system

Abstract

The system according to the embodiment aims to automate responses to emails and chats sent to individuals. [Solution] A system according to an embodiment includes a reading unit, an analysis unit, a summary generation unit, a selection unit, a reply generation unit, and a sending unit. The reading unit reads a message. The analysis unit analyzes the content of the message read by the reading unit and determines the emotion and warmth. The summary generation unit generates a summary based on the content analyzed by the analysis unit. The selection unit selects a reply pattern based on the summary generated by the summary generation unit. The reply generation unit generates a reply message based on the pattern selected by the selection unit. The sending unit automatically sends the reply message generated by the reply generation 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] Conventional technologies do not adequately automate responses to emails and chats sent to individuals, and there is room for improvement.

[0005] The system according to the embodiment aims to automate responses to emails and chats sent to individuals. [Means for solving the problem]

[0006] The system according to the embodiment includes a reading unit, an analysis unit, a summary generation unit, a selection unit, a reply generation unit, and a sending unit. The reading unit reads a message. The analysis unit analyzes the content of the message read by the reading unit and determines the emotion and warmth of the message. The summary generation unit generates a summary based on the content analyzed by the analysis unit. The selection unit selects a reply pattern based on the summary generated by the summary generation unit. The reply generation unit generates a reply message based on the pattern selected by the selection unit. The sending unit automatically sends the reply message generated by the reply generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can automate responses to emails and chats sent to individuals. [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 communication response automation system according to an embodiment of the present invention utilizes a generation AI to automate responses to emails, chats, and other communication tools sent to individuals. This system reads received messages, and the generation AI analyzes the content of the messages to determine their emotions (e.g., anger, sadness, etc.) and perceived tone. It then generates a short summary tailored to the situation. The user then views the generated summary and selects a reply pattern. Options include polite, normal, and casual. Once the user selects a reply pattern, the generation AI generates a reply based on that pattern and automatically sends it. Users can also choose between automated and semi-automated reply patterns for internal and external communications. This system significantly reduces the time it takes to reply. Users simply review the summary generated by the generation AI and select a reply pattern, saving time and effort. Furthermore, analyzing emotions and perceived tone enables appropriate replies and improves the quality of communication. For example, the system reads received emails, and the generation AI analyzes their contents to determine their emotions and perceived tone. The generation AI then generates a short summary based on the content. The user then views the summary and selects a reply pattern. Options include polite replies, normal replies, and casual replies. When the user selects a reply pattern, the generation AI generates a reply based on that pattern and sends it automatically. Users can also choose between automated and semi-automated replies for internal and external use. This allows the system to significantly reduce the time it takes to reply. Users only need to check the summary generated by the generation AI and select a reply pattern, saving them time. Analyzing emotions and feelings also enables appropriate replies, improving the quality of communication. This allows the communication response automation system to consistently perform everything from reading messages to automatically sending replies, significantly reducing the time it takes to reply.

[0029] A communication response automation system according to an embodiment includes a reading unit, an analysis unit, a summary generation unit, a selection unit, a reply generation unit, and a sending unit. The reading unit reads a message. The message may include, but is not limited to, an email, a message, or a notification. For example, the reading unit may obtain an email from a mail server, a message from a messaging app, or a notification from a notification system. The reading unit may also set the format of the message and the timing of the reading. For example, the reading unit may be configured to read messages during a specific time period. The analysis unit uses natural language processing technology to analyze the content of the message read by the reading unit and determine emotions and sentiments. Examples of emotions include, but are not limited to, positive, negative, neutral, etc. Examples of sentiments include, but are not limited to, urgency and importance. The analysis unit analyzes the content of the message using, for example, morphological analysis, grammatical analysis, semantic analysis, or other techniques. The summary generation unit generates a concise summary based on the content analyzed by the analysis unit. The summarization is performed based on, for example, the length of the text and the importance of the information to be summarized, but is not limited to these examples. The summary generation unit concisely summarizes the content of the communication using, for example, a generation AI. The selection unit provides an interface for the user to select a reply pattern. Examples of the interface include, but are not limited to, a GUI, a CLI, a web interface, etc. The selection unit provides, for example, a button or a menu for the user to select a reply pattern. The reply generation unit generates a reply message based on the pattern selected by the selection unit. Examples of the reply message include, but are not limited to, a grammar check and appropriateness of the content. The reply generation unit generates a reply message based on the selected pattern using, for example, a generation AI. The sending unit automatically sends the generated reply message. Examples of the sending include, but are not limited to, confirmation of the sending timing and the destination. The sending unit can, for example, send an email through a mail server, send a message through a messaging app, or send a notification through a notification system.As a result, the communication response automation system according to the embodiment can consistently perform processes from reading a message to automatically sending a reply, thereby significantly reducing the time it takes to reply.

