Information processing systems, information processing methods, and programs

Abstract

To provide an information processing system, information processing method, and program that 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.

Description

Technical Field

[0001] The present disclosure relates to an information processing system, an information processing method, and a program.

Background Art

[0002] Generative AI (Artificial Intelligence) services using large language models (LLMs (Large Language Models)), which are generative artificial intelligences that generate responses according to various requests of users, are becoming widespread. In addition, in relation to this, translation technologies using technologies such as generative AI are evolving.

[0003] For example, Patent Document 1 discloses an automatic natural language translation system including a storage device storing a plurality of grammar rules and a translation engine that controls translation by applying grammar control rules to at least a part.

[0004] Also, the web service described in Non-Patent Document 1 is a translation service adopting neural machine translation technology, and provides a context-aware translation using a deep learning model trained with a large language dataset.

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Non-Patent Documents

[0006]

Non-Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0007] )]] However, the aforementioned technologies have challenges when it comes to customizing translation results.

[0008] In view of the above issues, this disclosure aims to provide an information processing system, etc., that can suitably generate translated text in response to user requests. [Means for solving the problem]

[0009] The information processing system relating to this disclosure causes a generative artificial intelligence capable of generating tasks based on input received from a user terminal to perform translation. The information processing system comprises a source text receiving unit, a language setting unit, a format receiving unit, a translation instruction unit, and a presentation unit. The source text receiving unit receives the source text, which is text data to be input to the generative artificial intelligence, from the user terminal. The language setting unit sets the designated language, which is the language classification of the translated text, which is text data obtained by translating the source text. The format receiving unit receives the designated format, which is the format of the translated text, from the user terminal as text data. The translation instruction unit 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 source text into the designated language according to the designated format. The presentation unit presents the translated text to the user terminal.

[0010] The information processing method relating to this disclosure causes a generative artificial intelligence capable of generating tasks based on input received from a user terminal to perform translation. The computer receives a source text, which is text data to be input to the generative artificial intelligence, from the user terminal. The computer sets a designated language, which is the language classification of the translated text, which is text data obtained by translating the source text. The computer receives a designated format, which is the format of the translated text, from the user terminal as text data. The computer 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 source text into the designated language according to the designated format. The computer presents the translated text to the user terminal.

[0011] The program relating to this disclosure is a program that causes a computer to execute 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. The program has a source text reception step, a language setting step, a format reception step, a translation instruction step, and a presentation step. The source text reception step receives the source text, which is text data to be input into the generative artificial intelligence, from the user terminal. The language setting step 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 reception step receives the specified format, which is the format of the translated text, from the user terminal as text data. The translation instruction step 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 that translates the source text into the specified language according to the specified format. The presentation step presents the translated text to the user terminal. [Effects of the Invention]

[0012] According to this disclosure, it is possible to provide an information processing system, information processing method, and program that suitably generate translated text in response to user requests. [Brief explanation of the drawing]

[0013] [Figure 1] This is a block diagram of the information processing system according to the first embodiment. [Figure 2] This is a block diagram illustrating the hardware configuration of a computer. [Figure 3] This is a flowchart of the information processing method according to the first embodiment. [Figure 4] This diagram shows the processing in the translation instruction unit according to the first embodiment. [Figure 5] This is the first figure, which shows an image to be presented to users of the information processing system. [Figure 6] This is the second figure, which shows an image to be presented to users of the information processing system. [Figure 7] This is a block diagram of the information processing system according to the second embodiment. [Figure 8] It is a block diagram of an information processing apparatus according to the second embodiment. [Figure 9] It is a flowchart of an information processing method according to the second embodiment. [Figure 10] It is a diagram showing the processing in the translation instruction unit according to the second embodiment. [Figure 11] It is a fourth diagram showing an image presented to a user who uses an information processing system. [Figure 12] It is a fifth diagram showing an image presented to a user who uses an information processing system. [Figure 13] It is a sixth diagram showing an image presented to a user who uses an information processing system. [Figure 14] It is a diagram showing the processing in the translation instruction unit according to the third embodiment. [Figure 15] It is a seventh diagram showing an image presented to a user who uses an information processing system. [Figure 16] It is a diagram showing a translation sample according to the third embodiment. [Figure 17] It is a block diagram of an information processing apparatus according to the fourth embodiment. [Figure 18] It is a flowchart of an information processing method according to the fourth embodiment. [Figure 19] It is a diagram showing the processing of the translation instruction unit and the summary generation unit according to the fourth embodiment. [Figure 20] It is an eighth diagram showing an image presented to a user who uses an information processing system.

Embodiments for Carrying Out the Invention

[0014] Hereinafter, the present invention will be described through embodiments of the invention, but the invention according to the claims is not limited to the following embodiments. Also, not all of the configurations described in the embodiments are essential as means for solving the problems. For clarity of explanation, the following description and drawings have been appropriately omitted and simplified. In each drawing, the same elements are denoted by the same reference numerals, and duplicate explanations are omitted as necessary.

[0015] <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 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.

[0016] 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 have a neural network using deep learning, or it may include a Generative Pre-trained Transformer (GPT).

[0017] In this case, the above request may include data containing image data, audio data, or other information in addition to text data. Other data may include, for example, signals generated by a given sensor. In this case, the generative model is a multimodal artificial intelligence. In this case, the artificial intelligence is a multimodal language model, which may be referred to as, for example, an MMLLM (Multi-Moal Large Language Model) or a multimodal model. The multimodal language model may generate a response using text data, or it may generate a response including image data and audio data.

