response on behalf of a user by transmitting a prompt related to work-related data to a generative AI model. The present disclosure relates to a method and apparatus for generating a single AI response message for a plurality of messages. Additionally, the present disclosure relates to a method and apparatus for determining whether a generated AI response message corresponds to a received message.

Inventors

홍주선
장재혁
김대곤
서혜미
조무영

Assignees

삼성에스디에스 주식회사

Dates

Publication Date: 20260507
Application Date: 20241030

Claims (20)

In a method performed by a computing device, A step of obtaining a first message with a first user as the recipient; A step of generating a first message schedule indicating a time for generating a response to the first message using the analysis result of the first message; and The method includes the step of performing a process of automatically generating a response message for a response target message set including the first message and one or more additional messages at the time of generating a response to the first message according to the first message schedule, wherein The time of generating a response to the first message is a time that is delayed by more than a reference value compared to the time of acquiring the first message, and The above process is, Searching for information related to messages included in the above response target message set in the business information database of the organization to which the first user belongs; Automatically generating a first prompt for obtaining a response for each message included in the above response target message set—the first prompt including the above retrieved information; Transmitting the first prompt to a generative AI-based query service; and A method comprising receiving the response message in response to the transmission of the first prompt from the generative AI-based query service. Method for generating AI responses using personal data.
In Article 1, The above business information database is, Between the time of acquisition of the first message and the time of generation of a response to the first message, an update of information related to the first user is reflected, Method for generating AI responses using personal data.
In Article 1, The above set of response target messages is, A second message obtained from the sender of the first message, comprising Method for generating AI responses using personal data.
In Article 1, The above set of response target messages is, A second message obtained from a person different from the sender of the first message, comprising Method for generating AI responses using personal data.
In Article 1, The step of performing the above process is, Between the time of acquisition of the first message and the time of generation of a response to the first message, the step of checking the response message of the first user to the first message; and If the response message to the first message of the first user is not confirmed, the method includes the step of performing the process at the time of generating the response to the first message. Method for generating AI responses using personal data.
In a method performed by a computing device, A step of obtaining a first message with a first user as the recipient; A step of confirming a second message schedule that has the first user as the recipient and indicates a time for generating a response to a second message that is different from the first message; When the above second message schedule is confirmed, a step of determining whether to add the first message to a response target message set including the second message using the analysis results of the first message and the second message; When adding the first message to the response target message set, the method includes the step of performing a process to automatically generate a response message for the response message set at the time of generating a response for the response target message set according to the second message schedule. The time of generating a response for the above response target message set is a time delayed by more than a reference value compared to the time of acquiring the above second message, and The above process is, Searching for information related to messages included in the above response target message set in the business information database of the organization to which the first user belongs; Automatically generating a first prompt for obtaining a response for each message included in the above response target message set—the first prompt including the above retrieved information; Transmitting the first prompt to a generative AI-based query service; and A method comprising receiving the response message in response to the transmission of the first prompt from the generative AI-based query service. Method for generating AI responses using personal data.
In Article 6, The step of determining whether to add the first message to the above response target message set is: A step of automatically generating a second prompt for determining the similarity between the content of the second message and the content of the first message; A step of transmitting the second prompt to a generative artificial intelligence-based query service; A step of receiving a second answer in response to the transmission of the second prompt from the generative artificial intelligence-based query service; Based on the second response above, the step of determining whether to add the first message to the response target message set further comprises Method for generating AI responses using personal data.
In a method performed by a computing device, A step of obtaining a first message with a first user as the recipient; A step of searching for information related to the first message in the business information database of the organization to which the first user belongs; A step of automatically generating a first prompt for obtaining a response message to the first message—the first prompt includes the retrieved information—; A step of transmitting the first prompt to the first generative AI-based query service; A step of receiving a first answer in response to the transmission of the first prompt from the first generative AI-based query service; and If it is determined that the content of the above answer corresponds to the content of the above first message, the method includes the step of determining the above first answer as the above response message. Method for generating AI responses using personal data.
In Article 8, The step of automatically generating the first prompt above is, A step of determining whether to generate the response message using the above-mentioned searched information; and If it is determined that the above response message can be generated, the step of automatically generating the above first prompt is additionally included. Method for generating AI responses using personal data.
In Article 8, The above first prompt is, including setting information entered by the first user to generate the response message, Method for generating AI responses using personal data.
In Article 8, The step of determining the above first answer as the above response message is, A step of automatically generating a second prompt to determine whether the content of the first answer corresponds to the content of the first message; A step of transmitting the second prompt to a second generative AI-based query service; A step of receiving a second answer in response to the transmission of the second prompt from the second generative AI-based query service; and A method further comprising a step of determining whether the content of the first answer corresponds to the content of the first message using the second answer. Method for generating AI responses using personal data.
