System

Abstract

An object of a system according to an embodiment is to efficiently perform translation into a plurality of languages and matching confirmation of expressions thereof.SOLUTION: A system according to an embodiment includes a translation unit, an expression matching confirmation unit, and a prompt optimization unit. The translation part automatically translates the announcement sentence into three languages. An expression matching confirmation part confirms whether or not the announcement sentences of the three languages translated by the translation part are matched without any difference in expression. The prompt optimizer makes the process of translation and expression matching more efficient by devising the prompts.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional techniques have had the problem of making it difficult to efficiently translate into multiple languages ​​and check the consistency of the expressions.

[0005] The system according to the embodiment aims to efficiently perform translation into multiple languages ​​and check the consistency of the expressions therein. [Means for solving the problem]

[0006] The system according to the embodiment includes a translation unit, an expression consistency check unit, and a prompt optimization unit. The translation unit automatically translates a notice into three languages. The expression consistency check unit checks whether the notice in the three languages ​​translated by the translation unit matches without any differences in expression. The prompt optimization unit streamlines the translation and expression consistency check processes by devising prompts. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently perform translation into multiple languages ​​and check the consistency of the expressions. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The translation confirmation system according to an embodiment of the present invention automatically translates announcements into three languages, uses a generation AI to check for differences in expression, and improves work speed by providing prompts. This allows the translation confirmation system to efficiently translate announcements in three languages ​​following the LY merger and check for consistency of expression.

[0029] A translation confirmation system according to an embodiment includes a translation unit, an expression consistency check unit, and a prompt optimization unit. The translation unit automatically translates announcements into three languages. For example, a generation AI translates announcements from Japanese to English and Chinese. The generation AI also performs the translation based on prompts that specify the announcement to be translated and the language. The expression consistency check unit checks whether the translated announcements in the three languages ​​are consistent with each other. For example, the generation AI analyzes whether the announcements in Japanese, English, and Chinese have the same meaning. The generation AI also compares the translated announcements in the three languages ​​to evaluate their consistency. The prompt optimization unit streamlines the translation and expression consistency check process by using innovative prompts. For example, the generation AI can use prompts to instruct the AI ​​to perform translation and consistency check simultaneously, thereby eliminating the need for manual confirmation. This allows the translation confirmation system to efficiently translate and confirm the consistency of announcements in three languages ​​following the LY merger. For example, the rapid translation and confirmation of announcements can facilitate smooth communication after the merger. In addition, improved translation accuracy can help prevent misunderstandings and problems.

[0030] The translation unit can design prompts that take cultural background and nuances into account when translating. For example, the translation unit designs prompts that instruct the generation AI to take specific cultural background and nuances into account when translating. For example, when translating the Japanese phrase "Otsukaresama desu" into English, instead of simply saying "Good job," it can be translated as "Thank you for your hard work" depending on the situation. This makes it possible to translate with cultural background and nuances taken into account.

[0031] The translation unit can automatically recognize technical terms or industry-specific expressions and provide appropriate translations. For example, the translation unit designs prompts that instruct the generative AI to automatically recognize specific technical terms or industry-specific expressions and provide appropriate translations based on them. For example, when translating "CT scan" in the medical field into English, it would be translated as "CT scan." This allows for appropriate translation of technical terms and industry-specific expressions.

[0032] The translation unit can increase the number of languages ​​to be translated and design prompts that support multiple languages. For example, the translation unit designs prompts that instruct the generation AI to increase the number of languages ​​to be translated and support more languages. For example, translating from Japanese to English, Chinese, French, and Spanish. This makes it possible to translate into more languages.

[0033] The translation unit can take voice input and perform translation directly from the voice. For example, the translation unit designs prompts that instruct the generation AI to take voice input and perform translation directly from the voice. For example, Japanese voice is translated into English text. This makes it possible to perform translation directly from the voice.

