system

Abstract

The system according to the embodiment aims to accurately record the contents of telephone conversations, extract and manage tasks, and suggest necessary confirmation items. [Solution] A system according to an embodiment includes a voice input unit, a transcription unit, a task extraction unit, a transmission unit, and a check item suggestion unit. The voice input unit captures telephone conversation content in real time. The transcription unit analyzes the voice data captured by the voice input unit and transcribes it. The task extraction unit extracts tasks from the transcription results generated by the transcription unit and creates a task list. The transmission unit generates the task list created by the task extraction unit as a document and sends it by email. The check item suggestion unit suggests check items from a general business framework based on the transcription results generated by the transcription unit.

Description

[Technical Field]

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

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

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

[0004] With conventional technology, it is difficult to accurately record telephone conversations and extract and manage tasks, and there is a risk that items may be overlooked.

[0005] The system according to the embodiment aims to accurately record the contents of telephone conversations, extract and manage tasks, and suggest necessary confirmation items. [Means for solving the problem]

[0006] The system according to the embodiment includes a voice input unit, a transcription unit, a task extraction unit, a transmission unit, and a check item suggestion unit. The voice input unit captures telephone conversation content in real time. The transcription unit analyzes the voice data captured by the voice input unit and transcribes it. The task extraction unit extracts tasks from the transcription results generated by the transcription unit and creates a task list. The transmission unit generates the task list created by the task extraction unit as a document and sends it by email. The check item suggestion unit suggests check items from a general business framework based on the transcription results generated by the transcription unit. [Effects of the Invention]

[0007] The system according to the embodiment can accurately record the contents of telephone conversations, extract and manage tasks, and suggest necessary confirmation items. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

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

[0028] (Example 1) A system according to an embodiment of the present invention documents conversations, such as business negotiations over the phone or instructions from a superior, and creates tasks. This system captures the content of phone calls in real time and inputs it into an AI to transcribe them and create a task list. The AI ​​also suggests confirmation items based on a general business framework, thereby preventing later questions from arising. This allows the system to efficiently document conversations, such as business negotiations or instructions from a superior, and create tasks. The AI ​​also suggests necessary confirmation items, thereby preventing later questions from arising. For example, the system provides a voice input unit for capturing the content of phone calls. This voice input unit captures the content of phone conversations in real time and inputs it into the AI. The AI ​​then analyzes the input voice data and transcribes it. The transcription results are generated as a document and sent via email. The AI ​​then extracts tasks from the transcription results and creates a task list. This task list is also generated as a document and sent via email. For example, the system extracts next action items and deadlines from the content of business negotiations and compiles them into a task list. AI also suggests points that need to be checked based on common business frameworks, helping to avoid questions being asked later. For example, it suggests points that need to be checked or additional questions based on the content of a sales negotiation.

[0029] A conversation documentation system according to an embodiment includes a voice input unit, a transcription unit, a task extraction unit, a transmission unit, and a confirmation item suggestion unit. The voice input unit captures telephone conversation content in real time and inputs it to the transcription unit. For example, the voice input unit captures telephone conversation content using a high-precision microphone and converts it into digital data in real time. The voice input unit can also use noise-canceling technology to remove background noise and provide clear voice data. The voice input unit can also use AI to estimate a user's emotions and adjust the sensitivity of the voice input. For example, if the user is nervous, the voice input unit can increase the sensitivity of the voice input to capture the voice more clearly. The transcription unit uses AI to analyze the input voice data and transcribe it. For example, the transcription unit converts the voice data into text data using voice recognition technology. The transcription unit can also automatically recognize technical terms and industry jargon and convert them appropriately. The transcription unit can also understand the context of the conversation and emphasize important parts when transcribing. For example, the transcription unit transcribes business negotiations, emphasizing important information such as price and delivery date. The task extraction unit uses AI to extract tasks from the transcription results and create a task list. For example, the task extraction unit extracts next action items and deadlines from the content of business negotiations and organizes them in a task list. The task extraction unit can also understand the context of the conversation and automatically group related tasks. Furthermore, the task extraction unit can infer the user's emotions and determine task priority. For example, if the user is nervous, the task extraction unit can prioritize important tasks. The sending unit generates the task list as a document and sends it by email. For example, the sending unit documents the generated task list in PDF format and sends it to a specified email address. The sending unit can also automatically complete the recipient's email address. Furthermore, the sending unit can infer the user's emotions and adjust the format of the document to be sent. For example, if the user is nervous, the sending unit can use a concise and clear format.The confirmation item suggestion unit uses AI to suggest confirmation items from a general business framework based on the transcription results. For example, the confirmation item suggestion unit suggests points to be confirmed or additional questions based on the content of a business negotiation. The confirmation item suggestion unit can also estimate the user's emotions and determine the priority of confirmation items. For example, if the user is nervous, the confirmation item suggestion unit will prioritize suggesting important confirmation items. As a result, the conversation documentation system according to the embodiment can efficiently document the content of a telephone conversation, turn it into a task, and suggest necessary confirmation items.

[0030] The conversation documentation system includes an audio input unit with a filtering function that automatically removes background noise during audio input. The audio input unit uses AI to automatically remove background noise during audio input. For example, the audio input unit automatically removes air conditioner noise and external noise during a conference call in a conference room. The audio input unit can also filter out and remove background voices and music during a phone conversation in a public place such as a cafe. The audio input unit can also automatically remove engine noise and road noise during a phone conversation in a car. This removes background noise, allowing clear audio data to be obtained. Some or all of the above-described processing in the audio input unit may be performed using AI, for example, or without AI. For example, the audio input unit can input the acquired audio data to a generation AI and have the generation AI remove background noise.

[0031] The conversation documentation system includes a voice input unit that analyzes the characteristics of a speaker's voice during voice input and creates a different voice profile for each speaker. The voice input unit uses AI to analyze the characteristics of a speaker's voice during voice input and create a different voice profile for each speaker. For example, the voice input unit analyzes the characteristics of each speaker's voice during a conference with multiple speakers and creates an individual voice profile. The voice input unit can also create profiles that distinguish between the voice of the boss and the voice of the subordinate during a conversation between a boss and a subordinate. The voice input unit can also analyze the characteristics of the customer's voice during a phone call with a customer and automatically recognize it the next time the conversation occurs. This allows the voices of multiple speakers to be captured separately by creating a different voice profile for each speaker. Some or all of the above-described processing in the voice input unit may be performed using AI, for example, or without AI. For example, the voice input unit can input acquired voice data to a generation AI and have the generation AI analyze the characteristics of the speaker's voice.

[0032] The conversation documentation system includes a voice input unit that analyzes the context of a conversation during voice input and captures it with emphasis on important parts. The voice input unit uses AI to analyze the context of a conversation during voice input and captures it with emphasis on important parts. For example, the voice input unit captures important information such as price and delivery date during a business negotiation with emphasis. The voice input unit can also capture task priorities and deadlines with emphasis at the direction of a supervisor. The voice input unit can also capture important parts of a conversation with a customer with emphasis on requests and complaints. By capturing and emphasizing important parts of the conversation, important information can be recorded without missing anything. Some or all of the above-described processing in the voice input unit may be performed using, for example, AI, or may be performed without using AI. For example, the voice input unit can input acquired voice data to a generation AI and have the generation AI analyze the context of the conversation.

[0033] The conversation documentation system includes a voice input unit that selects voice input settings based on the user's geographic location information when the user inputs voice. The voice input unit uses AI to select optimal voice input settings by taking the user's geographic location information into consideration when the user inputs voice. For example, the voice input unit uses normal voice input settings when the user is in a quiet office. The voice input unit can also use voice input settings with enhanced noise cancellation when the user is in a noisy cafe. The voice input unit can also use voice input settings that remove engine noise when the user is in a moving car. This enables voice capture tailored to the environment by selecting optimal voice input settings based on the user's geographic location information. Some or all of the above-described processing in the voice input unit may be performed using AI, for example, or without AI. For example, the voice input unit can input the user's geographic location information to a generation AI and have the generation AI select optimal voice input settings.

[0034] The conversation documentation system includes a speech input unit that, when inputting speech, refers to a user's past conversation history to improve the accuracy of the speech input. The speech input unit uses AI to refer to the user's past conversation history to improve the accuracy of the speech input. For example, the speech input unit learns technical terms and phrases used by the user in the past to improve the accuracy of the speech input. The speech input unit can also learn the vocal characteristics of specific speakers from the user's past conversation history to improve the accuracy of the speech input. The speech input unit can also improve the accuracy of the speech input by referring to the context of the user's past conversations. In this way, the accuracy of the speech input can be improved by referring to the user's past conversation history. Some or all of the above-described processing in the speech input unit may be performed using AI, for example, or may be performed without using AI. For example, the speech input unit can input the user's past conversation history to a generation AI and have the generation AI improve the accuracy of the speech input.

[0035] The conversation documentation system includes a voice input unit that analyzes a user's social media activity and prioritizes capturing relevant conversation content when a user inputs voice. The voice input unit uses AI to analyze the user's social media activity and prioritizes capturing relevant conversation content when a user inputs voice. For example, the voice input unit prioritizes capturing topics that the user frequently mentions on social media. The voice input unit can also analyze the user's social media posts and prioritize capturing relevant conversation content. The voice input unit can also prioritize capturing relevant conversation content by referring to the activities of the user's friends on social media. In this way, by analyzing the user's social media activity, relevant conversation content can be prioritized. Some or all of the above-described processing in the voice input unit may be performed using AI, for example, or may be performed without using AI. For example, the voice input unit can input the user's social media activity data to a generation AI and cause the generation AI to prioritize capturing relevant conversation content.

[0036] The conversation documentation system includes a transcription unit that automatically recognizes and appropriately converts technical terms and industry jargon during transcription. The transcription unit uses AI to automatically recognize and appropriately convert technical terms and industry jargon during transcription. For example, the transcription unit automatically recognizes and appropriately converts technical terms in IT industry conversations. The transcription unit can also automatically recognize and appropriately convert technical terms in medical industry conversations. The transcription unit can also automatically recognize and appropriately convert technical terms in legal industry conversations. This allows for accurate transcription by appropriately converting technical terms and industry jargon. Some or all of the above-described processing in the transcription unit may be performed using AI, for example, or without AI. For example, the transcription unit can input acquired audio data into a generation AI and have the generation AI recognize and convert technical terms and industry jargon.

[0037] The conversation documentation system includes a transcription unit that has the function of transcribing in different formats for each speaker. The transcription unit uses AI to transcribe in different formats for each speaker. For example, when there are multiple speakers in a meeting, the transcription unit transcribes in a different format for each speaker. The transcription unit can also distinguish between the superior's and subordinate's comments in a conversation between a superior and a subordinate. The transcription unit can also distinguish between the customer's and the company's comments in a phone call with a customer. This allows the speech of multiple speakers to be recorded separately by transcribing in different formats for each speaker. Some or all of the above-described processing in the transcription unit may be performed using AI, for example, or without AI. For example, the transcription unit can input acquired audio data into a generation AI and have the generation AI transcribe in a format for each speaker.

[0038] The conversation documentation system includes a transcription unit that understands the context of a conversation and emphasizes important parts when transcribing. The transcription unit uses AI to understand the context of a conversation and emphasize important parts when transcribing. For example, during a business negotiation, the transcription unit may emphasize important information such as price and delivery date. The transcription unit may also emphasize task priorities and deadlines at the direction of a supervisor. The transcription unit may also emphasize important parts of a conversation with a customer, such as requests and complaints. This allows important information to be recorded without missing any important information by emphasizing the important parts of the conversation. Some or all of the above-described processing in the transcription unit may be performed using AI, for example, or without AI. For example, the transcription unit may input acquired audio data into a generation AI, which may then understand the context of the conversation and emphasize important parts.

[0039] The conversation documentation system includes a transcription unit that automatically records the start and end times of a conversation when transcribing. The transcription unit uses AI to automatically record the start and end times of a conversation when transcribing. For example, the transcription unit automatically records the start and end times of a meeting and reflects them in the transcription. The transcription unit can also automatically record the start and end times of a phone call and reflect them in the transcription. The transcription unit can also automatically record the start and end times of a business meeting and reflect them in the transcription. In this way, by automatically recording the start and end times of a conversation, accurate timestamps can be added to the transcription. Some or all of the above-described processing in the transcription unit may be performed using AI, or may be performed without AI. For example, the transcription unit can input acquired audio data into a generation AI and have the generation AI record the start and end times of the conversation.

[0040] The conversation documentation system includes a transcription unit that automatically tags data based on the content of the conversation during transcription. The transcription unit uses AI to automatically tag data based on the content of the conversation during transcription. For example, the transcription unit automatically tags data based on the price, delivery date, and conditions of a business meeting. The transcription unit can also automatically tag data based on instructions from a supervisor, such as tasks, deadlines, and priorities. The transcription unit can also automatically tag data based on requests, complaints, and feedback based on conversations with customers. This automatic tagging based on the content of the conversation facilitates future searches. Some or all of the above-described processing in the transcription unit may be performed using AI, or may be performed without AI. For example, the transcription unit can input acquired audio data into a generation AI and have the generation AI perform tagging.

[0041] The conversation documentation system includes a transcription unit that improves transcription accuracy by referencing the user's past transcription results during transcription. The transcription unit improves transcription accuracy by using AI to refer to the user's past transcription results during transcription. For example, the transcription unit learns technical terms and phrases used by the user in the past to improve transcription accuracy. The transcription unit can also improve transcription accuracy by learning the vocal characteristics of specific speakers from the user's past transcription results. The transcription unit can also improve transcription accuracy by referencing the context of the user's past conversations. In this way, transcription accuracy can be improved by referring to the user's past transcription results. Some or all of the above-described processing in the transcription unit may be performed using AI, for example, or without AI. For example, the transcription unit can input the user's past transcription results into a generation AI and have the generation AI improve transcription accuracy.

[0042] The conversation documentation system includes a task extraction unit that has a function of understanding the context of a conversation and automatically grouping related tasks when extracting tasks. The task extraction unit uses AI to understand the context of a conversation when extracting tasks and automatically group related tasks. For example, the task extraction unit automatically groups related tasks based on the content of a business negotiation. The task extraction unit can also automatically group related tasks based on instructions from a supervisor. The task extraction unit can also automatically group related tasks based on a conversation with a customer. This understanding of the context of a conversation and grouping related tasks improves task management efficiency. Some or all of the above-described processing in the task extraction unit may be performed using AI, for example, or may be performed without using AI. For example, the task extraction unit can input acquired conversation data to a generation AI and have the generation AI group related tasks.