[0030] The analysis unit can analyze emotions and feelings using natural language processing technology. Natural language processing technology includes, but is not limited to, morphological analysis, grammatical analysis, and semantic analysis. The analysis unit analyzes the content of the message using, for example, morphological analysis. For example, morphological analysis can divide the content of the message into words and analyze the meaning of each word. The analysis unit can also analyze the content of the message using grammatical analysis. For example, grammatical analysis can analyze the grammatical structure of the content of the message and understand the meaning of the sentence. The analysis unit can also analyze the content of the message using semantic analysis. For example, semantic analysis can analyze the meaning of the content of the message and understand the intent of the sentence. Thus, the use of natural language processing technology improves the analysis accuracy of emotions and feelings. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can analyze emotions and feelings using an AI model that inputs the content of the message and outputs emotions and feelings.

[0031] The summary generation unit can generate a concise summary based on the content analyzed by the analysis unit. A concise summary can be generated based on, for example, the length of the sentence or the importance of the information to be summarized, but is not limited to these examples. The summary generation unit can, for example, use a generation AI to concisely summarize the content of the communication. For example, the generation AI can input the content of the communication and output a concise summary. The summary generation unit can also use the generation AI to extract and summarize important parts of the content of the communication. For example, the generation AI can pick out particularly important information from the content of the communication and create a summary based on that information. This allows the user to quickly understand the content by generating a short summary. Some or all of the above-mentioned processing in the summary generation unit can be performed, for example, using AI, or can be performed without using AI. For example, the summary generation unit can generate a summary using an AI model that inputs the content of the communication and outputs a concise summary.

[0032] The selection unit can provide an interface for the user to select a reply pattern. Examples of interfaces include, but are not limited to, a GUI, a CLI, and a web interface. The selection unit can provide, for example, buttons and menus for the user to select a reply pattern. For example, a GUI interface provides buttons and menus that the user can operate visually. A CLI interface provides commands that the user can operate on a command line. A web interface provides buttons and menus that the user can operate through a web browser. This allows the user to easily select a reply pattern. Some or all of the above-described processing in the selection unit can be performed, for example, using AI or without AI. For example, the selection unit can select a reply pattern using an AI model that receives user operations as input and outputs a reply pattern.

[0033] The reply generation unit can generate a reply message based on the selected pattern. Examples of reply messages include, but are not limited to, grammar checks and content appropriateness checks. The reply generation unit can generate a reply message based on the selected pattern using, for example, a generation AI. For example, the generation AI can use the selected pattern as input and output a reply message. The reply generation unit can also generate a reply message while checking grammar using the generation AI. For example, the generation AI can check the grammar of the reply message and correct it to appropriate grammar. The reply generation unit can also generate a reply message while checking the appropriateness of the content using the generation AI. For example, the generation AI can check whether the content of the reply message is appropriate and correct inappropriate content. This allows an appropriate reply message to be generated based on the selected pattern. Some or all of the above-described processing in the reply generation unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the reply generation unit can generate a reply message using an AI model that uses the selected pattern as input and outputs a reply message.

[0034] The sending unit can automatically send the generated reply text. Examples of automatic sending include, but are not limited to, confirmation of the sending timing and the destination. For example, the sending unit can send an email through a mail server, a message through a messaging app, or a notification through a notification system. The sending unit can also set the sending timing. For example, the sending unit can set the reply text to be sent at a specific time period. The sending unit can also check the destination. For example, the sending unit can check whether the destination of the reply text is correct and prevent it from being sent to an incorrect destination. This reduces the effort required by automatically sending the generated reply text. Some or all of the above-described processing in the sending unit may be performed using, for example, AI, or may be performed without using AI. For example, the sending unit can automatically send the reply text using an AI model that receives the generated reply text as input and executes the transmission.

