system

Abstract

The system according to this embodiment aims to efficiently create notices distributed by PTAs and schools. [Solution] The system according to this embodiment comprises a reception unit, a generation unit, and an editing unit. The reception unit receives input of key points and objectives. The generation unit automatically creates a notice based on the key points and objectives received by the reception unit. The editing unit reviews and edits the notice generated by the generation unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to the description of the chatbot's 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that it takes time and labor to create notices distributed from PTAs or schools.

[0005] The system according to the embodiment aims to efficiently create notices distributed from PTAs or schools.

Means for Solving the Problems

[0006] The system according to the embodiment includes a reception unit, a generation unit, and an editing unit. The reception unit receives inputs of key points and purposes. The generation unit automatically creates a notice based on the key points and purposes received by the reception unit. The editing unit checks and edits the notice generated by the generation unit.

Effects of the Invention

[0007] The system according to this embodiment can efficiently create notices distributed by PTAs and schools. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0014] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the 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, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The automated notice generation system according to an embodiment of the present invention is a system in which AI automatically generates the content of postcards and notices distributed by PTAs and schools. This automated notice generation system allows users to input key points and objectives, and the AI ​​automatically creates notices in an appropriate tone and format. For example, it instantly generates notices tailored to the unique needs of schools, such as event announcements, emergency contacts, and requests to parents. The generated notices can be easily reviewed and edited. First, the user inputs the key points and objectives. At this stage, the user only needs to briefly input the content and purpose of the notice. For example, they might input key points such as "Notification of Sports Day" or "Emergency Contact." This information is then input to the AI. Next, the AI ​​analyzes the input key points and objectives and automatically creates a notice in an appropriate tone and format. The AI ​​generates the optimal text based on past data and example texts. For example, in the case of "Notification of Sports Day," a text including details such as the date, time, location, and items to bring is generated. The generated notices can be reviewed and edited by the user. For example, if there are errors in the generated text or if additional information needs to be added, users can easily edit it. This enables the creation of quick and accurate announcements. This system improves the efficiency of PTA and school operations and facilitates smooth communication of information to parents and stakeholders. For instance, prompt notification of events and emergency contacts increases parents' sense of security. Furthermore, since the AI ​​automatically generates the text, the burden on staff is reduced. As a result, the automated announcement generation system can quickly and accurately generate the content of postcards and announcements distributed by PTAs and schools.

[0029] The automated notification text generation system according to this embodiment comprises a reception unit, a generation unit, and an editing unit. The reception unit receives input of key points and objectives. Key points and objectives include, but are not limited to, event notifications, emergency contacts, and requests to parents. For example, the reception unit receives key points and objectives entered by the user in text format. The reception unit can also receive key points and objectives using voice input. For example, if the user inputs "Notification of Sports Day" by voice, the reception unit converts the content into text data. Furthermore, the reception unit can automatically display key points and objectives that the user frequently enters as candidates based on past input history. The generation unit automatically creates a notification text based on the key points and objectives received by the reception unit. For example, the generation unit generates the most suitable text based on past data and example sentences. The generation unit uses text generation AI (e.g., LLM) to generate text based on key points and objectives. Furthermore, the generation unit can use multimodal generation AI to generate notification texts that include not only text but also images, graphs, etc. For example, in the case of a notice to hold a sports day, a document containing details such as the date, time, location, and items to bring is generated. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or it may be performed without using a generation AI. The editing unit checks and edits the notice document generated by the generation unit. The editing unit allows users to easily edit the document if, for example, there are errors in the generated document or if additional information needs to be added. The editing unit can, for example, display the generated document in a text editor, allowing the user to edit it directly. The editing unit also has a function to highlight which parts of the generated document were generated by the AI. For example, by color-coding the AI-generated parts, it makes it easier for the user to edit. As a result, the automated notice document generation system according to this embodiment can automate and efficiently perform everything from inputting key points and objectives to generating, checking, and editing the notice document.

[0030] The reception desk accepts input of key points and objectives. These key points and objectives include, but are not limited to, event notifications, emergency contacts, and requests to parents. The reception desk accepts the key points and objectives entered by the user in text format. Specifically, when the user uses a keyboard, a dedicated input form is provided where the key points and objectives can be entered. This input form is designed to be simple and intuitive for ease of use. The reception desk can also accept key points and objectives using voice input. For example, if the user voice-inputs "Notification of Sports Day," the reception desk converts the content into text data. This voice input function is implemented using speech recognition technology, enabling high-precision conversion of user speech into text. Furthermore, the reception desk can automatically display key points and objectives that the user frequently inputs based on past input history. For example, if a user has frequently entered "Invitation to Parents' Meeting" in the past, "Invitation to Parents' Meeting" will be displayed as a suggestion the next time the user inputs. This function is implemented using an algorithm that learns the user's input history, making the user's input work more efficient. This allows the reception desk to support users in quickly and accurately entering key points and objectives, thereby improving the overall efficiency of the system.

[0031] The generation unit automatically creates announcement texts based on the key points and objectives received by the reception unit. For example, the generation unit generates the most suitable text based on past data and example sentences. Specifically, it refers to a database of previously created announcement texts and extracts example sentences based on similar key points and objectives. Based on these example sentences, the generation unit creates a new announcement text. The generation unit uses text generation AI (e.g., LLM) to generate text based on the key points and objectives. LLM has learned from a large amount of text data and has the ability to generate natural-sounding text. For example, if a user enters "Notification of Sports Day," LLM generates text including details such as the date, time, location, and items to bring. Furthermore, the generation unit can use multimodal generation AI to generate announcement texts that include not only text but also images and graphs. For example, in the case of a Sports Day notification, an announcement text including images such as a Sports Day poster and schedule will be generated. Some or all of the above-described processes in the generation unit may be performed using, for example, generation AI, or without generation AI. If generation AI is not used, text can be generated based on predefined templates or rules. This allows the generation unit to quickly and accurately generate optimal notification texts tailored to the user's key points and objectives.

[0032] The editorial team reviews and edits the announcement text generated by the generation team. For example, if there are errors in the generated text or if additional information needs to be added, the editorial team can easily edit it. Specifically, the generated text is displayed in a text editor, allowing users to edit it directly. This text editor provides an intuitive interface for user-friendliness, making it easy to correct or add to the text. The editorial team also includes a function to highlight which parts of the generated text were generated by AI. For example, AI-generated parts can be color-coded to make editing easier for the user. This feature helps users distinguish between AI-generated and manually entered parts, improving the efficiency of the editing process. Furthermore, the editorial team has a function to save the user's editing history for later reference. This allows users to review past edits and use them as a reference when making similar corrections. This ensures the quality of the generated announcement text and allows the editorial team to create content that satisfies users.

[0033] The automated notification text generation system includes a learning unit that learns from past data and example texts. The learning unit, for example, stores previously generated notification texts and example texts in a database and performs learning based on them. The learning unit uses a generation AI to analyze past data and example texts and build a model for optimal text generation. For example, the learning unit learns from past sports day announcements and emergency contact examples and accumulates knowledge to generate new notification texts based on them. Some or all of the above processing in the learning unit may be performed using the generation AI or not. As a result, the accuracy of the generated text improves by learning from past data and example texts.

[0034] The automated notification text generation system includes a relearning unit that relearns the content edited by the user. The relearning unit, for example, stores the content of the notification text edited by the user in a database and relearns based on that. The relearning unit uses a generation AI to analyze the content edited by the user and updates the generation model. For example, the relearning unit learns the information added or modified by the user and updates the knowledge for generating new notification texts based on that. Some or all of the above processing in the relearning unit may be performed using the generation AI or not. As a result, the accuracy of the generated text is further improved by relearning the content edited by the user.

[0035] The automated notification text generation system includes a display unit that clearly indicates which parts of the generated text were generated by AI. For example, the display unit can color-code the AI-generated parts of the text. The display unit uses the generation AI to analyze each part of the generated text and identify the AI-generated parts. For example, the display unit can underline and highlight the AI-generated parts of the text. The display unit can also display the AI-generated parts of the text in bold. Some or all of the above processing in the display unit may be performed using the generation AI, or it may be performed without the generation AI. This makes it easier for users to edit the text by clearly indicating which parts were generated by AI.

[0036] The generation unit can generate optimal text based on past data and example sentences. For example, the generation unit can learn from past examples of announcements for sports days and emergency notices, and generate new announcements based on them. The generation unit uses generation AI to analyze past data and example sentences and generate optimal text. For example, the generation unit can generate text that includes details such as the date, time, place, and items to bring, based on past data. The generation unit can also use generation AI to adjust the writing style and expression to generate optimal text. Some or all of the above processing in the generation unit may be performed using generation AI, or it may be performed without generation AI. This improves the quality of the generated text by generating optimal text based on past data and example sentences.

