System

Abstract

An object of a system according to an embodiment is to automatically generate a text to be transmitted in a chat or an e-mail and to reduce time and effort of a user.SOLUTION: A system includes a reading unit, a generation unit, and a proposal unit. The reading unit reads a chat conversation. The generation unit generates an appropriate proposed answer sentence based on the conversation read by the reading unit. The proposal unit proposes the sentence proposal generated by the generation unit to the user.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 technologies have had the problem that when chat or email messages are automatically generated, users have to manually create the messages, which is time-consuming.

[0005] The system according to the embodiment aims to automatically generate chat and email messages to be sent, thereby reducing the user's workload. [Means for solving the problem]

[0006] The system according to the embodiment includes a reading unit, a generating unit, and a suggesting unit. The reading unit reads chat conversations. The generating unit generates appropriate answer suggestions based on the conversations read by the reading unit. The suggesting unit suggests the suggestions generated by the generating unit to a user. [Effects of the Invention]

[0007] The system according to the embodiment can automatically generate chat and email messages, thereby reducing the user's workload. [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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[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 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[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) An automatic generation system according to an embodiment of the present invention automatically generates messages to be sent, such as chats and emails. In this automatic generation system, a generation AI reads all chat conversations and suggests appropriate response texts in a pop-up window. A user can send the suggested texts with just one click of a button. Furthermore, by entering a rough sentence in the field displayed in the pop-up window, the generation AI rewrites the sentence into a more appropriate text for sending and suggests it. For example, in the automatic generation system, a generation AI reads chat conversations. The generation AI analyzes the context and content of the conversation and generates an appropriate response text. For example, if a user asks, "What time does tomorrow's meeting start?", the generation AI generates a response text such as, "Tomorrow's meeting starts at 10:00 AM." The generated response text is then suggested to the user in a pop-up window. The user can review the suggested text and send it with just one click of a button. This allows the user to quickly and easily send an appropriate response. Furthermore, by entering a rough sentence in the field displayed in the pop-up window, the generation AI rewrites the sentence into a more appropriate text for sending and suggests it. For example, if a user types "What time is the meeting?", the generation AI will rewrite it into a more appropriate sentence to send, such as "What time does tomorrow's meeting start?", and suggest it. This allows users to easily create and send appropriate sentences. This allows the automatic generation system to quickly and easily generate and send chat and email messages. For example, in business situations, where quick responses are required, this system can be used to communicate efficiently. In private situations, too, the quality of communication is improved because appropriate sentences can be easily created and sent.

[0029] An automatic generation system according to an embodiment includes a reading unit, a generating unit, and a suggesting unit. The reading unit reads chat conversations. The reading unit analyzes the chat conversations using, for example, a generation AI to understand the context and content. The reading unit can also enable the generation AI to extract keywords and important phrases from the conversation. For example, the reading unit inputs a prompt such as "Please extract the main points of this conversation" to the generation AI to extract the main points of the conversation. The generation unit generates an appropriate answer proposal based on the conversation read by the reading unit. The generation unit analyzes the context and content of the conversation using, for example, the generation AI to generate an appropriate answer proposal. For example, the generation unit inputs a prompt such as "Please generate an appropriate answer to this conversation" to the generation AI to generate an answer proposal. The suggesting unit suggests the proposed sentences generated by the generation unit to a user. For example, the suggesting unit displays the generated proposed sentences in a pop-up. The suggesting unit can also allow a user to submit a sentence by clicking a button. For example, the suggestion unit displays the generated text suggestion in a pop-up window, and the user can click a button to send the text suggestion. This allows the automatic generation system according to the embodiment to automatically read chat conversations, generate appropriate response text suggestions, and suggest them to the user.

[0030] The suggestion unit can display the generated sentence suggestions in a pop-up. For example, the suggestion unit displays the generated sentence suggestions in a pop-up. The pop-up is displayed, for example, in the center of the screen. The suggestion unit can also adjust the timing of displaying the pop-up. For example, the suggestion unit displays the pop-up immediately after the user ends the chat. The suggestion unit can also adjust the display position of the pop-up. For example, the suggestion unit displays the pop-up in accordance with the user's line of sight. In this way, by displaying the generated sentence suggestions in a pop-up, the user can easily check them.

[0031] The suggestion unit can send a text by the user clicking a button. The suggestion unit, for example, sends a text by the user clicking a button. The button is displayed, for example, in a pop-up. The suggestion unit can also adjust the number of clicks of the button. For example, the suggestion unit can send a text with just one click by the user. The suggestion unit can also adjust the type of button. For example, the suggestion unit can display a send button in a large size so that the user can easily click it. This allows the user to send a text by just clicking the button.

[0032] The automatic generation system according to the embodiment includes an input unit for inputting simple sentences. The input unit allows a user to input simple sentences. Simple sentences include, but are not limited to, short sentences and the use of simple words. The input unit, for example, provides a text box to allow a user to input simple sentences. The input unit can also support voice input. For example, the input unit converts the user's voice into text using a microphone. The input unit can also support image input. For example, the input unit allows a user to take a photo of a handwritten note with a camera and convert the image into text. This allows a user to input simple sentences.

[0033] The input unit may include a rewriting unit that rewrites simple sentences into appropriate sentences. The rewriting unit can rewrite simple sentences input by a user into appropriate sentences. Appropriate sentences include, but are not limited to, grammatically correct sentences and sentences with related content. The rewriting unit rewrites simple sentences into appropriate sentences, for example, using a generation AI. For example, the rewriting unit inputs a prompt to the generation AI, such as "Please rewrite this sentence into an appropriate sentence," to generate the appropriate sentence. The rewriting unit can also analyze the context and keywords of sentences input by a user and rewrite them into appropriate sentences. For example, the rewriting unit uses a generation AI to analyze the context and keywords of the sentence and generate appropriate sentences. This allows simple sentences input by a user to be rewritten into appropriate sentences.

[0034] The generation unit may include an analysis unit that analyzes the conversation context and keywords. The analysis unit can analyze the conversation context and keywords. Context includes, for example, surrounding sentences and related topics, but is not limited to, examples. The analysis unit analyzes the conversation context using, for example, a generation AI. For example, the analysis unit inputs a prompt to the generation AI, such as "Please analyze the context of this conversation," and analyzes the context. The analysis unit can also extract keywords. Keywords include, for example, frequently occurring words and words extracted by co-occurrence network analysis, but are not limited to, examples. The analysis unit extracts keywords using, for example, a generation AI. For example, the analysis unit inputs a prompt to the generation AI, such as "Please extract keywords from this conversation," and extracts keywords. This allows the conversation context and keywords to be analyzed.

[0035] The rewriting unit can rewrite simple sentences input by a user into appropriate sentences. For example, the rewriting unit rewrites simple sentences input by a user into appropriate sentences. Simple sentences include, but are not limited to, short sentences and the use of simple words. The rewriting unit rewrites simple sentences into appropriate sentences, for example, using a generation AI. For example, the rewriting unit inputs a prompt to the generation AI, such as "Please rewrite this sentence into an appropriate sentence," to generate an appropriate sentence. The rewriting unit can also analyze the context and keywords of sentences input by a user and rewrite them into appropriate sentences. For example, the rewriting unit uses a generation AI to analyze the context and keywords of the sentence and generate an appropriate sentence. This allows simple sentences input by a user to be rewritten into appropriate sentences.

[0036] The reading unit can determine the reading priority based on the importance of the conversation when reading. For example, the reading unit determines the reading priority based on the importance of the conversation when reading. Importance includes, but is not limited to, the content and relevance of the conversation. The reading unit, for example, uses a generation AI to evaluate the importance of the conversation. For example, the reading unit inputs a prompt such as "Please rate the importance of this conversation" to the generation AI and evaluates the importance. The reading unit can also determine the reading priority based on the importance. For example, conversations regarding important meeting schedules are read with priority. Conversations regarding urgent requests or questions are read with priority. Everyday chatter and unimportant conversations are read later. In this way, the reading priority can be determined based on the importance of the conversation.

[0037] The reading unit can apply different reading algorithms depending on the category of the conversation when reading. For example, the reading unit applies different reading algorithms depending on the category of the conversation when reading. Categories include, but are not limited to, business-related, private, and technical conversations. The reading unit, for example, uses a generation AI to determine the category of the conversation. For example, the reading unit inputs a prompt such as "Please determine the category of this conversation" to the generation AI and determines the category. The reading unit can also apply different reading algorithms depending on the category. For example, an algorithm that takes technical terminology and business context into account is applied to business-related conversations. An algorithm that takes casual expressions and everyday context into account is applied to private conversations. An algorithm that takes technical terminology and specialized knowledge into account is applied to technical conversations. This makes it possible to apply different reading algorithms depending on the category of the conversation.

[0038] The reading unit can improve the accuracy of reading by referring to the user's past conversation history when reading. For example, the reading unit can improve the accuracy of reading by referring to the user's past conversation history when reading. The past conversation history includes, for example, phrases and expressions frequently used by the user in the past, but is not limited to such examples. The reading unit, for example, analyzes the past conversation history using a generation AI. For example, the reading unit inputs a prompt to the generation AI, such as "Please analyze this user's past conversation history," and analyzes the conversation history. The reading unit can also improve the accuracy of reading by referring to the past conversation history. For example, the reading unit improves the accuracy of reading by referring to phrases and expressions frequently used by the user in the past. The reading unit deepens understanding of specific contexts and topics from the user's past conversation history. The reading unit provides context to avoid misunderstandings based on the user's past conversation history. This makes it possible to improve the accuracy of reading by referring to the user's past conversation history.

[0039] The reading unit can prioritize reading highly relevant conversations by taking into account the geographical background of the conversation when reading. For example, the reading unit prioritizes reading highly relevant conversations by taking into account the geographical background of the conversation when reading. The geographical background includes, for example, the user's location information and regional characteristics, but is not limited to such examples. The reading unit analyzes the geographical background using, for example, a generation AI. For example, the reading unit inputs a prompt such as "Please analyze this user's geographical background" to the generation AI and analyzes the geographical background. The reading unit can also prioritize reading highly relevant conversations by taking into account the geographical background. For example, if the user is in a specific region, conversations related to that region are prioritized. If the user is traveling, conversations related to the travel destination are prioritized. If the user is on a business trip, conversations related to the business trip destination are prioritized. This makes it possible to prioritize reading highly relevant conversations by taking into account the geographical background of the conversation.

[0040] The reading unit can analyze the user's social media activity and read related conversations during reading. For example, the reading unit analyzes the user's social media activity and reads related conversations during reading. Social media activity includes, for example, the content of the user's posts and the frequency of activity, but is not limited to these examples. The reading unit analyzes the social media activity using, for example, a generation AI. For example, the reading unit inputs a prompt such as "Please analyze this user's social media activity" into the generation AI and analyzes the social media activity. The reading unit can also analyze the social media activity and read related conversations. For example, the reading unit prioritizes reading conversations related to topics mentioned by the user on social media. The reading unit analyzes the content of the user's social media posts and reads related conversations. Related conversations are read based on the activity of the user's friends on social media. In this way, the user's social media activity can be analyzed and related conversations can be read.

