Information processing system, information processing method, and program

Abstract

To provide an information processing system, an information processing method, and a program that generate a suitable translation in response to a user request. [Solution] In the information processing system 10, the original text receiving unit 111 receives the original text, which is text data to be input to the generative artificial intelligence, from a user terminal. The language setting unit 112 sets a designated language, which is the language classification of the translation, which is text data obtained by translating the original text. The format receiving unit 113 receives a designated format, which is the format of the translation, from the user terminal as text data. The translation instruction unit 114 causes the generative artificial intelligence to generate a translation by inputting a prompt to the generative artificial intelligence, which includes an instruction to execute a translation process that translates the original text into the designated language according to the designated format. The presentation unit 115 presents the translation on the user terminal.

Description

[Technical Field]

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

[0002] Generative AI (Artificial Intelligence) services using large-scale language models (LLMs), which are generative artificial intelligence that generate answers in response to various user requests, are becoming more common. In relation to this, translation technology using technologies such as generative AI is also advancing.

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

[0004] The web service described in Non-Patent Document 1 is a translation service that employs neural machine translation technology, providing translations with contextual understanding using a deep learning model trained on a large-scale language dataset. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Application Laid-Open No. 2002-197084 [Non-patent literature]

[0006] [Non-Patent Document 1] DeepL, September 29, 2024, Internet<URL:https: / / www.deepl.com / en / translator> Summary of the Invention [Problem to be solved by the invention]

[0007] However, the above-mentioned techniques have problems with customizing the translation results.

[0008] In view of the above-mentioned problems, the present disclosure aims to provide an information processing system and the like that generates a suitable translation in response to a user request. [Means for solving the problem]

[0009] An information processing system according to the present disclosure causes a generative artificial intelligence capable of generating a task based on input received from a user terminal to perform translation. The information processing system includes an original text receiving unit, a language setting unit, a format receiving unit, a translation instruction unit, and a presentation unit. The original text receiving unit receives an original text, which is text data to be input to the generative artificial intelligence, from the user terminal. The language setting unit sets a designated language, which is a language classification of a translation, which is text data obtained by translating the original text. The format receiving unit receives a designated format, which is the format of the translation, from the user terminal as text data. The translation instruction unit causes the generative artificial intelligence to generate a translation by inputting a prompt to the generative artificial intelligence, which includes an instruction to execute a translation process to translate the original text into the designated language in accordance with the designated format. The presentation unit presents the translation on the user terminal.

[0010] An information processing method according to the present disclosure causes a generative artificial intelligence capable of generating a task based on input received from a user terminal to perform a translation. A computer receives, from the user terminal, an original text, which is text data to be input to the generative artificial intelligence. The computer sets a designated language, which is a language classification of a translation, which is text data obtained by translating the original text. The computer receives, from the user terminal, a designated format, which is the format of the translation, as text data. The computer causes the generative artificial intelligence to generate the translation by inputting a prompt to the generative artificial intelligence that includes an instruction to execute a translation process to translate the original text into the designated language according to the designated format. The computer presents the translation on the user terminal.

[0011] A program according to the present disclosure causes a computer to execute an information processing method for causing a generative artificial intelligence capable of generating a task based on input received from a user terminal to perform translation. The program includes an original text receiving step, a language setting step, a format receiving step, a translation instruction step, and a presentation step. The original text receiving step receives, from the user terminal, an original text that is text data to be input to the generative artificial intelligence. The language setting step sets a designated language that is a language classification of a translation that is text data obtained by translating the original text. The format receiving step receives, from the user terminal, a designated format that is the format of the translation. The translation instruction step causes the generative artificial intelligence to generate a translation by inputting a prompt to the generative artificial intelligence that includes an instruction to execute a translation process that translates the original text into the designated language according to the designated format. The presentation step presents the translation to the user terminal. [Effects of the Invention]

[0012] According to the present disclosure, it is possible to provide an information processing system, an information processing method, and a program that generate a suitable translation in response to a user request. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a block diagram of an information processing system according to a first embodiment. [Figure 2] FIG. 2 is a block diagram illustrating an example of a hardware configuration of a computer. [Figure 3] 3 is a flowchart of an information processing method according to the first embodiment. [Figure 4] FIG. 4 is a diagram showing processing in a translation instruction unit according to the first embodiment. [Figure 5] FIG. 1 is a first diagram showing an image presented to a user who uses the information processing system. [Figure 6] FIG. 2 is a second diagram showing an image presented to a user who uses the information processing system. [Figure 7] FIG. 10 is a block diagram of an information processing system according to a second embodiment. [Figure 8] FIG. 10 is a block diagram of an information processing device according to a second embodiment. [Figure 9] 10 is a flowchart of an information processing method according to a second embodiment. [Figure 10] FIG. 11 is a diagram showing processing in a translation instruction unit according to the second embodiment. [Figure 11] FIG. 4 is a fourth diagram showing an image presented to a user who uses the information processing system. [Figure 12] FIG. 5 is a fifth diagram showing an image presented to a user who uses the information processing system. [Figure 13] FIG. 6 is a sixth diagram showing an image presented to a user using the information processing system. [Figure 14] FIG. 11 is a diagram showing processing in a translation instruction unit according to the third embodiment. [Figure 15] FIG. 7 is a seventh diagram showing an image presented to a user who uses the information processing system. [Figure 16] FIG. 11 is a diagram showing a translation sample according to the third embodiment. [Figure 17] FIG. 10 is a block diagram of an information processing device according to a fourth embodiment. [Figure 18] 10 is a flowchart of an information processing method according to a fourth embodiment. [Figure 19] FIG. 13 is a diagram illustrating the processing of a translation instruction unit and a summary generation unit according to the fourth embodiment. [Figure 20] FIG. 8 is an eighth figure showing an image presented to a user using the information processing system. DETAILED DESCRIPTION OF THE INVENTION