[0034] The expression matching unit can design prompts that evaluate the grammatical and structural similarity of the translated sentence in detail. The expression matching unit, for example, designs prompts that instruct the generation AI to evaluate the grammatical and structural similarity of the translated sentence in detail. For example, the grammatical structures of Japanese, English, and Chinese are compared and the degree of similarity is evaluated. This allows the grammatical and structural similarity of the translated sentence to be evaluated in detail.

[0035] The expression matching unit can perform flexible matching evaluation based on synonyms or similar words when checking the matching of translated sentences. For example, the expression matching unit designs prompts that instruct the generation AI to consider synonyms or similar words when checking the matching of translated sentences. For example, the English words "happy" and "joyful" are treated as synonyms. This enables flexible matching evaluation that takes synonyms and similar words into consideration.

[0036] The expression matching unit can design prompts so that matching of translated sentences can be applied to documents in different fields or industries. For example, the expression matching unit designs prompts that instruct the generation AI so that matching of translated sentences can be applied to documents in different fields or industries. For example, it can also be used for documents in the medical and legal fields. This enables matching that can be applied to documents in different fields or industries.

[0037] The expression matching unit can perform a comprehensive matching evaluation that includes non-text information such as images or charts when checking the matching of translated sentences. For example, the expression matching unit designs a prompt that instructs the generation AI to include non-text information such as images or charts when checking the matching of translated sentences. This corresponds to the translation of presentation materials, for example. This enables a comprehensive matching evaluation that includes non-text information.

[0038] The prompt optimization unit uses the generation AI to optimize the prompt and can design a prompt that simultaneously performs the translation and match confirmation processes. For example, the prompt optimization unit designs a prompt that instructs the generation AI to simultaneously perform the translation and match confirmation processes. For example, a Japanese notice is translated into English and Chinese, and the degree of match is evaluated simultaneously. This makes it possible to simultaneously perform the translation and match confirmation processes.

[0039] The prompt optimization unit can refer to the user's past translation history in the prompt to perform optimal translation and match confirmation. For example, the prompt optimization unit designs a prompt that instructs the generation AI to refer to the user's past translation history to perform optimal translation and match confirmation. For example, it translates a similar notice based on the past translation history. This makes it possible to perform optimal translation and match confirmation by referring to the user's past translation history.

[0040] The prompt optimization unit can create prompts that can be applied to different business processes by devising the prompts. For example, the prompt optimization unit designs prompts that instruct the generation AI so that they can be applied to different business processes by devising the prompts. For example, it can be used not only for translation work, but also for data analysis and report creation. This makes it possible to design prompts that can be applied to different business processes.

[0041] The prompt optimization unit can add a function to the prompt that reflects user feedback in real time and dynamically optimizes the prompt. For example, the prompt optimization unit designs a prompt that instructs the generation AI to reflect user feedback in real time and dynamically optimize the prompt. For example, the prompt is adjusted based on user opinions. This makes it possible to reflect user feedback in real time and dynamically optimize the prompt.

[0042] The translation unit can automatically analyze user feedback and create prompts to improve the translation results. For example, the translation unit designs prompts that instruct the generation AI to automatically analyze user feedback and improve the translation results. For example, the translation is revised based on user feedback. This allows the user feedback to be automatically analyzed and the translation results to be improved.

[0043] The translation unit can make corrections based on the user's expertise or background information during the feedback process. For example, the translation unit designs prompts that instruct the generation AI to take the user's expertise and background information into consideration during the feedback process. For example, the translation unit reflects technical terms and industry-specific expressions. This enables corrections that take the user's expertise and background information into consideration.

[0044] The translation department can create prompts so that the feedback and correction process can be applied to different business processes. For example, the translation department designs prompts that instruct the generation AI so that the feedback and correction process can be applied to different business processes. For example, this also applies to data analysis and report creation. This makes it possible to design a feedback and correction process that can be applied to different business processes.

[0045] The translation unit can add a function to reflect user feedback in real time during the feedback process and dynamically correct the translation results. For example, the translation unit designs prompts that instruct the generation AI to reflect user feedback in real time and dynamically correct the translation results. For example, it immediately corrects mistranslations pointed out by the user. This allows the translation results to be dynamically corrected by reflecting user feedback in real time.

