JP-2026075547-A - Information processing systems, information processing methods, and programs

JP2026075547AJP 2026075547 AJP2026075547 AJP 2026075547AJP-2026075547-A

Abstract

[Problem] To provide an information processing system, information processing method, and program that can suitably generate translated text in response to user requests. [Solution] In the information processing system 10, the source text receiving unit 111 receives the source text, which is text data to be input to the generative artificial intelligence, from the user terminal. The language setting unit 112 sets the specified language, which is the language classification of the translated text, which is text data obtained by translating the source text. The format receiving unit 113 receives the specified format, which is the format of the translated text, from the user terminal as text data. The translation instruction unit 114 inputs a prompt to the generative artificial intelligence that includes an instruction to perform a translation process to translate the source text into the specified language according to the specified format, thereby causing the generative artificial intelligence to generate the translated text. The presentation unit 115 presents the translated text to the user terminal. [Selection Diagram] Figure 1

Inventors

松岡清一

Assignees

株式会社FIXER

Dates

Publication Date: 20260508
Application Date: 20241022

Claims (13)

An information processing system that uses generative artificial intelligence capable of generating tasks based on input received from a user terminal to perform translation, A source text receiving unit receives source text, which is text data to be input into the aforementioned generative artificial intelligence, from a user terminal. A language setting unit sets a specified language, which is the language classification of the translated text, which is the text data obtained by translating the aforementioned original text. A format receiving unit that receives the specified format, which is the format of the translated text, from the user terminal as text data, A translation instruction unit that causes the generative artificial intelligence to generate the translated text by inputting a prompt to the generative artificial intelligence that includes an instruction to perform a translation process to translate the aforementioned source text into the specified language in accordance with the specified format, The system includes a display unit that displays the translated text to the user terminal. Information processing system.
In the information processing system described in claim 1, A conversation mode receiving unit that receives from the user terminal a request to enter conversation mode in which a prompt in the form of arbitrary text data is input to the generative artificial intelligence, The system further includes a translation mode receiving unit that receives from the user terminal a request to enter a translation mode in which a prompt related to the translation process is input to the generative artificial intelligence. Information processing system.
In the information processing system described in claim 1, The system further includes a glossary selection unit that receives a request from the user terminal to select at least one glossary from a storage unit that selectively stores glossaries containing translations for specific words or phrases. The translation instruction unit inputs a prompt to the generative artificial intelligence that includes an instruction to perform the translation process by referring to the selected glossary. Information processing system.
In the information processing system described in claim 3, The system further comprises a storage unit that selectively stores multiple glossaries, each containing a translation for a specific word or phrase. Information processing system.
In the information processing system described in claim 3, The translation instruction unit also inputs a prompt to the generative artificial intelligence instructing it to determine, token by token, whether or not to apply the selected glossary, according to the context of the source text. Information processing system.
In the information processing system described in claim 1, The translation instruction unit also inputs a prompt to the generative artificial intelligence that includes an instruction to access a storage unit that stores a translation sample including a sample source text and a sample translated text obtained by translating the sample source text in the specified language, and to execute the translation process according to the requirements based on the translation sample. Information processing system.
In the information processing system described in claim 6, The system further comprises a storage unit for storing the translation sample, which includes the sample source text and the sample translated text. Information processing system.
In the information processing system described in claim 6, The requirements for the translation process instructed by the translation instruction unit include requirements relating to at least one of the translation method for each token and the style or grammar of the translated text. Information processing system.
In the information processing system described in claim 1, The system further includes a summarization unit that generates a summary of a text to a predetermined length. The summary generation unit generates a summary of the original text and also generates a summary of the translated text. The display unit presents summaries of the original text and the translated text to the user terminal in a manner that allows for comparison with the original text and the translated text. Information processing system.
In the information processing system according to any one of claims 1 to 9, The system further includes an artificial intelligence selection unit that receives a selection from the user terminal for one of the generative artificial intelligences to perform the translation process from among a plurality of such generative artificial intelligences. Information processing system.
In the information processing system according to any one of claims 1 to 9, The system further includes an artificial intelligence selection unit that selects one of the generative artificial intelligences for performing the translation process from a plurality of generative artificial intelligences based on at least one of the language classification of the source text or the language classification of the translated text. Information processing system.
An information processing method that causes a generative artificial intelligence capable of generating tasks based on input received from a user terminal to perform translation, Computers The system receives the source text, which is text data to be input into the aforementioned generative artificial intelligence, from the user terminal. The language classification of the translated text, which is the text data obtained by translating the aforementioned original text, is set to a specified language. The specified format, which is the format of the translated text, is received from the user terminal as text data. By inputting a prompt to the generative artificial intelligence that includes an instruction to perform a translation process to translate the aforementioned source text into the specified language in accordance with the specified format, the generative artificial intelligence is made to generate the translated text. The translated text is presented to the user terminal. Information processing methods.
A program that causes a computer to execute an information processing method in which it has a generative artificial intelligence capable of generating tasks based on input received from a user terminal perform translation, A source text reception step in which the source text, which is text data to be input into the aforementioned generative artificial intelligence, is received from the user terminal, A language setting step to set a specified language, which is the language classification of the translated text, which is the text data obtained by translating the aforementioned original text, A format acceptance step in which the specified format, which is the format of the translated text, is received from the user terminal as text data, A translation instruction step involves inputting a prompt to the generative artificial intelligence that includes an instruction to perform a translation process to translate the aforementioned source text into the specified language in accordance with the specified format, thereby causing the generative artificial intelligence to generate the translated text; A presentation step of presenting the translated text to the user terminal, To have a computer execute an information processing method that includes the following: program.