[0035] Furthermore, the communication response automation system includes a selection setting unit that provides settings for selecting automation or semi-automation for internal and external communications. The selection setting unit provides settings for selecting automation or semi-automation for internal and external communications. For example, the selection setting unit can select automation for internal communications and semi-automation for external communications. In the automation setting, all processes from reading the communication to sending the reply are performed automatically. On the other hand, in the semi-automation setting, reading the communication and generating a summary are performed automatically, and reply text is generated and sent after user confirmation. This allows appropriate automation settings to be selected for internal and external communications. Some or all of the above-described processing in the selection setting unit may be performed using, for example, AI, or may be performed without AI. For example, the selection setting unit can provide settings using an AI model that inputs attributes of the communication and outputs a setting for automation or semi-automation.

[0036] The reading unit can analyze past contact history and select an appropriate reading method. For example, the reading unit can prioritize reading contacts from contacts with whom the user has frequently communicated in the past. The reading unit can also prioritize reading contacts that the user has previously deemed important. Furthermore, the reading unit can filter contacts that the user has previously ignored and read only important contacts. This allows the optimal reading method to be selected by analyzing the past contact history. The past contact history includes, for example, the type, frequency, and content of contacts. Some or all of the above-described processing in the reading unit may be performed using, for example, AI, or may be performed without using AI. For example, the reading unit can select a reading method using an AI model that inputs past contact history data and outputs an appropriate reading method.

[0037] The reading unit can filter messages based on their importance when reading them. For example, the reading unit can prioritize reading messages with high importance and postpone reading messages with low importance. It can also automatically archive messages with low importance and display only messages with high importance. It can also temporarily hold messages with medium importance and read them all at once later. By filtering based on the importance of messages, important messages can be prioritized. The importance of messages includes, for example, urgency and the importance of the content. Some or all of the above-described processing in the reading unit can be performed using, for example, AI, or can be performed without AI. For example, the reading unit can perform filtering using an AI model that inputs message importance data and outputs filtering results.

[0038] When reading a message, the reading unit can prioritize reading highly relevant messages by taking into account attribute information of the message sender. For example, the reading unit can prioritize reading messages from senders with whom the user frequently communicates. The reading unit can also prioritize reading messages from senders that the user determines to be important. Furthermore, the reading unit can filter messages from senders that the user has previously ignored and read only messages from important senders. This allows highly relevant messages to be processed preferentially by taking into account attribute information of the message sender. The attribute information of the sender includes, for example, the sender's job title and relationship. Some or all of the above-described processing in the reading unit may be performed using, for example, AI, or may be performed without using AI. For example, the reading unit can read messages using an AI model that inputs attribute information data of the sender and outputs highly relevant messages.

[0039] When reading a contact, the reading unit can automatically categorize the contact based on its content. For example, the reading unit can automatically categorize work-related contacts into a "work" category. Furthermore, the reading unit can automatically categorize private contacts into a "private" category. Furthermore, the reading unit can automatically categorize advertising and spam contacts into a "spam" category. This makes it easier to manage contacts by automatically categorizing them based on their content. Examples of categorization include the type of content and importance. Some or all of the above-described processing in the reading unit may be performed using, for example, AI, or may be performed without using AI. For example, the reading unit can perform categorization using an AI model that receives contact content data as input and outputs categorization results.

[0040] When analyzing the content of a communication, the analysis unit compares it with past communication content to improve the accuracy of the analysis. For example, the analysis unit can compare it with past communication content to identify similar communications and improve the accuracy of the analysis. Important keywords can also be extracted from past communication content and used in the analysis. Furthermore, the importance of a communication can be determined based on the past communication content to improve the accuracy of the analysis. Thus, by comparing it with past communication content, the accuracy of the analysis is improved. Past communication content includes, for example, the content, frequency, sender, etc. of the communication. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can improve the accuracy of the analysis using an AI model that inputs past communication content data and outputs analysis results.

[0041] When analyzing the content of a message, the analysis unit can perform the analysis while taking into consideration attribute information of the sender of the message. The analysis unit can determine the importance of the message, for example, by taking into consideration the sender's job title or position. The analysis unit can also analyze the content of the message based on the sender's past contact history. Furthermore, the analysis unit can analyze the content of the message while taking into consideration the sender's relationships (such as superior, colleague, or friend). This improves the accuracy of the analysis by taking into consideration the attribute information of the sender of the message. The attribute information of the sender includes, for example, the sender's job title and relationships. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can perform the analysis using an AI model that inputs attribute information data of the sender and outputs analysis results.