[0046] The translation unit can create prompts that automatically classify the translation history and save it in a format that is easy to reuse. For example, the translation unit designs prompts that instruct the generation AI to automatically classify the translation history and save it in a format that is easy to reuse. For example, by classification by type of notice or language. This allows the translation history to be automatically classified and saved in a format that is easy to reuse.

[0047] The translation unit can add a function that considers the user's past feedback when saving the translation history and selects the most appropriate translation history. For example, the translation unit designs a prompt that instructs the generation AI to consider the user's past feedback when saving the translation history. For example, the translation unit prioritizes saving translation histories that the user has given high ratings. This allows the optimal translation history to be selected by considering the user's past feedback.

[0048] The translation department can create prompts so that the process of saving and reusing translation history can be applied to different business processes. For example, the translation department designs prompts that instruct the generation AI so that the process of saving and reusing translation history can be applied to different business processes. For example, this also applies to data analysis and report creation. This makes it possible to design a process of saving and reusing translation history that can be applied to different business processes.

[0049] The translation unit can add a function to reflect user feedback in real time when saving the translation history and dynamically optimize the translation history. For example, the translation unit designs a prompt that instructs the generation AI to reflect user feedback in real time and dynamically optimize the translation history. For example, the translation history is adjusted based on the user's opinion. This allows the user's feedback to be reflected in real time and the translation history to be dynamically optimized.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The translation confirmation system can further include a speech recognition unit that converts a user's voice input into text. The speech recognition unit converts, for example, Japanese speech spoken by the user into text and sends the text to the translation unit. This allows the user to input and translate announcements by voice without using a keyboard. For example, the content spoken during a meeting can be translated in real time and provided to participants. The speech recognition unit can also handle different accents and dialects. This makes it possible to meet the needs of a wider variety of users.

[0052] The translation confirmation system may further include a quality evaluation unit that evaluates the quality of the translation. The quality evaluation unit evaluates, for example, the grammatical accuracy and naturalness of the translation and assigns a score. This allows the user to check the quality of the translation at a glance. For example, the quality evaluation unit may evaluate whether the translation is expressed naturally and display a score. The quality evaluation unit may also improve the quality of the translation based on user feedback. This allows the quality of the translation to be continuously improved.

[0053] The translation confirmation system can further include a context understanding unit that understands the context of the translated text and performs an appropriate translation. The context understanding unit, for example, analyzes the context before and after the translated text and performs an appropriate translation. This enables natural translation according to the context. For example, when the same word has different meanings depending on the context, it can select an appropriate translation. The context understanding unit can also handle technical terms and industry-specific expressions. This enables more accurate and natural translation.

[0054] The translation confirmation system may further include a readability evaluation unit that evaluates the readability of the translation. The readability evaluation unit may, for example, evaluate the length and complexity of the translation and assign a score. This allows the user to check the readability of the translation at a glance. For example, the readability evaluation unit may evaluate whether the translation is concise and easy to understand and display a score. The readability evaluation unit may also improve the readability of the translation based on user feedback. This allows the readability of the translation to be continuously improved.

[0055] The translation verification system may further include a consistency evaluation unit that evaluates the consistency of the translation. The consistency evaluation unit, for example, evaluates whether the terms and expressions used in the translation are consistent and assigns a score. This allows the user to check the consistency of the translation at a glance. For example, the consistency evaluation unit evaluates whether the same term is expressed differently in different translations and displays a score. The consistency evaluation unit can also improve the consistency of the translation based on user feedback. This allows the consistency of the translation to be continuously improved.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The translation unit automatically translates the announcement into three languages. For example, the generation AI translates the announcement from Japanese to English and Chinese. The generation AI also translates based on prompts that include the announcement to be translated and the language in which it is to be translated. Step 2: The expression consistency checker verifies whether the translated announcements in the three languages ​​are consistent and expressive. For example, the generation AI analyzes whether announcements in Japanese, English, and Chinese have the same meaning. The generation AI also compares the translated announcements in the three languages ​​to assess their consistency. Step 3: The prompt optimization unit streamlines the translation and expression matching process by using innovative prompts. For example, the generation AI can use prompts to instruct translation and matching in one go, eliminating the need for manual checking.