[0037] The editorial team can easily edit generated announcements if there are errors or if users wish to add additional information. For example, the editorial team can display the generated text in a text editor, allowing users to edit it directly. The editorial team can also use generation AI to automatically detect errors in the generated text and suggest corrections. For example, the editorial team can automatically detect grammatical errors and spelling mistakes in the generated text and suggest corrections. The editorial team can also automatically detect contextual errors in the generated text and suggest corrections. Some or all of the above processes in the editorial team may be performed using generation AI or not. This allows users to easily edit generated announcements if there are errors or if users wish to add additional information.

[0038] The reception desk can analyze the user's past input history and suggest the optimal input format. For example, the reception desk can automatically display as suggestions the key points and objectives that the user has frequently entered in the past. The reception desk uses generative AI to analyze the user's past input history and suggest the optimal input format. For example, the reception desk prioritizes suggesting input methods (voice, text, etc.) that the user has used in the past. The reception desk can also predict and suggest key points and objectives to be used at specific times based on the user's past input history. Some or all of the above processing in the reception desk may be performed using generative AI or not. This allows the reception desk to suggest the optimal input format to the user by analyzing past input history.

[0039] The reception unit can filter input content based on the user's current situation and areas of interest when they input key points and objectives. For example, the reception unit can prioritize displaying relevant key points and objectives according to the user's current situation. The reception unit uses generative AI to analyze the user's current situation and areas of interest and filter the input content. For example, the reception unit can suggest relevant key points and objectives based on the user's areas of interest. The reception unit can also filter out unnecessary input content based on the user's current situation and areas of interest. Some or all of the above processing in the reception unit may be performed using generative AI or not. This allows for the provision of more appropriate input content by filtering input content based on the user's current situation and areas of interest.

[0040] The reception desk can prioritize accepting highly relevant input content by considering the user's geographical location when inputting key points and objectives. For example, if the user is in a specific region, the reception desk will prioritize inputting key points and objectives related to that region. The reception desk uses generative AI to analyze the user's geographical location and suggest highly relevant input content. For example, if the user is on the move, the reception desk will suggest relevant key points and objectives based on their current location. The reception desk can also prioritize inputting key points and objectives related to a specific location if the user is in that location. Some or all of the above processing in the reception desk may be performed using generative AI, or it may be performed without generative AI. This allows the reception desk to prioritize accepting highly relevant input content by considering the user's geographical location.

[0041] The reception desk can analyze the user's social media activity when they input key points and objectives, and suggest relevant input content. For example, the reception desk can suggest relevant key points and objectives based on information the user has shared on social media. The reception desk uses generative AI to analyze the user's social media activity and suggest relevant input content. For example, the reception desk can extract topics of interest from the user's social media activity and suggest relevant key points and objectives. The reception desk can also analyze the user's social media activity history and suggest relevant key points and objectives. Some or all of the above processing in the reception desk may be performed using generative AI, or it may be performed without generative AI. This allows the reception desk to suggest relevant input content by analyzing the user's social media activity.

[0042] The generation unit can adjust the level of detail in the text based on the importance of the main points and objectives during generation. For example, if the main points or objectives are important, the generation unit will generate text that includes detailed explanations. The generation unit uses generation AI to analyze the importance of the main points and objectives and adjust the level of detail in the text. For example, if the main points or objectives are of low importance, the generation unit will generate concise text. The generation unit can also generate text with an appropriate level of detail depending on the importance of the main points and objectives. Some or all of the above processing in the generation unit may be performed using generation AI, or it may be performed without generation AI. This allows for the generation of text with an appropriate level of detail by adjusting the level of detail in the text based on the importance of the main points and objectives.

[0043] The generation unit can apply different generation algorithms depending on the category of key points and purpose during generation. For example, in the case of event notifications, the generation unit generates text that includes details such as the date, time, location, and items to bring. The generation unit uses generation AI to analyze the category of key points and purpose and apply an appropriate generation algorithm. For example, in the case of emergency contact, the generation unit generates a concise text for quick communication. The generation unit can also generate a text using polite language in the case of a request to parents. Some or all of the above processing in the generation unit may be performed using generation AI, or it may be performed without generation AI. This allows for the generation of more appropriate text by applying different generation algorithms depending on the category of key points and purpose.

[0044] The generation unit can determine the generation priority based on the submission timing of the main points and objectives during the generation process. For example, in the case of an urgent notice, the generation unit will generate the document with the highest priority. The generation unit uses generation AI to analyze the submission timing of the main points and objectives and determine the generation priority. For example, in the case of an event notification, the generation unit will determine the generation priority based on the submission timing. The generation unit can also adjust the generation priority according to the submission timing in the case of a request letter to a parent or guardian. Some or all of the above processing in the generation unit may be performed using generation AI or not. This allows for the generation of documents at the appropriate time by determining the generation priority based on the submission timing of the main points and objectives.

[0045] The generation unit can adjust the order of the generated text based on the relevance of key points and objectives during the generation process. For example, the generation unit may place important key points and objectives first, and then arrange related information sequentially. The generation unit uses generation AI to analyze the relevance of key points and objectives and adjust the order of the text. For example, the generation unit may group highly relevant key points and objectives and adjust their order. The generation unit can also generate text in an appropriate order based on the relevance of key points and objectives. Some or all of the above-described processes in the generation unit may be performed using generation AI, or they may not. This allows for the generation of more easily understandable text by adjusting the order of text based on the relevance of key points and objectives.

[0046] The editorial department can automatically detect errors in the generated text during editing and suggest corrections. For example, the editorial department can automatically detect grammatical errors in the generated text and suggest corrections. The editorial department can use generative AI to analyze errors in the generated text and suggest corrections. For example, the editorial department can automatically detect spelling mistakes in the generated text and suggest corrections. The editorial department can also automatically detect contextual errors in the generated text and suggest corrections. Some or all of the above processes in the editorial department may be performed using generative AI, or they may not. This improves the quality of the text by automatically detecting errors in the generated text and suggesting corrections.

[0047] The editorial team can suggest the optimal editing method by referring to the user's past editing history during the editing process. For example, the editorial team can suggest the optimal editing method based on the user's past editing history. The editorial team can also use generative AI to analyze the user's past editing history and suggest the optimal editing method. For example, the editorial team can prioritize suggesting frequently performed edits based on the user's past editing history. Furthermore, the editorial team can analyze the user's past editing history and suggest the optimal editing method. Some or all of the above processes in the editorial team may be performed using generative AI, or they may not. This allows the editorial team to suggest the optimal editing method by referring to the user's past editing history.

[0048] The editorial team can propose the optimal editing method while considering the user's geographical location. For example, if the user is in a specific region, the editorial team will prioritize editing content related to that region. The editorial team uses generative AI to analyze the user's geographical location and propose the optimal editing method. For example, if the user is on the move, the editorial team will propose the optimal editing method based on their current location. The editorial team can also prioritize editing content related to a specific location if the user is in that location. Some or all of the above processing by the editorial team may be performed using generative AI, or not. This allows the editorial team to propose the optimal editing method by considering the user's geographical location.

[0049] The editorial team can analyze users' social media activity during the editing process and suggest relevant editorial content. For example, the editorial team can suggest relevant editorial content based on information shared by users on social media. The editorial team can use generative AI to analyze users' social media activity and suggest relevant editorial content. For example, the editorial team can extract topics of interest from users' social media activity and suggest relevant editorial content. The editorial team can also analyze users' social media activity history and suggest relevant editorial content. Some or all of the above processes performed by the editorial team may be done using generative AI or not. This allows for the suggestion of relevant editorial content by analyzing users' social media activity.

[0050] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal learning algorithm based on past learning data. The learning unit can analyze past learning data using generative AI and optimize the learning algorithm. For example, the learning unit can extract effective learning patterns from past learning data and optimize the algorithm. The learning unit can also analyze past learning data and adjust the parameters of the learning algorithm. Some or all of the above processes in the learning unit may be performed using generative AI or not. This allows the learning algorithm to be optimized by referring to past learning data.

[0051] The learning unit can improve the accuracy of learning by combining different example sentences and data sources during training. For example, the learning unit ensures diversity in the training data by combining different example sentences. The learning unit uses generative AI to analyze different example sentences and data sources and improve the accuracy of learning. For example, the learning unit collects information from different data sources to improve the accuracy of learning. The learning unit can also improve the accuracy of the learning algorithm by combining different example sentences and data sources. Some or all of the above processing in the learning unit may be performed using generative AI or not. As a result, the accuracy of learning is improved by combining different example sentences and data sources.