In Article 8, The step of searching for information related to the first message in the business information database of the organization to which the first user belongs is: A step of automatically generating a second prompt to remove parts of the first message that are unrelated to the first user's work; A step of transmitting the second prompt to a generative AI-based query service; A step of receiving messages from which parts unrelated to the first user's work have been removed in response to the transmission of the second prompt from the generative AI-based query service; and The method further includes the step of searching for information related to the received messages from which parts unrelated to the first user's work have been removed in the work information database of the organization to which the first user belongs. Method for generating AI responses using personal data.
In Article 8, The step of searching for information related to the first message in the business information database of the organization to which the first user belongs is: A step of automatically generating a second prompt to extract keywords related to the first user's work from the first message; A step of transmitting the second prompt to a generative AI-based query service; A step of receiving keywords related to the first user's work in response to the transmission of the second prompt from the generative AI-based query service; and The method further includes the step of searching for information related to keywords associated with the received first user's work in the work information database of the organization to which the first user belongs. Method for generating AI responses using personal data.
Communication interface; Memory where a computer program is loaded; and The computer program described above includes one or more processors on which it is executed, The above computer program is, The operation of obtaining a first message with a first user as the recipient; The operation of generating a first message schedule indicating a time for generating a response to the first message using the analysis result of the first message; and The method includes an instruction for performing an operation to automatically generate a response message for a response target message set including the first message and one or more additional messages at the time of generating a response to the first message according to the first message schedule, wherein The time of generating a response to the first message is a time that is delayed by more than a reference value compared to the time of acquiring the first message, and The above process is, Searching for information related to messages included in the above response target message set in the business information database of the organization to which the first user belongs; Automatically generating a first prompt for obtaining a response for each message included in the above response target message set—the first prompt including the above retrieved information; Transmitting the first prompt to a generative AI-based query service; and A method comprising receiving the response message in response to the transmission of the first prompt from the generative AI-based query service. AI response generation device using personal data.
In Article 14, The above set of response messages is, A second message obtained from the sender of the first message, comprising AI response generation device using personal data.
In Article 14, The operation of performing the above process is, Between the time of acquisition of the first message and the time of generation of a response to the first message, an operation of checking the response message of the first user to the first message; and If the response message to the first message of the first user is not confirmed, the method includes an operation to perform the process at the time of generating the response to the first message. AI response generation device using personal data.
Communication interface; Memory where a computer program is loaded; and The computer program described above includes one or more processors on which it is executed, The above computer program is, The operation of obtaining a first message with a first user as the recipient; An operation to check a second message schedule that has the first user as the recipient and indicates a time for generating a response to a second message that is different from the first message; When the second message schedule is confirmed, an operation to determine whether to add the first message to a response target message set including the second message by using the similarity between the content of the second message and the content of the first message; When adding the first message to the response message set, the method includes an instruction for performing an operation to automatically generate a response message for the response message set at the time of generating a response for the response target message set according to the second message schedule, wherein The time of generating a response for the above response target message set is a time delayed by more than a reference value compared to the time of acquiring the above second message, and The above process is, Searching for information related to messages included in the above response target message set in the business information database of the organization to which the first user belongs; Automatically generating a first prompt for obtaining a response for each message included in the above response target message set—the first prompt including the above retrieved information; Transmitting the first prompt to a generative AI-based query service; and A method comprising receiving the response message in response to the transmission of the first prompt from the generative AI-based query service. AI response generation device using personal data.
Communication interface; Memory where a computer program is loaded; and The computer program described above includes one or more processors on which it is executed, The above computer program is, The operation of obtaining a first message with a first user as the recipient; The operation of searching for information related to the first message in the business information database of the organization to which the first user belongs; An operation to automatically generate a first prompt for obtaining a response message to the first message—the first prompt includes the searched information—; The operation of transmitting the first prompt to the first generative AI-based query service; The operation of receiving a first answer in response to the transmission of the first prompt from the first generative AI-based query service; and If it is determined that the content of the above answer corresponds to the content of the above first message, the method includes an instruction for performing an operation to determine the above first answer as the above response message. AI response generation device using personal data.
In Article 18, The operation of automatically generating the above-mentioned first prompt is, An operation to determine whether to generate the response message using the above-mentioned searched information; and If it is determined that the above response message can be generated, the operation of automatically generating the above first prompt is additionally included. AI response generation device using personal data.
In Article 18, The operation of determining the above first answer as the above response message is, An operation to automatically generate a second prompt for determining whether the content of the first answer corresponds to the content of the first message; The operation of transmitting the second prompt to the second generative AI-based query service; The operation of receiving a second answer in response to the transmission of the second prompt from the second generative AI-based query service; and A method further comprising an operation of determining whether the content of the first answer corresponds to the content of the first message using the second answer. AI response generation device using personal data.