[0018] The information processing system 10 mainly consists of an information processing device 100 and a server 200. The information processing device 100 and the server 200 are connected via a network N1. The information processing device 100 receives the original text data from the user terminal 300 via the network N1 and supplies the received original text data to the server 200. The information processing device 100 also instructs the server 200 to translate the original text into a predetermined language, along with the original text data. Furthermore, if the information processing device 100 receives the translated text from the server 200, it supplies the translated text to the user terminal 300.

[0019] The server 200 primarily consists of a first generation model 210. The first generation model 210 generates a translated text according to the source text data and translation instructions received from the information processing device 100. The first generation model 210 supplies the generated translated text to the information processing device 100.

[0020] The user terminal 300 is a computer used by the user. This includes personal computers, tablet devices, smartphones, wearable devices, or mobile phones. The user terminal 300 receives user input to generate original text data and supplies the generated text data to the information processing system 10. The user terminal 300 also receives the translated text from the information processing system 10 and presents it to the user.

[0021] (Information processing device 100) The information processing device 100 will now be described. The information processing system 10 mainly consists of a source text receiving unit 111, a language setting unit 112, a format receiving unit 113, a translation instruction unit 114, and a presentation unit 115.

[0022] The source text receiving unit 111 receives source text, which is text data to be input into the generative model (generative artificial intelligence), from the user terminal 300. The source text receiving unit 111 may also estimate the language classification of the received source text. Here, language classification refers to the classification of languages ​​used in each country or region. Specifically, for example, language classifications include Japanese, English, Chinese, or French. Language classifications may also be further subdivided, for example, English may be defined as British English, American English, Australian English, etc.

[0023] The language setting unit 112 sets the designated language, which is the language classification of the translated text, which is the text data obtained by translating the source text. The designated language may also be set via the user terminal 300 by the user. Alternatively, a predetermined language may be set as the initial setting. The language setting unit 112 may also be set automatically according to the language of the source text received by the source text receiving unit 111.

[0024] The format reception unit 113 receives the specified format, which is the format of the translated text, from the user terminal as text data. The specified format is the format of the translated text specified by the user. The specified format includes the style, grammar, and expression of the translated text. More specifically, for example, the specified format may include formal language, colloquial language, or polite language. The specified format may include grammar similar to that of a particular character, or grammar that uses specific expressions at the end of sentences. Furthermore, the specified format may include the frequent use of loanwords, the use of a particular dialect, or the use of grammar from a particular era.

[0025] The translation instruction unit 114 causes the generation model to generate a translated text by inputting a prompt to the generation model that includes an instruction to perform a translation process that translates the source text into a specified language according to a specified format. More specifically, the translation instruction unit 114 generates a system prompt to instruct the source text to be translated into a specified language according to a specified format, and inputs the generated system prompt to the generation model. By inputting the system prompt, the translation instruction unit 114 causes the generation model to generate a translated text and supply it to the presentation unit 115.

[0026] The presentation unit 115 presents the translated text to the user terminal. More specifically, the presentation unit 115 presents the translated text to the user terminal 300 in a manner that allows for comparison between the original text and the translated text. More specifically, for example, the presentation unit 115 generates a presentation image in which the original text and the translated text are arranged horizontally, and supplies this presentation image to the user terminal 300. In addition, the original text and the translated text may be arranged vertically in the presentation image generated by the presentation unit 115.

[0027] The information processing device 100 and the server 200 have been described above. In the information processing system 10, the first generative model 210 may be a language model called a Small Language Model (SLM). An SLM has several million to several billion parameters. On the other hand, an LLM has several billion to several trillion parameters.

[0028] (Example hardware configuration) Figure 2 is a block diagram illustrating the hardware configuration of a computer. The information processing device 100 described above may have the configuration shown in Figure 2. The computer 1000 has a bus 1010, a processor 1020, a memory 1030, a storage device 1040, an input / output interface 1050, and a network interface 1060.

[0029] Bus 1010 is a data transmission path for the processor 1020, memory 1030, storage device 1040, input / output interface 1050, and network interface 1060 to send and receive data to and from each other. However, the method of connecting the processor 1020 and the other components to each other is not limited to bus connection.

[0030] Processor 1020 is a circuit that includes arithmetic units such as a CPU (Central Processing Unit) and a GPU (Graphics Processing Unit).

[0031] Memory 1030 is a main memory device implemented using RAM (Random Access Memory), etc.

[0032] The storage device 1040 is an auxiliary storage device such as an HDD (Hard Disk Drive), SSD (Solid State Drive), flash memory, or ROM (Read Only Memory). The storage device 1040 stores a program for realizing the functions of this disclosure.

[0033] The processor 1020 reads this program into memory 1030 and executes it. This causes the processor 1020 to perform the function corresponding to this program. In other words, the program stored in memory 1030 causes the computer 1000 to perform the function of this disclosure.

[0034] The input / output interface 1050 connects the computer 1000 to a predetermined input / output device. The input / output device is, for example, an input device such as a keyboard, an output device such as a display, or an input / output device in which a touch panel is superimposed on a display.

[0035] The network interface 1060 is an interface for connecting the computer 1000 to a predetermined communication network.

[0036] The computer 1000 has been described above, but in addition to the above configuration, the computer 1000 may have an information input device for the user to input various information into the computer 1000 through operation. The information input device may be, for example, a keyboard, mouse, or touch panel. The computer 1000 may also have a display, speaker, vibration motor, or LED (light-emitting diode) for showing various information to the user.

[0037] Next, with reference to Figure 3, the processes performed by the information processing device 100 will be described. Figure 3 is a flowchart of the information processing method according to the first embodiment. The information processing method shown in Figure 3 causes a generative artificial intelligence capable of generating tasks based on input received from the user terminal 300 to perform translation. The flowchart shown in Figure 3 starts, for example, when the information processing device 100 receives the original text data from the user terminal 300.