[0043] The conversation documentation system includes a task extraction unit that has a function of automatically setting a task deadline and a person in charge when extracting a task. The task extraction unit automatically sets the task deadline and a person in charge when extracting a task using AI. For example, the task extraction unit automatically sets the task deadline based on the content of a business negotiation. The task extraction unit can also automatically set a task person in charge based on instructions from a supervisor. The task extraction unit can also automatically set the task deadline and a person in charge based on a conversation with a customer. This automatically setting the task deadline and a person in charge improves task management efficiency. Some or all of the above-mentioned processing in the task extraction unit may be performed using AI, for example, or may be performed without using AI. For example, the task extraction unit can input the acquired conversation data into a generation AI and have the generation AI set the task deadline and a person in charge.

[0044] The conversation documentation system includes a task extraction unit that has a function of automatically suggesting similar tasks by referring to past task history when extracting a task. The task extraction unit uses AI to automatically suggest similar tasks by referring to past task history when extracting a task. For example, the task extraction unit refers to the user's past task history and automatically suggests similar tasks. The task extraction unit can also suggest similar past tasks based on the content of business negotiations. The task extraction unit can also suggest similar past tasks based on instructions from a superior. This allows similar tasks to be efficiently suggested by referring to past task history. Some or all of the above-mentioned processing in the task extraction unit may be performed using AI, for example, or may be performed without using AI. For example, the task extraction unit can input the user's past task history into a generation AI and have the generation AI suggest similar tasks.

[0045] The conversation documentation system includes a task extraction unit that has a function of automatically setting reminders based on the content of the conversation when extracting a task. The task extraction unit uses AI to automatically set reminders based on the content of the conversation when extracting a task. For example, the task extraction unit automatically sets reminders for important tasks based on the content of a business negotiation. The task extraction unit can also automatically set reminders for tasks with deadlines based on instructions from a supervisor. The task extraction unit can also automatically set reminders for important tasks based on a conversation with a customer. By setting reminders based on the content of the conversation, important tasks can be managed without forgetting them. Some or all of the above-mentioned processing in the task extraction unit may be performed using AI, for example, or may be performed without using AI. For example, the task extraction unit can input the acquired conversation data into a generation AI and have the generation AI set reminders.

[0046] The conversation documentation system includes a task extraction unit that has a function of automatically tracking the progress of a task when the task is extracted. The task extraction unit automatically tracks the progress of the task when the task is extracted using AI. For example, the task extraction unit automatically tracks the progress of the task based on the content of a business negotiation. The task extraction unit can also automatically track the progress of the task based on instructions from a supervisor. The task extraction unit can also automatically track the progress of the task based on a conversation with a customer. This allows the task progress to be efficiently managed by automatically tracking the progress of the task. Some or all of the above-described processing in the task extraction unit may be performed using AI, for example, or may be performed without using AI. For example, the task extraction unit may input the acquired conversation data to a generation AI and cause the generation AI to track the progress of the task.

[0047] The conversation documentation system includes a task extraction unit that reflects a user's past feedback during task extraction to improve the accuracy of task extraction. The task extraction unit uses AI to reflect a user's past feedback during task extraction to improve the accuracy of task extraction. For example, the task extraction unit refers to a user's past feedback to improve the accuracy of task extraction. The task extraction unit can also reflect past feedback based on the content of a business negotiation to improve the accuracy of task extraction. The task extraction unit can also reflect past feedback based on instructions from a superior to improve the accuracy of task extraction. In this way, the accuracy of task extraction can be improved by reflecting the user's past feedback. Some or all of the above-described processing in the task extraction unit may be performed using AI, for example, or may be performed without using AI. For example, the task extraction unit can input a user's past feedback into a generation AI and cause the generation AI to improve the accuracy of task extraction.

[0048] The conversation documentation system includes a sending unit that has a function of automatically completing the recipient's email address when sending. The sending unit automatically completes the recipient's email address when sending using AI. For example, the sending unit automatically completes email addresses to which the user has sent in the past. The sending unit can also automatically complete the recipient's email address from the user's contact list. The sending unit can also automatically complete the complete email address from a partial email address entered by the user. This automatically completes the recipient's email address, thereby preventing sending errors. Some or all of the above-described processing in the sending unit may be performed using AI, for example, or may be performed without using AI. For example, the sending unit can input the user's contact list into a generation AI and have the generation AI complete the email address.

[0049] The conversation documentation system includes a sending unit that has a function of automatically setting a subject based on the content of a document when it is sent. The sending unit uses AI to automatically set a subject based on the content of a document when it is sent. For example, the sending unit automatically sets an appropriate subject based on the content of a business negotiation. The sending unit can also automatically set an appropriate subject based on instructions from a supervisor. The sending unit can also automatically set an appropriate subject based on a conversation with a customer. In this way, by automatically setting a subject based on the content of the document, it is possible to send a document with an appropriate subject. Some or all of the above-described processing in the sending unit may be performed using AI, for example, or may be performed without using AI. For example, the sending unit can input the content of the document into a generation AI and have the generation AI set the subject.

[0050] The conversation documentation system includes a transmission unit that has a function of automatically recording a transmission history at the time of transmission so that it can be referenced later. The transmission unit uses AI to automatically record the transmission history at the time of transmission so that it can be referenced later. For example, the transmission unit automatically records the history of sent documents so that it can be referenced later. The transmission unit can also automatically record the history of sent emails so that it can be referenced later. The transmission unit can also automatically record the history of sent task lists so that it can be referenced later. In this way, by automatically recording the transmission history, the transmitted content can be confirmed later. Some or all of the above-described processing in the transmission unit may be performed using AI, for example, or may be performed without using AI. For example, the transmission unit can input the transmission history to a generation AI and have the generation AI record the history.

[0051] The conversation documentation system includes a sending unit that has a function of tracking the reception status of the recipient in real time at the time of transmission. The sending unit uses AI to track the reception status of the recipient in real time at the time of transmission. For example, the sending unit tracks in real time whether a sent email has been received. The sending unit can also track in real time whether a sent document has been opened. The sending unit can also track in real time whether a sent task list has been checked. In this way, by tracking the reception status of the recipient in real time, it is possible to confirm whether the transmitted content has been reliably received. Some or all of the above-described processing in the sending unit may be performed using AI, for example, or may be performed without using AI. For example, the sending unit can input reception status data of the recipient into a generation AI and have the generation AI track the reception status.

[0052] The conversation documentation system includes a transmission unit that has a function of automatically adding attachments based on the content of a document when the document is sent. The transmission unit uses AI to automatically add attachments based on the content of the document when the document is sent. For example, the transmission unit automatically attaches related materials based on the content of a business negotiation. The transmission unit can also automatically attach related files based on instructions from a supervisor. The transmission unit can also automatically attach related documents based on a conversation with a customer. This allows related materials to be sent reliably by automatically adding attachments based on the content of the document. Some or all of the above-described processing in the transmission unit may be performed using AI, for example, or may be performed without using AI. For example, the transmission unit can input the content of the document into a generation AI and have the generation AI add attachments.

[0053] The conversation documentation system includes a transmission unit that has a function of referencing a user's past transmission history to customize the content of a message when sending the message. The transmission unit uses AI to refer to the user's past transmission history when sending the message and customize the content. For example, the transmission unit refers to the user's past transmission history to customize the content of a message. The transmission unit can also customize the content of a message by reflecting the past transmission history based on the content of a business negotiation. The transmission unit can also customize the content of a message by reflecting the past transmission history based on instructions from a superior. This allows the content of a message to be customized and sent with appropriate content by referring to the user's past transmission history. Some or all of the above-described processing in the transmission unit may be performed using AI, for example, or may be performed without using AI. For example, the transmission unit can input the user's past transmission history into a generation AI and have the generation AI customize the content of a message.

[0054] The conversation documentation system includes a confirmation item suggestion unit that has a function of understanding the context of the conversation and automatically grouping related confirmation items when proposing confirmation items. The confirmation item suggestion unit uses AI to understand the context of the conversation when proposing confirmation items and automatically group related confirmation items. For example, the confirmation item suggestion unit automatically groups related confirmation items based on the content of a business negotiation. The confirmation item suggestion unit can also automatically group related confirmation items based on instructions from a supervisor. The confirmation item suggestion unit can also automatically group related confirmation items based on a conversation with a customer. This understanding of the conversation context and grouping related confirmation items improves the efficiency of confirmation item management. Some or all of the above-described processing in the confirmation item suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the confirmation item suggestion unit can input acquired conversation data to a generation AI and have the generation AI group related confirmation items.

[0055] The conversation documentation system includes a check item suggestion unit that has a function of automatically suggesting similar check items by referring to past conversation history when proposing check items. The check item suggestion unit uses AI to automatically suggest similar check items by referring to past conversation history when proposing check items. For example, the check item suggestion unit refers to the user's past conversation history and automatically suggests similar check items. The check item suggestion unit can also suggest similar past check items based on the content of business negotiations. The check item suggestion unit can also suggest similar past check items based on instructions from a supervisor. This allows similar check items to be efficiently suggested by referring to past conversation history. Some or all of the above-mentioned processing in the check item suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the check item suggestion unit can input the user's past conversation history into a generation AI and have the generation AI suggest similar check items.

[0056] The conversation documentation system includes a confirmation item suggestion unit that has a function of adjusting the level of detail of the proposal based on the importance of the confirmation item when proposing the confirmation item. The confirmation item suggestion unit adjusts the level of detail of the proposal based on the importance of the confirmation item using AI when proposing the confirmation item. For example, the confirmation item suggestion unit makes detailed suggestions for important confirmation items. The confirmation item suggestion unit can also make standard suggestions for ordinary confirmation items. The confirmation item suggestion unit can also make concise suggestions for urgent confirmation items. In this way, by adjusting the level of detail of the proposal based on the importance of the confirmation item, it is possible to propose confirmation items with an appropriate level of detail. Some or all of the above-described processing in the confirmation item suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the confirmation item suggestion unit can input the acquired conversation data to a generation AI and cause the generation AI to adjust the level of detail of the proposal.

[0057] The conversation documentation system includes a confirmation item suggestion unit that has a function of automatically setting a reminder based on the content of the conversation when a confirmation item is suggested. The confirmation item suggestion unit automatically sets a reminder based on the content of the conversation when a confirmation item is suggested using AI. For example, the confirmation item suggestion unit automatically sets a reminder for important confirmation items based on the content of a business negotiation. The confirmation item suggestion unit can also automatically set a reminder for confirmation items with deadlines based on instructions from a supervisor. The confirmation item suggestion unit can also automatically set a reminder for important confirmation items based on a conversation with a customer. In this way, by setting a reminder based on the content of the conversation, important confirmation items can be managed without forgetting them. Some or all of the above-mentioned processing in the confirmation item suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the confirmation item suggestion unit can input the acquired conversation data into a generation AI and have the generation AI set a reminder.

[0058] The conversation documentation system includes a confirmation item suggestion unit that has a function of automatically tracking the progress of a confirmation item when the confirmation item is proposed. The confirmation item suggestion unit automatically tracks the progress of the confirmation item when the confirmation item is proposed using AI. For example, the confirmation item suggestion unit automatically tracks the progress of the confirmation item based on the content of a business negotiation. The confirmation item suggestion unit can also automatically track the progress of the confirmation item based on instructions from a supervisor. The confirmation item suggestion unit can also automatically track the progress of the confirmation item based on a conversation with a customer. This allows the progress of the confirmation item to be efficiently managed by automatically tracking the progress of the confirmation item. Some or all of the above-described processing in the confirmation item suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the confirmation item suggestion unit may input the acquired conversation data into a generation AI and cause the generation AI to track the progress of the confirmation item.

[0059] The conversation documentation system includes a confirmation item suggestion unit that, when proposing confirmation items, reflects the user's past feedback to improve the accuracy of the confirmation item suggestions. The confirmation item suggestion unit uses AI to reflect the user's past feedback when proposing confirmation items to improve the accuracy of the confirmation item suggestions. For example, the confirmation item suggestion unit refers to the user's past feedback to improve the accuracy of the confirmation item suggestions. The confirmation item suggestion unit can also reflect past feedback based on the content of a business negotiation to improve the accuracy of the confirmation item suggestions. The confirmation item suggestion unit can also reflect past feedback to improve the accuracy of the confirmation item suggestions based on instructions from a superior. In this way, the accuracy of the confirmation item suggestions can be improved by reflecting the user's past feedback. Some or all of the above-described processing in the confirmation item suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the confirmation item suggestion unit can input the user's past feedback into the generation AI and cause the generation AI to improve the accuracy of the confirmation item suggestions.

[0060] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0061] The conversation documentation system includes an audio input unit with a filtering function that automatically removes background noise during audio input. The audio input unit uses AI to automatically remove background noise during audio input. For example, the audio input unit automatically removes air conditioner noise and external noise during a conference call in a conference room. The audio input unit can also filter out and remove background voices and music during a phone conversation in a public place such as a cafe. The audio input unit can also automatically remove engine noise and road noise during a phone conversation in a car. This removes background noise, allowing clear audio data to be obtained. Some or all of the above-described processing in the audio input unit may be performed using AI, for example, or without AI. For example, the audio input unit can input the acquired audio data to a generation AI and have the generation AI remove background noise.

[0062] The conversation documentation system includes a voice input unit that analyzes the characteristics of a speaker's voice during voice input and creates a different voice profile for each speaker. The voice input unit uses AI to analyze the characteristics of a speaker's voice during voice input and create a different voice profile for each speaker. For example, the voice input unit analyzes the characteristics of each speaker's voice during a conference with multiple speakers and creates an individual voice profile. The voice input unit can also create profiles that distinguish between the voice of the boss and the voice of the subordinate during a conversation between a boss and a subordinate. The voice input unit can also analyze the characteristics of the customer's voice during a phone call with a customer and automatically recognize it the next time the conversation occurs. This allows the voices of multiple speakers to be captured separately by creating a different voice profile for each speaker. Some or all of the above-described processing in the voice input unit may be performed using AI, for example, or without AI. For example, the voice input unit can input acquired voice data to a generation AI and have the generation AI analyze the characteristics of the speaker's voice.

[0063] The conversation documentation system includes a voice input unit that analyzes the context of a conversation during voice input and captures it with emphasis on important parts. The voice input unit uses AI to analyze the context of a conversation during voice input and captures it with emphasis on important parts. For example, the voice input unit captures important information such as price and delivery date during a business negotiation with emphasis. The voice input unit can also capture task priorities and deadlines with emphasis at the direction of a supervisor. The voice input unit can also capture important parts of a conversation with a customer with emphasis on requests and complaints. By capturing and emphasizing important parts of the conversation, important information can be recorded without missing anything. Some or all of the above-described processing in the voice input unit may be performed using, for example, AI, or may be performed without using AI. For example, the voice input unit can input acquired voice data to a generation AI and have the generation AI analyze the context of the conversation.