[0052] The learning unit can weight the training data based on the submission dates of key points and objectives during training. For example, the learning unit can assign higher weights to training data for key points and objectives with upcoming submission dates. The learning unit uses generative AI to analyze the submission dates of key points and objectives and weight the training data. For example, the learning unit can assign lower weights to training data for key points and objectives with distant submission dates. The learning unit can also adjust the weighting of the training data based on the submission dates of key points and objectives. Some or all of the above processing in the learning unit may be performed using generative AI or not. This improves the effectiveness of training by weighting the training data based on the submission dates of key points and objectives.

[0053] The learning unit can select optimal training data during training by considering the user's geographical location information. For example, if the user is in a specific region, the learning unit will select training data related to that region. The learning unit uses generative AI to analyze the user's geographical location information and select optimal training data. For example, if the user is on the move, the learning unit will select optimal training data based on the user's current location. The learning unit can also select training data related to a specific location if the user is in that location. Some or all of the above processing in the learning unit may be performed using generative AI or not. This allows for the selection of optimal training data by considering the user's geographical location information.

[0054] The relearning unit can optimize the relearning algorithm by referring to past editing history during relearning. For example, the relearning unit selects the optimal relearning algorithm based on past editing history. The relearning unit analyzes past editing history using generative AI and optimizes the relearning algorithm. For example, the relearning unit extracts effective relearning patterns from past editing history and optimizes the algorithm. The relearning unit can also analyze past editing history and adjust the parameters of the relearning algorithm. Some or all of the above processing in the relearning unit may be performed using generative AI or not. This allows the relearning algorithm to be optimized by referring to past editing history.

[0055] The retraining unit can improve the accuracy of retraining by combining different example sentences and data sources during the retraining process. For example, the retraining unit ensures diversity in the retraining data by combining different example sentences. The retraining unit uses generative AI to analyze different example sentences and data sources and improve the accuracy of retraining. For example, the retraining unit collects information from different data sources to improve the accuracy of retraining. The retraining unit can also improve the accuracy of the retraining algorithm by combining different example sentences and data sources. Some or all of the above processing in the retraining unit may be performed using generative AI or not. This improves the accuracy of retraining by combining different example sentences and data sources.

[0056] The retraining unit can weight the retraining data based on the submission dates of key points and objectives during retraining. For example, the retraining unit can assign higher weights to key points and objectives with upcoming submission dates. The retraining unit uses generative AI to analyze the submission dates of key points and objectives and weight the retraining data. For example, the retraining unit can assign lower weights to key points and objectives with distant submission dates. The retraining unit can also adjust the weighting of the retraining data based on the submission dates of key points and objectives. Some or all of the above processing in the retraining unit may be performed using generative AI or not. This improves the effectiveness of retraining by weighting the retraining data based on the submission dates of key points and objectives.

[0057] The retraining unit can select the optimal retraining data by considering the user's geographical location information during retraining. For example, if the user is in a specific region, the retraining unit will select retraining data related to that region. The retraining unit uses generative AI to analyze the user's geographical location information and select the optimal retraining data. For example, if the user is on the move, the retraining unit will select the optimal retraining data based on the user's current location. The retraining unit can also select retraining data related to a specific location if the user is in that location. Some or all of the above processing in the retraining unit may be performed using generative AI or not. This allows for the selection of optimal retraining data by considering the user's geographical location information.

[0058] The display unit can highlight which parts of the generated text were generated by AI during display. For example, the display unit can highlight the AI-generated parts of the generated text by color-coding them. The display unit uses the generation AI to analyze each part of the generated text and identify the AI-generated parts. For example, the display unit can underline the AI-generated parts of the generated text to highlight them. The display unit can also highlight the AI-generated parts of the generated text in bold. Some or all of the above processing in the display unit may be performed using the generation AI, or it may be performed without using the generation AI. This makes it easier for the user to edit the text by highlighting which parts of the generated text were generated by AI.

[0059] The display unit can select the optimal display method by referring to the user's past display history when displaying information. For example, the display unit can select the optimal display method based on the display method the user has preferred to use in the past. The display unit can also use a generation AI to analyze the user's past display history and select the optimal display method. For example, the display unit can prioritize suggesting frequently used display methods based on the user's past display history. The display unit can also analyze the user's past display history and select the optimal display method. Some or all of the above processing in the display unit may be performed using a generation AI, or it may be performed without a generation AI. This allows the optimal display method to be selected by referring to the user's past display history.

[0060] The display unit can select the optimal display method when displaying information, taking into account the user's device information. For example, if the user is using a smartphone, the display unit provides a display method that matches the screen size. The display unit uses a generation AI to analyze the user's device information and select the optimal display method. For example, if the user is using a tablet, the display unit provides a display method optimized for a large screen. The display unit can also provide a concise and highly visible display method if the user is using a smartwatch. Some or all of the above processing in the display unit may be performed using a generation AI, or it may be performed without a generation AI. This allows the optimal display method to be selected by taking into account the user's device information.

[0061] The display unit can analyze the user's social media activity and suggest relevant display content when displaying information. For example, the display unit can suggest relevant display content based on information shared by the user on social media. The display unit can use generative AI to analyze the user's social media activity and suggest relevant display content. For example, the display unit can extract topics of interest from the user's social media activity and suggest relevant display content. The display unit can also analyze the user's social media activity history and suggest relevant display content. Some or all of the above processing in the display unit may be performed using generative AI or not. This allows the display unit to suggest relevant display content by analyzing the user's social media activity.

[0062] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0063] The automated notification message generation system can suggest the most suitable template based on the user's past input history. For example, it prioritizes displaying templates that the user has frequently used in the past. The reception desk uses generation AI to analyze the user's past input history and suggest the most suitable template. For example, it can suggest templates from the user's past used templates that are suitable for a specific time of day or event. It can also suggest templates based on specific keywords from the user's past input history. This streamlines the input process by suggesting the most suitable template based on the user's past input history.

[0064] The automated notification text generation system includes a display unit that clearly indicates which parts of the generated text were generated by AI. For example, the display unit can color-code the AI-generated parts of the text. The display unit uses the generation AI to analyze each part of the generated text and identify the AI-generated sections. For example, the display unit can underline and highlight the AI-generated parts of the text. The display unit can also display the AI-generated parts of the text in bold. This makes it easier for users to edit the text by clearly indicating which parts were generated by AI.

[0065] The automated notification message generation system can prioritize receiving highly relevant input content by considering the user's geographical location. For example, if the user is in a specific region, the reception unit will prioritize inputting key points and objectives related to that region. The reception unit uses generation AI to analyze the user's geographical location and suggest highly relevant input content. For instance, if the user is on the move, it will suggest relevant key points and objectives based on their current location. Furthermore, if the user is in a specific location, it can prioritize inputting key points and objectives related to that location. This allows the system to prioritize receiving highly relevant input content by considering the user's geographical location.

[0066] The automated notification message generation system can analyze a user's social media activity and suggest relevant input content. The reception desk, for example, suggests relevant points and objectives based on information shared by the user on social media. The reception desk uses generation AI to analyze the user's social media activity and suggest relevant input content. For example, it can extract topics of interest from the user's social media activity and suggest relevant points and objectives. It can also analyze the user's social media activity history and suggest relevant points and objectives. In this way, by analyzing the user's social media activity, it can suggest relevant input content.

[0067] The automated notification text generation system can suggest the optimal editing method by referring to the user's past editing history. The editorial department, for example, suggests the optimal editing method based on the user's past edits. The editorial department uses generation AI to analyze the user's past editing history and suggest the optimal editing method. For example, it prioritizes suggesting frequently performed edits based on the user's past editing history. It can also analyze the user's past editing history and suggest the optimal editing method. This allows the system to suggest the optimal editing method by referring to the user's past editing history.

[0068] The following briefly describes the processing flow for example form 1.

[0069] Step 1: The reception desk accepts input of key points and objectives. These include event notifications, emergency contacts, and requests to parents. The reception desk accepts the key points and objectives entered by the user in text format, and can also accept them using voice input. For example, if a user voice-inputs "Notification of Sports Day," the reception desk converts that into text data. Furthermore, the reception desk can automatically display frequently entered key points and objectives as suggestions based on past input history. Step 2: The generation unit automatically creates a notice based on the key points and purpose received by the reception unit. The generation unit generates the optimal text based on past data and example sentences, and uses text generation AI (e.g., LLM) to generate text that is based on the key points and purpose. In addition, the generation unit can use multimodal generation AI to generate notices that include not only text but also images, graphs, etc. For example, in the case of a sports day announcement, a text including details such as the date, time, location, and what to bring will be generated. Step 3: The editorial team reviews and edits the announcement text generated by the generation team. The editorial team can easily edit the generated text if there are errors or if additional information needs to be added. The editorial team displays the generated text in a text editor, allowing users to edit it directly. The editorial team also has a function to highlight which parts of the generated text were generated by AI. For example, the AI-generated parts can be color-coded to make it easier for users to edit.