[0038] In step S11, the source text receiving unit 111 receives the source text, which is text data to be input into the generative artificial intelligence, from the user terminal 300. At this time, the user inputs the source text on the user terminal 300. The user terminal 300 transmits the input source text to the information processing device 100. The source text receiving unit 111 supplies the received source text data to the translation instruction unit 114. The source text receiving unit 111 may also receive a file containing text data previously created by the user from the user terminal 300.

[0039] The source text receiving unit 111 may also automatically detect the received source text and identify the language classification of the detected source text. Furthermore, if the source text receiving unit 111 identifies the language classification, it may have a function to display the language classification of the source text to the user terminal 300. This allows the information processing device 100 to allow the user to recognize what language the source text entered by the user has been identified as.

[0040] In step S12, the language setting unit 112 sets the designated language, which is the language classification of the translated text, which is the text data obtained by translating the source text. The language setting unit 112 supplies information about the set designated language to the translation instruction unit 114. The language setting unit 112 may set the designated language automatically. The language setting unit 112 may receive information about the setting of the designated language from the user terminal 300.

[0041] In step S13, the format receiving unit 113 receives the specified format, which is the format of the translated text, from the user terminal 300 as text data. At this time, the user inputs the source text and also inputs instructions regarding the specified format in text on the user terminal 300.

[0042] In step S14, the translation instruction unit 114 inputs a prompt to the generation model that includes an instruction to perform a translation process to translate the source text into a specified language according to a specified format, thereby causing the generation model to generate a translated text. Once the translation instruction unit 114 has caused the generation model to generate a translated text, it supplies the generated translated text to the presentation unit 115.

[0043] In step S15, the presentation unit 115 presents the translated text received from the translation instruction unit 114 to the user terminal 300. At this time, the presentation unit 115 generates a presentation image in which the translated text is displayed on the display of the user terminal 300, and transmits the data of the presentation image including the translated text to the user terminal 300. As a result, the information processing device 100 presents the translated text to the user. Preferably, the presentation image generated by the presentation unit 115 is in a manner that allows the original text and the translated text to be compared side by side.

[0044] The processes executed by the information processing device 100 have been described above, but the processes executed by the information processing device 100 are not limited to those described above. For example, steps S11, S12, and S13 do not have to be in the order described above. For example, step S13 may come before step S11.

[0045] Next, the processing performed by the translation instruction unit 114 will be described with reference to Figure 4. Figure 4 is a diagram showing the processing in the translation instruction unit 114 according to the first embodiment. When the translation instruction unit 114 receives the source text data and the specified language setting, it generates a prompt for the first generation model 210 to generate the translated text. When the translation instruction unit 114 receives text data in a specified format, it generates a prompt for the first generation model 210 to reflect the specified format in the translated text. The translation instruction unit 114 inputs these generated prompts to the first generation model 210. In this case, for example, the translation instruction unit 114 first inputs a prompt for generating the translated text to the first generation model 210. After the first generation model 210 has generated the translated text, the translation instruction unit 114 inputs a prompt for indicating the specified format to the first generation model 210. The first generation model 210 can sequentially supply the generated translated text to the presentation unit 115.

[0046] A prompt includes elements to control the operation of the first generation model 210 and to guide its response. A prompt that the translation instruction unit 114 issues to the first generation model 210 to generate a translated text mainly includes a translation generation command, source text, and specified language. A prompt containing these elements might include content such as, "Translate the following source text into the specified language according to the specified format. The source text is "...", and the specified language is "...language." A prompt that reflects the specified format in the translated text mainly includes text data to indicate the specified format. In this case, a prompt might include content such as, "Please format the generated translated text in [specified format]."

[0047] As the translation instruction unit 114 performs the above-described process, the selected generation model generates a translated text by translating the source text into the specified language. Furthermore, the selected generation model reflects the specified format in the translated text according to prompts indicating the specified format. Finally, the selected generation model supplies the translated text, which reflects the instructions received from the translation instruction unit 114, to the presentation unit 115.

[0048] In addition to the above, the prompt may include the following additional elements. That is, the prompt may include explanations to supplement the elements described above. The prompt may define the format of the data to be supplied to the first generation model 210, or it may define the format of the data output by the first generation model 210. Here, the data format is text, images, or a combination thereof. Alternatively, the prompt may include information relating to the specific settings of the first generation model 210. Such additional elements are not set by the user, but are pre-set in the information processing device 100.

[0049] Next, the information that the information processing system 10 presents to the user will be described with reference to Figure 5. Figure 5 is the first diagram showing an image presented to a user using the information processing system 10. Figure 5 shows the presented image 400. The presented image 400 is an image generated by the presentation unit 115. The presentation unit 115 supplies the generated presented image 400 to the user terminal 300. The user views the presented image 400 displayed on the display of the user terminal 300. The presented image 400 mainly consists of a source text display field 410, a translated text display field 420, and a specified format input field 430.

[0050] The source text display field 410 displays the source text entered by the user. Above the source text display area, a pull-down menu 411 is located along with a display of the language classification. The pull-down menu 411 is set to allow the user to change the language classification of the source text. When the user selects from the pull-down menu 411, the presented image 400 displays selectable language classifications that can be translated.

[0051] The translated text display field 420 displays the translated text generated by the first generation model 210 by the translation instruction unit 114. Above the text display area of ​​the translated text, there is a display of the language classification of the translated text and a pull-down menu 421. When the user selects from the pull-down menu 421, the presented image 400 displays selectable language classifications that can be translated. The user can determine the language to be translated into by selecting a language classification from the pull-down menu 421.