[0064] The conversation documentation system includes a voice input unit that selects voice input settings based on the user's geographic location information when the user inputs voice. The voice input unit uses AI to select optimal voice input settings by taking the user's geographic location information into consideration when the user inputs voice. For example, the voice input unit uses normal voice input settings when the user is in a quiet office. The voice input unit can also use voice input settings with enhanced noise cancellation when the user is in a noisy cafe. The voice input unit can also use voice input settings that remove engine noise when the user is in a moving car. This enables voice capture tailored to the environment by selecting optimal voice input settings based on the user's geographic location information. Some or all of the above-described processing in the voice input unit may be performed using AI, for example, or without AI. For example, the voice input unit can input the user's geographic location information to a generation AI and have the generation AI select optimal voice input settings.

[0065] The conversation documentation system includes a speech input unit that, when inputting speech, refers to a user's past conversation history to improve the accuracy of the speech input. The speech input unit uses AI to refer to the user's past conversation history to improve the accuracy of the speech input. For example, the speech input unit learns technical terms and phrases used by the user in the past to improve the accuracy of the speech input. The speech input unit can also learn the vocal characteristics of specific speakers from the user's past conversation history to improve the accuracy of the speech input. The speech input unit can also improve the accuracy of the speech input by referring to the context of the user's past conversations. In this way, the accuracy of the speech input can be improved by referring to the user's past conversation history. Some or all of the above-described processing in the speech input unit may be performed using AI, for example, or may be performed without using AI. For example, the speech input unit can input the user's past conversation history to a generation AI and have the generation AI improve the accuracy of the speech input.

[0066] The conversation documentation system includes a voice input unit that analyzes a user's social media activity and prioritizes capturing relevant conversation content when a user inputs voice. The voice input unit uses AI to analyze the user's social media activity and prioritizes capturing relevant conversation content when a user inputs voice. For example, the voice input unit prioritizes capturing topics that the user frequently mentions on social media. The voice input unit can also analyze the user's social media posts and prioritize capturing relevant conversation content. The voice input unit can also prioritize capturing relevant conversation content by referring to the activities of the user's friends on social media. In this way, by analyzing the user's social media activity, relevant conversation content can be prioritized. Some or all of the above-described processing in the voice input unit may be performed using AI, for example, or may be performed without using AI. For example, the voice input unit can input the user's social media activity data to a generation AI and cause the generation AI to prioritize capturing relevant conversation content.

[0067] The conversation documentation system includes a transcription unit that automatically recognizes and appropriately converts technical terms and industry jargon during transcription. The transcription unit uses AI to automatically recognize and appropriately convert technical terms and industry jargon during transcription. For example, the transcription unit automatically recognizes and appropriately converts technical terms in IT industry conversations. The transcription unit can also automatically recognize and appropriately convert technical terms in medical industry conversations. The transcription unit can also automatically recognize and appropriately convert technical terms in legal industry conversations. This allows for accurate transcription by appropriately converting technical terms and industry jargon. Some or all of the above-described processing in the transcription unit may be performed using AI, for example, or without AI. For example, the transcription unit can input acquired audio data into a generation AI and have the generation AI recognize and convert technical terms and industry jargon.

[0068] The conversation documentation system includes a transcription unit that has the function of transcribing in different formats for each speaker. The transcription unit uses AI to transcribe in different formats for each speaker. For example, when there are multiple speakers in a meeting, the transcription unit transcribes in a different format for each speaker. The transcription unit can also distinguish between the superior's and subordinate's comments in a conversation between a superior and a subordinate. The transcription unit can also distinguish between the customer's and the company's comments in a phone call with a customer. This allows the speech of multiple speakers to be recorded separately by transcribing in different formats for each speaker. Some or all of the above-described processing in the transcription unit may be performed using AI, for example, or without AI. For example, the transcription unit can input acquired audio data into a generation AI and have the generation AI transcribe in a format for each speaker.

[0069] The conversation documentation system includes a transcription unit that understands the context of a conversation and emphasizes important parts when transcribing. The transcription unit uses AI to understand the context of a conversation and emphasize important parts when transcribing. For example, during a business negotiation, the transcription unit may emphasize important information such as price and delivery date. The transcription unit may also emphasize task priorities and deadlines at the direction of a supervisor. The transcription unit may also emphasize important parts of a conversation with a customer, such as requests and complaints. This allows important information to be recorded without missing any important information by emphasizing the important parts of the conversation. Some or all of the above-described processing in the transcription unit may be performed using AI, for example, or without AI. For example, the transcription unit may input acquired audio data into a generation AI, which may then understand the context of the conversation and emphasize important parts.

[0070] The conversation documentation system includes a transcription unit that automatically records the start and end times of a conversation when transcribing. The transcription unit uses AI to automatically record the start and end times of a conversation when transcribing. For example, the transcription unit automatically records the start and end times of a meeting and reflects them in the transcription. The transcription unit can also automatically record the start and end times of a phone call and reflect them in the transcription. The transcription unit can also automatically record the start and end times of a business meeting and reflect them in the transcription. In this way, by automatically recording the start and end times of a conversation, accurate timestamps can be added to the transcription. Some or all of the above-described processing in the transcription unit may be performed using AI, or may be performed without AI. For example, the transcription unit can input acquired audio data into a generation AI and have the generation AI record the start and end times of the conversation.

[0071] The conversation documentation system includes a transcription unit that automatically tags data based on the content of the conversation during transcription. The transcription unit uses AI to automatically tag data based on the content of the conversation during transcription. For example, the transcription unit automatically tags data based on the price, delivery date, and conditions of a business meeting. The transcription unit can also automatically tag data based on instructions from a supervisor, such as tasks, deadlines, and priorities. The transcription unit can also automatically tag data based on requests, complaints, and feedback based on conversations with customers. This automatic tagging based on the content of the conversation facilitates future searches. Some or all of the above-described processing in the transcription unit may be performed using AI, or may be performed without AI. For example, the transcription unit can input acquired audio data into a generation AI and have the generation AI perform tagging.

[0072] The conversation documentation system includes a transcription unit that improves transcription accuracy by referencing the user's past transcription results during transcription. The transcription unit improves transcription accuracy by using AI to refer to the user's past transcription results during transcription. For example, the transcription unit learns technical terms and phrases used by the user in the past to improve transcription accuracy. The transcription unit can also improve transcription accuracy by learning the vocal characteristics of specific speakers from the user's past transcription results. The transcription unit can also improve transcription accuracy by referencing the context of the user's past conversations. In this way, transcription accuracy can be improved by referring to the user's past transcription results. Some or all of the above-described processing in the transcription unit may be performed using AI, for example, or without AI. For example, the transcription unit can input the user's past transcription results into a generation AI and have the generation AI improve transcription accuracy.

[0073] The conversation documentation system includes a task extraction unit that has a function of understanding the context of a conversation and automatically grouping related tasks when extracting tasks. The task extraction unit uses AI to understand the context of a conversation when extracting tasks and automatically group related tasks. For example, the task extraction unit automatically groups related tasks based on the content of a business negotiation. The task extraction unit can also automatically group related tasks based on instructions from a supervisor. The task extraction unit can also automatically group related tasks based on a conversation with a customer. This understanding of the context of a conversation and grouping related tasks improves task management efficiency. Some or all of the above-described processing in the task extraction unit may be performed using AI, for example, or may be performed without using AI. For example, the task extraction unit can input acquired conversation data to a generation AI and have the generation AI group related tasks.

[0074] The conversation documentation system includes a task extraction unit that has a function of automatically setting a task deadline and a person in charge when extracting a task. The task extraction unit automatically sets the task deadline and a person in charge when extracting a task using AI. For example, the task extraction unit automatically sets the task deadline based on the content of a business negotiation. The task extraction unit can also automatically set a task person in charge based on instructions from a supervisor. The task extraction unit can also automatically set the task deadline and a person in charge based on a conversation with a customer. This automatically setting the task deadline and a person in charge improves task management efficiency. Some or all of the above-mentioned processing in the task extraction unit may be performed using AI, for example, or may be performed without using AI. For example, the task extraction unit can input the acquired conversation data into a generation AI and have the generation AI set the task deadline and a person in charge.

[0075] The conversation documentation system includes a task extraction unit that has a function of automatically suggesting similar tasks by referring to past task history when extracting a task. The task extraction unit uses AI to automatically suggest similar tasks by referring to past task history when extracting a task. For example, the task extraction unit refers to the user's past task history and automatically suggests similar tasks. The task extraction unit can also suggest similar past tasks based on the content of business negotiations. The task extraction unit can also suggest similar past tasks based on instructions from a superior. This allows similar tasks to be efficiently suggested by referring to past task history. Some or all of the above-mentioned processing in the task extraction unit may be performed using AI, for example, or may be performed without using AI. For example, the task extraction unit can input the user's past task history into a generation AI and have the generation AI suggest similar tasks.

[0076] The conversation documentation system includes a task extraction unit that has a function of automatically setting reminders based on the content of the conversation when extracting a task. The task extraction unit uses AI to automatically set reminders based on the content of the conversation when extracting a task. For example, the task extraction unit automatically sets reminders for important tasks based on the content of a business negotiation. The task extraction unit can also automatically set reminders for tasks with deadlines based on instructions from a supervisor. The task extraction unit can also automatically set reminders for important tasks based on a conversation with a customer. By setting reminders based on the content of the conversation, important tasks can be managed without forgetting them. Some or all of the above-mentioned processing in the task extraction unit may be performed using AI, for example, or may be performed without using AI. For example, the task extraction unit can input the acquired conversation data into a generation AI and have the generation AI set reminders.

[0077] The conversation documentation system includes a task extraction unit that has a function of automatically tracking the progress of a task when the task is extracted. The task extraction unit automatically tracks the progress of the task when the task is extracted using AI. For example, the task extraction unit automatically tracks the progress of the task based on the content of a business negotiation. The task extraction unit can also automatically track the progress of the task based on instructions from a supervisor. The task extraction unit can also automatically track the progress of the task based on a conversation with a customer. This allows the task progress to be efficiently managed by automatically tracking the progress of the task. Some or all of the above-described processing in the task extraction unit may be performed using AI, for example, or may be performed without using AI. For example, the task extraction unit may input the acquired conversation data to a generation AI and cause the generation AI to track the progress of the task.

[0078] The conversation documentation system includes a task extraction unit that reflects a user's past feedback during task extraction to improve the accuracy of task extraction. The task extraction unit uses AI to reflect a user's past feedback during task extraction to improve the accuracy of task extraction. For example, the task extraction unit refers to a user's past feedback to improve the accuracy of task extraction. The task extraction unit can also reflect past feedback based on the content of a business negotiation to improve the accuracy of task extraction. The task extraction unit can also reflect past feedback based on instructions from a superior to improve the accuracy of task extraction. In this way, the accuracy of task extraction can be improved by reflecting the user's past feedback. Some or all of the above-described processing in the task extraction unit may be performed using AI, for example, or may be performed without using AI. For example, the task extraction unit can input a user's past feedback into a generation AI and cause the generation AI to improve the accuracy of task extraction.

[0079] The conversation documentation system includes a sending unit that has a function of automatically completing the recipient's email address when sending. The sending unit automatically completes the recipient's email address when sending using AI. For example, the sending unit automatically completes email addresses to which the user has sent in the past. The sending unit can also automatically complete the recipient's email address from the user's contact list. The sending unit can also automatically complete the complete email address from a partial email address entered by the user. This automatically completes the recipient's email address, thereby preventing sending errors. Some or all of the above-described processing in the sending unit may be performed using AI, for example, or may be performed without using AI. For example, the sending unit can input the user's contact list into a generation AI and have the generation AI complete the email address.

[0080] The conversation documentation system includes a sending unit that has a function of automatically setting a subject based on the content of a document when it is sent. The sending unit uses AI to automatically set a subject based on the content of a document when it is sent. For example, the sending unit automatically sets an appropriate subject based on the content of a business negotiation. The sending unit can also automatically set an appropriate subject based on instructions from a supervisor. The sending unit can also automatically set an appropriate subject based on a conversation with a customer. In this way, by automatically setting a subject based on the content of the document, it is possible to send a document with an appropriate subject. Some or all of the above-described processing in the sending unit may be performed using AI, for example, or may be performed without using AI. For example, the sending unit can input the content of the document into a generation AI and have the generation AI set the subject.

[0081] The conversation documentation system includes a transmission unit that has a function of automatically recording a transmission history at the time of transmission so that it can be referenced later. The transmission unit uses AI to automatically record the transmission history at the time of transmission so that it can be referenced later. For example, the transmission unit automatically records the history of sent documents so that it can be referenced later. The transmission unit can also automatically record the history of sent emails so that it can be referenced later. The transmission unit can also automatically record the history of sent task lists so that it can be referenced later. In this way, by automatically recording the transmission history, the transmitted content can be confirmed later. Some or all of the above-described processing in the transmission unit may be performed using AI, for example, or may be performed without using AI. For example, the transmission unit can input the transmission history to a generation AI and have the generation AI record the history.

[0082] The conversation documentation system includes a sending unit that has a function of tracking the reception status of the recipient in real time at the time of transmission. The sending unit uses AI to track the reception status of the recipient in real time at the time of transmission. For example, the sending unit tracks in real time whether a sent email has been received. The sending unit can also track in real time whether a sent document has been opened. The sending unit can also track in real time whether a sent task list has been checked. In this way, by tracking the reception status of the recipient in real time, it is possible to confirm whether the transmitted content has been reliably received. Some or all of the above-described processing in the sending unit may be performed using AI, for example, or may be performed without using AI. For example, the sending unit can input reception status data of the recipient into a generation AI and have the generation AI track the reception status.

[0083] The conversation documentation system includes a transmission unit that has a function of automatically adding attachments based on the content of a document when the document is sent. The transmission unit uses AI to automatically add attachments based on the content of the document when the document is sent. For example, the transmission unit automatically attaches related materials based on the content of a business negotiation. The transmission unit can also automatically attach related files based on instructions from a supervisor. The transmission unit can also automatically attach related documents based on a conversation with a customer. This allows related materials to be sent reliably by automatically adding attachments based on the content of the document. Some or all of the above-described processing in the transmission unit may be performed using AI, for example, or may be performed without using AI. For example, the transmission unit can input the content of the document into a generation AI and have the generation AI add attachments.

[0084] The conversation documentation system includes a transmission unit that has a function of referencing a user's past transmission history to customize the content of a message when sending the message. The transmission unit uses AI to refer to the user's past transmission history when sending the message and customize the content. For example, the transmission unit refers to the user's past transmission history to customize the content of a message. The transmission unit can also customize the content of a message by reflecting the past transmission history based on the content of a business negotiation. The transmission unit can also customize the content of a message by reflecting the past transmission history based on instructions from a superior. This allows the content of a message to be customized and sent with appropriate content by referring to the user's past transmission history. Some or all of the above-described processing in the transmission unit may be performed using AI, for example, or may be performed without using AI. For example, the transmission unit can input the user's past transmission history into a generation AI and have the generation AI customize the content of a message.