[0041] The reading unit can customize the reading method by reflecting the user's past feedback when reading. For example, the reading unit customizes the reading method by reflecting the user's past feedback when reading. Past feedback includes, but is not limited to, feedback provided by the user in the past. The reading unit analyzes the past feedback using, for example, a generation AI. For example, the reading unit inputs a prompt such as "Please analyze this user's past feedback" to the generation AI and analyzes the feedback. The reading unit can also customize the reading method by reflecting the past feedback. For example, the reading accuracy can be improved based on feedback provided by the user in the past. A specific reading algorithm can be adjusted based on the user's past feedback. The reading method can be optimized by referring to the user's past feedback. In this way, the reading method can be customized by reflecting the user's past feedback.

[0042] The generation unit can adjust the level of detail of the generated sentences based on the importance of the conversation during generation. For example, the generation unit adjusts the level of detail of the generated sentences based on the importance of the conversation during generation. Importance includes, but is not limited to, the content and relevance of the conversation. For example, the generation unit evaluates the importance of the conversation using a generation AI. For example, the generation unit inputs a prompt such as "Please rate the importance of this conversation" to the generation AI and evaluates the importance. The generation unit can also adjust the level of detail of the generated sentences based on the importance. For example, for a conversation regarding an important meeting schedule, the generation unit generates sentences containing detailed information. For a conversation regarding an urgent request or question, the generation unit generates concise and to-the-point sentences. For everyday casual conversations or unimportant conversations, the generation unit generates sentences with a normal level of detail. This makes it possible to adjust the level of detail of the generated sentences based on the importance of the conversation.

[0043] The generation unit can apply different generation algorithms depending on the category of the conversation during generation. For example, the generation unit applies different generation algorithms depending on the category of the conversation during generation. Categories include, but are not limited to, business-related, private, and technical conversations. The generation unit, for example, uses a generation AI to determine the category of the conversation. For example, the generation unit inputs a prompt to the generation AI, such as "Please determine the category of this conversation," and determines the category. The generation unit can also apply different generation algorithms depending on the category. For example, for business-related conversations, a generation algorithm that takes into account technical terminology and business context is applied. For private conversations, a generation algorithm that takes into account casual expressions and everyday context is applied. For technical conversations, a generation algorithm that takes into account technical terminology and specialized knowledge is applied. This makes it possible to apply different generation algorithms depending on the category of the conversation.

[0044] The generation unit can improve the accuracy of generation by referring to the user's past generation results during generation. For example, the generation unit can improve the accuracy of generation by referring to the user's past generation results during generation. Past generation results include, but are not limited to, sentences generated by the user in the past. The generation unit can analyze the past generation results using, for example, a generation AI. For example, the generation unit inputs a prompt to the generation AI saying, "Please analyze this user's past generation results," and analyzes the generation results. The generation unit can also improve the accuracy of generation by referring to the past generation results. For example, the generation unit can improve the accuracy of generation by referring to sentences generated by the user in the past. The user's past generation results can be used to deepen understanding of a specific context or topic. The user's past generation results can be used to provide context to avoid misunderstandings. This can improve the accuracy of generation by referring to the user's past generation results.

[0045] The generation unit can determine the priority of sentences to be generated based on the submission time of the conversation at the time of generation. For example, the generation unit determines the priority of sentences to be generated based on the submission time of the conversation at the time of generation. The submission time includes, but is not limited to, for example, the submission date and time and the submission frequency. The generation unit, for example, uses a generation AI to evaluate the submission time. For example, the generation unit inputs a prompt to the generation AI, such as "Please evaluate the submission time of this conversation," and evaluates the submission time. The generation unit can also determine the priority of sentences to be generated based on the submission time. For example, conversations regarding urgent requests or questions can be generated with priority. Conversations regarding important meeting schedules can be generated with priority. Everyday chatter and unimportant conversations can be generated later. This makes it possible to determine the priority of sentences to be generated based on the submission time of the conversation.

[0046] The generation unit can adjust the order of sentences to be generated based on the relevance of the conversation during generation. For example, the generation unit adjusts the order of sentences to be generated based on the relevance of the conversation during generation. Relevance includes, but is not limited to, the context and topic of the conversation. The generation unit, for example, uses a generation AI to evaluate the relevance of the conversation. For example, the generation unit inputs a prompt such as "Please rate the relevance of this conversation" to the generation AI and evaluates the relevance. The generation unit can also adjust the order of sentences to be generated based on relevance. For example, the generation unit prioritizes generating highly relevant sentences based on the context of the conversation. The generation unit prioritizes generating highly relevant sentences based on the topic of the conversation. The generation unit prioritizes generating highly relevant sentences based on keywords in the conversation. This makes it possible to adjust the order of sentences to be generated based on the relevance of the conversation.

[0047] The generation unit can adjust the use of technical terms in the generated sentences according to the user's level of expertise at the time of generation. For example, the generation unit adjusts the use of technical terms in the generated sentences according to the user's level of expertise at the time of generation. Expertise levels include, but are not limited to, qualifications and years of experience. The generation unit, for example, uses a generation AI to evaluate the user's level of expertise. For example, the generation unit inputs a prompt to the generation AI, such as "Please rate this user's level of expertise," and evaluates the expertise level. The generation unit can also adjust the use of technical terms in the generated sentences according to the level of expertise. For example, if the user has expert knowledge, the generation unit generates sentences that use a lot of technical terms. If the user does not have expert knowledge, the generation unit generates sentences that explain things in simple terms. The generation unit generates sentences that use appropriate technical terms according to the user's level of expertise. This makes it possible to adjust the use of technical terms in the generated sentences according to the user's level of expertise.

[0048] The suggestion unit can determine the priority of the proposal based on the importance of the generated sentence when making the proposal. For example, the suggestion unit determines the priority of the proposal based on the importance of the generated sentence when making the proposal. The importance includes, for example, but is not limited to, the content and relevance of the sentence. The suggestion unit, for example, uses a generation AI to evaluate the importance of the generated sentence. For example, the suggestion unit inputs a prompt to the generation AI, such as "Please rate the importance of this sentence," and evaluates the importance. The suggestion unit can also determine the priority of the proposal based on the importance. For example, suggestions regarding important meeting schedules can be displayed with priority. Suggestions regarding urgent requests or questions can be displayed with priority. Everyday chatter and unimportant suggestions can be displayed later. In this way, the priority of the proposal can be determined based on the importance of the generated sentence.

[0049] The suggestion unit can improve the accuracy of suggestions by referring to the user's past suggestion history when making suggestions. For example, the suggestion unit can improve the accuracy of suggestions by referring to the user's past suggestion history when making suggestions. The past suggestion history includes, but is not limited to, suggestions that the user has previously accepted. The suggestion unit can analyze the past suggestion history using, for example, a generation AI. For example, the suggestion unit inputs a prompt to the generation AI saying, "Please analyze this user's past suggestion history," and analyzes the suggestion history. The suggestion unit can also improve the accuracy of suggestions by referring to the past suggestion history. For example, the suggestion unit can improve the accuracy of suggestions by referring to suggestions that the user has previously accepted. The suggestion unit can deepen understanding of specific contexts and topics from the user's past suggestion history. The suggestion unit can provide context to avoid misunderstandings based on the user's past suggestion history. This makes it possible to improve the accuracy of suggestions by referring to the user's past suggestion history.

[0050] The suggestion unit can customize the suggestion content according to the user's current task when making a suggestion. For example, the suggestion unit customizes the suggestion content according to the user's current task when making a suggestion. Current tasks include, but are not limited to, being in a meeting, replying to an email, or working on a project. The suggestion unit, for example, uses a generation AI to evaluate the user's current task. For example, the suggestion unit inputs a prompt such as "Please rate this user's current task" to the generation AI and evaluates the task. The suggestion unit can also customize the suggestion content according to the current task. For example, if the user is in a meeting, suggestions related to the meeting are preferentially displayed. If the user is replying to an email, suggestions related to the email are preferentially displayed. If the user is working on a project, suggestions related to the project are preferentially displayed. This allows the suggestion content to be customized according to the user's current task.

[0051] The suggestion unit can prioritize displaying highly relevant suggestions by taking into account the user's geographical background when making suggestions. For example, the suggestion unit prioritizes displaying highly relevant suggestions by taking into account the user's geographical background when making suggestions. The geographical background includes, but is not limited to, the user's location information and regional characteristics. The suggestion unit analyzes the geographical background using, for example, a generation AI. For example, the suggestion unit inputs a prompt such as "Please analyze this user's geographical background" to the generation AI and analyzes the geographical background. The suggestion unit can also prioritize displaying highly relevant suggestions by taking into account the geographical background. For example, if the user is in a specific area, suggestions related to that area are prioritized. If the user is traveling, suggestions related to the travel destination are prioritized. If the user is on a business trip, suggestions related to the business trip destination are prioritized. This makes it possible to prioritize displaying highly relevant suggestions by taking into account the user's geographical background.

[0052] The suggestion unit can analyze the user's social media activity and display related suggestions when making a suggestion. For example, the suggestion unit can analyze the user's social media activity and display related suggestions when making a suggestion. Social media activity includes, but is not limited to, the user's posted content and activity frequency. The suggestion unit can analyze the social media activity using, for example, a generation AI. For example, the suggestion unit inputs a prompt such as "Please analyze this user's social media activity" to the generation AI and analyzes the social media activity. The suggestion unit can also analyze the social media activity and display related suggestions. For example, the suggestion unit can prioritize suggestions related to topics mentioned by the user on social media. The suggestion unit can analyze the user's social media posts and display related suggestions. The suggestion unit can display related suggestions based on the activity of the user's friends on social media. In this way, the user's social media activity can be analyzed and related suggestions can be displayed.

[0053] The suggestion unit can customize the suggestion method by reflecting the user's past feedback when making a suggestion. For example, the suggestion unit customizes the suggestion method by reflecting the user's past feedback when making a suggestion. Past feedback includes, but is not limited to, feedback provided by the user in the past. The suggestion unit analyzes the past feedback using, for example, a generation AI. For example, the suggestion unit inputs a prompt to the generation AI saying, "Please analyze this user's past feedback," and analyzes the feedback. The suggestion unit can also customize the suggestion method by reflecting the past feedback. For example, the suggestion unit improves suggestion accuracy based on feedback provided by the user in the past. Adjusts a specific suggestion method based on the user's past feedback. Optimizes the suggestion method by referring to the user's past feedback. This makes it possible to customize the suggestion method by reflecting the user's past feedback.

[0054] The input unit can analyze the user's past input history and select the optimal input method when inputting data. For example, the input unit analyzes the user's past input history and selects the optimal input method when inputting data. The past input history includes, but is not limited to, input methods (voice, text, etc.) that the user has frequently used in the past. The input unit analyzes the past input history using, for example, a generation AI. For example, the input unit inputs a prompt to the generation AI saying, "Please analyze this user's past input history," and analyzes the input history. The input unit can also analyze the past input history and select the optimal input method. For example, the input unit preferentially suggests input methods that the user has frequently used in the past. The input method to be used in a specific time period is predicted and suggested from the user's past input history. The optimal input method is selected based on the user's past input history. In this way, the user's past input history can be analyzed and the optimal input method can be selected.