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

[0015] First Embodiment (Information Processing System 10) An information processing system 10 according to this embodiment will be described with reference to FIG. 1. FIG. 1 is a block diagram of the information processing system 10 according to the first embodiment. The information processing system 10 generates a translation by translating a sentence input by a user (hereinafter referred to as an original sentence) into a predetermined language different from the original sentence, and presents the translation to the user. The information processing system 10 is communicably connected to a user terminal 300 via a network N1. The information processing system 10 causes a generative artificial intelligence capable of generating a task based on the input received from the user terminal 300 to perform the translation.

[0016] In the following description, generative artificial intelligence is also referred to as generative AI or generative model. A generative model is an algorithm designed to generate various content, such as text, images, audio, or program code, in response to a specific request. A generative model in this disclosure has at least the function of generating text. That is, a generative model in this disclosure includes a language model. The architecture of the language model may have a neural network using deep learning or may include a Generative Pre-trained Transformer (GPT).

[0017] In this case, the request may be data including image data, audio data, or other information in addition to text data. Data including other information may be, for example, a signal generated by a predetermined sensor. In this case, the generative model is a multimodal AI. In this case, the multimodal AI language model may be, for example, what is called an MMLLM (Multi Modal Large Language Model) or a multimodal model. The multimodal language model may generate a response using text data, or may generate a response including image data or audio data.

[0018] The information processing system 10 mainly comprises an information processing device 100 and a server 200. The information processing device 100 and the server 200 are communicatively connected via a network N1. The information processing device 100 receives original text data from a 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, when the information processing device 100 receives a translation of the original text from the server 200, it supplies the translation to the user terminal 300.

[0019] The server 200 has as its main component a first generative model 210. The first generative model 210 generates a translation in accordance with the original text data and translation instructions received from the information processing device 100. The first generative model 210 supplies the generated translation to the information processing device 100.

[0020] The user terminal 300 is a computer used by a user. The computer used by a user may be a personal computer, tablet terminal, smartphone, wearable terminal, or mobile phone. The user terminal 300 generates text data of the original text by accepting user operations and supplies the generated text data to the information processing system 10. The user terminal 300 also receives a translation from the information processing system 10 and presents it to the user.

[0021] (Information processing device 100) The following describes the information processing device 100. The information processing system 10 has an original text receiving unit 111, a language setting unit 112, a format receiving unit 113, a translation instruction unit 114, and a presentation unit 115 as its main components.

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

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

[0024] The format receiving unit 113 receives a specified format, which is the format of the translation, from the user terminal as text data. The specified format is the format of the translation specified by the user. The specified format includes the style, grammar, and expression of the translation. More specifically, for example, the specified format may include literary, colloquial, or polite language. The specified format may include a grammar similar to that of a specific character or a grammar that uses specific expressions at the end of words. The specified format may also include the use of many foreign words, the use of a specific dialect, or the use of grammar from a specific era.

[0025] The translation instruction unit 114 inputs a prompt including an instruction to execute a translation process to translate an original text into a specified language in accordance with a specified format into the generative model, thereby causing the generative model to generate a translation. More specifically, the translation instruction unit 114 generates a system prompt for instructing the translation of the original text into a specified language in accordance with a specified format, and inputs the generated system prompt into the generative model. By inputting the system prompt, the translation instruction unit 114 causes the generative model to generate a translation and supply it to the presentation unit 115.

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

[0027] The above describes the information processing device 100 and the server 200. 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 millions to billions of parameters. On the other hand, an LLM has billions to trillions of parameters.

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

[0029] The bus 1010 is a data transmission path for transmitting and receiving data among the processor 1020, memory 1030, storage device 1040, input / output interface 1050, and network interface 1060. However, the method of connecting the processor 1020 and the like to each other is not limited to bus connection.

[0030] The processor 1020 is a circuit including an arithmetic unit such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit).

[0031] The memory 1030 is a main storage device realized using a RAM (Random Access Memory) or the like.

[0032] The storage device 1040 is an auxiliary storage device such as a hard disk drive (HDD), a solid state drive (SSD), a flash memory, or a read only memory (ROM), etc. The storage device 1040 stores programs for realizing the functions of the present disclosure.

[0033] The processor 1020 reads the program into the memory 1030 and executes it, thereby causing the processor 1020 to execute the functions corresponding to the program. In other words, the program stored in the memory 1030 causes the computer 1000 to execute the functions of the present 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 that allows a user to input various information to the computer 1000 through operation. The information input device is, for example, a keyboard, a mouse, or a touch panel. The computer 1000 may also have a display, a speaker, a vibration motor, an LED (light-emitting diode), or the like for displaying various information to the user.