[0085] The conversation documentation system includes a confirmation item suggestion unit that has a function of understanding the context of the conversation and automatically grouping related confirmation items when proposing confirmation items. The confirmation item suggestion unit uses AI to understand the context of the conversation when proposing confirmation items and automatically group related confirmation items. For example, the confirmation item suggestion unit automatically groups related confirmation items based on the content of a business negotiation. The confirmation item suggestion unit can also automatically group related confirmation items based on instructions from a supervisor. The confirmation item suggestion unit can also automatically group related confirmation items based on a conversation with a customer. This understanding of the conversation context and grouping related confirmation items improves the efficiency of confirmation item management. Some or all of the above-described processing in the confirmation item suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the confirmation item suggestion unit can input acquired conversation data to a generation AI and have the generation AI group related confirmation items.

[0086] The conversation documentation system includes a check item suggestion unit that has a function of automatically suggesting similar check items by referring to past conversation history when proposing check items. The check item suggestion unit uses AI to automatically suggest similar check items by referring to past conversation history when proposing check items. For example, the check item suggestion unit refers to the user's past conversation history and automatically suggests similar check items. The check item suggestion unit can also suggest similar past check items based on the content of business negotiations. The check item suggestion unit can also suggest similar past check items based on instructions from a supervisor. This allows similar check items to be efficiently suggested by referring to past conversation history. Some or all of the above-mentioned processing in the check item suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the check item suggestion unit can input the user's past conversation history into a generation AI and have the generation AI suggest similar check items.

[0087] The conversation documentation system includes a confirmation item suggestion unit that has a function of adjusting the level of detail of the proposal based on the importance of the confirmation item when proposing the confirmation item. The confirmation item suggestion unit adjusts the level of detail of the proposal based on the importance of the confirmation item using AI when proposing the confirmation item. For example, the confirmation item suggestion unit makes detailed suggestions for important confirmation items. The confirmation item suggestion unit can also make standard suggestions for ordinary confirmation items. The confirmation item suggestion unit can also make concise suggestions for urgent confirmation items. In this way, by adjusting the level of detail of the proposal based on the importance of the confirmation item, it is possible to propose confirmation items with an appropriate level of detail. Some or all of the above-described processing in the confirmation item suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the confirmation item suggestion unit can input the acquired conversation data to a generation AI and cause the generation AI to adjust the level of detail of the proposal.

[0088] The conversation documentation system includes a confirmation item suggestion unit that has a function of automatically setting a reminder based on the content of the conversation when a confirmation item is suggested. The confirmation item suggestion unit automatically sets a reminder based on the content of the conversation when a confirmation item is suggested using AI. For example, the confirmation item suggestion unit automatically sets a reminder for important confirmation items based on the content of a business negotiation. The confirmation item suggestion unit can also automatically set a reminder for confirmation items with deadlines based on instructions from a supervisor. The confirmation item suggestion unit can also automatically set a reminder for important confirmation items based on a conversation with a customer. In this way, by setting a reminder based on the content of the conversation, important confirmation items can be managed without forgetting them. Some or all of the above-mentioned processing in the confirmation item suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the confirmation item suggestion unit can input the acquired conversation data into a generation AI and have the generation AI set a reminder.

[0089] The conversation documentation system includes a confirmation item suggestion unit that has a function of automatically tracking the progress of a confirmation item when the confirmation item is proposed. The confirmation item suggestion unit automatically tracks the progress of the confirmation item when the confirmation item is proposed using AI. For example, the confirmation item suggestion unit automatically tracks the progress of the confirmation item based on the content of a business negotiation. The confirmation item suggestion unit can also automatically track the progress of the confirmation item based on instructions from a supervisor. The confirmation item suggestion unit can also automatically track the progress of the confirmation item based on a conversation with a customer. This allows the progress of the confirmation item to be efficiently managed by automatically tracking the progress of the confirmation item. Some or all of the above-described processing in the confirmation item suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the confirmation item suggestion unit may input the acquired conversation data into a generation AI and cause the generation AI to track the progress of the confirmation item.

[0090] The conversation documentation system includes a confirmation item suggestion unit that, when proposing confirmation items, reflects the user's past feedback to improve the accuracy of the confirmation item suggestions. The confirmation item suggestion unit uses AI to reflect the user's past feedback when proposing confirmation items to improve the accuracy of the confirmation item suggestions. For example, the confirmation item suggestion unit refers to the user's past feedback to improve the accuracy of the confirmation item suggestions. The confirmation item suggestion unit can also reflect past feedback based on the content of a business negotiation to improve the accuracy of the confirmation item suggestions. The confirmation item suggestion unit can also reflect past feedback to improve the accuracy of the confirmation item suggestions based on instructions from a superior. In this way, the accuracy of the confirmation item suggestions can be improved by reflecting the user's past feedback. Some or all of the above-described processing in the confirmation item suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the confirmation item suggestion unit can input the user's past feedback into the generation AI and cause the generation AI to improve the accuracy of the confirmation item suggestions.

[0091] The processing flow of the first embodiment will be briefly explained below.

[0092] Step 1: The voice input unit captures the content of the phone conversation in real time and inputs it into the transcription unit. For example, the voice input unit can capture the content of the conversation using a high-precision microphone and convert it into digital data in real time. It can also use noise-canceling technology to remove background noise and provide clear voice data. It can also use AI to estimate the user's emotions and adjust the sensitivity of the voice input. Step 2: The transcription section uses AI to analyze the input audio data and transcribe it. For example, it can use speech recognition technology to convert the audio data into text data, automatically recognizing technical terms and industry jargon and converting them appropriately. It can also understand the context of the conversation and emphasize important parts when transcribing. Step 3: The task extraction unit uses AI to extract tasks from the transcription results and create a task list. For example, it can extract next action items and deadlines from the content of a business meeting and compile them into a task list. It can also understand the context of the conversation and automatically group related tasks. It can also estimate the user's emotions and determine task priorities. Step 4: The sending unit generates the task list created by the task extraction unit as a document and sends it by email. For example, it can document the generated task list in PDF format and send it to a specified email address. It can also automatically complete the recipient's email address. It can also estimate the user's emotions and adjust the format of the document to be sent. Step 5: The confirmation suggestion section uses AI to suggest confirmation items based on a general business framework based on the transcription results. For example, it suggests points to be confirmed or additional questions to ask based on the content of the business negotiation. It can also estimate the user's emotions and determine the priority of confirmation items.

[0093] (Example 2) A system according to an embodiment of the present invention documents conversations, such as business negotiations over the phone or instructions from a superior, and creates tasks. This system captures the content of phone calls in real time and inputs it into an AI to transcribe them and create a task list. The AI ​​also suggests confirmation items based on a general business framework, thereby preventing later questions from arising. This allows the system to efficiently document conversations, such as business negotiations or instructions from a superior, and create tasks. The AI ​​also suggests necessary confirmation items, thereby preventing later questions from arising. For example, the system provides a voice input unit for capturing the content of phone calls. This voice input unit captures the content of phone conversations in real time and inputs it into the AI. The AI ​​then analyzes the input voice data and transcribes it. The transcription results are generated as a document and sent via email. The AI ​​then extracts tasks from the transcription results and creates a task list. This task list is also generated as a document and sent via email. For example, the system extracts next action items and deadlines from the content of business negotiations and compiles them into a task list. AI also suggests points that need to be checked based on common business frameworks, helping to avoid questions being asked later. For example, it suggests points that need to be checked or additional questions based on the content of a sales negotiation.

[0094] A conversation documentation system according to an embodiment includes a voice input unit, a transcription unit, a task extraction unit, a transmission unit, and a confirmation item suggestion unit. The voice input unit captures telephone conversation content in real time and inputs it to the transcription unit. For example, the voice input unit captures telephone conversation content using a high-precision microphone and converts it into digital data in real time. The voice input unit can also use noise-canceling technology to remove background noise and provide clear voice data. The voice input unit can also use AI to estimate a user's emotions and adjust the sensitivity of the voice input. For example, if the user is nervous, the voice input unit can increase the sensitivity of the voice input to capture the voice more clearly. The transcription unit uses AI to analyze the input voice data and transcribe it. For example, the transcription unit converts the voice data into text data using voice recognition technology. The transcription unit can also automatically recognize technical terms and industry jargon and convert them appropriately. The transcription unit can also understand the context of the conversation and emphasize important parts when transcribing. For example, the transcription unit transcribes business negotiations, emphasizing important information such as price and delivery date. The task extraction unit uses AI to extract tasks from the transcription results and create a task list. For example, the task extraction unit extracts next action items and deadlines from the content of business negotiations and organizes them in a task list. The task extraction unit can also understand the context of the conversation and automatically group related tasks. Furthermore, the task extraction unit can infer the user's emotions and determine task priority. For example, if the user is nervous, the task extraction unit can prioritize important tasks. The sending unit generates the task list as a document and sends it by email. For example, the sending unit documents the generated task list in PDF format and sends it to a specified email address. The sending unit can also automatically complete the recipient's email address. Furthermore, the sending unit can infer the user's emotions and adjust the format of the document to be sent. For example, if the user is nervous, the sending unit can use a concise and clear format.The confirmation item suggestion unit uses AI to suggest confirmation items from a general business framework based on the transcription results. For example, the confirmation item suggestion unit suggests points to be confirmed or additional questions based on the content of a business negotiation. The confirmation item suggestion unit can also estimate the user's emotions and determine the priority of confirmation items. For example, if the user is nervous, the confirmation item suggestion unit will prioritize suggesting important confirmation items. As a result, the conversation documentation system according to the embodiment can efficiently document the content of a telephone conversation, turn it into a task, and suggest necessary confirmation items.

[0095] The conversation documentation system includes a voice input unit that estimates a user's emotion and automatically adjusts the sensitivity of the voice input based on the estimated emotion. The voice input unit estimates the user's emotion using AI and adjusts the sensitivity of the voice input. For example, if the user is nervous, the voice input unit increases the sensitivity of the voice input to capture voice more clearly. If the user is relaxed, the voice input unit can set the sensitivity of the voice input to normal to capture natural conversation. If the user is excited, the voice input unit can adjust the sensitivity of the voice input to capture voice while removing excessive noise. Adjusting the sensitivity of the voice input according to the user's emotion enables clearer voice capture. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the voice input unit may be performed using, for example, AI, or without AI. For example, the voice input unit can input the user's voice data into the generation AI and have the generation AI estimate emotions.

[0096] The conversation documentation system includes an audio input unit with a filtering function that automatically removes background noise during audio input. The audio input unit uses AI to automatically remove background noise during audio input. For example, the audio input unit automatically removes air conditioner noise and external noise during a conference call in a conference room. The audio input unit can also filter out and remove background voices and music during a phone conversation in a public place such as a cafe. The audio input unit can also automatically remove engine noise and road noise during a phone conversation in a car. This removes background noise, allowing clear audio data to be obtained. Some or all of the above-described processing in the audio input unit may be performed using AI, for example, or without AI. For example, the audio input unit can input the acquired audio data to a generation AI and have the generation AI remove background noise.

[0097] The conversation documentation system includes a voice input unit that analyzes the characteristics of a speaker's voice during voice input and creates a different voice profile for each speaker. The voice input unit uses AI to analyze the characteristics of a speaker's voice during voice input and create a different voice profile for each speaker. For example, the voice input unit analyzes the characteristics of each speaker's voice during a conference with multiple speakers and creates an individual voice profile. The voice input unit can also create profiles that distinguish between the voice of the boss and the voice of the subordinate during a conversation between a boss and a subordinate. The voice input unit can also analyze the characteristics of the customer's voice during a phone call with a customer and automatically recognize it the next time the conversation occurs. This allows the voices of multiple speakers to be captured separately by creating a different voice profile for each speaker. Some or all of the above-described processing in the voice input unit may be performed using AI, for example, or without AI. For example, the voice input unit can input acquired voice data to a generation AI and have the generation AI analyze the characteristics of the speaker's voice.

[0098] The conversation documentation system includes a voice input unit that analyzes the context of a conversation during voice input and captures it with emphasis on important parts. The voice input unit uses AI to analyze the context of a conversation during voice input and captures it with emphasis on important parts. For example, the voice input unit captures important information such as price and delivery date during a business negotiation with emphasis. The voice input unit can also capture task priorities and deadlines with emphasis at the direction of a supervisor. The voice input unit can also capture important parts of a conversation with a customer with emphasis on requests and complaints. By capturing and emphasizing important parts of the conversation, important information can be recorded without missing anything. Some or all of the above-described processing in the voice input unit may be performed using, for example, AI, or may be performed without using AI. For example, the voice input unit can input acquired voice data to a generation AI and have the generation AI analyze the context of the conversation.

[0099] The conversation documentation system includes a speech input unit that estimates a user's emotion and adjusts the timing of the start of speech input based on the estimated emotion. The speech input unit estimates the user's emotion using AI and adjusts the timing of the start of speech input. For example, if the user is nervous, the speech input unit delays the start of speech input until the user relaxes. Alternatively, if the user is relaxed, the speech input unit can immediately start speech input. Alternatively, if the user is excited, the speech input unit can delay the start of speech input until the user calms down. This allows speech to be captured at an appropriate timing by adjusting the start of speech input according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the speech input unit may be performed using AI, for example, or without AI. For example, the speech input unit may input the user's speech data to the generation AI and have the generation AI perform emotion estimation.

[0100] The conversation documentation system includes a voice input unit that selects voice input settings based on the user's geographic location information when the user inputs voice. The voice input unit uses AI to select optimal voice input settings by taking the user's geographic location information into consideration when the user inputs voice. For example, the voice input unit uses normal voice input settings when the user is in a quiet office. The voice input unit can also use voice input settings with enhanced noise cancellation when the user is in a noisy cafe. The voice input unit can also use voice input settings that remove engine noise when the user is in a moving car. This enables voice capture tailored to the environment by selecting optimal voice input settings based on the user's geographic location information. Some or all of the above-described processing in the voice input unit may be performed using AI, for example, or without AI. For example, the voice input unit can input the user's geographic location information to a generation AI and have the generation AI select optimal voice input settings.

[0101] The conversation documentation system includes a speech input unit that, when inputting speech, refers to a user's past conversation history to improve the accuracy of the speech input. The speech input unit uses AI to refer to the user's past conversation history to improve the accuracy of the speech input. For example, the speech input unit learns technical terms and phrases used by the user in the past to improve the accuracy of the speech input. The speech input unit can also learn the vocal characteristics of specific speakers from the user's past conversation history to improve the accuracy of the speech input. The speech input unit can also improve the accuracy of the speech input by referring to the context of the user's past conversations. In this way, the accuracy of the speech input can be improved by referring to the user's past conversation history. Some or all of the above-described processing in the speech input unit may be performed using AI, for example, or may be performed without using AI. For example, the speech input unit can input the user's past conversation history to a generation AI and have the generation AI improve the accuracy of the speech input.