[0070] (Example of form 2) The automated notice generation system according to an embodiment of the present invention is a system in which AI automatically generates the content of postcards and notices distributed by PTAs and schools. This automated notice generation system allows users to input key points and objectives, and the AI ​​automatically creates notices in an appropriate tone and format. For example, it instantly generates notices tailored to the unique needs of schools, such as event announcements, emergency contacts, and requests to parents. The generated notices can be easily reviewed and edited. First, the user inputs the key points and objectives. At this stage, the user only needs to briefly input the content and purpose of the notice. For example, they might input key points such as "Notification of Sports Day" or "Emergency Contact." This information is then input to the AI. Next, the AI ​​analyzes the input key points and objectives and automatically creates a notice in an appropriate tone and format. The AI ​​generates the optimal text based on past data and example texts. For example, in the case of "Notification of Sports Day," a text including details such as the date, time, location, and items to bring is generated. The generated notices can be reviewed and edited by the user. For example, if there are errors in the generated text or if additional information needs to be added, users can easily edit it. This enables the creation of quick and accurate announcements. This system improves the efficiency of PTA and school operations and facilitates smooth communication of information to parents and stakeholders. For instance, prompt notification of events and emergency contacts increases parents' sense of security. Furthermore, since the AI ​​automatically generates the text, the burden on staff is reduced. As a result, the automated announcement generation system can quickly and accurately generate the content of postcards and announcements distributed by PTAs and schools.

[0071] The automated notification text generation system according to this embodiment comprises a reception unit, a generation unit, and an editing unit. The reception unit receives input of key points and objectives. Key points and objectives include, but are not limited to, event notifications, emergency contacts, and requests to parents. For example, the reception unit receives key points and objectives entered by the user in text format. The reception unit can also receive key points and objectives using voice input. For example, if the user inputs "Notification of Sports Day" by voice, the reception unit converts the content into text data. Furthermore, the reception unit can automatically display key points and objectives that the user frequently enters as candidates based on past input history. The generation unit automatically creates a notification text based on the key points and objectives received by the reception unit. For example, the generation unit generates the most suitable text based on past data and example sentences. The generation unit uses text generation AI (e.g., LLM) to generate text based on key points and objectives. Furthermore, the generation unit can use multimodal generation AI to generate notification texts that include not only text but also images, graphs, etc. For example, in the case of a notice to hold a sports day, a document containing details such as the date, time, location, and items to bring is generated. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or it may be performed without using a generation AI. The editing unit checks and edits the notice document generated by the generation unit. The editing unit allows users to easily edit the document if, for example, there are errors in the generated document or if additional information needs to be added. The editing unit can, for example, display the generated document in a text editor, allowing the user to edit it directly. The editing unit also has a function to highlight which parts of the generated document were generated by the AI. For example, by color-coding the AI-generated parts, it makes it easier for the user to edit. As a result, the automated notice document generation system according to this embodiment can automate and efficiently perform everything from inputting key points and objectives to generating, checking, and editing the notice document.

[0072] The reception desk accepts input of key points and objectives. These key points and objectives include, but are not limited to, event notifications, emergency contacts, and requests to parents. The reception desk accepts the key points and objectives entered by the user in text format. Specifically, when the user uses a keyboard, a dedicated input form is provided where the key points and objectives can be entered. This input form is designed to be simple and intuitive for ease of use. The reception desk can also accept key points and objectives using voice input. For example, if the user voice-inputs "Notification of Sports Day," the reception desk converts the content into text data. This voice input function is implemented using speech recognition technology, enabling high-precision conversion of user speech into text. Furthermore, the reception desk can automatically display key points and objectives that the user frequently inputs based on past input history. For example, if a user has frequently entered "Invitation to Parents' Meeting" in the past, "Invitation to Parents' Meeting" will be displayed as a suggestion the next time the user inputs. This function is implemented using an algorithm that learns the user's input history, making the user's input work more efficient. This allows the reception desk to support users in quickly and accurately entering key points and objectives, thereby improving the overall efficiency of the system.

[0073] The generation unit automatically creates announcement texts based on the key points and objectives received by the reception unit. For example, the generation unit generates the most suitable text based on past data and example sentences. Specifically, it refers to a database of previously created announcement texts and extracts example sentences based on similar key points and objectives. Based on these example sentences, the generation unit creates a new announcement text. The generation unit uses text generation AI (e.g., LLM) to generate text based on the key points and objectives. LLM has learned from a large amount of text data and has the ability to generate natural-sounding text. For example, if a user enters "Notification of Sports Day," LLM generates text including details such as the date, time, location, and items to bring. Furthermore, the generation unit can use multimodal generation AI to generate announcement texts that include not only text but also images and graphs. For example, in the case of a Sports Day notification, an announcement text including images such as a Sports Day poster and schedule will be generated. Some or all of the above-described processes in the generation unit may be performed using, for example, generation AI, or without generation AI. If generation AI is not used, text can be generated based on predefined templates or rules. This allows the generation unit to quickly and accurately generate optimal notification texts tailored to the user's key points and objectives.

[0074] The editorial team reviews and edits the announcement text generated by the generation team. For example, if there are errors in the generated text or if additional information needs to be added, the editorial team can easily edit it. Specifically, the generated text is displayed in a text editor, allowing users to edit it directly. This text editor provides an intuitive interface for user-friendliness, making it easy to correct or add to the text. The editorial team also includes a function to highlight which parts of the generated text were generated by AI. For example, AI-generated parts can be color-coded to make editing easier for the user. This feature helps users distinguish between AI-generated and manually entered parts, improving the efficiency of the editing process. Furthermore, the editorial team has a function to save the user's editing history for later reference. This allows users to review past edits and use them as a reference when making similar corrections. This ensures the quality of the generated announcement text and allows the editorial team to create content that satisfies users.

[0075] The automated notification text generation system includes a learning unit that learns from past data and example texts. The learning unit, for example, stores previously generated notification texts and example texts in a database and performs learning based on them. The learning unit uses a generation AI to analyze past data and example texts and build a model for optimal text generation. For example, the learning unit learns from past sports day announcements and emergency contact examples and accumulates knowledge to generate new notification texts based on them. Some or all of the above processing in the learning unit may be performed using the generation AI or not. As a result, the accuracy of the generated text improves by learning from past data and example texts.

[0076] The automated notification text generation system includes a relearning unit that relearns the content edited by the user. The relearning unit, for example, stores the content of the notification text edited by the user in a database and relearns based on that. The relearning unit uses a generation AI to analyze the content edited by the user and updates the generation model. For example, the relearning unit learns the information added or modified by the user and updates the knowledge for generating new notification texts based on that. Some or all of the above processing in the relearning unit may be performed using the generation AI or not. As a result, the accuracy of the generated text is further improved by relearning the content edited by the user.

[0077] The automated notification text generation system includes a display unit that clearly indicates which parts of the generated text were generated by AI. For example, the display unit can color-code the AI-generated parts of the text. The display unit uses the generation AI to analyze each part of the generated text and identify the AI-generated parts. For example, the display unit can underline and highlight the AI-generated parts of the text. The display unit can also display the AI-generated parts of the text in bold. Some or all of the above processing in the display unit may be performed using the generation AI, or it may be performed without the generation AI. This makes it easier for users to edit the text by clearly indicating which parts were generated by AI.

[0078] The generation unit can generate optimal text based on past data and example sentences. For example, the generation unit can learn from past examples of announcements for sports days and emergency notices, and generate new announcements based on them. The generation unit uses generation AI to analyze past data and example sentences and generate optimal text. For example, the generation unit can generate text that includes details such as the date, time, place, and items to bring, based on past data. The generation unit can also use generation AI to adjust the writing style and expression to generate optimal text. Some or all of the above processing in the generation unit may be performed using generation AI, or it may be performed without generation AI. This improves the quality of the generated text by generating optimal text based on past data and example sentences.

[0079] The editorial team can easily edit generated announcements if there are errors or if users wish to add additional information. For example, the editorial team can display the generated text in a text editor, allowing users to edit it directly. The editorial team can also use generation AI to automatically detect errors in the generated text and suggest corrections. For example, the editorial team can automatically detect grammatical errors and spelling mistakes in the generated text and suggest corrections. The editorial team can also automatically detect contextual errors in the generated text and suggest corrections. Some or all of the above processes in the editorial team may be performed using generation AI or not. This allows users to easily edit generated announcements if there are errors or if users wish to add additional information.