[0058] (Example 2) The translation confirmation system according to an embodiment of the present invention automatically translates announcements into three languages, uses a generation AI to check for differences in expression, and improves work speed by providing prompts. This allows the translation confirmation system to efficiently translate announcements in three languages ​​following the LY merger and check for consistency of expression.

[0059] A translation confirmation system according to an embodiment includes a translation unit, an expression consistency check unit, and a prompt optimization unit. The translation unit automatically translates announcements into three languages. For example, a generation AI translates announcements from Japanese to English and Chinese. The generation AI also performs the translation based on prompts that specify the announcement to be translated and the language. The expression consistency check unit checks whether the translated announcements in the three languages ​​are consistent with each other. For example, the generation AI analyzes whether the announcements in Japanese, English, and Chinese have the same meaning. The generation AI also compares the translated announcements in the three languages ​​to evaluate their consistency. The prompt optimization unit streamlines the translation and expression consistency check process by using innovative prompts. For example, the generation AI can use prompts to instruct the AI ​​to perform translation and consistency check simultaneously, thereby eliminating the need for manual confirmation. This allows the translation confirmation system to efficiently translate and confirm the consistency of announcements in three languages ​​following the LY merger. For example, the rapid translation and confirmation of announcements can facilitate smooth communication after the merger. In addition, improved translation accuracy can help prevent misunderstandings and problems.

[0060] The translation unit can design prompts that take cultural background and nuances into account when translating. For example, the translation unit designs prompts that instruct the generation AI to take specific cultural background and nuances into account when translating. For example, when translating the Japanese phrase "Otsukaresama desu" into English, instead of simply saying "Good job," it can be translated as "Thank you for your hard work" depending on the situation. This makes it possible to translate with cultural background and nuances taken into account.

[0061] The translation unit can automatically recognize technical terms or industry-specific expressions and provide appropriate translations. For example, the translation unit designs prompts that instruct the generative AI to automatically recognize specific technical terms or industry-specific expressions and provide appropriate translations based on them. For example, when translating "CT scan" in the medical field into English, it would be translated as "CT scan." This allows for appropriate translation of technical terms and industry-specific expressions.

[0062] The translation unit can use the emotion estimation function to evaluate the emotional impact that a translated sentence has on the user and perform a translation that elicits positive emotions. For example, the translation unit designs prompts that instruct the generation AI to use the emotion estimation function when translating to evaluate the emotional impact that a translated sentence has on the user. For example, it avoids negative expressions and selects positive expressions. This enables a translation that elicits positive emotions.

[0063] The translation unit can increase the number of languages ​​to be translated and design prompts that support multiple languages. For example, the translation unit designs prompts that instruct the generation AI to increase the number of languages ​​to be translated and support more languages. For example, translating from Japanese to English, Chinese, French, and Spanish. This makes it possible to translate into more languages.

[0064] The translation unit can take voice input and perform translation directly from the voice. For example, the translation unit designs prompts that instruct the generation AI to take voice input and perform translation directly from the voice. For example, Japanese voice is translated into English text. This makes it possible to perform translation directly from the voice.

[0065] The translation unit can use the emotion estimation function to evaluate how a translated sentence will be received in different cultural spheres and perform culturally appropriate translations. For example, the translation unit uses the emotion estimation function to design prompts that instruct the generation AI to evaluate how a translated sentence will be received in different cultural spheres. For example, the translation unit translates the Japanese phrase "Otsukaresama desu" into English as "Thank you for your hard work." This enables culturally appropriate translations.

[0066] The expression matching unit can design prompts that evaluate the grammatical and structural similarity of the translated sentence in detail. The expression matching unit, for example, designs prompts that instruct the generation AI to evaluate the grammatical and structural similarity of the translated sentence in detail. For example, the grammatical structures of Japanese, English, and Chinese are compared and the degree of similarity is evaluated. This allows the grammatical and structural similarity of the translated sentence to be evaluated in detail.