[0055] The input unit can filter input data based on the user's current situation and areas of interest. For example, the input unit can filter input data based on the user's current situation and areas of interest. Examples of current situations include, but are not limited to, being in a meeting, replying to an email, or working on a project. The input unit can evaluate the user's current situation using a generation AI. For example, the input unit can input a prompt such as "Please evaluate this user's current situation" to the generation AI and evaluate the situation. The input unit can also filter input data based on the current situation and areas of interest. For example, if the user is in a meeting, input content related to the meeting is preferentially displayed. If the user is replying to an email, input content related to the email is preferentially displayed. If the user is working on a project, input content related to the project is preferentially displayed. This allows filtering to be performed based on the user's current situation and areas of interest.

[0056] The input unit can select the optimal input means depending on the user's input method at the time of input. For example, the input unit selects the optimal input means depending on the user's input method at the time of input. Input methods include, but are not limited to, voice input, text input, and image input. The input unit evaluates the user's input method using, for example, a generation AI. For example, the input unit inputs a prompt to the generation AI saying, "Please rate this user's input method," and evaluates the input method. The input unit can also select the optimal input means depending on the input method. For example, if the user prefers voice input, the input unit preferentially suggests voice input. If the user prefers text input, the input unit preferentially suggests text input. If the user prefers image input, the input unit preferentially suggests image input. This makes it possible to select the optimal input means depending on the user's input method.

[0057] The input unit can prioritize input of highly relevant content in consideration of the user's geographical location information during input. For example, the input unit prioritizes input of highly relevant content in consideration of the user's geographical location information during input. Geographical location information includes, but is not limited to, the user's location information and regional characteristics, for example. The input unit analyzes the geographical location information using, for example, a generation AI. For example, the input unit inputs a prompt to the generation AI, such as "Please analyze this user's geographical location information," and analyzes the geographical location information. The input unit can also prioritize input of highly relevant content in consideration of the geographical location information. For example, if the user is in a specific region, input content related to that region is prioritized. If the user is traveling, input content related to the travel destination is prioritized. If the user is on a business trip, input content related to the business trip destination is prioritized. This makes it possible to prioritize input of highly relevant content in consideration of the user's geographical location information.

[0058] The input unit can analyze the user's social media activity at the time of input and input related content. For example, the input unit can analyze the user's social media activity at the time of input and input related content. Social media activity includes, for example, the user's posted content and activity frequency, but is not limited to such examples. The input unit can analyze the social media activity using, for example, a generation AI. For example, the input unit can input a prompt to the generation AI, such as "Please analyze this user's social media activity," and analyze the social media activity. The input unit can also analyze the social media activity and input related content. For example, the input unit can prioritize and display input content related to topics mentioned by the user on social media. The input unit can analyze the user's social media posts and display related input content. The input unit can display related input content based on the activity of the user's friends on social media. In this way, the user's social media activity can be analyzed and related content can be input.

[0059] The input unit can customize the input method by reflecting the user's past feedback at the time of input. For example, the input unit customizes the input method by reflecting the user's past feedback at the time of input. Past feedback includes, but is not limited to, feedback provided by the user in the past. The input unit analyzes the past feedback using, for example, a generation AI. For example, the input unit inputs a prompt to the generation AI saying, "Please analyze this user's past feedback," and analyzes the feedback. The input unit can also customize the input method by reflecting the past feedback. For example, the input accuracy can be improved based on feedback provided by the user in the past. A specific input method can be adjusted based on the user's past feedback. The input method can be optimized by referring to the user's past feedback. In this way, the input method can be customized by reflecting the user's past feedback.

[0060] The rewriting unit can adjust the level of detail of the rewriting based on the importance of the input sentence when rewriting. For example, the rewriting unit adjusts the level of detail of the rewriting based on the importance of the input sentence when rewriting. The importance includes, but is not limited to, the content and relevance of the sentence. For example, the rewriting unit evaluates the importance of the sentence using a generation AI. For example, the rewriting unit inputs a prompt to the generation AI, such as "Please rate the importance of this sentence," and evaluates the importance. The rewriting unit can also adjust the level of detail of the rewriting based on the importance. For example, a sentence regarding an important meeting schedule is rewritten to include detailed information. A sentence regarding an urgent request or question is rewritten to be concise and to the point. Everyday chatter or unimportant sentences are rewritten with a normal level of detail. In this way, the level of detail of the rewriting can be adjusted based on the importance of the input sentence.

[0061] The rewriting unit can apply different rewriting algorithms depending on the category of the input text when rewriting. For example, the rewriting unit applies different rewriting algorithms depending on the category of the input text when rewriting. Categories include, but are not limited to, business-related, private, and technical texts. The rewriting unit, for example, uses a generation AI to determine the category of the text. For example, the rewriting unit inputs a prompt to the generation AI, such as "Please determine the category of this text," and determines the category. The rewriting unit can also apply different rewriting algorithms depending on the category. For example, a rewriting algorithm that takes technical terminology and business context into account is applied to business-related text. A rewriting algorithm that takes casual expressions and everyday context into account is applied to private text. A rewriting algorithm that takes technical terminology and specialized knowledge into account is applied to technical text. This makes it possible to apply different rewriting algorithms depending on the category of the input text.

[0062] The rewriting unit can improve the accuracy of rewriting by referring to the user's past rewriting results when rewriting. For example, the rewriting unit can improve the accuracy of rewriting by referring to the user's past rewriting results when rewriting. Past rewriting results include, but are not limited to, sentences previously rewritten by the user. The rewriting unit can analyze the past rewriting results using, for example, a generation AI. For example, the rewriting unit inputs a prompt to the generation AI, such as "Please analyze this user's past rewriting results," and analyzes the rewriting results. The rewriting unit can also improve the accuracy of rewriting by referring to the past rewriting results. For example, the rewriting unit can improve the accuracy of rewriting by referring to sentences previously rewritten by the user. The user's past rewriting results can be used to deepen understanding of specific contexts and topics. The user's past rewriting results can be used to provide context to avoid misunderstandings. This can improve the accuracy of rewriting by referring to the user's past rewriting results.

[0063] The rewriting unit can determine the rewriting priority based on the submission time of the input sentence when rewriting. For example, the rewriting unit determines the rewriting priority based on the submission time of the input sentence when rewriting. The submission time includes, but is not limited to, for example, the submission date and time and the submission frequency. The rewriting unit evaluates the submission time using, for example, a generation AI. For example, the rewriting unit inputs a prompt to the generation AI, such as "Please evaluate the submission time of this sentence," and evaluates the submission time. The rewriting unit can also determine the rewriting priority based on the submission time. For example, sentences related to urgent requests or questions are rewritten with priority. Sentences related to important meeting schedules are rewritten with priority. Everyday chatter and unimportant sentences are rewritten later. In this way, the rewriting priority can be determined based on the submission time of the input sentence.

[0064] The rewriting unit can adjust the rewriting order based on the relevance of the input sentence when rewriting. For example, the rewriting unit adjusts the rewriting order based on the relevance of the input sentence when rewriting. Relevance includes, but is not limited to, the context and topic of the sentence, for example. The rewriting unit evaluates the relevance of the sentence using, for example, a generation AI. For example, the rewriting unit inputs a prompt to the generation AI, such as "Please rate the relevance of this sentence," and evaluates the relevance. The rewriting unit can also adjust the rewriting order based on the relevance. For example, the rewriting unit prioritizes rewriting highly relevant parts based on the context of the sentence; prioritizes rewriting highly relevant parts based on the topic of the sentence; or prioritizes rewriting highly relevant parts based on keywords in the sentence. This makes it possible to adjust the rewriting order based on the relevance of the input sentence.

[0065] The rewriting unit can adjust the use of technical terms in the rewriting depending on the user's level of expertise during rewriting. For example, the rewriting unit adjusts the use of technical terms in the rewriting depending on the user's level of expertise during rewriting. Expertise levels include, but are not limited to, qualifications and years of experience. The rewriting unit, for example, uses a generation AI to evaluate the user's level of expertise. For example, the rewriting unit inputs a prompt to the generation AI, such as "Please rate this user's level of expertise," and evaluates the expertise level. The rewriting unit can also adjust the use of technical terms in the rewriting depending on the level of expertise. For example, if the user has expert knowledge, the rewriting unit rewrites the text using a lot of technical terms. If the user does not have expert knowledge, the rewriting unit rewrites the text using simpler terms. The rewriting unit uses appropriate technical terms depending on the user's level of expertise. This makes it possible to adjust the use of technical terms in the rewriting depending on the user's level of expertise.

[0066] The analysis unit can adjust the level of detail of the analysis based on the context of the conversation during analysis. For example, the analysis unit adjusts the level of detail of the analysis based on the context of the conversation during analysis. Context includes, but is not limited to, preceding and following sentences and related topics. The analysis unit analyzes the context of the conversation using, for example, a generation AI. For example, the analysis unit inputs a prompt such as "Please analyze the context of this conversation" to the generation AI and analyzes the context. The analysis unit can also adjust the level of detail of the analysis based on the context. For example, a detailed analysis is performed for a conversation regarding an important meeting schedule. A brief analysis is performed for a conversation regarding an urgent request or question. An analysis with a normal level of detail is performed for everyday chatter or unimportant conversation. This makes it possible to adjust the level of detail of the analysis based on the context of the conversation.

[0067] The analysis unit can apply different analysis algorithms depending on the category of the conversation during analysis. For example, the analysis unit applies different analysis algorithms depending on the category of the conversation during analysis. Categories include, but are not limited to, business-related, private, and technical conversations. The analysis unit, for example, uses a generation AI to determine the category of the conversation. For example, the analysis unit inputs a prompt such as "Please determine the category of this conversation" to the generation AI and determines the category. The analysis unit can also apply different analysis algorithms depending on the category. For example, for business-related conversations, an analysis algorithm that takes into account technical terms and business context is applied. For private conversations, an analysis algorithm that takes into account casual expressions and everyday context is applied. For technical conversations, an analysis algorithm that takes into account technical terms and specialized knowledge is applied. This makes it possible to apply different analysis algorithms depending on the category of the conversation.

[0068] The analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results during analysis. For example, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results during analysis. Past analysis results include, but are not limited to, results analyzed by the user in the past. The analysis unit can analyze the past analysis results using, for example, a generation AI. For example, the analysis unit inputs a prompt to the generation AI, such as "Please analyze this user's past analysis results," and analyzes the analysis results. The analysis unit can also improve the accuracy of the analysis by referring to the past analysis results. For example, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. The analysis unit can deepen understanding of specific contexts and topics from the user's past analysis results. The analysis unit can provide context to avoid misunderstandings based on the user's past analysis results. This can improve the accuracy of the analysis by referring to the user's past analysis results.

[0069] The analysis unit can determine the priority of analysis based on the time of submission of the conversation during analysis. For example, the analysis unit determines the priority of analysis based on the time of submission of the conversation during analysis. The submission time includes, but is not limited to, for example, the submission date and time and the submission frequency. The analysis unit evaluates the submission time using, for example, a generation AI. For example, the analysis unit inputs a prompt to the generation AI saying, "Please evaluate the submission time of this conversation," and evaluates the submission time. The analysis unit can also determine the priority of analysis based on the time of submission. For example, conversations regarding urgent requests or questions can be analyzed with priority. Conversations regarding important meeting schedules can be analyzed with priority. Everyday chatter and unimportant conversations can be analyzed later. This makes it possible to determine the priority of analysis based on the time of submission of the conversation.