[0102] The conversation documentation system includes a voice input unit that analyzes a user's social media activity and prioritizes capturing relevant conversation content when a user inputs voice. The voice input unit uses AI to analyze the user's social media activity and prioritizes capturing relevant conversation content when a user inputs voice. For example, the voice input unit prioritizes capturing topics that the user frequently mentions on social media. The voice input unit can also analyze the user's social media posts and prioritize capturing relevant conversation content. The voice input unit can also prioritize capturing relevant conversation content by referring to the activities of the user's friends on social media. In this way, by analyzing the user's social media activity, relevant conversation content can be prioritized. Some or all of the above-described processing in the voice input unit may be performed using AI, for example, or may be performed without using AI. For example, the voice input unit can input the user's social media activity data to a generation AI and cause the generation AI to prioritize capturing relevant conversation content.

[0103] The conversation documentation system includes a transcription unit that estimates a user's emotions and changes the transcription expression style based on the estimated user emotions. The transcription unit estimates the user's emotions using AI and adjusts the transcription expression style. For example, if the user is nervous, the transcription unit uses a concise and clear expression style. Also, if the user is relaxed, the transcription unit can use a detailed expression style. Also, if the user is excited, the transcription unit can use an expression style that reflects the user's emotions. This allows the transcription to be performed using an appropriate expression style by adjusting the transcription expression style according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the transcription unit may be performed using AI, or without AI. For example, the transcription unit can input the user's voice data into the generation AI and have the generation AI perform emotion estimation.

[0104] The conversation documentation system includes a transcription unit that automatically recognizes and appropriately converts technical terms and industry jargon during transcription. The transcription unit uses AI to automatically recognize and appropriately convert technical terms and industry jargon during transcription. For example, the transcription unit automatically recognizes and appropriately converts technical terms in IT industry conversations. The transcription unit can also automatically recognize and appropriately convert technical terms in medical industry conversations. The transcription unit can also automatically recognize and appropriately convert technical terms in legal industry conversations. This allows for accurate transcription by appropriately converting technical terms and industry jargon. Some or all of the above-described processing in the transcription unit may be performed using AI, for example, or without AI. For example, the transcription unit can input acquired audio data into a generation AI and have the generation AI recognize and convert technical terms and industry jargon.

[0105] The conversation documentation system includes a transcription unit that has the function of transcribing in different formats for each speaker. The transcription unit uses AI to transcribe in different formats for each speaker. For example, when there are multiple speakers in a meeting, the transcription unit transcribes in a different format for each speaker. The transcription unit can also distinguish between the superior's and subordinate's comments in a conversation between a superior and a subordinate. The transcription unit can also distinguish between the customer's and the company's comments in a phone call with a customer. This allows the speech of multiple speakers to be recorded separately by transcribing in different formats for each speaker. Some or all of the above-described processing in the transcription unit may be performed using AI, for example, or without AI. For example, the transcription unit can input acquired audio data into a generation AI and have the generation AI transcribe in a format for each speaker.

[0106] The conversation documentation system includes a transcription unit that understands the context of a conversation and emphasizes important parts when transcribing. The transcription unit uses AI to understand the context of a conversation and emphasize important parts when transcribing. For example, during a business negotiation, the transcription unit may emphasize important information such as price and delivery date. The transcription unit may also emphasize task priorities and deadlines at the direction of a supervisor. The transcription unit may also emphasize important parts of a conversation with a customer, such as requests and complaints. This allows important information to be recorded without missing any important information by emphasizing the important parts of the conversation. Some or all of the above-described processing in the transcription unit may be performed using AI, for example, or without AI. For example, the transcription unit may input acquired audio data into a generation AI, which may then understand the context of the conversation and emphasize important parts.

[0107] The conversation documentation system includes a transcription unit that estimates a user's emotions and adjusts the length of the transcription based on the estimated user emotions. The transcription unit estimates the user's emotions using AI and adjusts the length of the transcription. For example, if the user is in a hurry, the transcription unit may provide a short transcription that focuses on the main points. If the user is relaxed, the transcription unit may also provide a detailed transcription. If the user is excited, the transcription unit may also provide a longer transcription that reflects the user's emotions. By adjusting the length of the transcription according to the user's emotions, the transcription can be performed at an appropriate length. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the transcription unit may be performed using, for example, AI, or without AI. For example, the transcription unit can input the user's voice data into the generation AI and have the generation AI estimate emotions.

[0108] The conversation documentation system includes a transcription unit that automatically records the start and end times of a conversation when transcribing. The transcription unit uses AI to automatically record the start and end times of a conversation when transcribing. For example, the transcription unit automatically records the start and end times of a meeting and reflects them in the transcription. The transcription unit can also automatically record the start and end times of a phone call and reflect them in the transcription. The transcription unit can also automatically record the start and end times of a business meeting and reflect them in the transcription. In this way, by automatically recording the start and end times of a conversation, accurate timestamps can be added to the transcription. Some or all of the above-described processing in the transcription unit may be performed using AI, or may be performed without AI. For example, the transcription unit can input acquired audio data into a generation AI and have the generation AI record the start and end times of the conversation.

[0109] The conversation documentation system includes a transcription unit that automatically tags data based on the content of the conversation during transcription. The transcription unit uses AI to automatically tag data based on the content of the conversation during transcription. For example, the transcription unit automatically tags data based on the price, delivery date, and conditions of a business meeting. The transcription unit can also automatically tag data based on instructions from a supervisor, such as tasks, deadlines, and priorities. The transcription unit can also automatically tag data based on requests, complaints, and feedback based on conversations with customers. This automatic tagging based on the content of the conversation facilitates future searches. Some or all of the above-described processing in the transcription unit may be performed using AI, or may be performed without AI. For example, the transcription unit can input acquired audio data into a generation AI and have the generation AI perform tagging.

[0110] The conversation documentation system includes a transcription unit that improves transcription accuracy by referencing the user's past transcription results during transcription. The transcription unit improves transcription accuracy by using AI to refer to the user's past transcription results during transcription. For example, the transcription unit learns technical terms and phrases used by the user in the past to improve transcription accuracy. The transcription unit can also improve transcription accuracy by learning the vocal characteristics of specific speakers from the user's past transcription results. The transcription unit can also improve transcription accuracy by referencing the context of the user's past conversations. In this way, transcription accuracy can be improved by referring to the user's past transcription results. Some or all of the above-described processing in the transcription unit may be performed using AI, for example, or without AI. For example, the transcription unit can input the user's past transcription results into a generation AI and have the generation AI improve transcription accuracy.

[0111] The conversation documentation system includes a task extraction unit that estimates a user's emotions and prioritizes tasks based on the estimated user emotions. The task extraction unit estimates the user's emotions using AI and determines the priority of tasks. For example, if the user is nervous, the task extraction unit may prioritize important tasks. If the user is relaxed, the task extraction unit may also prioritize tasks with normal priority. If the user is excited, the task extraction unit may also prioritize urgent tasks. This allows important tasks to be prioritized by determining the priority of tasks based on 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 may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the task extraction unit may be performed using AI, or may be performed without AI. For example, the task extraction unit may input user emotion data into the generation AI and have the generation AI determine the priority of tasks.

[0112] The conversation documentation system includes a task extraction unit that has a function of understanding the context of a conversation and automatically grouping related tasks when extracting tasks. The task extraction unit uses AI to understand the context of a conversation when extracting tasks and automatically group related tasks. For example, the task extraction unit automatically groups related tasks based on the content of a business negotiation. The task extraction unit can also automatically group related tasks based on instructions from a supervisor. The task extraction unit can also automatically group related tasks based on a conversation with a customer. This understanding of the context of a conversation and grouping related tasks improves task management efficiency. Some or all of the above-described processing in the task extraction unit may be performed using AI, for example, or may be performed without using AI. For example, the task extraction unit can input acquired conversation data to a generation AI and have the generation AI group related tasks.

[0113] The conversation documentation system includes a task extraction unit that has a function of automatically setting a task deadline and a person in charge when extracting a task. The task extraction unit automatically sets the task deadline and a person in charge when extracting a task using AI. For example, the task extraction unit automatically sets the task deadline based on the content of a business negotiation. The task extraction unit can also automatically set a task person in charge based on instructions from a supervisor. The task extraction unit can also automatically set the task deadline and a person in charge based on a conversation with a customer. This automatically setting the task deadline and a person in charge improves task management efficiency. Some or all of the above-mentioned processing in the task extraction unit may be performed using AI, for example, or may be performed without using AI. For example, the task extraction unit can input the acquired conversation data into a generation AI and have the generation AI set the task deadline and a person in charge.

[0114] The conversation documentation system includes a task extraction unit that has a function of automatically suggesting similar tasks by referring to past task history when extracting a task. The task extraction unit uses AI to automatically suggest similar tasks by referring to past task history when extracting a task. For example, the task extraction unit refers to the user's past task history and automatically suggests similar tasks. The task extraction unit can also suggest similar past tasks based on the content of business negotiations. The task extraction unit can also suggest similar past tasks based on instructions from a superior. This allows similar tasks to be efficiently suggested by referring to past task history. Some or all of the above-mentioned processing in the task extraction unit may be performed using AI, for example, or may be performed without using AI. For example, the task extraction unit can input the user's past task history into a generation AI and have the generation AI suggest similar tasks.

[0115] The conversation documentation system includes a task extraction unit that estimates a user's emotions and changes the display method of tasks based on the estimated user emotions. The task extraction unit estimates the user's emotions using AI and adjusts the display method of tasks. For example, if the user is nervous, the task extraction unit highlights important tasks. Furthermore, if the user is relaxed, the task extraction unit can also display tasks in a normal display method. Furthermore, if the user is excited, the task extraction unit can highlight urgent tasks. Thus, by adjusting the display method of tasks according to the user's emotions, important tasks can be highlighted. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the task extraction unit may be performed using AI, or without AI. For example, the task extraction unit can input user emotion data into the generation AI and cause the generation AI to adjust the display method of tasks.

[0116] The conversation documentation system includes a task extraction unit that has a function of automatically setting reminders based on the content of the conversation when extracting a task. The task extraction unit uses AI to automatically set reminders based on the content of the conversation when extracting a task. For example, the task extraction unit automatically sets reminders for important tasks based on the content of a business negotiation. The task extraction unit can also automatically set reminders for tasks with deadlines based on instructions from a supervisor. The task extraction unit can also automatically set reminders for important tasks based on a conversation with a customer. By setting reminders based on the content of the conversation, important tasks can be managed without forgetting them. Some or all of the above-mentioned processing in the task extraction unit may be performed using AI, for example, or may be performed without using AI. For example, the task extraction unit can input the acquired conversation data into a generation AI and have the generation AI set reminders.

[0117] The conversation documentation system includes a task extraction unit that has a function of automatically tracking the progress of a task when the task is extracted. The task extraction unit automatically tracks the progress of the task when the task is extracted using AI. For example, the task extraction unit automatically tracks the progress of the task based on the content of a business negotiation. The task extraction unit can also automatically track the progress of the task based on instructions from a supervisor. The task extraction unit can also automatically track the progress of the task based on a conversation with a customer. This allows the task progress to be efficiently managed by automatically tracking the progress of the task. Some or all of the above-described processing in the task extraction unit may be performed using AI, for example, or may be performed without using AI. For example, the task extraction unit may input the acquired conversation data to a generation AI and cause the generation AI to track the progress of the task.

[0118] The conversation documentation system includes a task extraction unit that reflects a user's past feedback during task extraction to improve the accuracy of task extraction. The task extraction unit uses AI to reflect a user's past feedback during task extraction to improve the accuracy of task extraction. For example, the task extraction unit refers to a user's past feedback to improve the accuracy of task extraction. The task extraction unit can also reflect past feedback based on the content of a business negotiation to improve the accuracy of task extraction. The task extraction unit can also reflect past feedback based on instructions from a superior to improve the accuracy of task extraction. In this way, the accuracy of task extraction can be improved by reflecting the user's past feedback. Some or all of the above-described processing in the task extraction unit may be performed using AI, for example, or may be performed without using AI. For example, the task extraction unit can input a user's past feedback into a generation AI and cause the generation AI to improve the accuracy of task extraction.

[0119] The conversation documentation system includes a sending unit that estimates a user's emotion and changes the format of a document to be sent based on the estimated user's emotion. The sending unit estimates the user's emotion using AI and adjusts the format of the document to be sent. For example, if the user is nervous, the sending unit uses a concise and clear format. If the user is relaxed, the sending unit can use a detailed format. If the user is excited, the sending unit can use a visually stimulating format. This allows the document to be sent in an appropriate format by adjusting the document format according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the sending unit may be performed using AI, for example, or without AI. For example, the sending unit may input user's emotion data into the generation AI and have the generation AI adjust the document format.

[0120] The conversation documentation system includes a sending unit that has a function of automatically completing the recipient's email address when sending. The sending unit automatically completes the recipient's email address when sending using AI. For example, the sending unit automatically completes email addresses to which the user has sent in the past. The sending unit can also automatically complete the recipient's email address from the user's contact list. The sending unit can also automatically complete the complete email address from a partial email address entered by the user. This automatically completes the recipient's email address, thereby preventing sending errors. Some or all of the above-described processing in the sending unit may be performed using AI, for example, or may be performed without using AI. For example, the sending unit can input the user's contact list into a generation AI and have the generation AI complete the email address.

[0121] The conversation documentation system includes a sending unit that has a function of automatically setting a subject based on the content of a document when it is sent. The sending unit uses AI to automatically set a subject based on the content of a document when it is sent. For example, the sending unit automatically sets an appropriate subject based on the content of a business negotiation. The sending unit can also automatically set an appropriate subject based on instructions from a supervisor. The sending unit can also automatically set an appropriate subject based on a conversation with a customer. In this way, by automatically setting a subject based on the content of the document, it is possible to send a document with an appropriate subject. Some or all of the above-described processing in the sending unit may be performed using AI, for example, or may be performed without using AI. For example, the sending unit can input the content of the document into a generation AI and have the generation AI set the subject.

[0122] The conversation documentation system includes a transmission unit that has a function of automatically recording a transmission history at the time of transmission so that it can be referenced later. The transmission unit uses AI to automatically record the transmission history at the time of transmission so that it can be referenced later. For example, the transmission unit automatically records the history of sent documents so that it can be referenced later. The transmission unit can also automatically record the history of sent emails so that it can be referenced later. The transmission unit can also automatically record the history of sent task lists so that it can be referenced later. In this way, by automatically recording the transmission history, the transmitted content can be confirmed later. Some or all of the above-described processing in the transmission unit may be performed using AI, for example, or may be performed without using AI. For example, the transmission unit can input the transmission history to a generation AI and have the generation AI record the history.