[0067] The expression matching unit can perform flexible matching evaluation based on synonyms or similar words when checking the matching of translated sentences. For example, the expression matching unit designs prompts that instruct the generation AI to consider synonyms or similar words when checking the matching of translated sentences. For example, the English words "happy" and "joyful" are treated as synonyms. This enables flexible matching evaluation that takes synonyms and similar words into consideration.

[0068] The expression matching unit can use the emotion estimation function to evaluate the emotional impact that the translated sentence has on the user and confirm whether or not there is an emotional match. For example, the expression matching unit designs a prompt that instructs the generation AI to evaluate the emotional impact that the translated sentence has on the user. For example, it translates the Japanese phrase "arigatou" (thank you) into English and evaluates whether or not there is an emotional match. This makes it possible to confirm whether or not there is an emotional match.

[0069] The expression matching unit can design prompts so that matching of translated sentences can be applied to documents in different fields or industries. For example, the expression matching unit designs prompts that instruct the generation AI so that matching of translated sentences can be applied to documents in different fields or industries. For example, it can also be used for documents in the medical and legal fields. This enables matching that can be applied to documents in different fields or industries.

[0070] The expression matching unit can perform a comprehensive matching evaluation that includes non-text information such as images or charts when checking the matching of translated sentences. For example, the expression matching unit designs a prompt that instructs the generation AI to include non-text information such as images or charts when checking the matching of translated sentences. This corresponds to the translation of presentation materials, for example. This enables a comprehensive matching evaluation that includes non-text information.

[0071] The expression matching verification unit can use the emotion estimation function to evaluate how the translated sentence will be received in the cultural sphere and verify whether or not there is cultural consistency. For example, the expression matching verification unit designs a prompt that instructs the generation AI to use the emotion estimation function to evaluate how the translated sentence will be received in a different cultural sphere. For example, the unit translates the Japanese phrase "otsukaresama desu" into English as "Thank you for your hard work" and evaluates whether or not there is cultural consistency. This allows for verification of whether or not there is cultural consistency.

[0072] The prompt optimization unit uses the generation AI to optimize the prompt and can design a prompt that simultaneously performs the translation and match confirmation processes. For example, the prompt optimization unit designs a prompt that instructs the generation AI to simultaneously perform the translation and match confirmation processes. For example, a Japanese notice is translated into English and Chinese, and the degree of match is evaluated simultaneously. This makes it possible to simultaneously perform the translation and match confirmation processes.

[0073] The prompt optimization unit can refer to the user's past translation history in the prompt to perform optimal translation and match confirmation. For example, the prompt optimization unit designs a prompt that instructs the generation AI to refer to the user's past translation history to perform optimal translation and match confirmation. For example, it translates a similar notice based on the past translation history. This makes it possible to perform optimal translation and match confirmation by referring to the user's past translation history.

[0074] The prompt optimization unit can use the emotion estimation function to evaluate the emotional impact of a prompt on the user and create a prompt that elicits positive emotions. For example, the prompt optimization unit designs a prompt that instructs the generation AI to evaluate the emotional impact of the prompt on the user. For example, it selects expressions that elicit positive emotions. This makes it possible to design a prompt that elicits positive emotions.

[0075] The prompt optimization unit can create prompts that can be applied to different business processes by devising the prompts. For example, the prompt optimization unit designs prompts that instruct the generation AI so that they can be applied to different business processes by devising the prompts. For example, it can be used not only for translation work, but also for data analysis and report creation. This makes it possible to design prompts that can be applied to different business processes.

[0076] The prompt optimization unit can add a function to the prompt that reflects user feedback in real time and dynamically optimizes the prompt. For example, the prompt optimization unit designs a prompt that instructs the generation AI to reflect user feedback in real time and dynamically optimize the prompt. For example, the prompt is adjusted based on user opinions. This makes it possible to reflect user feedback in real time and dynamically optimize the prompt.