[0070] The analysis unit can adjust the order of analysis based on the relevance of the conversation during analysis. For example, the analysis unit adjusts the order of analysis based on the relevance of the conversation during analysis. Relevance includes, but is not limited to, the context and topic of the conversation. The analysis unit, for example, uses a generation AI to evaluate the relevance of the conversation. For example, the analysis unit inputs a prompt such as "Please rate the relevance of this conversation" to the generation AI and evaluates the relevance. The analysis unit can also adjust the order of analysis based on relevance. For example, the analysis unit prioritizes analysis of highly relevant parts based on the context of the conversation. The analysis unit prioritizes analysis of highly relevant parts based on the topic of the conversation. The analysis unit prioritizes analysis of highly relevant parts based on keywords in the conversation. This makes it possible to adjust the order of analysis based on the relevance of the conversation.

[0071] The analysis unit can adjust the use of technical terms in the analysis according to the user's level of expertise during analysis. For example, the analysis unit adjusts the use of technical terms in the analysis according to the user's level of expertise during analysis. Expertise levels include, but are not limited to, qualifications and years of experience. The analysis unit, for example, uses a generation AI to evaluate the user's level of expertise. For example, the analysis unit inputs a prompt to the generation AI, such as "Please rate this user's level of expertise," and evaluates the expertise level. The analysis unit can also adjust the use of technical terms in the analysis according to the level of expertise. For example, if the user has expert knowledge, the analysis uses a lot of technical terms. If the user does not have expert knowledge, the analysis is performed using simple language. The analysis is performed using appropriate technical terms according to the user's level of expertise. This makes it possible to adjust the use of technical terms in the analysis according to the user's level of expertise.

[0072] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0073] The reader can refer to the user's past conversation history to more accurately understand the context of the current conversation. For example, it can infer the intention of the current conversation based on phrases and expressions frequently used by the user in the past. It can also accumulate knowledge about specific topics from past conversation history and provide related information. This makes it possible to utilize the user's past conversation history to perform more accurate conversation analysis.

[0074] The suggestion unit can customize the suggestion content according to the user's current task. For example, if the user is in a meeting, suggestion related to the meeting is displayed preferentially. If the user is replying to an email, suggestion related to the email is displayed preferentially. If the user is working on a project, suggestion related to the project is displayed preferentially. This makes it possible to provide optimal suggestions according to the user's current task.

[0075] The input unit can analyze the user's past input history and select the optimal input method. For example, it can prioritize and suggest input methods (voice, text, etc.) that the user has frequently used in the past. It can also predict and suggest the input method that will be used during a specific time period based on the user's past input history. This makes it possible to utilize the user's past input history to provide the optimal input method.

[0076] The generator can apply different generation algorithms depending on the category of the conversation. For example, for business-related conversations, it applies a generation algorithm that takes into account technical terminology and business context. For private conversations, it applies a generation algorithm that takes into account casual expressions and everyday context. For technical conversations, it applies a generation algorithm that takes into account technical terminology and specialized knowledge. This makes it possible to generate optimal sentences according to the category of the conversation.

[0077] The generation unit can improve the accuracy of generation by referring to the user's past generation results. For example, the generation unit can improve the accuracy of generation by referring to sentences generated by the user in the past. The user's past generation results can be used to deepen understanding of specific contexts and topics. This makes it possible to generate sentences with higher accuracy by utilizing the user's past generation results.

[0078] The rewriting unit can apply different rewriting algorithms depending on the category of the input text. For example, for business-related text, it applies a rewriting algorithm that takes into account technical terms and business context. For private text, it applies a rewriting algorithm that takes into account casual expressions and everyday context. For technical text, it applies a rewriting algorithm that takes into account technical terms and specialized knowledge. This enables optimal rewriting according to the category of the input text.

[0079] The processing flow of the first embodiment will be briefly explained below.

[0080] Step 1: The reader reads the chat conversation. The reader uses the generator AI to analyze the chat conversation and understand the context and content. The reader can also allow the generator AI to extract keywords and important phrases from the conversation. For example, the reader inputs a prompt to the generator AI saying, "Please extract the main points of this conversation," and extracts the main points of the conversation. Step 2: The generator generates appropriate response text suggestions based on the conversation read by the reader. The generator uses a generation AI to analyze the context and content of the conversation and generate appropriate response text suggestions. For example, the generator inputs a prompt to the generation AI saying, "Please generate an appropriate response to this conversation," and generates a response text suggestion. Step 3: The suggestion unit suggests the sentences generated by the generation unit to the user. The suggestion unit displays the generated sentences in a pop-up, and the user can click a button to submit the sentences.

[0081] (Example 2) An automatic generation system according to an embodiment of the present invention automatically generates messages to be sent, such as chats and emails. In this automatic generation system, a generation AI reads all chat conversations and suggests appropriate response texts in a pop-up window. A user can send the suggested texts with just one click of a button. Furthermore, by entering a rough sentence in the field displayed in the pop-up window, the generation AI rewrites the sentence into a more appropriate text for sending and suggests it. For example, in the automatic generation system, a generation AI reads chat conversations. The generation AI analyzes the context and content of the conversation and generates an appropriate response text. For example, if a user asks, "What time does tomorrow's meeting start?", the generation AI generates a response text such as, "Tomorrow's meeting starts at 10:00 AM." The generated response text is then suggested to the user in a pop-up window. The user can review the suggested text and send it with just one click of a button. This allows the user to quickly and easily send an appropriate response. Furthermore, by entering a rough sentence in the field displayed in the pop-up window, the generation AI rewrites the sentence into a more appropriate text for sending and suggests it. For example, if a user types "What time is the meeting?", the generation AI will rewrite it into a more appropriate sentence to send, such as "What time does tomorrow's meeting start?", and suggest it. This allows users to easily create and send appropriate sentences. This allows the automatic generation system to quickly and easily generate and send chat and email messages. For example, in business situations, where quick responses are required, this system can be used to communicate efficiently. In private situations, too, the quality of communication is improved because appropriate sentences can be easily created and sent.

[0082] An automatic generation system according to an embodiment includes a reading unit, a generating unit, and a suggesting unit. The reading unit reads chat conversations. The reading unit analyzes the chat conversations using, for example, a generation AI to understand the context and content. The reading unit can also enable the generation AI to extract keywords and important phrases from the conversation. For example, the reading unit inputs a prompt such as "Please extract the main points of this conversation" to the generation AI to extract the main points of the conversation. The generation unit generates an appropriate answer proposal based on the conversation read by the reading unit. The generation unit analyzes the context and content of the conversation using, for example, the generation AI to generate an appropriate answer proposal. For example, the generation unit inputs a prompt such as "Please generate an appropriate answer to this conversation" to the generation AI to generate an answer proposal. The suggesting unit suggests the proposed sentences generated by the generation unit to a user. For example, the suggesting unit displays the generated proposed sentences in a pop-up. The suggesting unit can also allow a user to submit a sentence by clicking a button. For example, the suggestion unit displays the generated text suggestion in a pop-up window, and the user can click a button to send the text suggestion. This allows the automatic generation system according to the embodiment to automatically read chat conversations, generate appropriate response text suggestions, and suggest them to the user.

[0083] The suggestion unit can display the generated sentence suggestions in a pop-up. For example, the suggestion unit displays the generated sentence suggestions in a pop-up. The pop-up is displayed, for example, in the center of the screen. The suggestion unit can also adjust the timing of displaying the pop-up. For example, the suggestion unit displays the pop-up immediately after the user ends the chat. The suggestion unit can also adjust the display position of the pop-up. For example, the suggestion unit displays the pop-up in accordance with the user's line of sight. In this way, by displaying the generated sentence suggestions in a pop-up, the user can easily check them.

[0084] The suggestion unit can send a text by the user clicking a button. The suggestion unit, for example, sends a text by the user clicking a button. The button is displayed, for example, in a pop-up. The suggestion unit can also adjust the number of clicks of the button. For example, the suggestion unit can send a text with just one click by the user. The suggestion unit can also adjust the type of button. For example, the suggestion unit can display a send button in a large size so that the user can easily click it. This allows the user to send a text by just clicking the button.

[0085] The automatic generation system according to the embodiment includes an input unit for inputting simple sentences. The input unit allows a user to input simple sentences. Simple sentences include, but are not limited to, short sentences and the use of simple words. The input unit, for example, provides a text box to allow a user to input simple sentences. The input unit can also support voice input. For example, the input unit converts the user's voice into text using a microphone. The input unit can also support image input. For example, the input unit allows a user to take a photo of a handwritten note with a camera and convert the image into text. This allows a user to input simple sentences.

[0086] The input unit may include a rewriting unit that rewrites simple sentences into appropriate sentences. The rewriting unit can rewrite simple sentences input by a user into appropriate sentences. Appropriate sentences include, but are not limited to, grammatically correct sentences and sentences with related content. The rewriting unit rewrites simple sentences into appropriate sentences, for example, using a generation AI. For example, the rewriting unit inputs a prompt to the generation AI, such as "Please rewrite this sentence into an appropriate sentence," to generate the appropriate sentence. The rewriting unit can also analyze the context and keywords of sentences input by a user and rewrite them into appropriate sentences. For example, the rewriting unit uses a generation AI to analyze the context and keywords of the sentence and generate appropriate sentences. This allows simple sentences input by a user to be rewritten into appropriate sentences.

[0087] The generation unit may include an analysis unit that analyzes the conversation context and keywords. The analysis unit can analyze the conversation context and keywords. Context includes, for example, surrounding sentences and related topics, but is not limited to, examples. The analysis unit analyzes the conversation context using, for example, a generation AI. For example, the analysis unit inputs a prompt to the generation AI, such as "Please analyze the context of this conversation," and analyzes the context. The analysis unit can also extract keywords. Keywords include, for example, frequently occurring words and words extracted by co-occurrence network analysis, but are not limited to, examples. The analysis unit extracts keywords using, for example, a generation AI. For example, the analysis unit inputs a prompt to the generation AI, such as "Please extract keywords from this conversation," and extracts keywords. This allows the conversation context and keywords to be analyzed.

[0088] The rewriting unit can rewrite simple sentences input by a user into appropriate sentences. For example, the rewriting unit rewrites simple sentences input by a user into appropriate sentences. Simple sentences include, but are not limited to, short sentences and the use of simple words. The rewriting unit rewrites simple sentences into appropriate sentences, for example, using a generation AI. For example, the rewriting unit inputs a prompt to the generation AI, such as "Please rewrite this sentence into an appropriate sentence," to generate an appropriate sentence. The rewriting unit can also analyze the context and keywords of sentences input by a user and rewrite them into appropriate sentences. For example, the rewriting unit uses a generation AI to analyze the context and keywords of the sentence and generate an appropriate sentence. This allows simple sentences input by a user to be rewritten into appropriate sentences.