[0042] When analyzing the content of a message, the analysis unit can determine the priority of analysis based on the time when the message was sent. For example, the analysis unit can prioritize analysis of messages sent most recently. Also, the analysis unit can postpone analysis of messages sent older than the current time. Furthermore, the analysis unit can prioritize analysis of messages sent during a specific time period (such as during business hours). In this way, by determining the priority of analysis based on the time when the message was sent, the most recent message can be processed preferentially. The time when the message was sent includes, for example, the date and time of sending and the frequency of sending. Some or all of the above-described processing by the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can determine the priority using an AI model that inputs sending time data and outputs the priority of analysis.

[0043] When analyzing the content of a communication, the analysis unit can improve the accuracy of the analysis by referring to literature related to the communication. For example, the analysis unit can improve the accuracy of the analysis by referring to literature related to the content of the communication. The analysis unit can also improve the accuracy of the analysis by referring to past emails and chats related to the content of the communication. Furthermore, the analysis unit can improve the accuracy of the analysis by referring to websites and articles related to the content of the communication. In this way, by referring to literature related to the communication, the accuracy of the analysis is improved. Related literature includes, for example, past research papers, technical documents, etc. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can improve the accuracy of the analysis by using an AI model that inputs related literature data and outputs analysis results.

[0044] The summary generation unit can adjust the specificity of the summary based on the importance of the contact when generating the summary. For example, the summary generation unit can describe summaries of highly important contacts in detail. Also, the summary generation unit can describe summaries of low-importance contacts in concise detail. Furthermore, the summary generation unit can describe summaries of medium-importance contacts with an appropriate level of detail. In this way, important contacts can be summarized in detail by adjusting the level of detail of the summary based on the importance of the contact. The importance of the contact includes, for example, urgency and the importance of the content. Some or all of the above-described processing in the summary generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the summary generation unit can adjust the level of detail using an AI model that inputs contact importance data and outputs the level of detail of the summary.

[0045] The summary generation unit can apply an appropriate summarization algorithm depending on the category of the contact when generating a summary. For example, the summary generation unit can apply a detailed summarization algorithm to work-related contacts. It can also apply a concise summarization algorithm to private contacts. It can also apply an algorithm that omits summarization to advertising or spam contacts. This allows an appropriate summary to be generated by applying the optimal summarization algorithm depending on the category of the contact. Examples of categories include business categories and technology categories. Examples of summarization algorithms include abstract summarization and extractive summarization. Some or all of the above-described processing in the summary generation unit may be performed using, for example, AI, or may be performed without AI. For example, the summary generation unit can apply an algorithm using an AI model that inputs contact category data and outputs a summarization algorithm.

[0046] When generating summaries, the summary generation unit can determine the priority of summaries based on the transmission time of the messages. For example, the summary generation unit can prioritize summarizing messages that were sent most recently. Also, the summary generation unit can postpone the transmission of messages that were sent oldest. Furthermore, messages sent during a specific time period (such as during business hours) can be prioritized for summarization. In this way, by determining the priority of summaries based on the transmission time of the messages, the most recent messages can be prioritized for summarization. The transmission time includes, for example, the transmission date and time, the transmission frequency, etc. Some or all of the above-described processing in the summary generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the summary generation unit can determine the priority using an AI model that inputs transmission time data and outputs the priority of summaries.

[0047] The summary generation unit can adjust the order of summaries based on the relevance of the contacts when generating summaries. For example, the summary generation unit can prioritize summarizing highly relevant contacts. It can also postpone summarizing low-relevant contacts. It can also appropriately summarize medium-relevant contacts. This allows highly relevant contacts to be prioritized for summarization by adjusting the order of summaries based on the relevance of the contacts. Relevance includes, for example, similarity of content and relationships between senders. Some or all of the above-described processing in the summary generation unit may be performed using, for example, AI, or may be performed without AI. For example, the summary generation unit can adjust the order using an AI model that inputs contact relevance data and outputs the order of summaries.

[0048] The selection unit can analyze past reply history and suggest an optimal reply pattern. For example, the selection unit can prioritize and suggest reply patterns that the user has frequently used in the past. The selection unit can also suggest the most appropriate reply pattern from among the reply patterns the user has used in the past. Furthermore, the selection unit can suggest a reply pattern suitable for a specific situation based on the user's past reply history. This makes it possible to suggest an optimal reply pattern by analyzing the past reply history. The past reply history includes, for example, the content, frequency, and sender of replies. Some or all of the above-mentioned processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can suggest a reply pattern using an AI model that inputs past reply history data and outputs an optimal reply pattern.