[0077] The prompt optimization unit can use the emotion estimation function to evaluate how the prompt will be received in the cultural sphere and create the culturally appropriate prompt. For example, the prompt optimization unit designs a prompt that instructs the generation AI to use the emotion estimation function to evaluate how the prompt will be received in different cultural spheres. For example, the prompt optimization unit translates a Japanese prompt into English or Chinese and evaluates whether it is culturally appropriate. This makes it possible to design a culturally appropriate prompt.

[0078] The translation unit can automatically analyze user feedback and create prompts to improve the translation results. For example, the translation unit designs prompts that instruct the generation AI to automatically analyze user feedback and improve the translation results. For example, the translation is revised based on user feedback. This allows the user feedback to be automatically analyzed and the translation results to be improved.

[0079] The translation unit can make corrections based on the user's expertise or background information during the feedback process. For example, the translation unit designs prompts that instruct the generation AI to take the user's expertise and background information into consideration during the feedback process. For example, the translation unit reflects technical terms and industry-specific expressions. This enables corrections that take the user's expertise and background information into consideration.

[0080] The translation unit can use the emotion estimation function to evaluate the emotional impact that feedback has on the user and provide feedback that elicits positive emotions. For example, the translation unit designs prompts that instruct the generation AI to evaluate the emotional impact that feedback has on the user. For example, it selects expressions that elicit positive emotions. This enables feedback that elicits positive emotions.

[0081] The translation department can create prompts so that the feedback and correction process can be applied to different business processes. For example, the translation department designs prompts that instruct the generation AI so that the feedback and correction process can be applied to different business processes. For example, this also applies to data analysis and report creation. This makes it possible to design a feedback and correction process that can be applied to different business processes.

[0082] The translation unit can add a function to reflect user feedback in real time during the feedback process and dynamically correct the translation results. For example, the translation unit designs prompts that instruct the generation AI to reflect user feedback in real time and dynamically correct the translation results. For example, it immediately corrects mistranslations pointed out by the user. This allows the translation results to be dynamically corrected by reflecting user feedback in real time.

[0083] The translation unit can use the emotion estimation function to evaluate how the feedback will be received in the cultural sphere and provide the culturally appropriate feedback. For example, the translation unit uses the emotion estimation function to design prompts that instruct the generation AI to evaluate how the feedback will be received in different cultural spheres. For example, the translation unit translates Japanese feedback into English or Chinese and evaluates whether it is culturally appropriate. This enables culturally appropriate feedback.

[0084] The translation unit can create prompts that automatically classify the translation history and save it in a format that is easy to reuse. For example, the translation unit designs prompts that instruct the generation AI to automatically classify the translation history and save it in a format that is easy to reuse. For example, by classification by type of notice or language. This allows the translation history to be automatically classified and saved in a format that is easy to reuse.

[0085] The translation unit can add a function that considers the user's past feedback when saving the translation history and selects the most appropriate translation history. For example, the translation unit designs a prompt that instructs the generation AI to consider the user's past feedback when saving the translation history. For example, the translation unit prioritizes saving translation histories that the user has given high ratings. This allows the optimal translation history to be selected by considering the user's past feedback.

[0086] The translation unit can add a function to use the emotion estimation function to evaluate the emotional impact that a translation history has on a user and save translation history that elicits positive emotions. For example, the translation unit designs a prompt that instructs the generation AI to use the emotion estimation function to evaluate the emotional impact that a translation history has on a user. For example, translation history that elicits positive emotions is preferentially saved. This makes it possible to save translation history that elicits positive emotions.

[0087] The translation department can create prompts so that the process of saving and reusing translation history can be applied to different business processes. For example, the translation department designs prompts that instruct the generation AI so that the process of saving and reusing translation history can be applied to different business processes. For example, this also applies to data analysis and report creation. This makes it possible to design a process of saving and reusing translation history that can be applied to different business processes.

[0088] The translation unit can add a function to reflect user feedback in real time when saving the translation history and dynamically optimize the translation history. For example, the translation unit designs a prompt that instructs the generation AI to reflect user feedback in real time and dynamically optimize the translation history. For example, the translation history is adjusted based on the user's opinion. This allows the user's feedback to be reflected in real time and the translation history to be dynamically optimized.