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

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

[0039] The original text receiving unit 111 may automatically detect the received original text and identify the language classification of the detected original text. When the original text receiving unit 111 identifies the language classification, the original text receiving unit 111 may have a function of presenting the language classification of the original text on the user terminal 300. This allows the information processing device 100 to allow the user to recognize the language of the original text input by the user.

[0040] In step S12, the language setting unit 112 sets a designated language, which is a language classification of a translation sentence, which is text data obtained by translating an original sentence. 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 also 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 designated format, which is the format of the translation, as text data from the user terminal 300. At this time, the user inputs the original text into the user terminal 300 and also inputs instructions regarding the designated format as text.

[0042] In step S14, the translation instruction unit 114 inputs a prompt including an instruction to execute a translation process to translate the original text into a specified language in accordance with a specified format to the generative model, thereby causing the generative model to generate a translation. After causing the generative model to generate a translation, the translation instruction unit 114 supplies the generated translation to the presentation unit 115.

[0043] In step S15, the presentation unit 115 presents the translation received from the translation request unit 114 to the user terminal 300. At this time, the presentation unit 115 generates a presentation image in a manner that displays the translation on a display of the user terminal 300, and transmits data of the presentation image including the translation to the user terminal 300. In this way, the information processing device 100 presents the translation to the user. Note that it is preferable that the presentation image generated by the presentation unit 115 is in a manner that allows the original text and the translation to be compared.

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

[0045] Next, processing performed by the translation instruction unit 114 will be described with reference to FIG. 4. FIG. 4 is a diagram showing processing by the translation instruction unit 114 according to the first embodiment. Upon receiving original text data and a specified language setting, the translation instruction unit 114 generates a prompt for causing the first generation model 210 to generate a translation. Furthermore, upon receiving text data in a specified format, the translation instruction unit 114 generates a prompt for causing the first generation model 210 to reflect the specified format in the translation. 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 causing the first generation model 210 to generate a translation. After the first generation model 210 generates a translation, the translation instruction unit 114 inputs a prompt for instructing the first generation model 210 on the specified format. Note that the first generation model 210 may sequentially supply the generated translations to the presentation unit 115.

[0046] The prompt includes elements for controlling the operation of the first generative model 210 and guiding its response. The prompt used by the translation instruction unit 114 to cause the first generative model 210 to generate a translation includes, as its main elements, a translation generation command, an original text, and a specified language. A prompt including these elements includes, for example, content such as "Please translate the original text shown below into the specified language according to the specified format. The original text is "...", and the specified language is "... language." Furthermore, a prompt for reflecting the specified format in the translation includes, as its main element, text data for specifying the specified format. In this case, the prompt includes, for example, content such as "Please make the generated translation [specified format]."

[0047] As a result of the translation instruction unit 114 performing the above-mentioned processing, the selected generative model generates a translation of the original text into the specified language. Furthermore, the selected generative model reflects the specified format in the translation in accordance with the prompt that specifies the specified format. The selected generative model then supplies the translation that reflects the instructions received from the translation instruction unit 114 to the presentation unit 115.

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

[0049] Next, information presented to a user by the information processing system 10 will be described with reference to Fig. 5. Fig. 5 is a first diagram showing an image presented to a user who uses the information processing system 10. Fig. 5 shows a 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 visually recognizes the presented image 400 displayed on the display of the user terminal 300. The presented image 400 mainly includes an original text display field 410, a translation text display field 420, and a specified format input field 430.

[0050] The original text display field 410 displays the original text entered by the user. A pull-down menu 411 is arranged above the original text display area, along with a display of the language classification. The pull-down menu 411 is set so that the language classification of the original text can be changed. When the user selects the pull-down menu 411, the presentation image 400 displays selectable language classifications that can be translated.

[0051] The translation display field 420 displays the translation that the translation instruction unit 114 has the first generation model 210 generate. Above the text display of the translation, a display of the language classification of the translation and a pull-down menu 421 are arranged. When the user selects the pull-down menu 421, the presentation image 400 displays selectable language classifications for translation. By selecting a language classification from the pull-down menu 421, the user can determine the language into which they want to translate.

[0052] The specified format input field 430 displays text for indicating 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 transmits the text data of the specified format entered by the user to the information processing system 10. That is, 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 translation that conforms to the specified format. In other words, when the apply button 431 is selected, the translation displayed in the translation display field 420 reflects the contents of the specified format.

[0053] A specific example of the presented image 400 shown in FIG. 5 will be described. The original text displayed in the original text display field 410 is in English. The original text is displayed as "A typhoon...their safety." Furthermore, "English (automatic detection)" is displayed at the top of the original text display field 410. This indicates that the original text receiving unit 111 of the information processing system 10 has detected the original text and identified that the detected original text is English.

[0054] The translation displayed in the translation display field 420 is in Japanese. The translation is displayed as "We strongly request that the typhoon..." The translation displayed in the translation display field 420 is written in the "desumasu" style. The specified format input field 430 displays "Please use the "desumasu" style." In other words, the user is instructing that the translation be in the "desumasu" style. Therefore, as described above, the translation in the translation display field 420 is displayed in the "desumasu" style in accordance with the specified format.

[0055] In the presented image 400, the original text display field 410 and the translation text display field 420 are arranged side by side. That is, the presenting unit 115 generates the presented image 400 in which the original text display field 410 and the translation text display field 420 are arranged side by side. In this way, the information processing system 10 presents the presented image 400 that allows the user to easily compare the original text with the translation text.