[0049] When selecting a reply pattern, the selection unit can filter options based on the importance of the message. For example, the selection unit can prioritize providing a polite reply pattern for a message of high importance. Furthermore, the selection unit can prioritize providing a concise reply pattern for a message of low importance. Furthermore, the selection unit can provide a reply pattern with an appropriate level of detail for a message of medium importance. Thus, by filtering options based on the importance of the message, an appropriate reply pattern can be provided. The importance of the message includes, for example, urgency and the importance of the content. Some or all of the above-described processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can filter options using an AI model that inputs message importance data and outputs the filtering results.

[0050] When selecting a reply pattern, the selection unit can provide options by taking into consideration attribute information of the sender of the message. For example, if the sender is a boss, the selection unit can preferentially provide a polite reply pattern. Furthermore, if the sender is a colleague, the selection unit can preferentially provide a normal reply pattern. Furthermore, if the sender is a friend, the selection unit can preferentially provide a casual reply pattern. This allows an appropriate reply pattern to be provided by taking into consideration the attribute information of the sender of the message. The attribute information of the sender includes, for example, the sender's job title, relationship, etc. Some or all of the above-mentioned processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can provide options using an AI model that inputs attribute information data of the sender and outputs reply pattern options.

[0051] When selecting a reply pattern, the selection unit can automatically present a recommended pattern based on the content of the message. For example, if the content of the message is a business message, the selection unit can recommend a polite reply pattern. Furthermore, if the content of the message is a private topic, the selection unit can recommend a casual reply pattern. Furthermore, if the content of the message is a question, the selection unit can recommend a detailed reply pattern. In this way, by automatically presenting recommended patterns based on the content of the message, an appropriate reply pattern can be provided. The content of the message includes, for example, text content, attachments, etc. Some or all of the above-mentioned processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can present recommended patterns using an AI model that inputs message content data and outputs recommended patterns.

[0052] When generating a reply, the reply generation unit can adjust the level of detail of the reply based on the importance of the message. For example, the reply generation unit can generate a detailed reply for a message of high importance. Furthermore, the reply generation unit can generate a concise reply for a message of low importance. Furthermore, the reply generation unit can generate a reply with an appropriate level of detail for a message of medium importance. By adjusting the level of detail of the reply based on the importance of the message, an appropriate reply can be generated for an important message. The importance of the message includes, for example, urgency and the importance of the content. Some or all of the above-described processing in the reply generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the reply generation unit can adjust the level of detail using an AI model that inputs message importance data and outputs the level of detail of the reply.

[0053] When generating a reply, the reply generation unit can apply different reply algorithms depending on the category of the contact. For example, the reply generation unit can apply a detailed reply algorithm to work-related contacts. Furthermore, the reply generation unit can apply a concise reply algorithm to private contacts. Furthermore, the reply generation unit can apply an algorithm that omits replies to advertising or spam contacts. This allows an appropriate reply to be generated by applying the optimal reply algorithm depending on the category of the contact. Categories include, for example, business categories, technical categories, etc. Reply algorithms include, for example, template-based, generative models, etc. Some or all of the above-mentioned processing in the reply generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the reply generation unit can apply an algorithm using an AI model that inputs contact category data and outputs a reply algorithm.

[0054] When generating a reply message, the reply generation unit can determine the priority of the reply message based on the time when the message was sent. For example, the reply generation unit can prioritize the reply to a message sent most recently. Also, the reply generation unit can postpone messages sent earlier. Furthermore, messages sent during a specific time period (such as during business hours) can be prioritized for reply. In this way, by determining the priority of reply messages based on the time when the message was sent, it is possible to quickly reply to the most recent message. The time when the message was sent includes, for example, the date and time of sending and the frequency of sending. Some or all of the above-described processing in the reply generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the reply generation unit can determine the priority using an AI model that inputs sending time data and outputs the priority of the reply message.

[0055] When generating replies, the reply generation unit can adjust the order of replies based on the relevance of the messages. For example, the reply generation unit can prioritize replies to messages with high relevance. It can also postpone messages with low relevance. It can also appropriately reply to messages with medium relevance. By adjusting the order of replies based on the relevance of the messages, it is possible to prioritize replies to messages with high relevance. Relevance includes, for example, similarity of content, the relationship of the senders, etc. Some or all of the above-described processing in the reply generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the reply generation unit can adjust the order using an AI model that inputs message relevance data and outputs the order of replies.