[0052] The specified format input field 430 displays text to indicate the specified format entered by the user. The specified format input field 430 also includes an apply button 431. When the apply button 431 is selected, the user terminal 300 sends the text data in the specified format entered by the user to the information processing system 10. In other words, when the apply button 431 is selected, the information processing system 10 generates a prompt including the specified format and causes the first generation model 210 to generate a translated text in accordance with the specified format. To put it another way, when the apply button 431 is selected, the translated text displayed in the translated text display field 420 will reflect the content of the specified format.

[0053] Let's explain a specific example of the presentation image 400 shown in Figure 5. The source text displayed in the source text display field 410 is in English. The source text is displayed as "A typhoon...their safety." Also, "English (Automatic Detection)" is displayed at the top of the source text display field 410. This indicates that the source text receiving unit 111 of the information processing system 10 has detected the source text and identified that the detected source text is in English.

[0054] The translated text displayed in the translated text display field 420 is in Japanese. The translated text is displayed as, "We strongly request that you take precautions against typhoons." The translated text displayed in the translated text display field 420 is in the polite "desu / masu" style. The specified format input field 430 displays "Please use the desu / masu style." In other words, the user has instructed that the translated text be in the "desu / masu" style. Therefore, as described above, the translated text in the translated text display field 420 is displayed in the "desu / masu" style according to the specified format.

[0055] In the presented image 400, the source text display field 410 and the translated text display field 420 are arranged side by side. That is, the presentation unit 115 generates a presented image 400 in which the source text display field 410 and the translated text display field 420 are arranged side by side. As a result, the information processing system 10 presents a presented image 400 that allows the user to easily compare the source text and the translated text.

[0056] Next, we will further explain the information that the information processing system 10 presents to the user, referring to Figure 6. Figure 6 is a second diagram showing the images presented to the user using the information processing system 10. The content of the specified format in Figure 6 differs from that in Figure 5. Therefore, the grammar of the translated text differs from that in Figure 5.

[0057] More specifically, in Figure 6, the user enters "Please use colloquial language" in the specified format input field 430. Therefore, the translated text displayed in the translated text display field 420 is displayed in colloquial language: "It looks like the typhoon will make landfall tomorrow... I've told them to take good care of themselves."

[0058] The information processing system 10 has been described above. Each component of the information processing device 100 may be implemented with dedicated hardware. In addition, some or all of each component may be implemented by general-purpose or dedicated circuits, processors, etc., or combinations thereof. These may be implemented by a single chip or by multiple chips connected via a bus. Some or all of each component may be implemented by a combination of the above-mentioned circuits, etc., and programs. In addition, a CPU (Central Processing Unit), GPU (Graphics Processing Unit), FPGA (field-programmable gate array), etc. can be used as the processor. Furthermore, at least some of the functions of this embodiment may be provided in the form of IaaS (Infrastructure as a Service), PaaS (Platform as a Service), or SaaS (Software as a Service).

[0059] As described above, the information processing system 10 can specify the format of the translated text. Therefore, according to this embodiment, it is possible to provide an information processing system, information processing method, and program that suitably generate translated text in response to a user's request.

[0060] <Second Embodiment> Next, a second embodiment will be described. Figure 7 is a block diagram of the information processing system 10 according to the second embodiment. The server 200 according to the second embodiment differs from the first embodiment in that it has multiple generation models. The information processing device 100 selects one of the two generation models that the server 200 has and instructs the selected generation model to translate the source text. The server 200 according to the second embodiment mainly consists of a first generation model 210 and a second generation model 220. The first generation model 210 and the second generation model 220 are different generation models.

[0061] The first generative model 210 and the second generative model 220 may be different versions of each other, or they may be models developed by different people. The first generative model 210 and the second generative model 220 may, for example, have different numbers of parameters. Also, one of the first generative model 210 and the second generative model 220 may be a statistical language model and the other a neural language model. The first generative model 210 and the second generative model 220 may be models that have different learning objectives. Differences in learning objectives may include, for example, learning translations for a specific classification of languages. More specifically, for example, a difference in learning objectives might be that the first generative model 210 is better at translating English than the second generative model 220, and the second generative model 220 is better at translating Chinese than the first generative model 210.

[0062] Next, the information processing device 100 according to the second embodiment will be described with reference to Figure 8. Figure 8 is a block diagram of the information processing device 100 according to the second embodiment. The information processing device 100 according to this embodiment differs from the information processing device 100 according to the first embodiment in that it further includes a conversation mode receiving unit 101, a conversation function unit 102, a translation mode receiving unit 110, a glossary selection unit 116, a generation model selection unit 117, and a storage unit 120.

[0063] The conversation mode reception unit 101 receives a request from the user terminal 300 to enter conversation mode, in which a prompt in the form of arbitrary text data is input to the generation model. Conversation mode is a state in which the system receives arbitrary requests from the user terminal 300 and generates responses to the received requests. Arbitrary requests include, for example, the generation of a summary of a document, the generation of a document based on predetermined conditions, the generation of an image, and the generation of program code. When the conversation mode reception unit 101 receives the selection of conversation mode, the information processing device 100 activates the conversation function unit 102. Conversation mode is, for example, a mode in which responses to requests are sequentially generated in a chat format.

[0064] The conversation function unit 102 performs the functions of the conversation mode described above. That is, when the conversation function unit 102 receives a request from the user terminal 300, it inputs the received request to the first generation model 210 or the second generation model 220. The user can select which of the multiple generation models to select. In this case, the conversation function unit 102 receives information from the user terminal 300 regarding the selection of a generation model. The conversation function unit 102 inputs the request received from the user terminal 300 to the generation model related to the selection and receives a response from the generation model. The conversation function unit 102 presents the response received from the generation model to the user terminal 300. The conversation function unit 102 may also have a RAG (Retrieval-Augmented Generation) function.