[0123] The conversation documentation system includes a transmission unit that estimates a user's emotion and adjusts the timing of transmission based on the estimated user emotion. The transmission unit estimates the user's emotion using AI and adjusts the timing of transmission. For example, if the user is nervous, the transmission unit delays transmission until the user relaxes. Alternatively, if the user is relaxed, the transmission unit can immediately transmit the document. Alternatively, if the user is excited, the transmission unit can adjust the transmission until the user calms down. This allows documents to be sent at an appropriate time by adjusting the transmission timing according to the user's emotion. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the transmission unit may be performed using AI, or may be performed without AI. For example, the transmission unit may input the user's emotion data into the generation AI and have the generation AI adjust the transmission timing.

[0124] The conversation documentation system includes a sending unit that has a function of tracking the reception status of the recipient in real time at the time of transmission. The sending unit uses AI to track the reception status of the recipient in real time at the time of transmission. For example, the sending unit tracks in real time whether a sent email has been received. The sending unit can also track in real time whether a sent document has been opened. The sending unit can also track in real time whether a sent task list has been checked. In this way, by tracking the reception status of the recipient in real time, it is possible to confirm whether the transmitted content has been reliably received. Some or all of the above-described processing in the sending unit may be performed using AI, for example, or may be performed without using AI. For example, the sending unit can input reception status data of the recipient into a generation AI and have the generation AI track the reception status.

[0125] The conversation documentation system includes a transmission unit that has a function of automatically adding attachments based on the content of a document when the document is sent. The transmission unit uses AI to automatically add attachments based on the content of the document when the document is sent. For example, the transmission unit automatically attaches related materials based on the content of a business negotiation. The transmission unit can also automatically attach related files based on instructions from a supervisor. The transmission unit can also automatically attach related documents based on a conversation with a customer. This allows related materials to be sent reliably by automatically adding attachments based on the content of the document. Some or all of the above-described processing in the transmission unit may be performed using AI, for example, or may be performed without using AI. For example, the transmission unit can input the content of the document into a generation AI and have the generation AI add attachments.

[0126] The conversation documentation system includes a transmission unit that has a function of referencing a user's past transmission history to customize the content of a message when sending the message. The transmission unit uses AI to refer to the user's past transmission history when sending the message and customize the content. For example, the transmission unit refers to the user's past transmission history to customize the content of a message. The transmission unit can also customize the content of a message by reflecting the past transmission history based on the content of a business negotiation. The transmission unit can also customize the content of a message by reflecting the past transmission history based on instructions from a superior. This allows the content of a message to be customized and sent with appropriate content by referring to the user's past transmission history. Some or all of the above-described processing in the transmission unit may be performed using AI, for example, or may be performed without using AI. For example, the transmission unit can input the user's past transmission history into a generation AI and have the generation AI customize the content of a message.

[0127] The conversation documentation system includes a check item suggestion unit that estimates a user's emotions and prioritizes check items based on the estimated user emotions. The check item suggestion unit estimates the user's emotions using AI and determines the priority of the check items. For example, if the user is nervous, the check item suggestion unit may prioritize important check items. If the user is relaxed, the check item suggestion unit may also prioritize check items based on normal priority. If the user is excited, the check item suggestion unit may also prioritize urgent check items. This allows the priority of check items to be determined based on the user's emotions, thereby prioritizing important check items. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the check item suggestion unit may be performed using AI or without AI. For example, the check item suggestion unit may input user emotion data into the generation AI and have the generation AI determine the priority of the check items.

[0128] The conversation documentation system includes a confirmation item suggestion unit that has a function of understanding the context of the conversation and automatically grouping related confirmation items when proposing confirmation items. The confirmation item suggestion unit uses AI to understand the context of the conversation when proposing confirmation items and automatically group related confirmation items. For example, the confirmation item suggestion unit automatically groups related confirmation items based on the content of a business negotiation. The confirmation item suggestion unit can also automatically group related confirmation items based on instructions from a supervisor. The confirmation item suggestion unit can also automatically group related confirmation items based on a conversation with a customer. This understanding of the conversation context and grouping related confirmation items improves the efficiency of confirmation item management. Some or all of the above-described processing in the confirmation item suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the confirmation item suggestion unit can input acquired conversation data to a generation AI and have the generation AI group related confirmation items.

[0129] The conversation documentation system includes a check item suggestion unit that has a function of automatically suggesting similar check items by referring to past conversation history when proposing check items. The check item suggestion unit uses AI to automatically suggest similar check items by referring to past conversation history when proposing check items. For example, the check item suggestion unit refers to the user's past conversation history and automatically suggests similar check items. The check item suggestion unit can also suggest similar past check items based on the content of business negotiations. The check item suggestion unit can also suggest similar past check items based on instructions from a supervisor. This allows similar check items to be efficiently suggested by referring to past conversation history. Some or all of the above-mentioned processing in the check item suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the check item suggestion unit can input the user's past conversation history into a generation AI and have the generation AI suggest similar check items.

[0130] The conversation documentation system includes a confirmation item suggestion unit that has a function of adjusting the level of detail of the proposal based on the importance of the confirmation item when proposing the confirmation item. The confirmation item suggestion unit adjusts the level of detail of the proposal based on the importance of the confirmation item using AI when proposing the confirmation item. For example, the confirmation item suggestion unit makes detailed suggestions for important confirmation items. The confirmation item suggestion unit can also make standard suggestions for ordinary confirmation items. The confirmation item suggestion unit can also make concise suggestions for urgent confirmation items. In this way, by adjusting the level of detail of the proposal based on the importance of the confirmation item, it is possible to propose confirmation items with an appropriate level of detail. Some or all of the above-described processing in the confirmation item suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the confirmation item suggestion unit can input the acquired conversation data to a generation AI and cause the generation AI to adjust the level of detail of the proposal.

[0131] The conversation documentation system includes a confirmation item suggestion unit that estimates a user's emotions and changes the display method of confirmation items based on the estimated user emotions. The confirmation item suggestion unit estimates the user's emotions using AI and adjusts the display method of confirmation items. For example, if the user is nervous, the confirmation item suggestion unit highlights important confirmation items. Also, if the user is relaxed, the confirmation item suggestion unit can display confirmation items in a normal display method. Also, if the user is excited, the confirmation item suggestion unit can highlight urgent confirmation items. In this way, by adjusting the display method of confirmation items according to the user's emotions, important confirmation items can be highlighted. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the confirmation item suggestion unit may be performed using AI or without AI. For example, the confirmation item suggestion unit may input user emotion data into the generation AI and cause the generation AI to adjust the display method of the confirmation items.

[0132] The conversation documentation system includes a confirmation item suggestion unit that has a function of automatically setting a reminder based on the content of the conversation when a confirmation item is suggested. The confirmation item suggestion unit automatically sets a reminder based on the content of the conversation when a confirmation item is suggested using AI. For example, the confirmation item suggestion unit automatically sets a reminder for important confirmation items based on the content of a business negotiation. The confirmation item suggestion unit can also automatically set a reminder for confirmation items with deadlines based on instructions from a supervisor. The confirmation item suggestion unit can also automatically set a reminder for important confirmation items based on a conversation with a customer. In this way, by setting a reminder based on the content of the conversation, important confirmation items can be managed without forgetting them. Some or all of the above-mentioned processing in the confirmation item suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the confirmation item suggestion unit can input the acquired conversation data into a generation AI and have the generation AI set a reminder.

[0133] The conversation documentation system includes a confirmation item suggestion unit that has a function of automatically tracking the progress of a confirmation item when the confirmation item is proposed. The confirmation item suggestion unit automatically tracks the progress of the confirmation item when the confirmation item is proposed using AI. For example, the confirmation item suggestion unit automatically tracks the progress of the confirmation item based on the content of a business negotiation. The confirmation item suggestion unit can also automatically track the progress of the confirmation item based on instructions from a supervisor. The confirmation item suggestion unit can also automatically track the progress of the confirmation item based on a conversation with a customer. This allows the progress of the confirmation item to be efficiently managed by automatically tracking the progress of the confirmation item. Some or all of the above-described processing in the confirmation item suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the confirmation item suggestion unit may input the acquired conversation data into a generation AI and cause the generation AI to track the progress of the confirmation item.

[0134] The conversation documentation system includes a confirmation item suggestion unit that, when proposing confirmation items, reflects the user's past feedback to improve the accuracy of the confirmation item suggestions. The confirmation item suggestion unit uses AI to reflect the user's past feedback when proposing confirmation items to improve the accuracy of the confirmation item suggestions. For example, the confirmation item suggestion unit refers to the user's past feedback to improve the accuracy of the confirmation item suggestions. The confirmation item suggestion unit can also reflect past feedback based on the content of a business negotiation to improve the accuracy of the confirmation item suggestions. The confirmation item suggestion unit can also reflect past feedback to improve the accuracy of the confirmation item suggestions based on instructions from a superior. In this way, the accuracy of the confirmation item suggestions can be improved by reflecting the user's past feedback. Some or all of the above-described processing in the confirmation item suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the confirmation item suggestion unit can input the user's past feedback into the generation AI and cause the generation AI to improve the accuracy of the confirmation item suggestions. === Hard Collateral 1-1 === Each of the multiple elements, including the voice input unit, transcription unit, task extraction unit, transmission unit, and confirmation item suggestion unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the voice input unit captures telephone conversation content in real time using the microphone 38B of the smart device 14 and inputs it to the specific processing unit 290 of the data processing device 12. The transcription unit, realized by the specific processing unit 290 of the data processing device 12, analyzes the input voice data and transcribes it. The task extraction unit, realized by the specific processing unit 290 of the data processing device 12, extracts tasks from the transcription results and creates a task list. The transmission unit sends the generated task list by email using the communication I / F 44 of the smart device 14. The confirmation item suggestion unit, realized by the specific processing unit 290 of the data processing device 12, suggests confirmation items based on a general business framework. === Hard Collateral 1-2 === Each of the multiple elements, including the voice input unit, transcription unit, task extraction unit, transmission unit, and confirmation item suggestion unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the voice input unit captures telephone conversation content in real time using the microphone 238 of the smart glasses 214 and inputs it to the specific processing unit 290 of the data processing device 12. The transcription unit, realized by the specific processing unit 290 of the data processing device 12, analyzes the input voice data and transcribes it. The task extraction unit, realized by the specific processing unit 290 of the data processing device 12, extracts tasks from the transcription results and creates a task list. The transmission unit sends the generated task list by email using the communication I / F 44 of the smart glasses 214. The confirmation item suggestion unit, realized by the specific processing unit 290 of the data processing device 12, suggests confirmation items based on a general business framework. === Hard Collateral 1-3 === Each of the multiple elements, including the voice input unit, transcription unit, task extraction unit, transmission unit, and confirmation item suggestion unit, is realized, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the voice input unit captures telephone conversation content in real time using the microphone 238 of the headset terminal 314 and inputs it to the specific processing unit 290 of the data processing device 12. The transcription unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the input voice data to transcribe it. The task extraction unit is realized by the specific processing unit 290 of the data processing device 12 and extracts tasks from the transcription results and creates a task list. The transmission unit sends the generated task list by email using the communication I / F 44 of the headset terminal 314. The confirmation item suggestion unit is realized by the specific processing unit 290 of the data processing device 12 and suggests confirmation items based on a general business framework. === Hard Collateral 1-4 === Each of the multiple elements, including the voice input unit, transcription unit, task extraction unit, transmission unit, and confirmation item suggestion unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the voice input unit captures telephone conversation content in real time using the microphone 238 of the robot 414 and inputs it to the specific processing unit 290 of the data processing device 12. The transcription unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the input voice data to transcribe it. The task extraction unit is realized by the specific processing unit 290 of the data processing device 12 and extracts tasks from the transcription results and creates a task list. The transmission unit sends the generated task list by email using the communication I / F 44 of the robot 414. The confirmation item suggestion unit is realized by the specific processing unit 290 of the data processing device 12 and suggests confirmation items based on a general business framework.

[0135] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0136] The conversation documentation system includes a voice input unit that estimates a user's emotion and automatically adjusts the sensitivity of the voice input based on the estimated emotion. The voice input unit estimates the user's emotion using AI and adjusts the sensitivity of the voice input. For example, if the user is nervous, the voice input unit increases the sensitivity of the voice input to capture voice more clearly. If the user is relaxed, the voice input unit can set the sensitivity of the voice input to normal to capture natural conversation. If the user is excited, the voice input unit can adjust the sensitivity of the voice input to capture voice while removing excessive noise. Adjusting the sensitivity of the voice input according to the user's emotion enables clearer voice capture. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the voice input unit may be performed using, for example, AI, or without AI. For example, the voice input unit can input the user's voice data into the generation AI and have the generation AI estimate emotions.

[0137] The conversation documentation system includes an audio input unit with a filtering function that automatically removes background noise during audio input. The audio input unit uses AI to automatically remove background noise during audio input. For example, the audio input unit automatically removes air conditioner noise and external noise during a conference call in a conference room. The audio input unit can also filter out and remove background voices and music during a phone conversation in a public place such as a cafe. The audio input unit can also automatically remove engine noise and road noise during a phone conversation in a car. This removes background noise, allowing clear audio data to be obtained. Some or all of the above-described processing in the audio input unit may be performed using AI, for example, or without AI. For example, the audio input unit can input the acquired audio data to a generation AI and have the generation AI remove background noise.

[0138] The conversation documentation system includes a voice input unit that analyzes the characteristics of a speaker's voice during voice input and creates a different voice profile for each speaker. The voice input unit uses AI to analyze the characteristics of a speaker's voice during voice input and create a different voice profile for each speaker. For example, the voice input unit analyzes the characteristics of each speaker's voice during a conference with multiple speakers and creates an individual voice profile. The voice input unit can also create profiles that distinguish between the voice of the boss and the voice of the subordinate during a conversation between a boss and a subordinate. The voice input unit can also analyze the characteristics of the customer's voice during a phone call with a customer and automatically recognize it the next time the conversation occurs. This allows the voices of multiple speakers to be captured separately by creating a different voice profile for each speaker. Some or all of the above-described processing in the voice input unit may be performed using AI, for example, or without AI. For example, the voice input unit can input acquired voice data to a generation AI and have the generation AI analyze the characteristics of the speaker's voice.

[0139] The conversation documentation system includes a voice input unit that analyzes the context of a conversation during voice input and captures it with emphasis on important parts. The voice input unit uses AI to analyze the context of a conversation during voice input and captures it with emphasis on important parts. For example, the voice input unit captures important information such as price and delivery date during a business negotiation with emphasis. The voice input unit can also capture task priorities and deadlines with emphasis at the direction of a supervisor. The voice input unit can also capture important parts of a conversation with a customer with emphasis on requests and complaints. By capturing and emphasizing important parts of the conversation, important information can be recorded without missing anything. Some or all of the above-described processing in the voice input unit may be performed using, for example, AI, or may be performed without using AI. For example, the voice input unit can input acquired voice data to a generation AI and have the generation AI analyze the context of the conversation.