Description

This disclosure relates to information processing systems, information processing methods, and programs. Generative AI (Artificial Intelligence) services, such as Large Language Models (LLMs), which generate responses to various user requests, are becoming widespread. Related to this, translation technologies utilizing generative AI and other related technologies are also advancing. For example, Patent Document 1 discloses an automatic natural language translation system comprising a memory device storing multiple grammatical rules and a translation engine that controls translation by applying grammatical control rules to at least some of them. Furthermore, the web service described in Non-Patent Document 1 is a translation service employing neural machine translation technology, providing contextually responsive translations using a deep learning model trained on a large-scale language dataset. Japanese Patent Publication No. 2002-197084 DeepL, September 29, 2020, Internet <URL: https://www. deeppl. com/en/translator> This is a block diagram of the information processing system according to the first embodiment.This is a block diagram illustrating the hardware configuration of a computer.This is a flowchart of the information processing method according to the first embodiment.This diagram shows the processing in the translation instruction unit according to the first embodiment.This is the first figure, which shows an image to be presented to users of the information processing system.This is the second figure, which shows an image to be presented to users of the information processing system.This is a block diagram of the information processing system according to the second embodiment.This is a block diagram of the information processing device according to the second embodiment.This is a flowchart of the information processing method according to the second embodiment.This figure shows the processing in the translation instruction unit according to the second embodiment.This is the fourth figure, showing an image to be presented to users of the information processing system.This is the fifth figure, showing an image to be presented to users of the information processing system.This is the sixth figure, showing an image to be presented to users of the information processing system.This diagram shows the processing in the translation instruction unit according to the third embodiment.This is Figure 7, which shows an image to be presented to users of the information processing system.This figure shows a translation sample according to the third embodiment.This is a block diagram of the information processing device according to the fourth embodiment.This is a flowchart of the information processing method according to the fourth embodiment.This figure shows the processing of the translation instruction unit and the summary generation unit according to the fourth embodiment.This is Figure 8, which shows an image to be presented to users of the information processing system. The present invention will be described below through embodiments, but the claims are not limited to these embodiments. Furthermore, not all configurations described in the embodiments are necessarily essential for solving the problem. For clarity, the following descriptions and drawings have been omitted and simplified as appropriate. In each drawing, the same elements are denoted by the same reference numerals, and redundant explanations have been omitted where necessary. <First Embodiment> (Information processing system 10) The information processing system 10 according to this embodiment will be described with reference to Figure 1. Figure 1 is a block diagram of the information processing system 10 according to the first embodiment. The information processing system 10 generates a translated text by translating a text input by the user (hereinafter referred to as the original text) into a predetermined language different from the original text and presents it to the user. The information processing system 10 is connected to the user terminal 300 via a network N1 so as to be able to communicate. The information processing system 10 causes a generative artificial intelligence capable of generating tasks based on input received from the user terminal 300 to perform the translation. In the following description, generative artificial intelligence will also be referred to as generative AI or generative model. A generative model is an algorithm designed to generate various types of content, such as text, images, audio, or program code, in response to a given request. The generative model in this disclosure has at least the ability to generate text; that is, the generative model in this disclosure includes a language model. The architecture of the language model may include a neural network using deep learning, or it may include a Generative Pre-trained Transformer (GPT). In this case, the above request may include data containing image d