[0065] The translation mode reception unit 110 receives from the user terminal 300 that it is in translation mode, which involves inputting a prompt related to translation processing into the generation model. Upon receiving confirmation that translation mode has been selected, the information processing device 100 performs the function of translating the source text received from the user terminal 300. In other words, in this embodiment, the information processing device 100 performs the functions of conversation mode when conversation mode is selected, and performs the functions of translation mode when translation mode is selected.

[0066] The glossary selection unit 116 receives a request from the user terminal 300 to select at least one glossary from the storage unit 120, which stores glossaries containing translations for specific words or phrases. The glossary selection unit 116 supplies information about the selected glossary to the translation instruction unit 114. In this case, the translation instruction unit 114 inputs a prompt to the generation model that includes an instruction to perform translation processing by referring to the selected glossary. As a result, the information processing system 10 can generate a translated text that appropriately applies the glossary selected by the user when performing translation processing.

[0067] Furthermore, the translation instruction unit 114 may also have a function to input a prompt to the generation model that instructs it to decide whether or not to apply the selected glossary for each token, depending on the context of the source text. This allows the information processing system 10 to suppress the uniformity of the translated texts generated by the generation model and prevent the inclusion of inappropriate translations. In other words, the information processing system 10 can generate suitable translated texts that flexibly apply the information from the glossary.

[0068] The generative model selection unit 117 receives a selection request from the user terminal 300 for one generative model to perform the translation process from among multiple generative models. This allows the information processing system 10 to provide a translated text using a generative model that suits the user's preferences. The generative model selection unit 117 is also referred to as the generative artificial intelligence selection unit.

[0069] The generation model selection unit 117 may select one generation model from a plurality of generation models for performing the translation process, based on at least one of the language classifications of the source text or the translation text. In this case, the information processing system 10 selects a suitable generation model according to the language classification of the language to be translated.

[0070] The memory unit 120 selectively stores multiple glossaries containing translations for specific words or phrases. By storing multiple selectable glossaries, the information processing system 10 can reduce the burden on the user of having to rewrite the glossary each time a translation is performed.

[0071] Next, the processing performed by the information processing device 100 according to this embodiment will be described. Figure 9 is a flowchart of the information processing method according to the second embodiment. The flowchart shown in Figure 9 differs from the flowchart shown in Figure 3 in that it has steps S21 to S23 between steps S13 and S14. Also, the flowchart shown in Figure 9 is started when the user selects a translation mode.

[0072] After step S13, in step S21, the glossary selection unit 116 determines whether or not a glossary selection has been made. If the glossary selection unit 116 determines that a glossary selection has been made (step S21: YES), the information processing device 100 proceeds to step S22. If the glossary selection unit 116 does not determine that a glossary selection has been made (step S21: NO), the information processing device 100 proceeds to step S23.

[0073] In step S22, the glossary selection unit 116 reads the selected glossary from the storage unit 120. The glossary selection unit 116 supplies the information of the read glossary to the translation instruction unit 114.

[0074] In step S23, the generation model selection unit 117 selects a generation model. Here, the generation model selection unit 117 may accept a generation model selection by user operation, or it may select a generation model according to a pre-set algorithm. A pre-set algorithm is, for example, the selection of a generation model according to the language classification of the source text and the specified language information of the translation text. The generation model selection unit 117 supplies information about the selected generation model to the translation instruction unit 114.

[0075] In step S14, the translation instruction unit 114 instructs the selected generative model to generate a translated text by inputting an instruction to perform a translation process that translates the source text into a specified language according to a specified format, and a prompt that includes a glossary to be referenced. Once the selected generative model has generated the translated text, the translation instruction unit 114 receives the generated translated text and supplies the received translated text to the presentation unit 115.

[0076] Next, the processing performed by the translation instruction unit 114 according to this embodiment will be described with reference to Figure 10. Figure 10 is a diagram showing the processing in the translation instruction unit 114 according to the second embodiment. When the translation instruction unit 114 receives the source text data and the setting of the specified language, it generates a prompt for the selected generation model to generate a translated text. When the translation instruction unit 114 receives text data in a specified format, it generates a prompt for the selected generation model to reflect the specified format in the translated text. Furthermore, when the translation instruction unit 114 receives information regarding the selection of a glossary, it reads the selected glossary from the glossary 121 stored in the storage unit 120 and supplies the read glossary to the selected generation model. Next, the translation instruction unit 114 supplies the read glossary to the selected generation model. The translation instruction unit 114 may also be instructed to determine whether or not to apply the selected glossary on a token-by-to-token basis according to the context of the source text. Furthermore, the translation instruction unit 114 inputs a prompt to the selected generation model to indicate the specified format. The selected generation model can generate a new translated text each time it receives a prompt or glossary. Furthermore, the generation model can sequentially supply the generated translated texts to the presentation unit 115.

[0077] The prompts provided by the translation instruction unit 114 in this embodiment to the generation model for generating a translated text mainly include a translation generation command, source text, and a specified language. A prompt including these elements may include, for example, content such as, "Translate the following source text into the specified language. The source text is 'A typhoon is...', and the specified language is 'Japanese'." Furthermore, when the translation instruction unit 114 supplies a glossary to the generation model, it supplies the glossary information to the generation model in a manner that allows the generation model to reflect the information from the glossary in the translated text. Prompts for reflecting a specified format in the translated text may include, for example, instructions in text data such as, "Please make the generated translated text in a polite, formal style."

[0078] As the translation instruction unit 114 performs the above-described process, the selected generation model generates a translated text by translating the source text into the specified language. Next, the selected generation model reflects the information from the selected glossary into the translated text according to the information from the glossary. Furthermore, the selected generation model reflects the specified format into the translated text according to prompts indicating the specified format. Finally, the selected generation model supplies the translated text, which reflects the instructions received from the translation instruction unit 114, to the presentation unit 115.