[0140] The conversation documentation system includes a speech input unit that estimates a user's emotion and adjusts the timing of the start of speech input based on the estimated emotion. The speech input unit estimates the user's emotion using AI and adjusts the timing of the start of speech input. For example, if the user is nervous, the speech input unit delays the start of speech input until the user relaxes. Alternatively, if the user is relaxed, the speech input unit can immediately start speech input. Alternatively, if the user is excited, the speech input unit can delay the start of speech input until the user calms down. This allows speech to be captured at an appropriate timing by adjusting the start of speech input according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the speech input unit may be performed using AI, for example, or without AI. For example, the speech input unit may input the user's speech data to the generation AI and have the generation AI perform emotion estimation.

[0141] The conversation documentation system includes a voice input unit that selects voice input settings based on the user's geographic location information when the user inputs voice. The voice input unit uses AI to select optimal voice input settings by taking the user's geographic location information into consideration when the user inputs voice. For example, the voice input unit uses normal voice input settings when the user is in a quiet office. The voice input unit can also use voice input settings with enhanced noise cancellation when the user is in a noisy cafe. The voice input unit can also use voice input settings that remove engine noise when the user is in a moving car. This enables voice capture tailored to the environment by selecting optimal voice input settings based on the user's geographic location information. Some or all of the above-described processing in the voice input unit may be performed using AI, for example, or without AI. For example, the voice input unit can input the user's geographic location information to a generation AI and have the generation AI select optimal voice input settings.

[0142] The conversation documentation system includes a speech input unit that, when inputting speech, refers to a user's past conversation history to improve the accuracy of the speech input. The speech input unit uses AI to refer to the user's past conversation history to improve the accuracy of the speech input. For example, the speech input unit learns technical terms and phrases used by the user in the past to improve the accuracy of the speech input. The speech input unit can also learn the vocal characteristics of specific speakers from the user's past conversation history to improve the accuracy of the speech input. The speech input unit can also improve the accuracy of the speech input by referring to the context of the user's past conversations. In this way, the accuracy of the speech input can be improved by referring to the user's past conversation history. Some or all of the above-described processing in the speech input unit may be performed using AI, for example, or may be performed without using AI. For example, the speech input unit can input the user's past conversation history to a generation AI and have the generation AI improve the accuracy of the speech input.

[0143] The conversation documentation system includes a voice input unit that analyzes a user's social media activity and prioritizes capturing relevant conversation content when a user inputs voice. The voice input unit uses AI to analyze the user's social media activity and prioritizes capturing relevant conversation content when a user inputs voice. For example, the voice input unit prioritizes capturing topics that the user frequently mentions on social media. The voice input unit can also analyze the user's social media posts and prioritize capturing relevant conversation content. The voice input unit can also prioritize capturing relevant conversation content by referring to the activities of the user's friends on social media. In this way, by analyzing the user's social media activity, relevant conversation content can be prioritized. Some or all of the above-described processing in the voice input unit may be performed using AI, for example, or may be performed without using AI. For example, the voice input unit can input the user's social media activity data to a generation AI and cause the generation AI to prioritize capturing relevant conversation content.

[0144] The conversation documentation system includes a transcription unit that estimates a user's emotions and changes the transcription expression style based on the estimated user emotions. The transcription unit estimates the user's emotions using AI and adjusts the transcription expression style. For example, if the user is nervous, the transcription unit uses a concise and clear expression style. Also, if the user is relaxed, the transcription unit can use a detailed expression style. Also, if the user is excited, the transcription unit can use an expression style that reflects the user's emotions. This allows the transcription to be performed using an appropriate expression style by adjusting the transcription expression style according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the transcription unit may be performed using AI, or without AI. For example, the transcription unit can input the user's voice data into the generation AI and have the generation AI perform emotion estimation.

[0145] The conversation documentation system includes a transcription unit that automatically recognizes and appropriately converts technical terms and industry jargon during transcription. The transcription unit uses AI to automatically recognize and appropriately convert technical terms and industry jargon during transcription. For example, the transcription unit automatically recognizes and appropriately converts technical terms in IT industry conversations. The transcription unit can also automatically recognize and appropriately convert technical terms in medical industry conversations. The transcription unit can also automatically recognize and appropriately convert technical terms in legal industry conversations. This allows for accurate transcription by appropriately converting technical terms and industry jargon. Some or all of the above-described processing in the transcription unit may be performed using AI, for example, or without AI. For example, the transcription unit can input acquired audio data into a generation AI and have the generation AI recognize and convert technical terms and industry jargon.

[0146] The conversation documentation system includes a transcription unit that has the function of transcribing in different formats for each speaker. The transcription unit uses AI to transcribe in different formats for each speaker. For example, when there are multiple speakers in a meeting, the transcription unit transcribes in a different format for each speaker. The transcription unit can also distinguish between the superior's and subordinate's comments in a conversation between a superior and a subordinate. The transcription unit can also distinguish between the customer's and the company's comments in a phone call with a customer. This allows the speech of multiple speakers to be recorded separately by transcribing in different formats for each speaker. Some or all of the above-described processing in the transcription unit may be performed using AI, for example, or without AI. For example, the transcription unit can input acquired audio data into a generation AI and have the generation AI transcribe in a format for each speaker.

[0147] The conversation documentation system includes a transcription unit that understands the context of a conversation and emphasizes important parts when transcribing. The transcription unit uses AI to understand the context of a conversation and emphasize important parts when transcribing. For example, during a business negotiation, the transcription unit may emphasize important information such as price and delivery date. The transcription unit may also emphasize task priorities and deadlines at the direction of a supervisor. The transcription unit may also emphasize important parts of a conversation with a customer, such as requests and complaints. This allows important information to be recorded without missing any important information by emphasizing the important parts of the conversation. Some or all of the above-described processing in the transcription unit may be performed using AI, for example, or without AI. For example, the transcription unit may input acquired audio data into a generation AI, which may then understand the context of the conversation and emphasize important parts.

[0148] The conversation documentation system includes a transcription unit that estimates a user's emotions and adjusts the length of the transcription based on the estimated user emotions. The transcription unit estimates the user's emotions using AI and adjusts the length of the transcription. For example, if the user is in a hurry, the transcription unit may provide a short transcription that focuses on the main points. If the user is relaxed, the transcription unit may also provide a detailed transcription. If the user is excited, the transcription unit may also provide a longer transcription that reflects the user's emotions. By adjusting the length of the transcription according to the user's emotions, the transcription can be performed at an appropriate length. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the transcription unit may be performed using, for example, AI, or without AI. For example, the transcription unit can input the user's voice data into the generation AI and have the generation AI estimate emotions.

[0149] The conversation documentation system includes a transcription unit that automatically records the start and end times of a conversation when transcribing. The transcription unit uses AI to automatically record the start and end times of a conversation when transcribing. For example, the transcription unit automatically records the start and end times of a meeting and reflects them in the transcription. The transcription unit can also automatically record the start and end times of a phone call and reflect them in the transcription. The transcription unit can also automatically record the start and end times of a business meeting and reflect them in the transcription. In this way, by automatically recording the start and end times of a conversation, accurate timestamps can be added to the transcription. Some or all of the above-described processing in the transcription unit may be performed using AI, or may be performed without AI. For example, the transcription unit can input acquired audio data into a generation AI and have the generation AI record the start and end times of the conversation.

[0150] The conversation documentation system includes a transcription unit that automatically tags data based on the content of the conversation during transcription. The transcription unit uses AI to automatically tag data based on the content of the conversation during transcription. For example, the transcription unit automatically tags data based on the price, delivery date, and conditions of a business meeting. The transcription unit can also automatically tag data based on instructions from a supervisor, such as tasks, deadlines, and priorities. The transcription unit can also automatically tag data based on requests, complaints, and feedback based on conversations with customers. This automatic tagging based on the content of the conversation facilitates future searches. Some or all of the above-described processing in the transcription unit may be performed using AI, or may be performed without AI. For example, the transcription unit can input acquired audio data into a generation AI and have the generation AI perform tagging.

[0151] The conversation documentation system includes a transcription unit that improves transcription accuracy by referencing the user's past transcription results during transcription. The transcription unit improves transcription accuracy by using AI to refer to the user's past transcription results during transcription. For example, the transcription unit learns technical terms and phrases used by the user in the past to improve transcription accuracy. The transcription unit can also improve transcription accuracy by learning the vocal characteristics of specific speakers from the user's past transcription results. The transcription unit can also improve transcription accuracy by referencing the context of the user's past conversations. In this way, transcription accuracy can be improved by referring to the user's past transcription results. Some or all of the above-described processing in the transcription unit may be performed using AI, for example, or without AI. For example, the transcription unit can input the user's past transcription results into a generation AI and have the generation AI improve transcription accuracy.

[0152] The conversation documentation system includes a task extraction unit that estimates a user's emotions and prioritizes tasks based on the estimated user emotions. The task extraction unit estimates the user's emotions using AI and determines the priority of tasks. For example, if the user is nervous, the task extraction unit may prioritize important tasks. If the user is relaxed, the task extraction unit may also prioritize tasks with normal priority. If the user is excited, the task extraction unit may also prioritize urgent tasks. This allows important tasks to be prioritized by determining the priority of tasks based on 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 may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the task extraction unit may be performed using AI, or may be performed without AI. For example, the task extraction unit may input user emotion data into the generation AI and have the generation AI determine the priority of tasks.

[0153] The conversation documentation system includes a task extraction unit that has a function of understanding the context of a conversation and automatically grouping related tasks when extracting tasks. The task extraction unit uses AI to understand the context of a conversation when extracting tasks and automatically group related tasks. For example, the task extraction unit automatically groups related tasks based on the content of a business negotiation. The task extraction unit can also automatically group related tasks based on instructions from a supervisor. The task extraction unit can also automatically group related tasks based on a conversation with a customer. This understanding of the context of a conversation and grouping related tasks improves task management efficiency. Some or all of the above-described processing in the task extraction unit may be performed using AI, for example, or may be performed without using AI. For example, the task extraction unit can input acquired conversation data to a generation AI and have the generation AI group related tasks.

[0154] The conversation documentation system includes a task extraction unit that has a function of automatically setting a task deadline and a person in charge when extracting a task. The task extraction unit automatically sets the task deadline and a person in charge when extracting a task using AI. For example, the task extraction unit automatically sets the task deadline based on the content of a business negotiation. The task extraction unit can also automatically set a task person in charge based on instructions from a supervisor. The task extraction unit can also automatically set the task deadline and a person in charge based on a conversation with a customer. This automatically setting the task deadline and a person in charge improves task management efficiency. Some or all of the above-mentioned processing in the task extraction unit may be performed using AI, for example, or may be performed without using AI. For example, the task extraction unit can input the acquired conversation data into a generation AI and have the generation AI set the task deadline and a person in charge.

[0155] The conversation documentation system includes a task extraction unit that has a function of automatically suggesting similar tasks by referring to past task history when extracting a task. The task extraction unit uses AI to automatically suggest similar tasks by referring to past task history when extracting a task. For example, the task extraction unit refers to the user's past task history and automatically suggests similar tasks. The task extraction unit can also suggest similar past tasks based on the content of business negotiations. The task extraction unit can also suggest similar past tasks based on instructions from a superior. This allows similar tasks to be efficiently suggested by referring to past task history. Some or all of the above-mentioned processing in the task extraction unit may be performed using AI, for example, or may be performed without using AI. For example, the task extraction unit can input the user's past task history into a generation AI and have the generation AI suggest similar tasks.

[0156] The conversation documentation system includes a task extraction unit that estimates a user's emotions and changes the display method of tasks based on the estimated user emotions. The task extraction unit estimates the user's emotions using AI and adjusts the display method of tasks. For example, if the user is nervous, the task extraction unit highlights important tasks. Furthermore, if the user is relaxed, the task extraction unit can also display tasks in a normal display method. Furthermore, if the user is excited, the task extraction unit can highlight urgent tasks. Thus, by adjusting the display method of tasks according to the user's emotions, important tasks can be highlighted. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the task extraction unit may be performed using AI, or without AI. For example, the task extraction unit can input user emotion data into the generation AI and cause the generation AI to adjust the display method of tasks.

[0157] The conversation documentation system includes a task extraction unit that has a function of automatically setting reminders based on the content of the conversation when extracting a task. The task extraction unit uses AI to automatically set reminders based on the content of the conversation when extracting a task. For example, the task extraction unit automatically sets reminders for important tasks based on the content of a business negotiation. The task extraction unit can also automatically set reminders for tasks with deadlines based on instructions from a supervisor. The task extraction unit can also automatically set reminders for important tasks based on a conversation with a customer. By setting reminders based on the content of the conversation, important tasks can be managed without forgetting them. Some or all of the above-mentioned processing in the task extraction unit may be performed using AI, for example, or may be performed without using AI. For example, the task extraction unit can input the acquired conversation data into a generation AI and have the generation AI set reminders.

[0158] The conversation documentation system includes a task extraction unit that has a function of automatically tracking the progress of a task when the task is extracted. The task extraction unit automatically tracks the progress of the task when the task is extracted using AI. For example, the task extraction unit automatically tracks the progress of the task based on the content of a business negotiation. The task extraction unit can also automatically track the progress of the task based on instructions from a supervisor. The task extraction unit can also automatically track the progress of the task based on a conversation with a customer. This allows the task progress to be efficiently managed by automatically tracking the progress of the task. Some or all of the above-described processing in the task extraction unit may be performed using AI, for example, or may be performed without using AI. For example, the task extraction unit may input the acquired conversation data to a generation AI and cause the generation AI to track the progress of the task.

[0159] The conversation documentation system includes a task extraction unit that reflects a user's past feedback during task extraction to improve the accuracy of task extraction. The task extraction unit uses AI to reflect a user's past feedback during task extraction to improve the accuracy of task extraction. For example, the task extraction unit refers to a user's past feedback to improve the accuracy of task extraction. The task extraction unit can also reflect past feedback based on the content of a business negotiation to improve the accuracy of task extraction. The task extraction unit can also reflect past feedback based on instructions from a superior to improve the accuracy of task extraction. In this way, the accuracy of task extraction can be improved by reflecting the user's past feedback. Some or all of the above-described processing in the task extraction unit may be performed using AI, for example, or may be performed without using AI. For example, the task extraction unit can input a user's past feedback into a generation AI and cause the generation AI to improve the accuracy of task extraction.

[0160] The conversation documentation system includes a sending unit that estimates a user's emotion and changes the format of a document to be sent based on the estimated user's emotion. The sending unit estimates the user's emotion using AI and adjusts the format of the document to be sent. For example, if the user is nervous, the sending unit uses a concise and clear format. If the user is relaxed, the sending unit can use a detailed format. If the user is excited, the sending unit can use a visually stimulating format. This allows the document to be sent in an appropriate format by adjusting the document format according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the sending unit may be performed using AI, for example, or without AI. For example, the sending unit may input user's emotion data into the generation AI and have the generation AI adjust the document format.

