KR-102963641-B1 - METHOD AND SYSTEM FOR PROVIDING RESPONSE THAT ASYNCHRONNOUSLY TRANSMIT RESPONSE FROM LANGUAGE MODEL BY CONSIDERING RESPONSE REQUEST TIME OF CHATBOT SERVER

KR102963641B1KR 102963641 B1KR102963641 B1KR 102963641B1KR-102963641-B1

Abstract

A method and system for providing a response that asynchronously delivers a response from a language model, taking into account the response request time of a chatbot server. A method for providing a response according to one embodiment may include: generating a prompt based on a message included in a user's request; delivering the generated prompt to a language model; delivering a response delay notice including a re-request function to the user if the response from the language model is not received within the response time limit of a session corresponding to the user's request; storing the response received from the language model in a database; receiving a re-request from the user through the re-request function; and extracting the response stored in the database in response to the received re-request and providing it to the user.

Inventors

최원석

Assignees

국립한국해양대학교산학협력단

Dates

Publication Date: 20260512
Application Date: 20250509

Claims (15)

In a method for providing a response of a response providing system implemented by at least one computer device, The above at least one computer device includes at least one processor, and The above method of providing a response is, A step of generating a prompt based on a message containing a user's request by the above-mentioned at least one processor; A step of transmitting the generated prompt to a language model by the above at least one processor; A step of delivering a response delay notice including a re-request function to the user by the at least one processor if the response from the language model is not received within the response time limit of the session corresponding to the user's request; A step of storing a response received from the language model in a database by the above at least one processor; The step of receiving a re-request from the user through the re-request function by the at least one processor; and A step of extracting a response stored in the database and providing it to the user in response to the received re-request by the at least one processor. A method for providing a response characterized by including
In paragraph 1, The step of delivering the above response delay notice to the user is, Providing the response delay notice to the user's terminal so that the response delay notice message and the re-request function are displayed on the terminal according to the control of the chatbot client installed and running on the user's terminal. A method for providing a response characterized by
In paragraph 1, A method for providing a response characterized by the above-mentioned re-request function including a message for inducing the user to make a re-request through the user's input and a link for making a re-request according to the user's input.
In paragraph 1, The above-mentioned saving step is, A step of storing a response from the above language model in the above database in association with the above session; and A step of setting a final response tag of a first value in the database indicating that the response from the language model associated with the above session has been stored in the database. A method for providing a response characterized by including
In paragraph 4, The step of extracting the response stored in the above database and providing it to the user is: A step of checking the final response tag in the database in response to the received re-request, and if the final response tag is set to the first value, extracting the response stored in the database in association with the session. A method for providing a response characterized by including
In paragraph 1, The above method of providing a response is, The step of storing the response in the database when the response from the language model is received by the at least one processor within the response time limit of the session corresponding to the user's request; and The step of providing a response stored in the database to the user as a response corresponding to the user's request by the above at least one processor A method for providing a response characterized by further including
In paragraph 1, The above language model includes a Large Language Model (LLM) implemented based on a transformer architecture, and The above user request is generated through the above-mentioned massive language model-based chatbot service. A method for providing a response characterized by
A computer program stored on a computer-readable recording medium to execute the method of any one of claims 1 to 7 on a computer device in combination with a computer device.
A computer-readable recording medium having a computer program recorded thereon for executing the method of any one of paragraphs 1 through 7 on a computer device.
In a response providing system implemented by at least one computer device, The above at least one computer device includes at least one processor, and By the above at least one processor, Generate a prompt based on the message included in the user's request, and Pass the above-generated prompt to the language model, and If a response from the above language model is not received within the response timeout of the session corresponding to the user's request, a response delay notice including a re-request function is delivered to the user, and The response received from the above language model is stored in a database, and Receives a re-request from the user through the above re-request function, and Responding to the received re-request above, extracting the response stored in the database and providing it to the user A response providing system characterized by
In Paragraph 10, In order to deliver the above response delay notice to the above user, by the above at least one processor, Providing the response delay notice to the user's terminal so that the response delay notice message and the re-request function are displayed on the terminal according to the control of the chatbot client installed and running on the user's terminal. A response providing system characterized by
In Paragraph 10, A response providing system characterized by the above-mentioned re-request function including a message for inducing the user to make a re-request through the user's input and a link for making a re-request according to the user's input.
In Paragraph 10, In order to store a response received from the above language model in a database, by the at least one processor, The response from the above language model is stored in the above database in conjunction with the above session, and Setting a final response tag of a first value in the database indicating that the response from the language model associated with the above session has been stored in the database. A response providing system characterized by
In Paragraph 13, In order to extract a response stored in the above database, by the at least one processor, In response to the received re-request, the final response tag is checked in the database, and if the final response tag is set to the first value, the response stored in the database in association with the session is extracted. A response providing system characterized by
In Paragraph 10, By the above at least one processor, If a response from the above language model is received within the response timeout of the session corresponding to the user's request, the response is stored in the database, and Providing the user with a response stored in the above database as a response corresponding to the user's request. A response providing system characterized by