[0079] In addition to the above, the prompt may also include instructions regarding the application of the glossary, such as applying the glossary information on a contextual basis rather than mechanically applying it to every word or phrase.

[0080] Next, with reference to Figure 11, the information presented by the presentation unit 115 to the user of the information processing system 10 according to this embodiment will be described. Figure 11 is the fourth figure showing an image presented to the user of the information processing device 100.

[0081] The presentation image 400 shown in Figure 11 differs from the presentation image 400 according to the first embodiment in that it has a menu display 401. The menu display 401 includes the user-selectable options "New Conversation," "Translate," "History," and "Account."

[0082] When the user selects "New Conversation," the information processing system 10 enters conversation mode. In other words, when the user selects "New Conversation," the conversation mode reception unit 101 of the information processing device 100 receives confirmation that conversation mode has been selected.

[0083] When the user selects "Translate," the information processing system 10 enters translation mode. In other words, when the user selects "Translate," the translation mode receiving unit 110 of the information processing device 100 receives confirmation that translation mode has been selected.

[0084] "History" is a function that displays the conversation history. When the user selects "History," the conversation and translation history will be displayed below the "History" display. When the user selects "Account," the user's account information will be displayed.

[0085] Furthermore, the presentation image 400 shown in Figure 11 differs from the presentation image 400 according to the first embodiment in that it has a glossary display field 440. The glossary display field 440 includes a pull-down menu. The user selects from the pull-down menu to select a glossary.

[0086] Figure 12 is a fifth figure showing an image to be presented to a user of the information processing device 100. The presented image 400 shown in Figure 12 shows the situation after the user has selected the glossary display field 440 in the presented image 400 shown in Figure 11. The presented image 400 in Figure 12 includes a glossary selection field 441 below the glossary display field 440.

[0087] The glossary selection field 441 includes the options "Glossary A," "Glossary B," and "Create New." When the user selects "Glossary A," "Glossary A" is displayed in the glossary display field 440. An ellipsis is displayed to the right of "Glossary A" in the glossary selection field 441. If the user selects the ellipsis, buttons are displayed to edit or delete "Glossary A."

[0088] When the user selects "Glossary B," "Glossary B" is displayed in the glossary display field 440. An ellipsis (3-dot) is also displayed to the right of "Glossary B" in the glossary selection field 441, similar to the case for Glossary A. If the user selects the ellipsis, buttons for editing or deleting "Glossary B" are displayed. If the user selects "Create New," a screen for creating a new glossary is displayed.

[0089] The presentation image 400 shown in Figure 12 displays "Glossary A" in the glossary display field 440. In other words, the presentation image 400 in Figure 12 shows the state in which the user has selected Glossary A. The glossary display field 440 also displays a switch that can be toggled on or off. By toggling this switch, the user can choose whether or not to apply the glossary to the translation.

[0090] Next, we will explain how to create and edit a glossary, referring to Figure 13. Figure 13 is the sixth figure showing an image to be presented to a user using the information processing device 100. The presented image 400 shown in Figure 13 includes a glossary editing field 442. The glossary editing field 442 includes a name input field 443, a translation information input field 444, a registration button 445, a translation information display field 446, and an import button 447.

[0091] The name input field 443 accepts the name of the glossary. The translation information input field 444 accepts the translation information. "Translation information" refers to information that includes a word or phrase before translation and the corresponding word or phrase after translation. The registration button 445 accepts the registration of the entered glossary name and translation information when the user selects or presses the registration button 445. The registered information is stored in the storage unit 120.

[0092] The bilingual information display field 446 displays registered bilingual information. The bilingual information display field 446 is configured to allow deletion and modification of registered bilingual information. Furthermore, the bilingual information display field 446 can also register bilingual information when the combination of source text and translated text is reversed. With these settings, the information processing system 10 can handle translations when the combination of source text and translated text is reversed by the user selecting a single glossary.

[0093] The import button 447 allows you to import multiple glossary files created by the user in a predetermined file format.

[0094] The second embodiment has been described above. In this embodiment, the information processing system 10 displays a translation-dedicated interface on the user terminal 300 by setting a generation model having conversation mode functionality to translation mode. The information processing system 10 also stores selectable glossaries in the storage unit 120, and by the user selecting one glossary, it can suitably handle translation in a specific field, for example. Furthermore, the information processing system 10 can suitably set the style and expression of the translated text by accepting a specified format as text data. Thus, according to this embodiment, it is possible to provide an information processing system, information processing method, and program that suitably generate translated text in response to user requests.

[0095] <Third Embodiment> Next, a third embodiment will be described. The third embodiment differs from the embodiments described above in that it stores translation samples and uses these translation samples in the generative model.

[0096] Figure 14 shows the processing in the translation instruction unit 114 according to the third embodiment. As shown in Figure 14, the storage unit 120 stores a translation sample 122 which includes a sample source text and a sample translated text.

[0097] Translation sample 122 is text data consisting of a pair of source text and a translated text. Translation samples differ from glossaries in that they are sentences, not just words and phrases. Translation samples are used to instruct a generative model that generates the translated text on the translation requirements. The translation instruction unit 114 estimates the translation requirements by referring to the translation samples. More specifically, for example, the translation instruction unit 114 causes a predetermined generative model to estimate the translation requirements by inputting the translation samples. The predetermined generative model described above is a generative model configured to estimate translation requirements from translation samples. The reference to translations in the translation samples includes translations of words and phrases. Furthermore, the reference to translations in the translation samples includes translations of style, grammar, and expression. By utilizing translation samples, the information processing system 10 can instruct the generative model on the translation requirements without receiving detailed instructions on the translation requirements from the user.

[0098] The translation instruction unit 114 according to this embodiment receives the source text data and the setting of the specified language. From the received information, the translation instruction unit 114 generates prompts for the selected generative model to generate the translated text.