[0056] Next, the information presented to the user by the information processing system 10 will be further described with reference to Fig. 6. Fig. 6 is a second diagram showing an image presented to the user who uses the information processing system 10. The content of the specified format in Fig. 6 differs from that in Fig. 5. Therefore, the grammar of the translated sentence differs from that in Fig. 5.

[0057] 6, the user has entered "Please use colloquial language" in the specified format input field 430. As a result, the translation displayed in the translation display field 420 is displayed in colloquial language as "It looks like a typhoon will hit tomorrow. They're telling us to take care to catch it."

[0058] The information processing system 10 has been described above. Each component of the information processing device 100 may be realized by dedicated hardware. Furthermore, some or all of the components may be realized by general-purpose or dedicated circuits, processors, etc., or a combination thereof. These may be configured by a single chip, or by multiple chips connected via a bus. Some or all of the components may be realized by a combination of the above-mentioned circuits, etc., and a program. Furthermore, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an FPGA (Field-Programmable Gate Array), etc. may 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), SaaS (Software as a Service), etc.

[0059] As described above, the information processing system 10 can specify the format of the translation. Therefore, according to the present embodiment, it is possible to provide an information processing system, an information processing method, and a program that generate a translation in an appropriate manner in response to a user request.

[0060] Second Embodiment Next, a second embodiment will be described. FIG. 7 is a block diagram of an 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 a plurality of generative models. The information processing device 100 selects one of two generative models held by the server 200 and instructs the selected generative model to translate the original text. The server 200 according to the second embodiment mainly includes a first generative model 210 and a second generative model 220. The first generative model 210 and the second generative model 220 are mutually different generative models.

[0061] The first generative model 210 and the second generative model 220 may be different versions of the models or may be models developed by different developers. The first generative model 210 and the second generative model 220 may have different numbers of parameters, for example. Furthermore, 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 with different learning content. The difference in learning content may be, for example, learning translation for a specific category of languages. More specifically, the difference in learning content may be, for example, that the first generative model 210 is more suitable for translating English than the second generative model 220, and the second generative model 220 is more suitable for translating Chinese than the first generative model 210.

[0062] Next, an information processing device 100 according to a second embodiment will be described with reference to Fig. 8. Fig. 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 acceptance unit 101, a conversation function unit 102, a translation mode acceptance unit 110, a glossary selection unit 116, a generation model selection unit 117, and a storage unit 120.

[0063] The conversation mode receiving unit 101 receives from the user terminal 300 a request to enter a conversation mode in which a prompt using arbitrary text data is input to a generative model. The conversation mode is a state in which an arbitrary request is received from the user terminal 300 and a response to the received request is generated. The arbitrary request may be, for example, generation of a summary of a text, generation of a text under predetermined conditions, generation of an image, or generation of program code. When the conversation mode receiving unit 101 receives the selection of the conversation mode, the information processing device 100 activates the conversation function unit 102. The 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 function 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 generative model 210 or the second generative model 220. The user can select which of the multiple generative models to select. That is, in this case, the conversation function unit 102 receives information regarding the selection of a generative model from the user terminal 300. The conversation function unit 102 inputs the request received from the user terminal 300 to the selected generative model, and receives a response to the input from the generative model. The conversation function unit 102 presents the response received from the generative model to the user terminal 300. Note that the conversation function unit 102 may have a RAG (Retrieval-Augmented Generation) function.

[0065] The translation mode receiving unit 110 receives from the user terminal 300 a request to enter a translation mode in which a prompt related to translation processing is input to a generative model. Upon receiving the selection of the translation mode, the information processing device 100 performs a function of translating the original text received from the user terminal 300. That is, the information processing device 100 according to this embodiment performs the function of the conversation mode described above when the conversation mode is selected, and performs the function of the translation mode when the translation mode is selected.

[0066] The glossary selection unit 116 receives, from the user terminal 300, a request to select at least one glossary from the storage unit 120, which stores selectable glossaries that contain translations for specific words or phrases. The glossary selection unit 116 provides information about the selected glossary to the translation instruction unit 114. In this case, the translation instruction unit 114 inputs a prompt to the generative model, the prompt including an instruction to execute translation processing by referring to the selected glossary. This allows the information processing system 10 to generate a translation that appropriately applies the glossary selected by the user when executing translation processing.

[0067] The translation instruction unit 114 may also have a function of inputting a prompt to the generative model, instructing the model to determine whether or not to apply the selected glossary for each token depending on the context of the original sentence. This allows the information processing system 10 to prevent translations generated by the generative model from becoming uniform and including inappropriate translations. In other words, the information processing system 10 can generate suitable translations by flexibly applying glossary information.

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

[0069] The generation model selection unit 117 may select one generation model for executing the translation process from a plurality of generation models based on at least one of the language classification of the original sentence and the language classification of the translation sentence. In this case, the information processing system 10 selects an appropriate generation model according to the language classification related to the translation.

[0070] The storage unit 120 stores a plurality of selectable glossaries each storing translations for a specific word or phrase. By storing a plurality of selectable glossaries, the information processing system 10 can reduce the burden on the user of rewriting the glossary each time a translation is performed.