[0080] The reception unit can estimate the user's emotions and adjust the input method for key points and objectives based on the estimated emotions. For example, if the user is stressed, the reception unit can provide a simple interface and minimize the input steps. The reception unit estimates the user's emotions using an emotion engine or generative AI. For example, the reception unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The reception unit can also record the user's voice and estimate their emotions using voice analysis technology. Furthermore, the reception unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This reduces the burden on the user by adjusting the input method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception unit may be performed using generative AI or not.

[0081] The reception desk can analyze the user's past input history and suggest the optimal input format. For example, the reception desk can automatically display as suggestions the key points and objectives that the user has frequently entered in the past. The reception desk uses generative AI to analyze the user's past input history and suggest the optimal input format. For example, the reception desk prioritizes suggesting input methods (voice, text, etc.) that the user has used in the past. The reception desk can also predict and suggest key points and objectives to be used at specific times based on the user's past input history. Some or all of the above processing in the reception desk may be performed using generative AI or not. This allows the reception desk to suggest the optimal input format to the user by analyzing past input history.

[0082] The reception unit can filter input content based on the user's current situation and areas of interest when they input key points and objectives. For example, the reception unit can prioritize displaying relevant key points and objectives according to the user's current situation. The reception unit uses generative AI to analyze the user's current situation and areas of interest and filter the input content. For example, the reception unit can suggest relevant key points and objectives based on the user's areas of interest. The reception unit can also filter out unnecessary input content based on the user's current situation and areas of interest. Some or all of the above processing in the reception unit may be performed using generative AI or not. This allows for the provision of more appropriate input content by filtering input content based on the user's current situation and areas of interest.

[0083] The reception unit can estimate the user's emotions and prioritize input content based on the estimated emotions. For example, if the user is nervous, the reception unit will prioritize inputting important points or objectives. The reception unit estimates the user's emotions using an emotion engine or generative AI. For example, the reception unit can capture the user's facial expression with a camera and estimate the emotions using an emotion estimation algorithm. The reception unit can also record the user's voice and estimate the emotions using voice analysis technology. Furthermore, the reception unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate the emotions using an emotion estimation algorithm. This allows the system to prioritize input content according to the user's emotions, thereby prioritizing the input of important information. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception unit may be performed using generative AI or not.

[0084] The reception desk can prioritize accepting highly relevant input content by considering the user's geographical location when inputting key points and objectives. For example, if the user is in a specific region, the reception desk will prioritize inputting key points and objectives related to that region. The reception desk uses generative AI to analyze the user's geographical location and suggest highly relevant input content. For example, if the user is on the move, the reception desk will suggest relevant key points and objectives based on their current location. The reception desk can also prioritize inputting key points and objectives related to a specific location if the user is in that location. Some or all of the above processing in the reception desk may be performed using generative AI, or it may be performed without generative AI. This allows the reception desk to prioritize accepting highly relevant input content by considering the user's geographical location.

[0085] The reception desk can analyze the user's social media activity when they input key points and objectives, and suggest relevant input content. For example, the reception desk can suggest relevant key points and objectives based on information the user has shared on social media. The reception desk uses generative AI to analyze the user's social media activity and suggest relevant input content. For example, the reception desk can extract topics of interest from the user's social media activity and suggest relevant key points and objectives. The reception desk can also analyze the user's social media activity history and suggest relevant key points and objectives. Some or all of the above processing in the reception desk may be performed using generative AI, or it may be performed without generative AI. This allows the reception desk to suggest relevant input content by analyzing the user's social media activity.

[0086] The generation unit can estimate the user's emotions and adjust the expression of the generated text based on the estimated emotions. For example, if the user is relaxed, the generation unit will generate text using softer language. The generation unit estimates the user's emotions using an emotion engine or a generation AI. For example, the generation unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The generation unit can also record the user's voice and estimate their emotions using voice analysis technology. Furthermore, the generation unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows for the generation of more appropriate text by adjusting the expression of the text according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the generation unit may be performed using a generation AI or not.

[0087] The generation unit can adjust the level of detail in the text based on the importance of the main points and objectives during generation. For example, if the main points or objectives are important, the generation unit will generate text that includes detailed explanations. The generation unit uses generation AI to analyze the importance of the main points and objectives and adjust the level of detail in the text. For example, if the main points or objectives are of low importance, the generation unit will generate concise text. The generation unit can also generate text with an appropriate level of detail depending on the importance of the main points and objectives. Some or all of the above processing in the generation unit may be performed using generation AI, or it may be performed without generation AI. This allows for the generation of text with an appropriate level of detail by adjusting the level of detail in the text based on the importance of the main points and objectives.

[0088] The generation unit can apply different generation algorithms depending on the category of key points and purpose during generation. For example, in the case of event notifications, the generation unit generates text that includes details such as the date, time, location, and items to bring. The generation unit uses generation AI to analyze the category of key points and purpose and apply an appropriate generation algorithm. For example, in the case of emergency contact, the generation unit generates a concise text for quick communication. The generation unit can also generate a text using polite language in the case of a request to parents. Some or all of the above processing in the generation unit may be performed using generation AI, or it may be performed without generation AI. This allows for the generation of more appropriate text by applying different generation algorithms depending on the category of key points and purpose.

[0089] The generation unit can estimate the user's emotions and adjust the length of the generated text based on the estimated emotions. For example, if the user is in a hurry, the generation unit will generate a short, concise text. The generation unit estimates the user's emotions using an emotion engine or generation AI. For example, the generation unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The generation unit can also record the user's voice and estimate their emotions using voice analysis technology. Furthermore, the generation unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows for the generation of more appropriate text by adjusting the length of the text according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the generation unit may be performed using a generation AI or not.

[0090] The generation unit can determine the generation priority based on the submission timing of the main points and objectives during the generation process. For example, in the case of an urgent notice, the generation unit will generate the document with the highest priority. The generation unit uses generation AI to analyze the submission timing of the main points and objectives and determine the generation priority. For example, in the case of an event notification, the generation unit will determine the generation priority based on the submission timing. The generation unit can also adjust the generation priority according to the submission timing in the case of a request letter to a parent or guardian. Some or all of the above processing in the generation unit may be performed using generation AI or not. This allows for the generation of documents at the appropriate time by determining the generation priority based on the submission timing of the main points and objectives.

[0091] The generation unit can adjust the order of the generated text based on the relevance of key points and objectives during the generation process. For example, the generation unit may place important key points and objectives first, and then arrange related information sequentially. The generation unit uses generation AI to analyze the relevance of key points and objectives and adjust the order of the text. For example, the generation unit may group highly relevant key points and objectives and adjust their order. The generation unit can also generate text in an appropriate order based on the relevance of key points and objectives. Some or all of the above-described processes in the generation unit may be performed using generation AI, or they may not. This allows for the generation of more easily understandable text by adjusting the order of text based on the relevance of key points and objectives.

[0092] The editorial team can estimate the user's emotions and adjust the editing interface based on those emotions. For example, if the user is stressed, the editorial team can provide an interface with calming colors to reduce visual stress. The editorial team estimates the user's emotions using an emotion engine or generative AI. For example, the editorial team can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The editorial team can also record the user's voice and estimate their emotions using voice analysis technology. Furthermore, the editorial team can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This makes the editing process more comfortable by adjusting the editing interface according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the editorial team may be performed using generative AI or not.

[0093] The editorial department can automatically detect errors in the generated text during editing and suggest corrections. For example, the editorial department can automatically detect grammatical errors in the generated text and suggest corrections. The editorial department can use generative AI to analyze errors in the generated text and suggest corrections. For example, the editorial department can automatically detect spelling mistakes in the generated text and suggest corrections. The editorial department can also automatically detect contextual errors in the generated text and suggest corrections. Some or all of the above processes in the editorial department may be performed using generative AI, or they may not. This improves the quality of the text by automatically detecting errors in the generated text and suggesting corrections.

[0094] The editorial team can suggest the optimal editing method by referring to the user's past editing history during the editing process. For example, the editorial team can suggest the optimal editing method based on the user's past editing history. The editorial team can also use generative AI to analyze the user's past editing history and suggest the optimal editing method. For example, the editorial team can prioritize suggesting frequently performed edits based on the user's past editing history. Furthermore, the editorial team can analyze the user's past editing history and suggest the optimal editing method. Some or all of the above processes in the editorial team may be performed using generative AI, or they may not. This allows the editorial team to suggest the optimal editing method by referring to the user's past editing history.