[0099] The translation instruction unit 114 reads the translation sample 122 stored in the memory unit 120 and causes the predetermined generation model described above to estimate the translation requirements from the read translation sample. As a result, the translation instruction unit 114 generates a prompt that indicates the translation requirements from the translation sample. The translation instruction unit 114 inputs the generated prompt into the first generation model 210. As shown in Figure 14, at this time the translation instruction unit 114 inputs both the prompt to generate the translated sentence and the prompt indicating the requirements based on the translation sample into the generation model.

[0100] When the translation instruction unit 114 receives information regarding the selection of a glossary, it reads the selected glossary from the glossary 121 stored in the memory unit 120 and supplies the read glossary to the selected generative model. The translation instruction unit 114 may also instruct the system to determine whether or not to apply the selected glossary on a token-by-to-token basis, depending on the context of the source text.

[0101] The translation instruction unit 114 inputs a prompt to the selected generation model to specify the format. The selected generation model can generate a new translated text each time it receives a prompt or glossary and supply it sequentially to the presentation unit 115.

[0102] The prompts provided by the translation instruction unit 114 in this embodiment to the generation model for generating a translated text mainly include a translation generation command, source text, and a specified language. A prompt containing these elements may include, for example, "Translate the following source text into the specified language. The source text is "A typhoon is...", and the specified language is "Japanese."

[0103] A prompt indicating requirements based on a translation sample might, for example, instruct the translated text to use the same grammar as the translation sample. A prompt indicating requirements based on a translation sample might also instruct the system to read the translations of individual words and phrases and to translate those words and phrases. Alternatively, a prompt indicating requirements based on a translation sample might infer the translation rules included in the translation sample and instruct the system to translate in accordance with the identified translation rules. Because the prompt is as described above, the information processing system 10 can, for example, easily generate a translation that follows a similar format from a user-created translation 1 and present it to the user.

[0104] The glossary information supplied to the generation model by the translation instruction unit 114 is provided in a manner that allows the generation model to reflect the glossary information in the translated text. Furthermore, prompts for reflecting the specified format in the translated text include, for example, text data instructions such as, "Please format the generated translation into a polite, formal style."

[0105] As the translation instruction unit 114 performs the above-described process, the selected generation model generates a translated text by translating the source text into the specified language. At this time, the selected generation model generates the translated text according to the translation requirements based on the translation sample. Next, the selected generation model reflects the information of the selected glossary into the translated text according to the information of the selected glossary. Furthermore, the selected generation model reflects the specified format into the translated text according to prompts indicating the specified format. Finally, the selected generation model supplies the translated text, which reflects the instructions received from the translation instruction unit 114, to the presentation unit 115.

[0106] As described above, the translation instruction unit 114 also inputs a prompt to the generation model that includes instructions to access the storage unit 120 and perform translation processing according to the requirements based on the translation sample 122. In this case, the requirements for translation processing instructed by the translation instruction unit 114 may be translation rules relating to at least one of the following: the translation method for each token and the style or grammar of the translated text.

[0107] Next, an example of a presentation image 400 according to this embodiment will be described with reference to Figure 15. Figure 15 is the seventh figure showing an image to be presented to a user using the information processing device 100. The presentation image 400 shown in Figure 15 has a translation sample display field 450 next to the glossary display field 440. By selecting the translation sample display field 450, the user can register or delete translation samples.

[0108] Furthermore, the translation sample display field 450 may be configured to allow registration of multiple translation samples, similar to the glossary display field 440. The translation sample display field 450 may also have a toggle switch to toggle whether or not to apply registered translation samples to the generation of the translated text.

[0109] Next, an example of a translation sample will be described with reference to Figure 16. Figure 16 is a diagram showing a translation sample 122 according to the third embodiment. The translation sample 122 includes a sample source text and a sample translated text, which is a sentence obtained by translating the sample source text into a specified language.

[0110] In translation sample 122 shown in Figure 16, the sample source text is in English and contains the content, "When a typhoon is approaching landfall, ...your surroundings." The sample translation is a Japanese translation of the above sample source text and contains the content, "When a typhoon makes landfall, ...take action." By referencing this translation sample to the generative model, the generative model is set to translate, for example, "approaching landfall" as "landfall." Furthermore, by referencing this translation sample to the generative model, the generative model is set to generate a translation that follows the style of the Japanese translation, using polite language.

[0111] The third embodiment has been described above. The information processing system 10 according to this embodiment can suitably instruct the generation model on the translation method by utilizing translation samples. Therefore, according to this embodiment, it is possible to provide an information processing system, information processing method, and program that suitably generate translated text in response to user requests.

[0112] <Fourth Embodiment> Next, a fourth embodiment will be described. Figure 17 is a block diagram of the information processing device 100 according to the fourth embodiment. The information processing device 100 according to this embodiment differs from the embodiments described above in that it has a summary generation unit 118.

[0113] The summary generation unit 118 generates a summary of the text to a predetermined length. The summary generation unit 118 generates a summary of the original text and simultaneously generates a summary of the translated text. At this time, the presentation unit 115 presents the summaries of the original text and the translated text to the user terminal 300 in a manner that allows for comparison with the original text and the translated text. This allows the information processing system 10 to suitably present to the user whether the content of the translated text is as intended by the user, especially when the original text is lengthy.

[0114] Next, the processing performed by the information processing device 100 will be described with reference to Figure 18. Figure 18 is a flowchart of the information processing method according to the fourth embodiment. The flowchart shown in Figure 18 differs from the flowchart shown in Figure 9 in that, after step S14, steps S41 and S42 are included instead of step S15.