Description

Method for generating AI responses using personal data and apparatus therefor The present disclosure relates to a method and apparatus for generating an AI response using personal data. Specifically, it relates to a method and apparatus for generating a work-related response on behalf of a user by transmitting a prompt related to work-related data to a generative AI model. Generative AI models refer to artificial neural networks capable of generating new text, images, voice, and more based on given data. Generative AI models can be utilized to automatically generate various forms of content. Chatbots utilizing generative AI models can provide conversational services to answer user questions or assist with tasks. These chatbots are being used efficiently in various fields, such as customer support and information retrieval. However, current generative AI models perform machine learning based on general data. Therefore, chatbots utilizing current generative AI models may lack accuracy in tasks requiring up-to-date information or personal information. Consequently, there is a demand for chatbots utilizing generative AI models that can assist specific individuals with their work. FIG. 1 is a conceptual diagram showing the overall configuration of an AI response generation system using personal data according to one embodiment of the present disclosure. FIG. 2 is a flowchart exemplarily illustrating a method for generating an AI response using personal data according to one embodiment of the present disclosure. Figure 3 is an example diagram specifically illustrating the method of generating an AI response using personal data described with reference to Figure 2. Figure 4 is a flowchart showing an example related to the response message generation process described with reference to Figure 2. Figure 4 is an example diagram specifically illustrating the method of generating an AI response using personal data described with reference to Figure 2. Figure 5 is another example diagram specifically illustrating the method of generating an AI response using personal data described with reference to Figure 2. Figure 6 is another example diagram specifically illustrating the method of generating an AI response using personal data described with reference to Figure 2. FIG. 7 is a flowchart exemplarily illustrating a method for generating an AI response using personal data according to another embodiment of the present disclosure. FIG. 8 is a flowchart exemplarily illustrating step S220 of FIG. 6. Figure 9 is an example diagram specifically illustrating the method of generating an AI response using personal data described with reference to Figure 6. FIG. 10 is a flowchart exemplarily illustrating a method for generating an AI response using personal data according to another embodiment of the present disclosure. Figure 11 is an example diagram specifically illustrating a method for generating an AI response using personal data, as described with reference to Figure 10. FIG. 12 is a flowchart exemplarily illustrating step S420 of FIG. 10. Figure 13 is another example diagram specifically illustrating the method of generating an AI response using personal data described with reference to Figure 10. FIG. 14 is a hardware configuration diagram of a computing device (1000) for a method of generating an AI response using personal data according to some embodiments of the present disclosure. Hereinafter, embodiments of the present disclosure will be described in detail with reference to the attached drawings. The advantages and features of the embodiments of the present disclosure and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the attached drawings. However, the technical concept of the present disclosure is not limited to the following embodiments but can be implemented in various different forms. The following embodiments are provided merely to complete the technical concept of the present disclosure and to fully inform those skilled in the art of the scope of the present disclosure, and the technical concept of the present disclosure is defined only by the scope of the claims. It should be noted that when 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 embodiments of the present disclosure, if it is determined that a detailed description of related known components or functions could obscure the essence of the matter, such detailed description is omitted. Unless otherwise defined, all terms used in this disclosure (including technical and scientific terms) may be used in a meaning commonly understood by those skilled in the art to which the embodiments of this disclosure pertain. Additionally, terms defined in commonly used dictionaries are not to be interpreted ideally or excessively