[0095] The editorial team can estimate the user's emotions and determine editing priorities based on those estimated emotions. For example, if the user is nervous, the editorial team will prioritize important editing. The editorial team estimates the user's emotions using an emotion engine or generative AI. For example, the editorial team can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. Alternatively, the editorial team can record the user's voice and estimate their emotions using voice analysis technology. Furthermore, the editorial team can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows the editorial team to prioritize important editing by determining editing priorities according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the editorial team may be performed using generative AI or not.

[0096] The editorial team can propose the optimal editing method while considering the user's geographical location. For example, if the user is in a specific region, the editorial team will prioritize editing content related to that region. The editorial team uses generative AI to analyze the user's geographical location and propose the optimal editing method. For example, if the user is on the move, the editorial team will propose the optimal editing method based on their current location. The editorial team can also prioritize editing content related to a specific location if the user is in that location. Some or all of the above processing by the editorial team may be performed using generative AI, or not. This allows the editorial team to propose the optimal editing method by considering the user's geographical location.

[0097] The editorial team can analyze users' social media activity during the editing process and suggest relevant editorial content. For example, the editorial team can suggest relevant editorial content based on information shared by users on social media. The editorial team can use generative AI to analyze users' social media activity and suggest relevant editorial content. For example, the editorial team can extract topics of interest from users' social media activity and suggest relevant editorial content. The editorial team can also analyze users' social media activity history and suggest relevant editorial content. Some or all of the above processes performed by the editorial team may be done using generative AI or not. This allows for the suggestion of relevant editorial content by analyzing users' social media activity.

[0098] The learning unit can estimate the user's emotions and select training data based on the estimated emotions. For example, if the user is relaxed, the learning unit will select training data that includes soft expressions. The learning unit estimates the user's emotions using an emotion engine or generative AI. For example, the learning unit can capture the user's facial expressions with a camera and estimate the emotions using an emotion estimation algorithm. The learning unit can also record the user's voice and estimate the emotions using voice analysis technology. Furthermore, the learning unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate the emotions using an emotion estimation algorithm. This allows for more appropriate learning by selecting training data according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the learning unit may be performed using generative AI or not.

[0099] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal learning algorithm based on past learning data. The learning unit can analyze past learning data using generative AI and optimize the learning algorithm. For example, the learning unit can extract effective learning patterns from past learning data and optimize the algorithm. The learning unit can also analyze past learning data and adjust the parameters of the learning algorithm. Some or all of the above processes in the learning unit may be performed using generative AI or not. This allows the learning algorithm to be optimized by referring to past learning data.

[0100] The learning unit can improve the accuracy of learning by combining different example sentences and data sources during training. For example, the learning unit ensures diversity in the training data by combining different example sentences. The learning unit uses generative AI to analyze different example sentences and data sources and improve the accuracy of learning. For example, the learning unit collects information from different data sources to improve the accuracy of learning. The learning unit can also improve the accuracy of the learning algorithm by combining different example sentences and data sources. Some or all of the above processing in the learning unit may be performed using generative AI or not. As a result, the accuracy of learning is improved by combining different example sentences and data sources.

[0101] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For example, if the user is relaxed, the learning unit will set a lower learning frequency. The learning unit estimates the user's emotions using an emotion engine or generative AI. For example, the learning unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The learning unit can also record the user's voice and estimate their emotions using voice analysis technology. Furthermore, the learning unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows the learning unit to provide an optimal learning environment by adjusting the learning frequency according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the learning unit may be performed using or without generative AI.

[0102] The learning unit can weight the training data based on the submission dates of key points and objectives during training. For example, the learning unit can assign higher weights to training data for key points and objectives with upcoming submission dates. The learning unit uses generative AI to analyze the submission dates of key points and objectives and weight the training data. For example, the learning unit can assign lower weights to training data for key points and objectives with distant submission dates. The learning unit can also adjust the weighting of the training data based on the submission dates of key points and objectives. Some or all of the above processing in the learning unit may be performed using generative AI or not. This improves the effectiveness of training by weighting the training data based on the submission dates of key points and objectives.

[0103] The learning unit can select optimal training data during training by considering the user's geographical location information. For example, if the user is in a specific region, the learning unit will select training data related to that region. The learning unit uses generative AI to analyze the user's geographical location information and select optimal training data. For example, if the user is on the move, the learning unit will select optimal training data based on the user's current location. The learning unit can also select training data related to a specific location if the user is in that location. Some or all of the above processing in the learning unit may be performed using generative AI or not. This allows for the selection of optimal training data by considering the user's geographical location information.

[0104] The retraining unit can estimate the user's emotions and select retraining data based on the estimated emotions. For example, if the user is relaxed, the retraining unit will select retraining data that includes soft expressions. The retraining unit estimates the user's emotions using an emotion engine or generative AI. For example, the retraining unit can capture the user's facial expressions with a camera and estimate the emotions using an emotion estimation algorithm. The retraining unit can also record the user's voice and estimate the emotions using voice analysis technology. Furthermore, the retraining unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate the emotions using an emotion estimation algorithm. This allows for more appropriate retraining by selecting retraining data according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the retraining unit may be performed using generative AI or not.

[0105] The relearning unit can optimize the relearning algorithm by referring to past editing history during relearning. For example, the relearning unit selects the optimal relearning algorithm based on past editing history. The relearning unit analyzes past editing history using generative AI and optimizes the relearning algorithm. For example, the relearning unit extracts effective relearning patterns from past editing history and optimizes the algorithm. The relearning unit can also analyze past editing history and adjust the parameters of the relearning algorithm. Some or all of the above processing in the relearning unit may be performed using generative AI or not. This allows the relearning algorithm to be optimized by referring to past editing history.

[0106] The retraining unit can improve the accuracy of retraining by combining different example sentences and data sources during the retraining process. For example, the retraining unit ensures diversity in the retraining data by combining different example sentences. The retraining unit uses generative AI to analyze different example sentences and data sources and improve the accuracy of retraining. For example, the retraining unit collects information from different data sources to improve the accuracy of retraining. The retraining unit can also improve the accuracy of the retraining algorithm by combining different example sentences and data sources. Some or all of the above processing in the retraining unit may be performed using generative AI or not. This improves the accuracy of retraining by combining different example sentences and data sources.

[0107] The relearning unit can estimate the user's emotions and adjust the frequency of relearning based on the estimated emotions. For example, if the user is relaxed, the relearning unit will set a lower frequency of relearning. The relearning unit estimates the user's emotions using an emotion engine or generative AI. For example, the relearning unit can capture the user's facial expressions with a camera and estimate emotions using an emotion estimation algorithm. The relearning unit can also record the user's voice and estimate emotions using voice analysis technology. Furthermore, the relearning unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate emotions using an emotion estimation algorithm. This allows for the provision of an optimal relearning environment by adjusting the frequency of relearning according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the relearning unit may be performed using or without a generative AI.

[0108] The retraining unit can weight the retraining data based on the submission dates of key points and objectives during retraining. For example, the retraining unit can assign higher weights to key points and objectives with upcoming submission dates. The retraining unit uses generative AI to analyze the submission dates of key points and objectives and weight the retraining data. For example, the retraining unit can assign lower weights to key points and objectives with distant submission dates. The retraining unit can also adjust the weighting of the retraining data based on the submission dates of key points and objectives. Some or all of the above processing in the retraining unit may be performed using generative AI or not. This improves the effectiveness of retraining by weighting the retraining data based on the submission dates of key points and objectives.

[0109] The retraining unit can select the optimal retraining data by considering the user's geographical location information during retraining. For example, if the user is in a specific region, the retraining unit will select retraining data related to that region. The retraining unit uses generative AI to analyze the user's geographical location information and select the optimal retraining data. For example, if the user is on the move, the retraining unit will select the optimal retraining data based on the user's current location. The retraining unit can also select retraining data related to a specific location if the user is in that location. Some or all of the above processing in the retraining unit may be performed using generative AI or not. This allows for the selection of optimal retraining data by considering the user's geographical location information.

[0110] The display unit can estimate the user's emotions and adjust the display method based on the estimated emotions. For example, if the user is tense, the display unit can provide a display method with calming colors to reduce visual stress. The display unit estimates the user's emotions using an emotion engine or generative AI. For example, the display unit can capture the user's facial expression with a camera and estimate the emotion using an emotion estimation algorithm. The display unit can also record the user's voice and estimate the emotion using voice analysis technology. Furthermore, the display unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate the emotion using an emotion estimation algorithm. This makes the viewing experience more comfortable by adjusting the display method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the display unit may be performed using or without generative AI.