[0089] The translation unit can add a function to use an emotion estimation function to evaluate how the translation history will be received in the cultural sphere and store the culturally appropriate translation history. For example, the translation unit designs a prompt that instructs the generation AI to use the emotion estimation function to evaluate how the translation history will be received in different cultural spheres. For example, the translation unit translates a Japanese translation history into English or Chinese and evaluates whether it is culturally appropriate. This allows the culturally appropriate translation history to be stored.

[0090] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0091] The translation confirmation system can further include a speech recognition unit that converts a user's voice input into text. The speech recognition unit converts, for example, Japanese speech spoken by the user into text and sends the text to the translation unit. This allows the user to input and translate announcements by voice without using a keyboard. For example, the content spoken during a meeting can be translated in real time and provided to participants. The speech recognition unit can also handle different accents and dialects. This makes it possible to meet the needs of a wider variety of users.

[0092] The translation confirmation system can further include an emotion adjustment unit that estimates the user's emotion and adjusts the tone of the translation based on the estimated emotion. For example, if the user is angry, the emotion adjustment unit adjusts the tone of the translation to be gentler. This makes it possible to avoid emotional misunderstandings. For example, when translating an email responding to a complaint, the emotion adjustment unit can translate the text in an appropriate tone, taking into account the user's emotion. Furthermore, if the user is happy, the emotion adjustment unit can add positive expressions to the translation. This makes it possible to provide an appropriate translation that matches the user's emotion.

[0093] The translation confirmation system may further include a quality evaluation unit that evaluates the quality of the translation. The quality evaluation unit evaluates, for example, the grammatical accuracy and naturalness of the translation and assigns a score. This allows the user to check the quality of the translation at a glance. For example, the quality evaluation unit may evaluate whether the translation is expressed naturally and display a score. The quality evaluation unit may also improve the quality of the translation based on user feedback. This allows the quality of the translation to be continuously improved.

[0094] The translation confirmation system may further include an emotional expression adjustment unit that estimates the user's emotions and adjusts the expression of the translated text based on the estimated emotions. For example, if the user is sad, the emotional expression adjustment unit adjusts the expression of the translated text to be gentler. This enables translation that takes the user's emotions into consideration. For example, when translating a message of comfort, the emotional expression adjustment unit can translate it using appropriate expressions taking the user's emotions into consideration. Furthermore, if the user is excited, the emotional expression adjustment unit can add energetic expressions to the translated text. This enables appropriate translation that corresponds to the user's emotions.

[0095] The translation confirmation system can further include a context understanding unit that understands the context of the translated text and performs an appropriate translation. The context understanding unit, for example, analyzes the context before and after the translated text and performs an appropriate translation. This enables natural translation according to the context. For example, when the same word has different meanings depending on the context, it can select an appropriate translation. The context understanding unit can also handle technical terms and industry-specific expressions. This enables more accurate and natural translation.

[0096] The translation confirmation system can further include a style adjustment unit that estimates the user's emotions and adjusts the style of the translation based on the estimated emotions. For example, the style adjustment unit adjusts the style of the translation to be more formal when the user intends to use it in a formal situation. This enables an appropriate translation depending on the situation. For example, when translating a business email, the translation can be made using formal expressions taking the user's emotions into consideration. The style adjustment unit can also adjust the style of the translation to be more casual when the user intends to use it in a casual situation. This enables an appropriate translation depending on the user's emotions.

[0097] The translation confirmation system may further include a readability evaluation unit that evaluates the readability of the translation. The readability evaluation unit may, for example, evaluate the length and complexity of the translation and assign a score. This allows the user to check the readability of the translation at a glance. For example, the readability evaluation unit may evaluate whether the translation is concise and easy to understand and display a score. The readability evaluation unit may also improve the readability of the translation based on user feedback. This allows the readability of the translation to be continuously improved.