[0071] Next, the processing executed by the information processing device 100 according to this embodiment will be described. Fig. 9 is a flowchart of an information processing method according to the second embodiment. The flowchart shown in Fig. 9 differs from the flowchart shown in Fig. 3 in that steps S21 to S23 are provided between steps S13 and S14. The flowchart shown in Fig. 9 starts 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 has been selected. If the glossary selection unit 116 determines that a glossary has been selected (step S21: YES), the information processing device 100 proceeds to step S22. If the glossary selection unit 116 does not determine that a glossary has been selected (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 translation instruction unit 114 with information about the read glossary.

[0074] In step S23, the generative model selection unit 117 selects a generative model. Here, the generative model selection unit 117 may accept the selection of a generative model by a user operation, or may select a generative model according to a preset algorithm. The preset algorithm is, for example, the selection of a generative model according to information on the language classification of the original text and the specified language of the translation text. The generative model selection unit 117 supplies information on the selected generative model to the translation instruction unit 114.

[0075] In step S14, the translation instruction unit 114 inputs to the selected generative model an instruction to execute a translation process to translate the original text into the specified language in accordance with the specified format, and a prompt including a glossary to reference, thereby causing the generative model to generate a translation. After causing the selected generative model to generate a translation, the translation instruction unit 114 receives the generated translation and supplies the received translation to the presentation unit 115.

[0076] Next, processing performed by the translation instruction unit 114 according to this embodiment will be described with reference to FIG. 10. FIG. 10 is a diagram illustrating processing performed by the translation instruction unit 114 according to the second embodiment. Upon receiving text data of an original sentence and a specified language setting, the translation instruction unit 114 generates a prompt for causing a selected generative model to generate a translation. Furthermore, upon receiving text data in a specified format, the translation instruction unit 114 generates a prompt for causing the selected generative model to reflect the specified format in the translation. Furthermore, upon receiving information regarding glossary selection, the translation instruction unit 114 reads the selected glossary from the glossary 121 stored in the storage unit 120 and supplies the read glossary to the selected generative model. Next, the translation instruction unit 114 supplies the read glossary to the selected generative model. The translation instruction unit 114 may also instruct the system to determine, for each token, whether or not to apply the selected glossary depending on the context of the original sentence. Furthermore, the translation instruction unit 114 inputs a prompt for instructing the specified format to the selected generative model. Note that the selected generative model may generate a new translation each time it receives a prompt or glossary. The generative model can also sequentially supply the generated translations to the presenting unit 115.

[0077] The prompt that the translation instruction unit 114 in this embodiment uses to cause the generative model to generate a translation includes, as its main elements, a translation generation command, an original text, and a specified language. A prompt including these elements includes, for example, content such as, "Please translate the original text shown below into the specified language. The original text is 'A typhoon is...' and the specified language is 'Japanese'." Furthermore, when the translation instruction unit 114 supplies a glossary to the generative model, the translation instruction unit 114 supplies the glossary information to the generative model in a manner that allows the generative model to reflect the glossary information in the translation. Furthermore, a prompt for reflecting a specified format in the translation includes, for example, an instruction in the form of text data such as, "Please use the formal pronouns in the generated translation."

[0078] As a result of the translation instruction unit 114 performing the above-mentioned process, the selected generative model generates a translation of the original text into the specified language. Next, the selected generative model reflects the glossary information in the translation in accordance with the information about the selected glossary. Furthermore, the selected generative model reflects the specified format in the translation in accordance with a prompt that specifies the specified format. The selected generative model then supplies the translation that reflects the instructions received from the translation instruction unit 114 to the presentation unit 115.

[0079] In addition to the above content, the prompt may also include content that instructs the user to apply glossary information according to the context, rather than automatically applying glossary information to all words or phrases.

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

[0081] 11 differs from the presentation image 400 according to the first embodiment in that it includes a menu display 401. The menu display 401 includes displays such as "New Conversation," "Translation," "History," and "Account," which can be selected by the user.

[0082] When the user selects "New Conversation," the information processing system 10 enters the conversation mode. That is, when the user selects "New Conversation," the conversation mode receiving unit 101 of the information processing device 100 receives that the conversation mode has been selected.

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

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

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

[0086] Fig. 12 is a fifth diagram showing an image presented to a user who uses information processing device 100. Presentation image 400 shown in Fig. 12 shows a situation after the user selects glossary display field 440 in presentation image 400 shown in Fig. 11. Presentation image 400 in Fig. 12 includes glossary selection field 441 below glossary display field 440.

[0087] Glossary selection field 441 includes displays for "Glossary A," "Glossary B," and "Create New." When the user selects "Glossary A," "Glossary A" is displayed in glossary display field 440. An ellipsis is displayed to the right of "Glossary A" in glossary selection field 441. When the user selects the ellipsis, buttons for editing or deleting "Glossary A" are displayed.

[0088] When the user selects "Glossary B," "Glossary B" is displayed in glossary display field 440. As with glossary A, an ellipsis is also displayed to the right of "Glossary B" in glossary selection field 441. When the user selects the ellipsis, buttons for editing or deleting "Glossary B" are displayed. When the user selects "Create New," a screen for creating a new glossary is displayed.

[0089] In the presented image 400 shown in Fig. 12, "Glossary A" is displayed in the glossary display field 440. That is, the presented image 400 in Fig. 12 shows a state in which the user has selected glossary A. Note that the glossary display field 440 also displays a switch that can be switched on and off. By switching this switch, the user can decide whether or not to apply the glossary to the translation.