[0111] The display unit can highlight which parts of the generated text were generated by AI during display. For example, the display unit can highlight the AI-generated parts of the generated text by color-coding them. The display unit uses the generation AI to analyze each part of the generated text and identify the AI-generated parts. For example, the display unit can underline the AI-generated parts of the generated text to highlight them. The display unit can also highlight the AI-generated parts of the generated text in bold. Some or all of the above processing in the display unit may be performed using the generation AI, or it may be performed without using the generation AI. This makes it easier for the user to edit the text by highlighting which parts of the generated text were generated by AI.

[0112] The display unit can select the optimal display method by referring to the user's past display history when displaying information. For example, the display unit can select the optimal display method based on the display method the user has preferred to use in the past. The display unit can also use a generation AI to analyze the user's past display history and select the optimal display method. For example, the display unit can prioritize suggesting frequently used display methods based on the user's past display history. The display unit can also analyze the user's past display history and select the optimal display method. Some or all of the above processing in the display unit may be performed using a generation AI, or it may be performed without a generation AI. This allows the optimal display method to be selected by referring to the user's past display history.

[0113] The display unit can estimate the user's emotions and determine the display priority based on the estimated emotions. For example, if the user is nervous, the display unit will prioritize displaying important content. The display unit estimates the user's emotions using an emotion engine or generative AI. For example, the display unit can capture the user's facial expression with a camera and estimate the emotion using an emotion estimation algorithm. The display unit can also record the user's voice and estimate the emotion using voice analysis technology. Furthermore, the display unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate the emotion using an emotion estimation algorithm. This allows the display unit to prioritize the display according to the user's emotions, thereby prioritizing the display of important content. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the display unit may be performed using or without generative AI.

[0114] The display unit can select the optimal display method when displaying information, taking into account the user's device information. For example, if the user is using a smartphone, the display unit provides a display method that matches the screen size. The display unit uses a generation AI to analyze the user's device information and select the optimal display method. For example, if the user is using a tablet, the display unit provides a display method optimized for a large screen. The display unit can also provide a concise and highly visible display method if the user is using a smartwatch. Some or all of the above processing in the display unit may be performed using a generation AI, or it may be performed without a generation AI. This allows the optimal display method to be selected by taking into account the user's device information.

[0115] The display unit can analyze the user's social media activity and suggest relevant display content when displaying information. For example, the display unit can suggest relevant display content based on information shared by the user on social media. The display unit can use generative AI to analyze the user's social media activity and suggest relevant display content. For example, the display unit can extract topics of interest from the user's social media activity and suggest relevant display content. The display unit can also analyze the user's social media activity history and suggest relevant display content. Some or all of the above processing in the display unit may be performed using generative AI or not. This allows the display unit to suggest relevant display content by analyzing the user's social media activity.

[0116] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0117] The automated notification message generation system can estimate the user's emotions and adjust the tone of the generated text based on those emotions. For example, if the user is stressed, the system will generate text in a softer tone. The generation unit captures the user's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. It can also record the user's voice and estimate their emotions using voice analysis technology. Furthermore, it can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows the system to generate more appropriate messages by adjusting the tone of the text according to the user's emotions.

[0118] The automated notification message generation system can suggest the most suitable template based on the user's past input history. For example, it prioritizes displaying templates that the user has frequently used in the past. The reception desk uses generation AI to analyze the user's past input history and suggest the most suitable template. For example, it can suggest templates from the user's past used templates that are suitable for a specific time of day or event. It can also suggest templates based on specific keywords from the user's past input history. This streamlines the input process by suggesting the most suitable template based on the user's past input history.

[0119] The automated notification message generation system can estimate the user's emotions and adjust the input interface based on those emotions. For example, if the user is relaxed, it can provide more detailed input options. The reception desk captures the user's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. It can also record the user's voice and estimate their emotions using voice analysis technology. Furthermore, it can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows for a more comfortable input environment by adjusting the input interface according to the user's emotions.

[0120] The automated notification text generation system includes a display unit that clearly indicates which parts of the generated text were generated by AI. For example, the display unit can color-code the AI-generated parts of the text. The display unit uses the generation AI to analyze each part of the generated text and identify the AI-generated sections. For example, the display unit can underline and highlight the AI-generated parts of the text. The display unit can also display the AI-generated parts of the text in bold. This makes it easier for users to edit the text by clearly indicating which parts were generated by AI.

[0121] The automated notification message generation system can estimate the user's emotions and adjust the length of the generated message based on those emotions. For example, if the user is in a hurry, it will generate a short, concise message. The generation unit captures the user's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. It can also record the user's voice and estimate their emotions using voice analysis technology. Furthermore, it can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. By adjusting the length of the message according to the user's emotions, it can generate more appropriate messages.

[0122] The automated notification message generation system can prioritize receiving highly relevant input content by considering the user's geographical location. For example, if the user is in a specific region, the reception unit will prioritize inputting key points and objectives related to that region. The reception unit uses generation AI to analyze the user's geographical location and suggest highly relevant input content. For instance, if the user is on the move, it will suggest relevant key points and objectives based on their current location. Furthermore, if the user is in a specific location, it can prioritize inputting key points and objectives related to that location. This allows the system to prioritize receiving highly relevant input content by considering the user's geographical location.

[0123] The automated notification message generation system can estimate the user's emotions and adjust the expression of the generated text based on those emotions. For example, if the user is relaxed, it will generate text using softer language. The generation unit captures the user's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. It can also record the user's voice and estimate their emotions using voice analysis technology. Furthermore, it can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. By adjusting the expression of the text according to the user's emotions, it can generate more appropriate messages.

[0124] The automated notification message generation system can analyze a user's social media activity and suggest relevant input content. The reception desk, for example, suggests relevant points and objectives based on information shared by the user on social media. The reception desk uses generation AI to analyze the user's social media activity and suggest relevant input content. For example, it can extract topics of interest from the user's social media activity and suggest relevant points and objectives. It can also analyze the user's social media activity history and suggest relevant points and objectives. In this way, by analyzing the user's social media activity, it can suggest relevant input content.

[0125] The automated notification message generation system can estimate the user's emotions and prioritize input content based on those emotions. For example, if the user is nervous, the reception desk will prioritize inputting important points and objectives. The reception desk captures the user's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. It can also record the user's voice and estimate their emotions using voice analysis technology. Furthermore, it can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. By prioritizing input content according to the user's emotions, important information can be entered preferentially.

[0126] The automated notification text generation system can suggest the optimal editing method by referring to the user's past editing history. The editorial department, for example, suggests the optimal editing method based on the user's past edits. The editorial department uses generation AI to analyze the user's past editing history and suggest the optimal editing method. For example, it prioritizes suggesting frequently performed edits based on the user's past editing history. It can also analyze the user's past editing history and suggest the optimal editing method. This allows the system to suggest the optimal editing method by referring to the user's past editing history.

[0127] The following briefly describes the processing flow for example form 2.

[0128] Step 1: The reception desk accepts input of key points and objectives. These include event notifications, emergency contacts, and requests to parents. The reception desk accepts the key points and objectives entered by the user in text format, and can also accept them using voice input. For example, if a user voice-inputs "Notification of Sports Day," the reception desk converts that into text data. Furthermore, the reception desk can automatically display frequently entered key points and objectives as suggestions based on past input history. Step 2: The generation unit automatically creates a notice based on the key points and purpose received by the reception unit. The generation unit generates the optimal text based on past data and example sentences, and uses text generation AI (e.g., LLM) to generate text that is based on the key points and purpose. In addition, the generation unit can use multimodal generation AI to generate notices that include not only text but also images, graphs, etc. For example, in the case of a sports day announcement, a text including details such as the date, time, location, and what to bring will be generated. Step 3: The editorial team reviews and edits the announcement text generated by the generation team. The editorial team can easily edit the generated text if there are errors or if additional information needs to be added. The editorial team displays the generated text in a text editor, allowing users to edit it directly. The editorial team also has a function to highlight which parts of the generated text were generated by AI. For example, the AI-generated parts can be color-coded to make it easier for users to edit.