[0115] In step S41, the summary generation unit 118 generates summaries of the source text received by the source text receiving unit 111 and the translated text received by the translation instruction unit 114 from the generation model. The summary generation unit 118 supplies the generated summaries of the source text and the translated text to the presentation unit 115.

[0116] In step S42, the presentation unit 115 presents the translation and summary to the user terminal 300. At this time, the presentation unit 115 presents the original text and the translated text to the user terminal 300 in a manner that allows for comparison. The presentation unit 115 also presents the summary of the original text and the summary of the translated text to the user terminal 300 in a manner that allows for comparison.

[0117] Next, the processing of the summary generation unit 118 will be described with reference to Figure 19. Figure 19 is a diagram showing the processing of the translation instruction unit 114 and the summary generation unit 118 according to the fourth embodiment. In Figure 19, the translation instruction unit 114 receives the source text and outputs the translated text. At this time, the translation instruction unit 114 works in conjunction with the generation model.

[0118] Meanwhile, the summary generation unit 118 receives the source text and generates a summary of it. At this time, the summary generation unit 118 generates a prompt that includes an instruction to generate a summary of the received source text, and then inputs this prompt and the source text into the generation model. As a result, the summary generation unit 118 outputs a summary of the source text.

[0119] Furthermore, the summary generation unit 118 receives the translated text and generates a summary of the translated text. At this time, the summary generation unit 118 generates a prompt that includes an instruction to generate a summary of the received translated text, and then inputs this prompt and the translated text into the generation model. As a result, the summary generation unit 118 outputs a summary of the translated text.

[0120] The processing of the translation instruction unit 114 and the summary generation unit 118 has been described above. The generation model that the translation instruction unit 114 works with and the generation model that the summary generation unit 118 works with may be the same or different.

[0121] Next, with reference to Figure 20, the presentation image 400 according to this embodiment will be described. Figure 20 is the eighth figure showing an image to be presented to a user using the information processing device 100. The presentation image 400 shown in Figure 20 has a source text display field 410 and a translated text display field 420 arranged side by side in the left-right direction. The presentation image 400 also has a summary display field 460 below the source text display field 410 and the translated text display field 420. The summary display field 460 includes a source text summary field 461 and a translated text summary field 462. The source text summary field 461 is located below the source text display field 410. On the other hand, the translated text summary field 462 is located below the translated text display field 420. The source text summary field 461 and the translated text summary field 462 are arranged side by side in the left-right direction. As a result, the information processing system 10 presents the user terminal 300 with display images 400 arranged in a way that facilitates comparison between the original text and the translated text, comparison between the original text and its summary, comparison between the translated text and its summary, and comparison between the summary of the original text and the summary of the translated text.

[0122] The fourth embodiment has been described above. The information processing system 10 according to this embodiment can provide information that allows for easy understanding of the translation's outline when the source text is lengthy, by generating a summary. According to this embodiment, it is possible to provide an information processing system, information processing method, and program that suitably generate translated text in response to user requests.

[0123] The program described above includes a set of instructions (or software code) that, when loaded into a computer, causes the computer to perform one or more of the functions described in the embodiments. The program may be stored on a non-temporary computer-readable medium or a physical storage medium. Examples, but not limited to, include computer-readable mediums or physical storage mediums such as RAM (random-access memory), ROM (read-only memory), flash memory, SSD (solid-state drive), or other memory technologies. Examples, but not limited to, include CD-ROMs, DVDs (digital versatile discs), Blu-ray discs, or other optical disc storage. Examples, but not limited to, include magnetic tape, magnetic disk storage, or other magnetic storage devices. The program may be transmitted over a temporary computer-readable medium or a communication medium. Examples, but not limited to, include temporary computer-readable mediums or communication mediums such as electrical, optical, acoustic, or other forms of propagating signals.

[0124] The embodiments have been described above, but the configurations of the embodiments described above may be combined with each other, or some of the configurations may be replaced with other configurations. Furthermore, the configurations of the embodiments described above may be modified in various ways without departing from the spirit of the invention.

[0125] Each drawing is merely illustrative to illustrate one or more embodiments. Each drawing may be associated not only with one embodiment but also with one or more other embodiments. As those skilled in the art will understand, various features or steps described with reference to any one drawing can be combined with features or steps shown in one or more other drawings to create embodiments that are not explicitly shown or described. Not all features or steps shown in any one drawing to illustrate an exemplary embodiment are necessarily required, and some features or steps may be omitted. The order of steps shown in any of the drawings may be changed as appropriate. [Explanation of symbols]

[0126] 10 Information Processing Systems 100 Information Processing Devices 101 Conversation Mode Reception Unit 102 Conversation Function Unit 110 Translation Mode Reception Section 111 Original Text Reception Department 112 Language Settings Section 113 Format Reception Department 114 Translation Instructions Section 115 Presentation section 116 Glossary Selection Section 117 Generative Model Selection Section 118 Summary generator 120 Storage section 121 Glossary 122 Translation Samples 200 servers 210 First Generative Model 220 Second Generative Model 300 user terminals 400 images presented 401 Menu Display 410 Original text display field 420 Translation display field 430 Specified format input field 431 Apply button 440 Glossary Display Fields 441 Glossary Selection Field 442 Glossary Editing Field 450 Translation Sample Display Fields 460 Summary Display Fields 461 Original Text Summary Field 462 Translation Summary Field 1000 computers 1010 Bus 1020 Processor 1030 memory 1040 Storage Devices 1050 Input / Output Interface 1060 Network Interfaces N1 Network

Claims

1. 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.

2. 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.

3. 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.

4. 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.

5. 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.

6. 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.

7. 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.

8. 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.

9. 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.

10. 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.

11. 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 classifications of the source text or the translation text. Information processing system.

12. 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.

13. 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.

Images