[0090] Next, creating and editing a glossary will be described with reference to Fig. 13. Fig. 13 is a sixth diagram showing an image presented to a user using information processing device 100. Presentation image 400 shown in Fig. 13 includes a glossary editing field 442. Glossary editing field 442 includes a name input field 443, a bilingual information input field 444, a register button 445, a bilingual information display field 446, and an import button 447.

[0091] The name input field 443 accepts input of the name of the glossary. The bilingual information input field 444 accepts input of bilingual information. "Bialling information" refers to information including a combination of a word or phrase before translation and a translated word or phrase corresponding to this word or phrase. The registration button 445 accepts registration of the input glossary name and bilingual information when the user selects or presses the registration button 445. The registered information is stored in the memory unit 120.

[0092] The bilingual information display field 446 displays registered bilingual information. The bilingual information display field 446 is set up so that registered bilingual information can be deleted and modified. The bilingual information display field 446 is also set up so that bilingual information can be registered when the combination of the original text and the translation is swapped. With this setting, the information processing system 10 can also handle translations when the combination of the original text and the translation is swapped, by having the user select one glossary.

[0093] The import button 447 imports glossary files created by the user in a predetermined file format, for example.

[0094] The second embodiment has been described above. The information processing system 10 according to this embodiment displays a translation-specific interface on the user terminal 300 by setting a generative model with conversation mode functionality to translation mode. The information processing system 10 also stores selectable glossaries in the storage unit 120, and allows the user to select one glossary, thereby enabling translation in a specific field, for example. Furthermore, the information processing system 10 can appropriately set the style and expression of the translation by accepting the specified format as text data. Therefore, this embodiment can provide an information processing system, information processing method, and program that appropriately generate a translation in response to a user request.

[0095] <Third embodiment> Next, a third embodiment will be described. The third embodiment differs from the above-described embodiments in that translation samples are stored and used in a generative model.

[0096] Fig. 14 is a diagram showing the processing in the translation request unit 114 according to the third embodiment. As shown in Fig. 14, the storage unit 120 stores translation samples 122 including sample original sentences and sample translations.

[0097] The translation sample 122 is text data that pairs an original text with a translation. The translation sample differs from a glossary in that it is a sentence rather than a word or phrase. The translation sample is used to instruct a generative model that generates a translation about translation requirements. The translation instruction unit 114 estimates the translation requirements by referencing the translation sample's translation. More specifically, the translation instruction unit 114 inputs the translation sample into a predetermined generative model to estimate the translation requirements. The predetermined generative model is a generative model configured to estimate the translation requirements from the translation sample. The reference to the translation sample's translation includes translations of words and phrases. The reference to the translation sample's translation also includes translations of style, grammar, and expression. By using the translation sample, the information processing system 10 can instruct the generative model about translation requirements without receiving detailed instructions from the user regarding the translation requirements.

[0098] The translation instruction unit 114 according to this embodiment receives the original text data and the specified language setting, and generates a prompt from the received information to cause the selected generative model to generate a translation.

[0099] The translation instruction unit 114 reads the translation sample 122 stored in the storage unit 120 and causes the above-mentioned predetermined generative model to estimate 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 to the first generative model 210. As shown in FIG. 14 , the translation instruction unit 114 inputs both the prompt that generates a translation and the prompt that indicates the requirements based on the translation sample to the generative 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 storage unit 120 and supplies the read glossary to the selected generative model. Note that the translation instruction unit 114 may also instruct to determine whether or not to apply the selected glossary for each token depending on the context of the original text.

[0101] The translation instruction unit 114 inputs a prompt to the selected generative model to indicate the specified format. Note that the selected generative model may generate new translations each time it receives a prompt or glossary and sequentially supply them to the presentation unit 115.

[0102] The prompt that the translation instruction unit 114 according to this embodiment uses to cause the generative model to generate a translation includes, as its main elements, a translation generation command, an original text, and a specified language. A prompt including these elements includes, for example, content such as "Please translate the original text shown below into the specified language. The original text is 'A typhoon is...' and the specified language is 'Japanese'."

[0103] The prompt specifying requirements based on the translation sample may, for example, specify that the translation should have the same grammar as the translation sample. The prompt specifying requirements based on the translation sample may read the translations of individual words and phrases and specify the translation of the read words and phrases. The prompt specifying requirements based on the translation sample may also estimate translation rules contained in the translation sample and specify the translation in accordance with the read translation rules. By using the prompts as described above, the information processing system 10 can, for example, easily generate a translation that follows a similar format from a translation created by the user and present it to the user.

[0104] The glossary-related information provided to the generative model by the translation instruction unit 114 is in a form that allows the generative model to reflect the glossary information in the translation. The prompt for reflecting the specified format in the translation includes an instruction in the form of text data such as, for example, "Please use the desu-masu style in the generated translation."

[0105] By performing the above-mentioned process by the translation instruction unit 114, the selected generative model generates a translation of the original text into the specified language. At this time, the selected generative model generates the translation in accordance with the translation requirements based on the translation sample. Next, the selected generative model reflects the information in the selected glossary in the translation in accordance with the information about the glossary. Furthermore, the selected generative model reflects the specified format in the translation in accordance with a prompt that specifies the specified format. Then, the selected generative model supplies the translation that 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 to the generative model a prompt including an instruction to access the storage unit 120 and execute translation processing in accordance with requirements based on the translation sample 122. In this case, the translation processing requirements instructed by the translation instruction unit 114 may be translation rules relating to at least one of a translation method for each token and the style and / or grammar of the translated sentence.