[0098] The translation confirmation system may further include a format adjustment unit that estimates the user's emotions and adjusts the format of the translation based on the estimated emotions. For example, if the user intends to use the system in an emergency, the format adjustment unit adjusts the format of the translation to be simpler. This enables appropriate translation in an emergency. For example, when translating an emergency notice, the translation can be made simpler, taking the user's emotions into consideration. The format adjustment unit can also make the format of the translation more detailed if the user requires more detailed explanations. This enables appropriate translation according to the user's emotions.

[0099] The translation verification system may further include a consistency evaluation unit that evaluates the consistency of the translation. The consistency evaluation unit, for example, evaluates whether the terms and expressions used in the translation are consistent and assigns a score. This allows the user to check the consistency of the translation at a glance. For example, the consistency evaluation unit evaluates whether the same term is expressed differently in different translations and displays a score. The consistency evaluation unit can also improve the consistency of the translation based on user feedback. This allows the consistency of the translation to be continuously improved.

[0100] The translation confirmation system can further include a layout adjustment unit that estimates the user's emotions and adjusts the layout of the translation based on the estimated emotions. For example, when the user is in a relaxed state, the layout adjustment unit adjusts the layout of the translation to make it easier to read. This enables appropriate translation in a relaxed state. For example, when translating an email with a relaxed atmosphere, the translation can be made in an easy-to-read layout that takes the user's emotions into consideration. The layout adjustment unit can also simplify the layout of the translation when the user is in a tense state. This enables appropriate translation according to the user's emotions.

[0101] The processing flow of the second embodiment will be briefly explained below.

[0102] Step 1: The translation unit automatically translates the announcement into three languages. For example, the generation AI translates the announcement from Japanese to English and Chinese. The generation AI also translates based on prompts that include the announcement to be translated and the language in which it is to be translated. Step 2: The expression consistency checker verifies whether the translated announcements in the three languages ​​are consistent and expressive. For example, the generation AI analyzes whether announcements in Japanese, English, and Chinese have the same meaning. The generation AI also compares the translated announcements in the three languages ​​to assess their consistency. Step 3: The prompt optimization unit streamlines the translation and expression matching process by using innovative prompts. For example, the generation AI can use prompts to instruct translation and matching in one go, eliminating the need for manual checking.

[0103] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0104] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0105] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0106] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0107] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0108] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0109] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0110] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0111] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0112] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0113] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0114] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0115] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0116] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0117] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0118] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0119] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0120] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0121] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0122] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0123] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0124] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0125] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0126] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0127] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0128] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0129] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0130] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0131] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0132] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0133] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0134] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0135] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0136] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0137] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0138] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0139] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0140] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0141] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0142] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0143] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0144] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0145] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0146] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0147] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0148] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0149] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0150] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0151] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0152] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0153] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0154] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0155] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0156] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0157] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0158] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0159] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0160] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0161] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0162] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0163] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0164] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0165] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0166] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0167] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0168] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0169] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0170] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A translation department that automatically translates announcements into three languages, an expression consistency check unit that checks whether the three language notices translated by the translation unit are consistent with each other; A prompt optimization unit that streamlines the translation and expression match confirmation process by devising prompts. A system characterized by:

2. The translation unit Automatically recognize technical or industry-specific terms and translate them appropriately 2. The system of claim 1.

3. The translation unit Introducing voice input and direct translation from your voice 2. The system of claim 1.

4. The expression matching verification unit Design prompts to thoroughly evaluate the grammatical and structural match of the translation 2. The system of claim 1.

5. The prompt optimization unit: Using generative AI to optimize the prompts and design prompts that simultaneously perform the translation and match checking processes.

2. The system of claim 1.

6. The translation unit Evaluate the emotional impact of the translation on the user and perform translations that elicit positive emotions 2. The system of claim 1.

7. The expression matching verification unit Evaluate the emotional impact of the translation on the user and ensure it matches emotionally 2. The system of claim 1.

8. The prompt optimization unit: Evaluate the emotional impact of the prompts on users and create prompts that elicit positive emotions 2. The system of claim 1.

Images