Description

Method and system for providing response that asynchronously transmits a response from a language model considering the response request time of a chatbot server The following description relates to a response provision method and system that asynchronously delivers the response of a language model, taking into account the response request time of the chatbot server. Since conventional conversations between a user and a chatbot server must operate synchronously, if the response request time (the response time limit, which is the time during which a response must be delivered to a user's request) is exceeded due to response delays of the language model, the chatbot server cannot deliver the response of the language model to the user. For example, in large-scale social media services, the transmission of messages not requested by the user is classified as 'advertising' and incurs costs; therefore, chatbot servers are configured to provide responses only to user requests, and there is a response request time (or response time limit) of a certain period (as short as 5 seconds to as long as 1 minute) after a user request. When integrating a chatbot server using a language model, due to the response delay of the language model (language models take time to respond, ranging from as short as 1 second to as long as 30 seconds or more), there may be cases where the language model's response is not delivered within the response request time required by the social media service after the user's request. In this case, if the response request time (response time limit) for the user request is exceeded, there is a problem in that the response delivered by the artificial intelligence cannot be delivered to the user without a new request from the user. [Prior Art No.] Korean Registered Patent No. 10-2699424 FIG. 1 is a drawing illustrating an example of a network environment according to an embodiment of the present invention. FIG. 2 is a block diagram illustrating an example of a computer device according to an embodiment of the present invention. FIG. 3 is a diagram illustrating an example of a general view of a response providing system in one embodiment of the present invention. FIG. 4 is a diagram illustrating an example of a response providing process in an embodiment of the present invention. FIG. 5 is a diagram illustrating another example of a response providing process in one embodiment of the present invention. FIG. 6 is a diagram illustrating an example of a message for response delay guidance in one embodiment of the present invention. FIG. 7 is a flowchart illustrating an example of a response providing method in one embodiment of the present invention. Hereinafter, embodiments will be described in detail with reference to the attached drawings. A response providing system according to embodiments of the present invention may be implemented by at least one computer device. In this case, a computer program according to one embodiment of the present invention may be installed and run on at least one computer device, and at least one computer device may perform a response providing method according to embodiments of the present invention under the control of the run computer program. The above-described computer program may be stored on a computer-readable recording medium to be combined with at least one computer device to execute the response providing method on a computer. FIG. 1 is a diagram illustrating an example of a network environment according to an embodiment of the present invention. The network environment of FIG. 1 illustrates an example including a plurality of electronic devices (110, 120, 130, 140), a plurality of servers (150, 160), and a network (170). FIG. 1 is an example for explaining the invention, and the number of electronic devices or servers is not limited to that shown in FIG. 1. Furthermore, the network environment of FIG. 1 is merely an example of one of the environments applicable to the present embodiments, and the environments applicable to the present embodiments are not limited to the network environment of FIG. 1. Multiple electronic devices (110, 120, 130, 140) may be fixed terminals or mobile terminals implemented as computer devices. Examples of multiple electronic devices (110, 120, 130, 140) include smartphones, mobile phones, navigation systems, computers, laptops, digital broadcasting terminals, PDAs (Personal Digital Assistants), PMPs (Portable Multimedia Players), tablet PCs, etc. For example, FIG. 1 shows the shape of a smartphone as an example of an electronic device (110), but in embodiments of the present invention, the electronic device (110) may substantially refer to one of various physical computer devices capable of communicating with other electronic devices (120, 130, 140) and/or servers (150, 160) via a network (170) using a wireless or wired communication method. The communication method is not limited and may include not only communication methods utilizi