[0089] The reading unit can estimate the user's emotions and adjust the accuracy of the conversation reading based on the estimated user emotions. The reading unit, for example, estimates the user's emotions and adjusts the accuracy of the conversation reading based on the estimated user emotions. Emotions include, but are not limited to, stress, relaxation, and hurry. The reading unit, for example, uses a generation AI to estimate the user's emotions. For example, the reading unit inputs a prompt such as "Please estimate this user's emotions" to the generation AI and estimates the emotions. The reading unit can also adjust the accuracy of the conversation reading based on the estimated emotions. For example, if the user is stressed, the generation AI increases the accuracy of the conversation reading and performs detailed analysis to avoid misunderstandings. If the user is relaxed, the generation AI maintains the accuracy of the conversation reading at a normal level and performs quick analysis. If the user is in a hurry, the generation AI decreases the accuracy of the conversation reading and quickly generates an appropriate response. This allows the accuracy of the conversation reading to be adjusted based on the user's emotions.

[0090] The reading unit can determine the reading priority based on the importance of the conversation when reading. For example, the reading unit determines the reading priority based on the importance of the conversation when reading. Importance includes, but is not limited to, the content and relevance of the conversation. The reading unit, for example, uses a generation AI to evaluate the importance of the conversation. For example, the reading unit inputs a prompt such as "Please rate the importance of this conversation" to the generation AI and evaluates the importance. The reading unit can also determine the reading priority based on the importance. For example, conversations regarding important meeting schedules are read with priority. Conversations regarding urgent requests or questions are read with priority. Everyday chatter and unimportant conversations are read later. In this way, the reading priority can be determined based on the importance of the conversation.

[0091] The reading unit can apply different reading algorithms depending on the category of the conversation when reading. For example, the reading unit applies different reading algorithms depending on the category of the conversation when reading. Categories include, but are not limited to, business-related, private, and technical conversations. The reading unit, for example, uses a generation AI to determine the category of the conversation. For example, the reading unit inputs a prompt such as "Please determine the category of this conversation" to the generation AI and determines the category. The reading unit can also apply different reading algorithms depending on the category. For example, an algorithm that takes technical terminology and business context into account is applied to business-related conversations. An algorithm that takes casual expressions and everyday context into account is applied to private conversations. An algorithm that takes technical terminology and specialized knowledge into account is applied to technical conversations. This makes it possible to apply different reading algorithms depending on the category of the conversation.

[0092] The reading unit can improve the accuracy of reading by referring to the user's past conversation history when reading. For example, the reading unit can improve the accuracy of reading by referring to the user's past conversation history when reading. The past conversation history includes, for example, phrases and expressions frequently used by the user in the past, but is not limited to such examples. The reading unit, for example, analyzes the past conversation history using a generation AI. For example, the reading unit inputs a prompt to the generation AI, such as "Please analyze this user's past conversation history," and analyzes the conversation history. The reading unit can also improve the accuracy of reading by referring to the past conversation history. For example, the reading unit improves the accuracy of reading by referring to phrases and expressions frequently used by the user in the past. The reading unit deepens understanding of specific contexts and topics from the user's past conversation history. The reading unit provides context to avoid misunderstandings based on the user's past conversation history. This makes it possible to improve the accuracy of reading by referring to the user's past conversation history.

[0093] The reading unit can estimate the user's emotions and determine the priority of conversations to be read based on the estimated user emotions. The reading unit, for example, estimates the user's emotions and determines the priority of conversations to be read based on the estimated user emotions. Emotions include, but are not limited to, stress, relaxation, and hurry. The reading unit, for example, uses a generation AI to estimate the user's emotions. For example, the reading unit inputs a prompt such as "Please estimate this user's emotions" to the generation AI and estimates the emotions. The reading unit can also determine the priority of conversations to be read based on the estimated emotions. For example, if the user is feeling stressed, important conversations are read with priority. If the user is relaxed, conversations are read with normal priority. If the user is in a hurry, urgent conversations are read with top priority. This makes it possible to determine the priority of conversations to be read based on the user's emotions.

[0094] The reading unit can prioritize reading highly relevant conversations by taking into account the geographical background of the conversation when reading. For example, the reading unit prioritizes reading highly relevant conversations by taking into account the geographical background of the conversation when reading. The geographical background includes, for example, the user's location information and regional characteristics, but is not limited to such examples. The reading unit analyzes the geographical background using, for example, a generation AI. For example, the reading unit inputs a prompt such as "Please analyze this user's geographical background" to the generation AI and analyzes the geographical background. The reading unit can also prioritize reading highly relevant conversations by taking into account the geographical background. For example, if the user is in a specific region, conversations related to that region are prioritized. If the user is traveling, conversations related to the travel destination are prioritized. If the user is on a business trip, conversations related to the business trip destination are prioritized. This makes it possible to prioritize reading highly relevant conversations by taking into account the geographical background of the conversation.

[0095] The reading unit can analyze the user's social media activity and read related conversations during reading. For example, the reading unit analyzes the user's social media activity and reads related conversations during reading. Social media activity includes, for example, the content of the user's posts and the frequency of activity, but is not limited to these examples. The reading unit analyzes the social media activity using, for example, a generation AI. For example, the reading unit inputs a prompt such as "Please analyze this user's social media activity" into the generation AI and analyzes the social media activity. The reading unit can also analyze the social media activity and read related conversations. For example, the reading unit prioritizes reading conversations related to topics mentioned by the user on social media. The reading unit analyzes the content of the user's social media posts and reads related conversations. Related conversations are read based on the activity of the user's friends on social media. In this way, the user's social media activity can be analyzed and related conversations can be read.

[0096] The reading unit can customize the reading method by reflecting the user's past feedback when reading. For example, the reading unit customizes the reading method by reflecting the user's past feedback when reading. Past feedback includes, but is not limited to, feedback provided by the user in the past. The reading unit analyzes the past feedback using, for example, a generation AI. For example, the reading unit inputs a prompt such as "Please analyze this user's past feedback" to the generation AI and analyzes the feedback. The reading unit can also customize the reading method by reflecting the past feedback. For example, the reading accuracy can be improved based on feedback provided by the user in the past. A specific reading algorithm can be adjusted based on the user's past feedback. The reading method can be optimized by referring to the user's past feedback. In this way, the reading method can be customized by reflecting the user's past feedback.

[0097] The generation unit can estimate the user's emotions and adjust the expression style of the generated sentences based on the estimated user emotions. For example, the generation unit can estimate the user's emotions and adjust the expression style of the generated sentences based on the estimated user emotions. Emotions include, but are not limited to, stress, relaxation, and hurry. The generation unit can estimate the user's emotions using, for example, a generation AI. For example, the generation unit inputs a prompt such as "Please estimate this user's emotions" to the generation AI and estimates the emotions. The generation unit can also adjust the expression style of the generated sentences based on the estimated emotions. For example, if the user is stressed, a concise and clear expression style is used. If the user is relaxed, a detailed and polite expression style is used. If the user is in a hurry, a quickly understandable expression style is used. This makes it possible to adjust the expression style of the generated sentences based on the user's emotions.

[0098] The generation unit can adjust the level of detail of the generated sentences based on the importance of the conversation during generation. For example, the generation unit adjusts the level of detail of the generated sentences based on the importance of the conversation during generation. Importance includes, but is not limited to, the content and relevance of the conversation. For example, the generation unit evaluates the importance of the conversation using a generation AI. For example, the generation unit inputs a prompt such as "Please rate the importance of this conversation" to the generation AI and evaluates the importance. The generation unit can also adjust the level of detail of the generated sentences based on the importance. For example, for a conversation regarding an important meeting schedule, the generation unit generates sentences containing detailed information. For a conversation regarding an urgent request or question, the generation unit generates concise and to-the-point sentences. For everyday casual conversations or unimportant conversations, the generation unit generates sentences with a normal level of detail. This makes it possible to adjust the level of detail of the generated sentences based on the importance of the conversation.

[0099] The generation unit can apply different generation algorithms depending on the category of the conversation during generation. For example, the generation unit applies different generation algorithms depending on the category of the conversation during generation. Categories include, but are not limited to, business-related, private, and technical conversations. The generation unit, for example, uses a generation AI to determine the category of the conversation. For example, the generation unit inputs a prompt to the generation AI, such as "Please determine the category of this conversation," and determines the category. The generation unit can also apply different generation algorithms depending on the category. For example, for business-related conversations, a generation algorithm that takes into account technical terminology and business context is applied. For private conversations, a generation algorithm that takes into account casual expressions and everyday context is applied. For technical conversations, a generation algorithm that takes into account technical terminology and specialized knowledge is applied. This makes it possible to apply different generation algorithms depending on the category of the conversation.

[0100] The generation unit can improve the accuracy of generation by referring to the user's past generation results during generation. For example, the generation unit can improve the accuracy of generation by referring to the user's past generation results during generation. Past generation results include, but are not limited to, sentences generated by the user in the past. The generation unit can analyze the past generation results using, for example, a generation AI. For example, the generation unit inputs a prompt to the generation AI saying, "Please analyze this user's past generation results," and analyzes the generation results. The generation unit can also improve the accuracy of generation by referring to the past generation results. For example, the generation unit can improve the accuracy of generation by referring to sentences generated by the user in the past. The user's past generation results can be used to deepen understanding of a specific context or topic. The user's past generation results can be used to provide context to avoid misunderstandings. This can improve the accuracy of generation by referring to the user's past generation results.

[0101] The generation unit can estimate the user's emotion and adjust the length of the generated sentence based on the estimated user's emotion. For example, the generation unit can estimate the user's emotion and adjust the length of the generated sentence based on the estimated user's emotion. Emotions include, but are not limited to, stress, relaxation, and hurry. The generation unit can estimate the user's emotion using, for example, a generation AI. For example, the generation unit inputs a prompt such as "Please estimate this user's emotion" to the generation AI and estimates the emotion. The generation unit can also adjust the length of the generated sentence based on the estimated emotion. For example, if the user is stressed, the generation unit generates short, to-the-point sentences. If the user is relaxed, the generation unit generates longer sentences with detailed explanations. If the user is in a hurry, the generation unit generates short sentences that can be quickly understood. This allows the length of the generated sentences to be adjusted based on the user's emotion.

[0102] The generation unit can determine the priority of sentences to be generated based on the submission time of the conversation at the time of generation. For example, the generation unit determines the priority of sentences to be generated based on the submission time of the conversation at the time of generation. The submission time includes, but is not limited to, for example, the submission date and time and the submission frequency. The generation unit, for example, uses a generation AI to evaluate the submission time. For example, the generation unit inputs a prompt to the generation AI, such as "Please evaluate the submission time of this conversation," and evaluates the submission time. The generation unit can also determine the priority of sentences to be generated based on the submission time. For example, conversations regarding urgent requests or questions can be generated with priority. Conversations regarding important meeting schedules can be generated with priority. Everyday chatter and unimportant conversations can be generated later. This makes it possible to determine the priority of sentences to be generated based on the submission time of the conversation.