[0161] The conversation documentation system includes a sending unit that has a function of automatically completing the recipient's email address when sending. The sending unit automatically completes the recipient's email address when sending using AI. For example, the sending unit automatically completes email addresses to which the user has sent in the past. The sending unit can also automatically complete the recipient's email address from the user's contact list. The sending unit can also automatically complete the complete email address from a partial email address entered by the user. This automatically completes the recipient's email address, thereby preventing sending errors. Some or all of the above-described processing in the sending unit may be performed using AI, for example, or may be performed without using AI. For example, the sending unit can input the user's contact list into a generation AI and have the generation AI complete the email address.

[0162] The conversation documentation system includes a sending unit that has a function of automatically setting a subject based on the content of a document when it is sent. The sending unit uses AI to automatically set a subject based on the content of a document when it is sent. For example, the sending unit automatically sets an appropriate subject based on the content of a business negotiation. The sending unit can also automatically set an appropriate subject based on instructions from a supervisor. The sending unit can also automatically set an appropriate subject based on a conversation with a customer. In this way, by automatically setting a subject based on the content of the document, it is possible to send a document with an appropriate subject. Some or all of the above-described processing in the sending unit may be performed using AI, for example, or may be performed without using AI. For example, the sending unit can input the content of the document into a generation AI and have the generation AI set the subject.

[0163] The conversation documentation system includes a transmission unit that has a function of automatically recording a transmission history at the time of transmission so that it can be referenced later. The transmission unit uses AI to automatically record the transmission history at the time of transmission so that it can be referenced later. For example, the transmission unit automatically records the history of sent documents so that it can be referenced later. The transmission unit can also automatically record the history of sent emails so that it can be referenced later. The transmission unit can also automatically record the history of sent task lists so that it can be referenced later. In this way, by automatically recording the transmission history, the transmitted content can be confirmed later. Some or all of the above-described processing in the transmission unit may be performed using AI, for example, or may be performed without using AI. For example, the transmission unit can input the transmission history to a generation AI and have the generation AI record the history.

[0164] The conversation documentation system includes a transmission unit that estimates a user's emotion and adjusts the timing of transmission based on the estimated user emotion. The transmission unit estimates the user's emotion using AI and adjusts the timing of transmission. For example, if the user is nervous, the transmission unit delays transmission until the user relaxes. Alternatively, if the user is relaxed, the transmission unit can immediately transmit the document. Alternatively, if the user is excited, the transmission unit can adjust the transmission until the user calms down. This allows documents to be sent at an appropriate time by adjusting the transmission timing according to the user's emotion. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the transmission unit may be performed using AI, or may be performed without AI. For example, the transmission unit may input the user's emotion data into the generation AI and have the generation AI adjust the transmission timing.

[0165] The conversation documentation system includes a sending unit that has a function of tracking the reception status of the recipient in real time at the time of transmission. The sending unit uses AI to track the reception status of the recipient in real time at the time of transmission. For example, the sending unit tracks in real time whether a sent email has been received. The sending unit can also track in real time whether a sent document has been opened. The sending unit can also track in real time whether a sent task list has been checked. In this way, by tracking the reception status of the recipient in real time, it is possible to confirm whether the transmitted content has been reliably received. Some or all of the above-described processing in the sending unit may be performed using AI, for example, or may be performed without using AI. For example, the sending unit can input reception status data of the recipient into a generation AI and have the generation AI track the reception status.

[0166] The conversation documentation system includes a transmission unit that has a function of automatically adding attachments based on the content of a document when the document is sent. The transmission unit uses AI to automatically add attachments based on the content of the document when the document is sent. For example, the transmission unit automatically attaches related materials based on the content of a business negotiation. The transmission unit can also automatically attach related files based on instructions from a supervisor. The transmission unit can also automatically attach related documents based on a conversation with a customer. This allows related materials to be sent reliably by automatically adding attachments based on the content of the document. Some or all of the above-described processing in the transmission unit may be performed using AI, for example, or may be performed without using AI. For example, the transmission unit can input the content of the document into a generation AI and have the generation AI add attachments.

[0167] The conversation documentation system includes a transmission unit that has a function of referencing a user's past transmission history to customize the content of a message when sending the message. The transmission unit uses AI to refer to the user's past transmission history when sending the message and customize the content. For example, the transmission unit refers to the user's past transmission history to customize the content of a message. The transmission unit can also customize the content of a message by reflecting the past transmission history based on the content of a business negotiation. The transmission unit can also customize the content of a message by reflecting the past transmission history based on instructions from a superior. This allows the content of a message to be customized and sent with appropriate content by referring to the user's past transmission history. Some or all of the above-described processing in the transmission unit may be performed using AI, for example, or may be performed without using AI. For example, the transmission unit can input the user's past transmission history into a generation AI and have the generation AI customize the content of a message.

[0168] The conversation documentation system includes a check item suggestion unit that estimates a user's emotions and prioritizes check items based on the estimated user emotions. The check item suggestion unit estimates the user's emotions using AI and determines the priority of the check items. For example, if the user is nervous, the check item suggestion unit may prioritize important check items. If the user is relaxed, the check item suggestion unit may also prioritize check items based on normal priority. If the user is excited, the check item suggestion unit may also prioritize urgent check items. This allows the priority of check items to be determined based on the user's emotions, thereby prioritizing important check items. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the check item suggestion unit may be performed using AI or without AI. For example, the check item suggestion unit may input user emotion data into the generation AI and have the generation AI determine the priority of the check items.

[0169] The conversation documentation system includes a confirmation item suggestion unit that has a function of understanding the context of the conversation and automatically grouping related confirmation items when proposing confirmation items. The confirmation item suggestion unit uses AI to understand the context of the conversation when proposing confirmation items and automatically group related confirmation items. For example, the confirmation item suggestion unit automatically groups related confirmation items based on the content of a business negotiation. The confirmation item suggestion unit can also automatically group related confirmation items based on instructions from a supervisor. The confirmation item suggestion unit can also automatically group related confirmation items based on a conversation with a customer. This understanding of the conversation context and grouping related confirmation items improves the efficiency of confirmation item management. Some or all of the above-described processing in the confirmation item suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the confirmation item suggestion unit can input acquired conversation data to a generation AI and have the generation AI group related confirmation items.

[0170] The conversation documentation system includes a check item suggestion unit that has a function of automatically suggesting similar check items by referring to past conversation history when proposing check items. The check item suggestion unit uses AI to automatically suggest similar check items by referring to past conversation history when proposing check items. For example, the check item suggestion unit refers to the user's past conversation history and automatically suggests similar check items. The check item suggestion unit can also suggest similar past check items based on the content of business negotiations. The check item suggestion unit can also suggest similar past check items based on instructions from a supervisor. This allows similar check items to be efficiently suggested by referring to past conversation history. Some or all of the above-mentioned processing in the check item suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the check item suggestion unit can input the user's past conversation history into a generation AI and have the generation AI suggest similar check items.

[0171] The conversation documentation system includes a confirmation item suggestion unit that has a function of adjusting the level of detail of the proposal based on the importance of the confirmation item when proposing the confirmation item. The confirmation item suggestion unit adjusts the level of detail of the proposal based on the importance of the confirmation item using AI when proposing the confirmation item. For example, the confirmation item suggestion unit makes detailed suggestions for important confirmation items. The confirmation item suggestion unit can also make standard suggestions for ordinary confirmation items. The confirmation item suggestion unit can also make concise suggestions for urgent confirmation items. In this way, by adjusting the level of detail of the proposal based on the importance of the confirmation item, it is possible to propose confirmation items with an appropriate level of detail. Some or all of the above-described processing in the confirmation item suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the confirmation item suggestion unit can input the acquired conversation data to a generation AI and cause the generation AI to adjust the level of detail of the proposal.

[0172] The conversation documentation system includes a confirmation item suggestion unit that estimates a user's emotions and changes the display method of confirmation items based on the estimated user emotions. The confirmation item suggestion unit estimates the user's emotions using AI and adjusts the display method of confirmation items. For example, if the user is nervous, the confirmation item suggestion unit highlights important confirmation items. Also, if the user is relaxed, the confirmation item suggestion unit can display confirmation items in a normal display method. Also, if the user is excited, the confirmation item suggestion unit can highlight urgent confirmation items. In this way, by adjusting the display method of confirmation items according to the user's emotions, important confirmation items can be highlighted. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the confirmation item suggestion unit may be performed using AI or without AI. For example, the confirmation item suggestion unit may input user emotion data into the generation AI and cause the generation AI to adjust the display method of the confirmation items.

[0173] The conversation documentation system includes a confirmation item suggestion unit that has a function of automatically setting a reminder based on the content of the conversation when a confirmation item is suggested. The confirmation item suggestion unit automatically sets a reminder based on the content of the conversation when a confirmation item is suggested using AI. For example, the confirmation item suggestion unit automatically sets a reminder for important confirmation items based on the content of a business negotiation. The confirmation item suggestion unit can also automatically set a reminder for confirmation items with deadlines based on instructions from a supervisor. The confirmation item suggestion unit can also automatically set a reminder for important confirmation items based on a conversation with a customer. In this way, by setting a reminder based on the content of the conversation, important confirmation items can be managed without forgetting them. Some or all of the above-mentioned processing in the confirmation item suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the confirmation item suggestion unit can input the acquired conversation data into a generation AI and have the generation AI set a reminder.

[0174] The conversation documentation system includes a confirmation item suggestion unit that has a function of automatically tracking the progress of a confirmation item when the confirmation item is proposed. The confirmation item suggestion unit automatically tracks the progress of the confirmation item when the confirmation item is proposed using AI. For example, the confirmation item suggestion unit automatically tracks the progress of the confirmation item based on the content of a business negotiation. The confirmation item suggestion unit can also automatically track the progress of the confirmation item based on instructions from a supervisor. The confirmation item suggestion unit can also automatically track the progress of the confirmation item based on a conversation with a customer. This allows the progress of the confirmation item to be efficiently managed by automatically tracking the progress of the confirmation item. Some or all of the above-described processing in the confirmation item suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the confirmation item suggestion unit may input the acquired conversation data into a generation AI and cause the generation AI to track the progress of the confirmation item.

[0175] The conversation documentation system includes a confirmation item suggestion unit that, when proposing confirmation items, reflects the user's past feedback to improve the accuracy of the confirmation item suggestions. The confirmation item suggestion unit uses AI to reflect the user's past feedback when proposing confirmation items to improve the accuracy of the confirmation item suggestions. For example, the confirmation item suggestion unit refers to the user's past feedback to improve the accuracy of the confirmation item suggestions. The confirmation item suggestion unit can also reflect past feedback based on the content of a business negotiation to improve the accuracy of the confirmation item suggestions. The confirmation item suggestion unit can also reflect past feedback to improve the accuracy of the confirmation item suggestions based on instructions from a superior. In this way, the accuracy of the confirmation item suggestions can be improved by reflecting the user's past feedback. Some or all of the above-described processing in the confirmation item suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the confirmation item suggestion unit can input the user's past feedback into the generation AI and cause the generation AI to improve the accuracy of the confirmation item suggestions.

[0176] The processing flow of the second embodiment will be briefly explained below.

[0177] Step 1: The voice input unit captures the content of the phone conversation in real time and inputs it into the transcription unit. For example, the voice input unit can capture the content of the conversation using a high-precision microphone and convert it into digital data in real time. It can also use noise-canceling technology to remove background noise and provide clear voice data. It can also use AI to estimate the user's emotions and adjust the sensitivity of the voice input. Step 2: The transcription section uses AI to analyze the input audio data and transcribe it. For example, it can use speech recognition technology to convert the audio data into text data, automatically recognizing technical terms and industry jargon and converting them appropriately. It can also understand the context of the conversation and emphasize important parts when transcribing. Step 3: The task extraction unit uses AI to extract tasks from the transcription results and create a task list. For example, it can extract next action items and deadlines from the content of a business meeting and compile them into a task list. It can also understand the context of the conversation and automatically group related tasks. It can also estimate the user's emotions and determine task priorities. Step 4: The sending unit generates the task list created by the task extraction unit as a document and sends it by email. For example, it can document the generated task list in PDF format and send it to a specified email address. It can also automatically complete the recipient's email address. It can also estimate the user's emotions and adjust the format of the document to be sent. Step 5: The confirmation suggestion section uses AI to suggest confirmation items based on a general business framework based on the transcription results. For example, it suggests points to be confirmed or additional questions to ask based on the content of the business negotiation. It can also estimate the user's emotions and determine the priority of confirmation items.

[0178] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0179] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0180] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0181] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0182] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0183] 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.

[0184] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0185] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0186] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0187] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0188] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0189] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0190] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0191] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0192] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0193] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0194] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0195] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0196] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0197] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0198] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0199] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0200] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0201] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0202] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0203] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0204] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0205] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0206] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0207] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0208] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0209] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0210] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0211] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0212] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0213] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0214] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0215] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0216] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0217] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0218] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0219] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0220] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0221] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0222] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0223] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0224] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0225] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0226] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0227] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0228] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0229] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0230] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0231] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0232] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0233] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0234] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0235] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0236] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0237] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0238] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0239] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0240] 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.

[0241] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0242] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0243] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0244] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0245] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0246] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0247] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0248] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0249] [Explanation of symbols]

[0250] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A voice input unit that captures the contents of telephone conversations in real time; a transcription unit that analyzes the voice data captured by the voice input unit and transcribes it; a task extraction unit that extracts tasks from the transcription results generated by the transcription unit and creates a task table; a sending unit that generates the task table created by the task extraction unit as a document and sends it by email; a confirmation item suggestion unit that suggests confirmation items from a general business framework based on the transcription result generated by the transcription unit; Equipped with A system characterized by:

2. The voice input unit Estimate the user's emotions and automatically change the sensitivity of the voice input based on the estimated user emotions.

2. The system of claim 1.

3. The voice input unit Equipped with a filtering function that automatically removes background noise when inputting voice 2. The system of claim 1.

4. The voice input unit When you input voice, the speaker's voice characteristics are analyzed and a different voice profile is created for each speaker.

2. The system of claim 1.

5. The voice input unit When you input voice, it analyzes the context of the conversation and captures it by emphasizing the important parts.

2. The system of claim 1.

6. The voice input unit The system estimates the user's emotions and adjusts the timing of voice input based on the estimated user emotions.

2. The system of claim 1.

7. The voice input unit When using voice input, select voice input settings based on the user's geographic location.

2. The system of claim 1.

8. The voice input unit When inputting voice data, the accuracy of voice input is improved by referring to the user's past conversation history.

2. The system of claim 1.

Images