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

[0108] Note that the translation sample may be configured to allow multiple translation samples to be registered, similar to glossary display field 440. Furthermore, translation sample display field 450 may have a switch for switching whether or not a registered translation sample is to be applied to generating a translation.

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

[0110] In the translation sample 122 shown in FIG. 16, the sample original text is in English and includes the content, "When a typhoon is approaching landfall, your surroundings." The sample translated sentence is a Japanese translation of the above sample original text and includes the content, "When a typhoon makes landfall, take action." By referencing this translation sample to a generative model, the generative model is configured to translate, for example, "approaching landfall" as "landfall." Furthermore, by referencing this translation sample to a generative model, the generative model is configured to generate a translation in the polite form, following the Japanese style of the translation text.

[0111] The third embodiment has been described above. The information processing system 10 according to this embodiment can appropriately instruct the generative model on the translation method by using translation samples. Therefore, this embodiment can provide an information processing system, an information processing method, and a program that can appropriately generate a translation in response to a user request.

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

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

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

[0115] In step S41, the summary generation unit 118 generates summaries of the original text received by the original text receiving unit 111 and the translation text received from the generative model by the translation instruction unit 114. The summary generation unit 118 supplies the generated summaries of the original text and the translation 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 translation to the user terminal 300 in a manner that allows them to be compared. The presentation unit 115 also presents the summary of the original text and the summary of the translation to the user terminal 300 in a manner that allows them to be compared.

[0117] Next, the processing of the summary generation unit 118 will be described with reference to Fig. 19. Fig. 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 Fig. 19, the translation instruction unit 114 accepts an original sentence and outputs a translation. At this time, the translation instruction unit 114 works in conjunction with a generative model.

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

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

[0120] The above describes the processing of the translation instruction unit 114 and the summary generation unit 118. Note that the generative model that the translation instruction unit 114 cooperates with and the generative model that the summary generation unit 118 cooperates with may be the same or different.

[0121] Next, a presentation image 400 according to this embodiment will be described with reference to FIG. 20. FIG. 20 is an eighth diagram showing an image presented to a user of the information processing device 100. In the presentation image 400 shown in FIG. 20, an original text display field 410 and a translation text display field 420 are arranged side by side in the left-right direction. The presentation image 400 also has a summary display field 460 below the original text display field 410 and the translation text display field 420. The summary display field 460 includes an original text summary field 461 and a translation text summary field 462. The original text summary field 461 is arranged below the original text display field 410. Meanwhile, the translation text summary field 462 is arranged below the translation text display field 420. The original text summary field 461 and the translation text summary field 462 are also arranged side by side in the left-right direction. As a result, the information processing system 10 presents to the user terminal 300 a presentation image 400 arranged in a way that makes it easy to compare the original text with its translation, the original text with its summary, the translation with its summary, and the summary of the original text with the summary of the translation.

[0122] The fourth embodiment has been described above. The information processing system 10 according to this embodiment can generate a summary to present information that allows a user to easily grasp the outline of the translation when the original text is long. This embodiment can provide an information processing system, an information processing method, and a program that generate a suitable translation in response to a user request.

[0123] The above-mentioned program includes instructions (or software code) that, when loaded into a computer, cause the computer to perform one or more functions described in the embodiments. The program may be stored in a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, the computer-readable medium or tangible storage medium includes random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD), or other memory technology. The computer-readable medium or tangible storage medium includes CD-ROM, digital versatile disc (DVD), Blu-ray disc, or other optical disk storage. The computer-readable medium or tangible storage medium includes magnetic tape, magnetic disk storage, or other magnetic storage devices. The program may be transmitted on a transitory computer-readable medium or communication medium. By way of example and not limitation, the transitory computer-readable medium or communication medium includes electrical, optical, acoustic, or other forms of propagated signals.

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

[0125] Each drawing is merely an example for describing one or more embodiments. Each drawing may relate not only to one embodiment but also to one or more other embodiments. As will be understood by those skilled in the art, 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, for example, an embodiment not explicitly shown or described. Not all features or steps shown in any one drawing are necessary to describe an exemplary embodiment, and some features or steps may be omitted. The order of steps described in any drawing may be changed as appropriate. [Explanation of symbols]

[0126] 10 Information Processing Systems 100 Information processing device 101 Conversation mode reception 102 Conversation function unit 110 Translation mode reception 111 Original Text Reception Department 112 Language setting section 113 Form Reception Department 114 Translation Instructions 115 Presentation section 116 Glossary Selection Section 117 Generative Model Selection 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 Presentation Images 401 Menu display 410 Original Text Field 420 Translation display field 430 Specified Format Input Field 431 Apply button 440 Glossary Display Field 441 Glossary selection field 442 Glossary Edit Field 450 Translation sample display field 460 Summary Display Field 461 Original Summary Field 462 Translation Summary Field 1000 computers 1010 Bus 1020 processor 1030 memory 1040 Storage Device 1050 Input / Output Interface 1060 Network Interface N1 Network