[0103] The generation unit can adjust the order of sentences to be generated based on the relevance of the conversation during generation. For example, the generation unit adjusts the order of sentences to be generated based on the relevance of the conversation during generation. Relevance includes, but is not limited to, the context and topic of the conversation. The generation unit, for example, uses a generation AI to evaluate the relevance of the conversation. For example, the generation unit inputs a prompt such as "Please rate the relevance of this conversation" to the generation AI and evaluates the relevance. The generation unit can also adjust the order of sentences to be generated based on relevance. For example, the generation unit prioritizes generating highly relevant sentences based on the context of the conversation. The generation unit prioritizes generating highly relevant sentences based on the topic of the conversation. The generation unit prioritizes generating highly relevant sentences based on keywords in the conversation. This makes it possible to adjust the order of sentences to be generated based on the relevance of the conversation.

[0104] The generation unit can adjust the use of technical terms in the generated sentences according to the user's level of expertise at the time of generation. For example, the generation unit adjusts the use of technical terms in the generated sentences according to the user's level of expertise at the time of generation. Expertise levels include, but are not limited to, qualifications and years of experience. The generation unit, for example, uses a generation AI to evaluate the user's level of expertise. For example, the generation unit inputs a prompt to the generation AI, such as "Please rate this user's level of expertise," and evaluates the expertise level. The generation unit can also adjust the use of technical terms in the generated sentences according to the level of expertise. For example, if the user has expert knowledge, the generation unit generates sentences that use a lot of technical terms. If the user does not have expert knowledge, the generation unit generates sentences that explain things in simple terms. The generation unit generates sentences that use appropriate technical terms according to the user's level of expertise. This makes it possible to adjust the use of technical terms in the generated sentences according to the user's level of expertise.

[0105] The suggestion unit can estimate the user's emotions and adjust the display method of suggestions based on the estimated user emotions. For example, the suggestion unit estimates the user's emotions and adjusts the display method of suggestions based on the estimated user emotions. Emotions include, but are not limited to, stress, relaxation, and hurry. The suggestion unit, for example, uses a generation AI to estimate the user's emotions. For example, the suggestion unit inputs a prompt such as "Please estimate this user's emotions" to the generation AI and estimates the emotions. The suggestion unit can also adjust the display method of suggestions based on the estimated emotions. For example, if the user is stressed, a simple, highly visible display method is provided. If the user is relaxed, a display method including detailed information is provided. If the user is in a hurry, a display method that focuses on the main points is provided. This makes it possible to adjust the display method of suggestions based on the user's emotions.

[0106] The suggestion unit can determine the priority of the proposal based on the importance of the generated sentence when making the proposal. For example, the suggestion unit determines the priority of the proposal based on the importance of the generated sentence when making the proposal. The importance includes, for example, but is not limited to, the content and relevance of the sentence. The suggestion unit, for example, uses a generation AI to evaluate the importance of the generated sentence. For example, the suggestion unit inputs a prompt to the generation AI, such as "Please rate the importance of this sentence," and evaluates the importance. The suggestion unit can also determine the priority of the proposal based on the importance. For example, suggestions regarding important meeting schedules can be displayed with priority. Suggestions regarding urgent requests or questions can be displayed with priority. Everyday chatter and unimportant suggestions can be displayed later. In this way, the priority of the proposal can be determined based on the importance of the generated sentence.

[0107] The suggestion unit can improve the accuracy of suggestions by referring to the user's past suggestion history when making suggestions. For example, the suggestion unit can improve the accuracy of suggestions by referring to the user's past suggestion history when making suggestions. The past suggestion history includes, but is not limited to, suggestions that the user has previously accepted. The suggestion unit can analyze the past suggestion history using, for example, a generation AI. For example, the suggestion unit inputs a prompt to the generation AI saying, "Please analyze this user's past suggestion history," and analyzes the suggestion history. The suggestion unit can also improve the accuracy of suggestions by referring to the past suggestion history. For example, the suggestion unit can improve the accuracy of suggestions by referring to suggestions that the user has previously accepted. The suggestion unit can deepen understanding of specific contexts and topics from the user's past suggestion history. The suggestion unit can provide context to avoid misunderstandings based on the user's past suggestion history. This makes it possible to improve the accuracy of suggestions by referring to the user's past suggestion history.

[0108] The suggestion unit can customize the suggestion content according to the user's current task when making a suggestion. For example, the suggestion unit customizes the suggestion content according to the user's current task when making a suggestion. Current tasks include, but are not limited to, being in a meeting, replying to an email, or working on a project. The suggestion unit, for example, uses a generation AI to evaluate the user's current task. For example, the suggestion unit inputs a prompt such as "Please rate this user's current task" to the generation AI and evaluates the task. The suggestion unit can also customize the suggestion content according to the current task. For example, if the user is in a meeting, suggestions related to the meeting are preferentially displayed. If the user is replying to an email, suggestions related to the email are preferentially displayed. If the user is working on a project, suggestions related to the project are preferentially displayed. This allows the suggestion content to be customized according to the user's current task.

[0109] The suggestion unit can estimate the user's emotions and adjust the display order of suggestions based on the estimated user emotions. For example, the suggestion unit can estimate the user's emotions and adjust the display order of suggestions based on the estimated user emotions. Emotions include, but are not limited to, stress, relaxation, and hurry. The suggestion unit can estimate the user's emotions using, for example, a generation AI. For example, the suggestion unit inputs a prompt such as "Please estimate this user's emotions" to the generation AI and estimates the emotions. The suggestion unit can also adjust the display order of suggestions based on the estimated emotions. For example, if the user is feeling stressed, important suggestions are displayed first. If the user is relaxed, suggestions are displayed in a normal order. If the user is in a hurry, urgent suggestions are displayed as the top priority. This makes it possible to adjust the display order of suggestions based on the user's emotions.

[0110] The suggestion unit can prioritize displaying highly relevant suggestions by taking into account the user's geographical background when making suggestions. For example, the suggestion unit prioritizes displaying highly relevant suggestions by taking into account the user's geographical background when making suggestions. The geographical background includes, but is not limited to, the user's location information and regional characteristics. The suggestion unit analyzes the geographical background using, for example, a generation AI. For example, the suggestion unit inputs a prompt such as "Please analyze this user's geographical background" to the generation AI and analyzes the geographical background. The suggestion unit can also prioritize displaying highly relevant suggestions by taking into account the geographical background. For example, if the user is in a specific area, suggestions related to that area are prioritized. If the user is traveling, suggestions related to the travel destination are prioritized. If the user is on a business trip, suggestions related to the business trip destination are prioritized. This makes it possible to prioritize displaying highly relevant suggestions by taking into account the user's geographical background.

[0111] The suggestion unit can analyze the user's social media activity and display related suggestions when making a suggestion. For example, the suggestion unit can analyze the user's social media activity and display related suggestions when making a suggestion. Social media activity includes, but is not limited to, the user's posted content and activity frequency. The suggestion unit can analyze the social media activity using, for example, a generation AI. For example, the suggestion unit inputs a prompt such as "Please analyze this user's social media activity" to the generation AI and analyzes the social media activity. The suggestion unit can also analyze the social media activity and display related suggestions. For example, the suggestion unit can prioritize suggestions related to topics mentioned by the user on social media. The suggestion unit can analyze the user's social media posts and display related suggestions. The suggestion unit can display related suggestions based on the activity of the user's friends on social media. In this way, the user's social media activity can be analyzed and related suggestions can be displayed.

[0112] The suggestion unit can customize the suggestion method by reflecting the user's past feedback when making a suggestion. For example, the suggestion unit customizes the suggestion method by reflecting the user's past feedback when making a suggestion. Past feedback includes, but is not limited to, feedback provided by the user in the past. The suggestion unit analyzes the past feedback using, for example, a generation AI. For example, the suggestion unit inputs a prompt to the generation AI saying, "Please analyze this user's past feedback," and analyzes the feedback. The suggestion unit can also customize the suggestion method by reflecting the past feedback. For example, the suggestion unit improves suggestion accuracy based on feedback provided by the user in the past. Adjusts a specific suggestion method based on the user's past feedback. Optimizes the suggestion method by referring to the user's past feedback. This makes it possible to customize the suggestion method by reflecting the user's past feedback.

[0113] The input unit can estimate the user's emotion and adjust the timing of the input based on the estimated user's emotion. For example, the input unit can estimate the user's emotion and adjust the timing of the input based on the estimated user's emotion. Emotions include, but are not limited to, stress, relaxation, and hurry. The input unit can estimate the user's emotion using, for example, a generation AI. For example, the input unit inputs a prompt such as "Please estimate this user's emotion" to the generation AI and estimates the emotion. The input unit can also adjust the timing of the input based on the estimated emotion. For example, if the user is feeling stressed, the input timing can be delayed to relax the user. If the user is relaxed, the input is prompted at a normal timing. If the user is in a hurry, the input is prompted quickly. This makes it possible to adjust the timing of the input based on the user's emotion.

[0114] The input unit can analyze the user's past input history and select the optimal input method when inputting data. For example, the input unit analyzes the user's past input history and selects the optimal input method when inputting data. The past input history includes, but is not limited to, input methods (voice, text, etc.) that the user has frequently used in the past. The input unit analyzes the past input history using, for example, a generation AI. For example, the input unit inputs a prompt to the generation AI saying, "Please analyze this user's past input history," and analyzes the input history. The input unit can also analyze the past input history and select the optimal input method. For example, the input unit preferentially suggests input methods that the user has frequently used in the past. The input method to be used in a specific time period is predicted and suggested from the user's past input history. The optimal input method is selected based on the user's past input history. In this way, the user's past input history can be analyzed and the optimal input method can be selected.

[0115] The input unit can filter input data based on the user's current situation and areas of interest. For example, the input unit can filter input data based on the user's current situation and areas of interest. Examples of current situations include, but are not limited to, being in a meeting, replying to an email, or working on a project. The input unit can evaluate the user's current situation using a generation AI. For example, the input unit can input a prompt such as "Please evaluate this user's current situation" to the generation AI and evaluate the situation. The input unit can also filter input data based on the current situation and areas of interest. For example, if the user is in a meeting, input content related to the meeting is preferentially displayed. If the user is replying to an email, input content related to the email is preferentially displayed. If the user is working on a project, input content related to the project is preferentially displayed. This allows filtering to be performed based on the user's current situation and areas of interest.

[0116] The input unit can select the optimal input means depending on the user's input method at the time of input. For example, the input unit selects the optimal input means depending on the user's input method at the time of input. Input methods include, but are not limited to, voice input, text input, and image input. The input unit evaluates the user's input method using, for example, a generation AI. For example, the input unit inputs a prompt to the generation AI saying, "Please rate this user's input method," and evaluates the input method. The input unit can also select the optimal input means depending on the input method. For example, if the user prefers voice input, the input unit preferentially suggests voice input. If the user prefers text input, the input unit preferentially suggests text input. If the user prefers image input, the input unit preferentially suggests image input. This makes it possible to select the optimal input means depending on the user's input method.

[0117] The input unit can estimate the user's emotions and determine the priority of the content to be input based on the estimated user emotions. The input unit, for example, estimates the user's emotions and determines the priority of the content to be input based on the estimated user emotions. Emotions include, but are not limited to, stress, relaxation, and hurry. The input unit, for example, uses a generation AI to estimate the user's emotions. For example, the input unit inputs a prompt such as "Please estimate this user's emotions" to the generation AI and estimates the emotion. The input unit can also determine the priority of the content to be input based on the estimated emotions. For example, if the user is feeling stressed, important input content is displayed with priority. If the user is relaxed, input content is displayed with normal priority. If the user is in a hurry, urgent input content is displayed with top priority. This makes it possible to determine the priority of the content to be input based on the user's emotions.