[0129] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0130] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0131] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0132] Each of the multiple elements described above, including the reception unit, generation unit, editing unit, learning unit, retraining unit, and display unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14 and receives input of the user's main points and purpose. The generation unit is implemented by the specific processing unit 290 of the data processing device 12 and automatically creates a notification text based on the input main points and purpose. The editing unit is implemented by the control unit 46A of the smart device 14 and checks and edits the generated notification text. The learning unit and retraining unit are implemented by the specific processing unit 290 of the data processing device 12 and learn past data and user editing content to update the generation model. The display unit is implemented by the control unit 46A of the smart device 14 and highlights the AI-generated portion of the generated text. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0133] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0134] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0135] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0136] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0137] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0138] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0139] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0140] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0141] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0142] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0143] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0144] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0145] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0146] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0147] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0148] Each of the multiple elements described above, including the reception unit, generation unit, editing unit, learning unit, retraining unit, and display unit, is implemented in at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is implemented by the control unit 46A of the smart glasses 214 and receives input of the user's main points and purpose. The generation unit is implemented by the specific processing unit 290 of the data processing device 12 and automatically creates a notification text based on the input main points and purpose. The editing unit is implemented by the control unit 46A of the smart glasses 214 and checks and edits the generated notification text. The learning unit and retraining unit are implemented by the specific processing unit 290 of the data processing device 12 and learn past data and user editing content to update the generation model. The display unit is implemented by the control unit 46A of the smart glasses 214 and highlights the AI-generated portion of the generated text. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0149] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0150] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0151] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0152] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0153] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0154] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0155] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0156] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0157] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0158] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0159] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0160] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0161] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0162] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0163] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0164] Each of the multiple elements described above, including the reception unit, generation unit, editing unit, learning unit, retraining unit, and display unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314 and receives input of the user's main points and purpose. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically creates a notification text based on the input main points and purpose. The editing unit is implemented by the control unit 46A of the headset terminal 314 and confirms and edits the generated notification text. The learning unit and retraining unit are implemented by the specific processing unit 290 of the data processing unit 12 and learn past data and user editing content to update the generation model. The display unit is implemented by the control unit 46A of the headset terminal 314 and highlights the AI-generated portion of the generated text. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0165] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0166] As shown in Figure 7, the 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.

[0167] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0168] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0169] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0170] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0171] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0172] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0173] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0174] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0175] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0176] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0177] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0178] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0179] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0180] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0181] Each of the multiple elements described above, including the reception unit, generation unit, editing unit, learning unit, retraining unit, and display unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the robot 414 and receives input of the user's main points and purpose. The generation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and automatically creates a notification text based on the input main points and purpose. The editing unit is implemented by, for example, the control unit 46A of the robot 414 and checks and edits the generated notification text. The learning unit and retraining unit are implemented by, for example, the specific processing unit 290 of the data processing unit 12 and learn past data and user editing content to update the generation model. The display unit is implemented by, for example, the control unit 46A of the robot 414 and highlights the AI-generated portion of the generated text. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0182] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0183] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0184] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0185] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0186] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0187] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0188] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0189] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0190] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0191] 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.

[0192] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0193] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0194] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0195] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0196] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0197] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0198] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0199] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0200] (Note 1) A reception area where key points and objectives are entered, A generation unit that automatically creates a notice based on the key points and purpose received by the reception unit, The system comprises an editing unit that checks and edits the notification text generated by the generation unit. A system characterized by the following features. (Note 2) It includes a learning unit that learns from past data and example sentences. The system described in Appendix 1, characterized by the features described herein. (Note 3) It includes a relearning unit that relearns the content edited by the user. The system described in Appendix 1, characterized by the features described herein. (Note 4) It includes a display unit that clearly indicates which parts of the generated text were generated by AI. The system described in Appendix 1, characterized by the features described herein. (Note 5) The generating unit is Generates the most suitable sentences based on past data and example sentences. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned editorial department, If there are errors in the generated announcement text, or if users want to add additional information, they can easily edit it. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is It estimates the user's emotions and adjusts the input method for key points and objectives based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is It analyzes the user's past input history and suggests the optimal input format. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is When users enter key points or objectives, the system filters the input based on their current situation and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is It estimates the user's emotions and prioritizes input content based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is When users input key points or objectives, the system prioritizes accepting input that is highly relevant, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is When users input key points and objectives, the system analyzes their social media activity and suggests relevant input content. The system described in Appendix 1, characterized by the features described herein. (Note 13) The generating unit is It estimates the user's emotions and adjusts the way the generated text is expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The generating unit is During generation, the level of detail in the text is adjusted based on the importance of the main points and objectives. The system described in Appendix 1, characterized by the features described herein. (Note 15) The generating unit is During generation, different generation algorithms are applied depending on the category of key points and objectives. The system described in Appendix 1, characterized by the features described herein. (Note 16) The generating unit is It estimates the user's emotions and adjusts the length of the generated text based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The generating unit is During generation, the priority of generation is determined based on the submission timing of the key points and objectives. The system described in Appendix 1, characterized by the features described herein. (Note 18) The generating unit is During generation, the order of generated sentences is adjusted based on the relevance of key points and objectives. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned editorial department, It estimates the user's emotions and adjusts the editing interface based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned editorial department, During editing, the system automatically detects errors in the generated text and suggests corrections. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned editorial department, During editing, the system will refer to the user's past editing history to suggest the optimal editing method. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned editorial department, It estimates the user's emotions and determines editing priorities based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned editorial department, During editing, the system will suggest the optimal editing method, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned editorial department, During editing, the system analyzes the user's social media activity and suggests relevant editing content. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 26) The aforementioned learning unit, During training, the learning algorithm is optimized by referring to past training data. The system described in Appendix 2, characterized by the features described herein. (Note 27) The aforementioned learning unit, During training, combine different example sentences and data sources to improve the accuracy of the learning process. The system described in Appendix 2, characterized by the features described herein. (Note 28) The aforementioned learning unit, It estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The system described in Appendix 2, characterized by the features described herein. (Note 29) The aforementioned learning unit, During learning, the learning data is weighted based on the submission timing of key points and objectives. The system described in Appendix 2, characterized by the features described herein. (Note 30) The aforementioned learning unit, During training, the optimal training data is selected by considering the user's geographical location. The system described in Appendix 2, characterized by the features described herein. (Note 31) The aforementioned relearning unit, The system estimates the user's emotions and selects retraining data based on the estimated user emotions. The system described in Appendix 3, characterized by the features described herein. (Note 32) The aforementioned relearning unit, During retraining, the retraining algorithm is optimized by referring to past editing history. The system described in Appendix 3, characterized by the features described herein. (Note 33) The aforementioned relearning unit, During retraining, combine different example sentences and data sources to improve the accuracy of the retraining process. The system described in Appendix 3, characterized by the features described herein. (Note 34) The aforementioned relearning unit, It estimates the user's emotions and adjusts the frequency of retraining based on the estimated user emotions. The system described in Appendix 3, characterized by the features described herein. (Note 35) The aforementioned relearning unit, During relearning, the relearning data is weighted based on the submission deadlines for key points and objectives. The system described in Appendix 3, characterized by the features described herein. (Note 36) The aforementioned relearning unit, During retraining, the optimal retraining data is selected by considering the user's geographical location information. The system described in Appendix 3, characterized by the features described herein. (Note 37) The aforementioned display unit is It estimates the user's emotions and adjusts the display method based on the estimated user emotions. The system described in Appendix 4, characterized by the features described herein. (Note 38) The aforementioned display unit is When displayed, the AI ​​will highlight which parts of the generated text were generated by AI. The system described in Appendix 4, characterized by the features described herein. (Note 39) The aforementioned display unit is When displaying content, the system selects the optimal display method by referring to the user's past viewing history. The system described in Appendix 4, characterized by the features described herein. (Note 40) The aforementioned display unit is It estimates the user's emotions and determines the display priority based on the estimated user emotions. The system described in Appendix 4, characterized by the features described herein. (Note 41) The aforementioned display unit is When displaying content, the system selects the optimal display method by considering the user's device information. The system described in Appendix 4, characterized by the features described herein. (Note 42) The aforementioned display unit is When displaying content, the system analyzes the user's social media activity and suggests relevant content. The system described in Appendix 4, characterized by the features described herein. [Explanation of Symbols]

[0201] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A reception area where key points and objectives are entered, A generation unit that automatically creates a notice based on the key points and purpose received by the reception unit, The system comprises an editing unit that checks and edits the notification text generated by the generation unit. A system characterized by the following features.

2. It includes a learning unit that learns from past data and example sentences. The system according to feature 1.

3. It includes a relearning unit that relearns the content edited by the user. The system according to feature 1.

4. It includes a display unit that clearly indicates which parts of the generated text were generated by AI. The system according to feature 1.

5. The generating unit is Generates the most suitable sentences based on past data and example sentences. The system according to feature 1.

6. The aforementioned editorial department, If there are errors in the generated announcement text, or if users want to add additional information, they can easily edit it. The system according to feature 1.

7. The aforementioned reception unit is It estimates the user's emotions and adjusts the input method for key points and objectives based on the estimated user emotions. The system according to feature 1.

8. The aforementioned reception unit is It analyzes the user's past input history and suggests the optimal input format. The system according to feature 1.

9. The aforementioned reception unit is When users enter key points or objectives, the system filters the input based on their current situation and areas of interest. The system according to feature 1.

Images