Claims

1. An information processing system that causes a generative artificial intelligence capable of generating a task based on an input received from a user terminal to perform translation, an original text receiving unit that receives original text, which is text data to be input to the generative artificial intelligence, from an original text display field of a user terminal; a language setting unit that sets a designated language, which is a language classification of a translation sentence that is text data obtained by translating the original sentence; a format receiving unit that receives, as text data, a designated format, which is the format of the translation, from a designated format input field that is displayed simultaneously with the original text display field on the user terminal; a translation instruction unit that, when an application button in the specified format input field is selected to instruct application of the specified format, causes the generative artificial intelligence to generate the translation by inputting a prompt to the generative artificial intelligence that includes an instruction to execute a translation process to translate the original text into the specified language in accordance with the specified format input in the specified format input field; and a presentation unit that presents the translation on the user terminal; the translation instruction unit generates a first prompt for causing the generative artificial intelligence to generate the translation, generates a second prompt for instructing the generative artificial intelligence on the specified format, and causes the generative artificial intelligence to perform processing according to the second prompt as a process separate from the processing according to the first prompt at a timing different from the processing according to the first prompt for generating the translation; Information processing system.

2. 2. The information processing system according to claim 1, the translation instruction unit inputs the second prompt to the generative artificial intelligence after the generative artificial intelligence has generated the translation, for the purpose of reflecting the specified format in the translation generated by the generative artificial intelligence in response to the first prompt; Information processing system.

3. 2. The information processing system according to claim 1, a conversation mode receiving unit that receives from the user terminal a request to enter a conversation mode in which a prompt using any text data is input to the generative artificial intelligence; and 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 processing is input to the generative artificial intelligence. Information processing system.

4. 2. The information processing system according to claim 1, a glossary selection unit that receives, from the user terminal, a selection of at least one glossary from a storage unit that selectably stores glossaries that store translations of specific words or phrases; The translation instruction unit inputs a prompt including an instruction to execute the translation process by referring to the selected glossary to the generative artificial intelligence. Information processing system.

5. 5. The information processing system according to claim 4, The storage unit further stores a plurality of glossaries each storing a translation for a specific word or phrase in a selectable manner. Information processing system.

6. 5. The information processing system according to claim 4, The translation instruction unit inputs a prompt to the generative artificial intelligence, which also instructs the generative artificial intelligence to determine whether or not to apply the selected glossary for each token depending on the context of the original text. Information processing system.

7. 2. The information processing system according to claim 1, a summary generation unit that generates a summary of a sentence in a predetermined length; the summary generation unit generates a summary of the original text and also generates a summary of the translation text; the presentation unit presents summaries of the original text and the translation on the user terminal in a manner that allows comparison with the original text and the translation. Information processing system.

8. In the information processing system according to any one of claims 1 to 7, Further, an artificial intelligence selection unit is provided that receives, from the user terminal, a selection of one of the plurality of generative artificial intelligences to execute the translation process. Information processing system.

9. In the information processing system according to any one of claims 1 to 7, and an artificial intelligence selection unit that selects one of the plurality of generative artificial intelligences to execute the translation process based on at least one of the language classification of the original text and the language classification of the translation text. Information processing system.

10. An information processing method for causing a generative artificial intelligence (AI) capable of generating a task based on an input received from a user terminal to perform translation, comprising: The computer Accepting an original text, which is text data to be input to the generative artificial intelligence, from an original text display field of a user terminal; Set a designated language, which is a language classification of the translation text, which is text data obtained by translating the original text; accepts a designated format, which is the format of the translation, as text data from a designated format input field displayed simultaneously with the original text display field on the user terminal; When an application button in the specified format input field is selected to instruct application of the specified format, a prompt including an instruction to execute a translation process to translate the original text into the specified language in accordance with the specified format input in the specified format input field is input to the generative artificial intelligence, thereby causing the generative artificial intelligence to generate the translated text; An information processing method for presenting the translation on the user terminal, comprising: generating a first prompt for causing the generative artificial intelligence to generate the translation, generating a second prompt for instructing the generative artificial intelligence to use the specified format, and causing the generative artificial intelligence to perform processing according to the second prompt as a process separate from the processing according to the first prompt at a timing different from the processing according to the first prompt for generating the translation; Information processing methods.

11. A program that causes a computer to execute an information processing method for causing a generative artificial intelligence capable of generating a task based on an input received from a user terminal to perform translation, an original text receiving step of receiving an original text, which is text data to be input to the generative artificial intelligence, from an original text display field of a user terminal; a language setting step of setting a designated language, which is a language classification of a translation sentence, which is text data obtained by translating the original sentence; a format receiving step of receiving, from the user terminal, a designated format, which is the format of the translation, as text data from a designated format input field displayed simultaneously with the original text display field on the user terminal; a translation instruction step of causing the generative artificial intelligence to generate the translation sentence by inputting a prompt to the generative artificial intelligence, the prompt including an instruction to execute a translation process of translating the original text into the specified language according to the specified format input in the specified format input field, when application of the specified format is instructed by selecting an apply button in the specified format input field; a presentation step of presenting the translation on the user terminal, The translation instruction step generates a first prompt for causing the generative artificial intelligence to generate the translation, generates a second prompt for instructing the generative artificial intelligence on the specified format, and causes the generative artificial intelligence to perform processing according to the second prompt as a process separate from the processing according to the first prompt at a timing different from the processing according to the first prompt for generating the translation. causing a computer to execute an information processing method; program.

Images