[0118] The input unit can prioritize input of highly relevant content in consideration of the user's geographical location information during input. For example, the input unit prioritizes input of highly relevant content in consideration of the user's geographical location information during input. Geographical location information includes, but is not limited to, the user's location information and regional characteristics, for example. The input unit analyzes the geographical location information using, for example, a generation AI. For example, the input unit inputs a prompt to the generation AI, such as "Please analyze this user's geographical location information," and analyzes the geographical location information. The input unit can also prioritize input of highly relevant content in consideration of the geographical location information. For example, if the user is in a specific region, input content related to that region is prioritized. If the user is traveling, input content related to the travel destination is prioritized. If the user is on a business trip, input content related to the business trip destination is prioritized. This makes it possible to prioritize input of highly relevant content in consideration of the user's geographical location information.

[0119] The input unit can analyze the user's social media activity at the time of input and input related content. For example, the input unit can analyze the user's social media activity at the time of input and input related content. Social media activity includes, for example, the user's posted content and activity frequency, but is not limited to such examples. The input unit can analyze the social media activity using, for example, a generation AI. For example, the input unit can input a prompt to the generation AI, such as "Please analyze this user's social media activity," and analyze the social media activity. The input unit can also analyze the social media activity and input related content. For example, the input unit can prioritize and display input content related to topics mentioned by the user on social media. The input unit can analyze the user's social media posts and display related input content. The input unit can display related input content based on the activity of the user's friends on social media. In this way, the user's social media activity can be analyzed and related content can be input.

[0120] The input unit can customize the input method by reflecting the user's past feedback at the time of input. For example, the input unit customizes the input method by reflecting the user's past feedback at the time of input. Past feedback includes, but is not limited to, feedback provided by the user in the past. The input unit analyzes the past feedback using, for example, a generation AI. For example, the input unit inputs a prompt to the generation AI saying, "Please analyze this user's past feedback," and analyzes the feedback. The input unit can also customize the input method by reflecting the past feedback. For example, the input accuracy can be improved based on feedback provided by the user in the past. A specific input method can be adjusted based on the user's past feedback. The input method can be optimized by referring to the user's past feedback. In this way, the input method can be customized by reflecting the user's past feedback.

[0121] The rewriting unit can estimate the user's emotions and adjust the rewriting expression based on the estimated user emotions. For example, the rewriting unit estimates the user's emotions and adjusts the rewriting expression based on the estimated user emotions. Emotions include, but are not limited to, stress, relaxation, and hurry. The rewriting unit estimates the user's emotions using, for example, a generation AI. For example, the rewriting unit inputs a prompt such as "Please estimate this user's emotions" to the generation AI and estimates the emotions. The rewriting unit can also adjust the rewriting expression based on the estimated emotions. For example, if the user is stressed, a concise and clear expression is used. If the user is relaxed, a detailed and polite expression is used. If the user is in a hurry, a quickly understandable expression is used. This makes it possible to adjust the rewriting expression based on the user's emotions.

[0122] The rewriting unit can adjust the level of detail of the rewriting based on the importance of the input sentence when rewriting. For example, the rewriting unit adjusts the level of detail of the rewriting based on the importance of the input sentence when rewriting. The importance includes, but is not limited to, the content and relevance of the sentence. For example, the rewriting unit evaluates the importance of the sentence using a generation AI. For example, the rewriting unit inputs a prompt to the generation AI, such as "Please rate the importance of this sentence," and evaluates the importance. The rewriting unit can also adjust the level of detail of the rewriting based on the importance. For example, a sentence regarding an important meeting schedule is rewritten to include detailed information. A sentence regarding an urgent request or question is rewritten to be concise and to the point. Everyday chatter or unimportant sentences are rewritten with a normal level of detail. In this way, the level of detail of the rewriting can be adjusted based on the importance of the input sentence.

[0123] The rewriting unit can apply different rewriting algorithms depending on the category of the input text when rewriting. For example, the rewriting unit applies different rewriting algorithms depending on the category of the input text when rewriting. Categories include, but are not limited to, business-related, private, and technical texts. The rewriting unit, for example, uses a generation AI to determine the category of the text. For example, the rewriting unit inputs a prompt to the generation AI, such as "Please determine the category of this text," and determines the category. The rewriting unit can also apply different rewriting algorithms depending on the category. For example, a rewriting algorithm that takes technical terminology and business context into account is applied to business-related text. A rewriting algorithm that takes casual expressions and everyday context into account is applied to private text. A rewriting algorithm that takes technical terminology and specialized knowledge into account is applied to technical text. This makes it possible to apply different rewriting algorithms depending on the category of the input text.

[0124] The rewriting unit can improve the accuracy of rewriting by referring to the user's past rewriting results when rewriting. For example, the rewriting unit can improve the accuracy of rewriting by referring to the user's past rewriting results when rewriting. Past rewriting results include, but are not limited to, sentences previously rewritten by the user. The rewriting unit can analyze the past rewriting results using, for example, a generation AI. For example, the rewriting unit inputs a prompt to the generation AI, such as "Please analyze this user's past rewriting results," and analyzes the rewriting results. The rewriting unit can also improve the accuracy of rewriting by referring to the past rewriting results. For example, the rewriting unit can improve the accuracy of rewriting by referring to sentences previously rewritten by the user. The user's past rewriting results can be used to deepen understanding of specific contexts and topics. The user's past rewriting results can be used to provide context to avoid misunderstandings. This can improve the accuracy of rewriting by referring to the user's past rewriting results.

[0125] The rewriting unit can estimate the user's emotions and adjust the length of the rewrite based on the estimated user emotions. The rewriting unit, for example, estimates the user's emotions and adjusts the length of the rewrite based on the estimated user emotions. Emotions include, but are not limited to, stress, relaxation, and hurry. The rewriting unit, for example, uses a generation AI to estimate the user's emotions. For example, the rewriting unit inputs a prompt such as "Please estimate this user's emotions" to the generation AI and estimates the emotions. The rewriting unit can also adjust the length of the rewrite based on the estimated emotions. For example, if the user is stressed, the rewrite is short and to the point. If the user is relaxed, the rewrite is longer and includes detailed explanations. If the user is in a hurry, the rewrite is short and easy to understand. This allows the length of the rewrite to be adjusted based on the user's emotions.

[0126] The rewriting unit can determine the rewriting priority based on the submission time of the input sentence when rewriting. For example, the rewriting unit determines the rewriting priority based on the submission time of the input sentence when rewriting. The submission time includes, but is not limited to, for example, the submission date and time and the submission frequency. The rewriting unit evaluates the submission time using, for example, a generation AI. For example, the rewriting unit inputs a prompt to the generation AI, such as "Please evaluate the submission time of this sentence," and evaluates the submission time. The rewriting unit can also determine the rewriting priority based on the submission time. For example, sentences related to urgent requests or questions are rewritten with priority. Sentences related to important meeting schedules are rewritten with priority. Everyday chatter and unimportant sentences are rewritten later. In this way, the rewriting priority can be determined based on the submission time of the input sentence.

[0127] The rewriting unit can adjust the rewriting order based on the relevance of the input sentence when rewriting. For example, the rewriting unit adjusts the rewriting order based on the relevance of the input sentence when rewriting. Relevance includes, but is not limited to, the context and topic of the sentence, for example. The rewriting unit evaluates the relevance of the sentence using, for example, a generation AI. For example, the rewriting unit inputs a prompt to the generation AI, such as "Please rate the relevance of this sentence," and evaluates the relevance. The rewriting unit can also adjust the rewriting order based on the relevance. For example, the rewriting unit prioritizes rewriting highly relevant parts based on the context of the sentence; prioritizes rewriting highly relevant parts based on the topic of the sentence; or prioritizes rewriting highly relevant parts based on keywords in the sentence. This makes it possible to adjust the rewriting order based on the relevance of the input sentence.

[0128] The rewriting unit can adjust the use of technical terms in the rewriting depending on the user's level of expertise during rewriting. For example, the rewriting unit adjusts the use of technical terms in the rewriting depending on the user's level of expertise during rewriting. Expertise levels include, but are not limited to, qualifications and years of experience. The rewriting unit, for example, uses a generation AI to evaluate the user's level of expertise. For example, the rewriting unit inputs a prompt to the generation AI, such as "Please rate this user's level of expertise," and evaluates the expertise level. The rewriting unit can also adjust the use of technical terms in the rewriting depending on the level of expertise. For example, if the user has expert knowledge, the rewriting unit rewrites the text using a lot of technical terms. If the user does not have expert knowledge, the rewriting unit rewrites the text using simpler terms. The rewriting unit uses appropriate technical terms depending on the user's level of expertise. This makes it possible to adjust the use of technical terms in the rewriting depending on the user's level of expertise.

[0129] The analysis unit can estimate the user's emotions and adjust the analysis method based on the estimated user emotions. For example, the analysis unit can estimate the user's emotions and adjust the analysis method based on the estimated user emotions. Emotions include, but are not limited to, stress, relaxation, and hurry. The analysis unit can estimate the user's emotions using, for example, a generation AI. For example, the analysis unit inputs a prompt such as "Please estimate this user's emotions" to the generation AI and estimates the emotions. The analysis unit can also adjust the analysis method based on the estimated emotions. For example, if the user is stressed, a detailed analysis is performed and information to avoid misunderstandings is provided. If the user is relaxed, a normal analysis method is used. If the user is in a hurry, a quick analysis is performed and information that focuses on the main points is provided. This makes it possible to adjust the analysis method based on the user's emotions.

[0130] The analysis unit can adjust the level of detail of the analysis based on the context of the conversation during analysis. For example, the analysis unit adjusts the level of detail of the analysis based on the context of the conversation during analysis. Context includes, but is not limited to, preceding and following sentences and related topics. The analysis unit analyzes the context of the conversation using, for example, a generation AI. For example, the analysis unit inputs a prompt such as "Please analyze the context of this conversation" to the generation AI and analyzes the context. The analysis unit can also adjust the level of detail of the analysis based on the context. For example, a detailed analysis is performed for a conversation regarding an important meeting schedule. A brief analysis is performed for a conversation regarding an urgent request or question. An analysis with a normal level of detail is performed for everyday chatter or unimportant conversation. This makes it possible to adjust the level of detail of the analysis based on the context of the conversation.

[0131] The analysis unit can apply different analysis algorithms depending on the category of the conversation during analysis. For example, the analysis unit applies different analysis algorithms depending on the category of the conversation during analysis. Categories include, but are not limited to, business-related, private, and technical conversations. The analysis unit, for example, uses a generation AI to determine the category of the conversation. For example, the analysis unit inputs a prompt such as "Please determine the category of this conversation" to the generation AI and determines the category. The analysis unit can also apply different analysis algorithms depending on the category. For example, for business-related conversations, an analysis algorithm that takes into account technical terms and business context is applied. For private conversations, an analysis algorithm that takes into account casual expressions and everyday context is applied. For technical conversations, an analysis algorithm that takes into account technical terms and specialized knowledge is applied. This makes it possible to apply different analysis algorithms depending on the category of the conversation.

[0132] The analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results during analysis. For example, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results during analysis. Past analysis results include, but are not limited to, results analyzed by the user in the past. The analysis unit can analyze the past analysis results using, for example, a generation AI. For example, the analysis unit inputs a prompt to the generation AI, such as "Please analyze this user's past analysis results," and analyzes the analysis results. The analysis unit can also improve the accuracy of the analysis by referring to the past analysis results. For example, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. The analysis unit can deepen understanding of specific contexts and topics from the user's past analysis results. The analysis unit can provide context to avoid misunderstandings based on the user's past analysis results. This can improve the accuracy of the analysis by referring to the user's past analysis results.

[0133] The analysis unit can estimate the user's emotions and determine the analysis priority based on the estimated user's emotions. The analysis unit, for example, estimates the user's emotions and determines the analysis priority based on the estimated user's emotions. Emotions include, but are not limited to, stress, relaxation, and hurry. The analysis unit, for example, uses a generation AI to estimate the user's emotions. For example, the analysis unit inputs a prompt such as "Please estimate this user's emotions" to the generation AI and estimates the emotions. The analysis unit can also determine the analysis priority based on the estimated emotions. For example, if the user is stressed, important analysis is given top priority. If the user is relaxed, analysis is given normal priority. If the user is in a hurry, urgent analysis is given top priority. This makes it possible to determine the analysis priority based on the user's emotions.

[0134] The analysis unit can determine the priority of analysis based on the time of submission of the conversation during analysis. For example, the analysis unit determines the priority of analysis based on the time of submission of the conversation during analysis. The submission time includes, but is not limited to, for example, the submission date and time and the submission frequency. The analysis unit evaluates the submission time using, for example, a generation AI. For example, the analysis unit inputs a prompt to the generation AI saying, "Please evaluate the submission time of this conversation," and evaluates the submission time. The analysis unit can also determine the priority of analysis based on the time of submission. For example, conversations regarding urgent requests or questions can be analyzed with priority. Conversations regarding important meeting schedules can be analyzed with priority. Everyday chatter and unimportant conversations can be analyzed later. This makes it possible to determine the priority of analysis based on the time of submission of the conversation.

[0135] The analysis unit can adjust the order of analysis based on the relevance of the conversation during analysis. For example, the analysis unit adjusts the order of analysis based on the relevance of the conversation during analysis. Relevance includes, but is not limited to, the context and topic of the conversation. The analysis unit, for example, uses a generation AI to evaluate the relevance of the conversation. For example, the analysis unit inputs a prompt such as "Please rate the relevance of this conversation" to the generation AI and evaluates the relevance. The analysis unit can also adjust the order of analysis based on relevance. For example, the analysis unit prioritizes analysis of highly relevant parts based on the context of the conversation. The analysis unit prioritizes analysis of highly relevant parts based on the topic of the conversation. The analysis unit prioritizes analysis of highly relevant parts based on keywords in the conversation. This makes it possible to adjust the order of analysis based on the relevance of the conversation.

[0136] The analysis unit can adjust the use of technical terms in the analysis according to the user's level of expertise during analysis. For example, the analysis unit adjusts the use of technical terms in the analysis according to the user's level of expertise during analysis. Expertise levels include, but are not limited to, qualifications and years of experience. The analysis unit, for example, uses a generation AI to evaluate the user's level of expertise. For example, the analysis unit inputs a prompt to the generation AI, such as "Please rate this user's level of expertise," and evaluates the expertise level. The analysis unit can also adjust the use of technical terms in the analysis according to the level of expertise. For example, if the user has expert knowledge, the analysis uses a lot of technical terms. If the user does not have expert knowledge, the analysis is performed using simple language. The analysis is performed using appropriate technical terms according to the user's level of expertise. This makes it possible to adjust the use of technical terms in the analysis according to the user's level of expertise. === Hard Collateral 1-1 === Each of the multiple elements including the reading unit, generating unit, suggesting unit, and input unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reading unit can read chat conversations using the camera 42 or microphone 38B of the smart device 14. The generating unit is realized by the specific processing unit 290 of the data processing device 12 and generates appropriate answer suggestions based on the read conversations. The suggesting unit is realized by the control unit 46A of the smart device 14 and suggests the generated suggestion to the user in a pop-up. The input unit can input simple sentences using the touch panel 38A or microphone 38B of the smart device 14. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned reading unit, generating unit, suggesting unit, and input unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reading unit can read chat conversations using the camera 42 and microphone 238 of the smart glasses 214. The generating unit is realized by the specific processing unit 290 of the data processing device 12 and generates appropriate answer proposals based on the read conversations. The suggesting unit is realized by the control unit 46A of the smart glasses 214 and suggests the generated proposals to the user in a pop-up. The input unit can input simple sentences using the microphone 238 of the smart glasses 214. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned reading unit, generating unit, suggesting unit, and input unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the reading unit can read chat conversations using the camera 42 or microphone 238 of the headset type terminal 314. The generating unit is realized by the specific processing unit 290 of the data processing device 12 and generates appropriate answer proposals based on the read conversations. The suggesting unit is realized by the control unit 46A of the headset type terminal 314 and suggests the generated proposals to the user in a pop-up. The input unit can input simple sentences using the microphone 238 of the headset type terminal 314. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reading unit, generating unit, suggesting unit, and input unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reading unit can read chat conversations using the camera 42 or microphone 238 of the robot 414. The generating unit is realized by the specific processing unit 290 of the data processing device 12 and generates appropriate answer proposals based on the read conversations. The suggesting unit is realized by the control unit 46A of the robot 414 and suggests the generated proposals to the user in a pop-up. The input unit can input simple sentences using the microphone 238 of the robot 414.

[0137] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0138] The reader can refer to the user's past conversation history to more accurately understand the context of the current conversation. For example, it can infer the intention of the current conversation based on phrases and expressions frequently used by the user in the past. It can also accumulate knowledge about specific topics from past conversation history and provide related information. This makes it possible to utilize the user's past conversation history to perform more accurate conversation analysis.

[0139] The suggestion unit can estimate the user's emotions and adjust the display method of suggestions based on the estimated emotions. For example, if the user is feeling stressed, a simple, highly visible display method is provided. If the user is relaxed, a display method including detailed information is provided. If the user is in a hurry, a display method that focuses on the main points is provided. This makes it possible to display optimal suggestions according to the user's emotions.

[0140] The suggestion unit can customize the suggestion content according to the user's current task. For example, if the user is in a meeting, suggestion related to the meeting is displayed preferentially. If the user is replying to an email, suggestion related to the email is displayed preferentially. If the user is working on a project, suggestion related to the project is displayed preferentially. This makes it possible to provide optimal suggestions according to the user's current task.

[0141] The input unit can estimate the user's emotions and adjust the timing of input based on the estimated emotions. For example, if the user is feeling stressed, the input timing can be delayed to relax the user. If the user is relaxed, the input can be prompted at a normal timing. If the user is in a hurry, the input can be prompted quickly. This makes it possible to optimize the input timing based on the user's emotions.

[0142] The input unit can analyze the user's past input history and select the optimal input method. For example, it can prioritize and suggest input methods (voice, text, etc.) that the user has frequently used in the past. It can also predict and suggest the input method that will be used during a specific time period based on the user's past input history. This makes it possible to utilize the user's past input history to provide the optimal input method.

[0143] The generation unit can estimate the user's emotions and adjust the expression style of the generated sentences based on the estimated emotions. For example, if the user is stressed, a concise and clear expression style is used. If the user is relaxed, a detailed and polite expression style is used. If the user is in a hurry, an expression style that can be quickly understood is used. This makes it possible to generate optimal sentence expressions based on the user's emotions.

[0144] The generator can apply different generation algorithms depending on the category of the conversation. For example, for business-related conversations, it applies a generation algorithm that takes into account technical terminology and business context. For private conversations, it applies a generation algorithm that takes into account casual expressions and everyday context. For technical conversations, it applies a generation algorithm that takes into account technical terminology and specialized knowledge. This makes it possible to generate optimal sentences according to the category of the conversation.

[0145] The generation unit can improve the accuracy of generation by referring to the user's past generation results. For example, the generation unit can improve the accuracy of generation by referring to sentences generated by the user in the past. The user's past generation results can be used to deepen understanding of specific contexts and topics. This makes it possible to generate sentences with higher accuracy by utilizing the user's past generation results.

[0146] The rewriting unit can estimate the user's emotions and adjust the rewritten expression based on the estimated emotions. For example, if the user is stressed, a concise and clear expression is used. If the user is relaxed, a detailed and polite expression is used. If the user is in a hurry, an expression that can be quickly understood is used. This makes it possible to optimally rewrite the expression based on the user's emotions.

[0147] The rewriting unit can apply different rewriting algorithms depending on the category of the input text. For example, for business-related text, it applies a rewriting algorithm that takes into account technical terms and business context. For private text, it applies a rewriting algorithm that takes into account casual expressions and everyday context. For technical text, it applies a rewriting algorithm that takes into account technical terms and specialized knowledge. This enables optimal rewriting according to the category of the input text.

[0148] The processing flow of the second embodiment will be briefly explained below.

[0149] Step 1: The reader reads the chat conversation. The reader uses the generator AI to analyze the chat conversation and understand the context and content. The reader can also allow the generator AI to extract keywords and important phrases from the conversation. For example, the reader inputs a prompt to the generator AI saying, "Please extract the main points of this conversation," and extracts the main points of the conversation. Step 2: The generator generates appropriate response text suggestions based on the conversation read by the reader. The generator uses a generation AI to analyze the context and content of the conversation and generate appropriate response text suggestions. For example, the generator inputs a prompt to the generation AI saying, "Please generate an appropriate response to this conversation," and generates a response text suggestion. Step 3: The suggestion unit suggests the sentences generated by the generation unit to the user. The suggestion unit displays the generated sentences in a pop-up, and the user can click a button to submit the sentences.

[0150] 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.

[0151] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<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.

[0152] 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.

[0153] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0154] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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).

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0164] 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. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0170] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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).

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0180] 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 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0186] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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).

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0197] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. 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 the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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).

[0207] 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.

[0208] 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."

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] [Explanation of symbols]

[0222] 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 reading unit that reads chat conversations; a generator that generates appropriate answer suggestions based on the conversation read by the reader; a suggestion unit that suggests the sentence suggestions generated by the generation unit to a user. A system characterized by:

2. The proposal unit Display generated text suggestions in a popup The system of claim 1 .

3. The proposal unit The user clicks a button to send the text The system of claim 1 .

4. Equipped with an input section for entering simple sentences The system of claim 1 .

5. The input unit Equipped with a rewriting unit that rewrites simple sentences into appropriate sentences 5. The system of claim 4.

6. The generation unit Equipped with an analysis unit that analyzes conversation context and keywords The system of claim 1 .

7. The rewriting unit Rewrite simple sentences entered by the user into appropriate sentences 6. The system of claim 5.

8. The reading unit Estimate the user's emotions and adjust the accuracy of conversation interpretation based on the estimated user emotions. The system of claim 1 .

9. The reading unit When reading, prioritize reading based on the importance of the conversation The system of claim 1 .

Images