[0056] The transmitting unit can determine the priority of transmission based on the importance of the contact at the time of transmission. For example, the transmitting unit can prioritize transmission of contacts with high importance. Also, the transmitting unit can postpone transmission of contacts with low importance. Furthermore, the transmitting unit can appropriately transmit contacts with medium importance. In this way, by determining the priority of transmission based on the importance of the contact, important contacts can be transmitted with priority. The importance of the contact includes, for example, urgency and importance of the content. Some or all of the above-described processing in the transmitting unit may be performed using, for example, AI, or may be performed without using AI. For example, the transmitting unit can determine the priority using an AI model that inputs contact importance data and outputs transmission priority.

[0057] When sending, the sending unit can select a sending method by taking into account attribute information of the sender of the message. For example, if the sender is a boss, the sending unit can select a polite sending method. If the sender is a colleague, the sending unit can select a normal sending method. Furthermore, if the sender is a friend, the sending unit can select a casual sending method. This allows an appropriate sending method to be selected by taking into account attribute information of the sender of the message. Attribute information of the sender includes, for example, the sender's job title, relationship, etc. Some or all of the above-mentioned processing in the sending unit may be performed using, for example, AI, or may be performed without using AI. For example, the sending unit can select a sending method using an AI model that inputs attribute information data of the sender and outputs a sending method.

[0058] At the time of transmission, the transmission unit can determine the priority of transmission based on the transmission time of the message. For example, the transmission unit can prioritize transmission of a message that was sent most recently. Also, the transmission unit can postpone transmission of a message that was sent older. Furthermore, the transmission unit can prioritize transmission of messages sent during a specific time period (such as during business hours). In this way, by determining the priority of transmission based on the transmission time of the message, the most recent message can be sent preferentially. The transmission time includes, for example, the transmission date and time, the transmission frequency, etc. Some or all of the above-described processing in the transmission unit may be performed using, for example, AI, or may be performed without using AI. For example, the transmission unit can determine the priority using an AI model that inputs transmission time data and outputs the transmission priority.

[0059] The sending unit can improve the accuracy of the transmission by referring to literature related to the message at the time of transmission. For example, the sending unit can improve the accuracy of the transmission by referring to literature related to the content of the message. The sending unit can also improve the accuracy of the transmission by referring to past emails or chats related to the content of the message. Furthermore, the sending unit can improve the accuracy of the transmission by referring to websites or articles related to the content of the message. In this way, the accuracy of the transmission is improved by referring to literature related to the message. Related literature includes, for example, past research papers, technical documents, etc. Some or all of the above-described processing in the sending unit may be performed using, for example, AI, or may be performed without using AI. For example, the sending unit can improve the accuracy by using an AI model that inputs related literature data and outputs the accuracy of the transmission.

[0060] The selection and setting unit can analyze past setting history and suggest optimal settings. For example, the selection and setting unit can prioritize and suggest settings that the user has frequently used in the past. Furthermore, the selection and setting unit can suggest the most appropriate settings from among the settings that the user has used in the past. Furthermore, the selection and setting unit can suggest settings suitable for a specific situation based on the user's past setting history. In this way, optimal settings can be suggested by analyzing the past setting history. The past setting history includes, for example, the type of setting, frequency, and success stories. Some or all of the above-mentioned processing in the selection and setting unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection and setting unit can suggest settings using an AI model that inputs past setting history data and outputs optimal settings.

[0061] During setup, the selection setting unit can filter automation and semi-automation options based on the importance of the contact. For example, the selection setting unit can prioritize providing an automation setting for contacts with high importance. Furthermore, the selection setting unit can prioritize providing a semi-automation setting for contacts with low importance. Furthermore, for contacts with medium importance, it can provide appropriate automation and semi-automation settings. Thus, by filtering the automation and semi-automation options based on the importance of the contact, appropriate settings can be provided. The importance of the contact includes, for example, urgency and the importance of the content. Some or all of the above-described processing in the selection setting unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection setting unit can filter the options using an AI model that inputs contact importance data and outputs the filtering results.

[0062] The selection setting unit can provide settings taking into consideration attribute information of the sender of the contact when setting the settings. For example, if the sender is a boss, the selection setting unit can provide a polite setting preferentially. If the sender is a colleague, the selection setting unit can provide a normal setting preferentially. If the sender is a friend, the selection setting unit can provide a casual setting preferentially. This allows appropriate settings to be provided by taking into consideration the attribute information of the sender of the contact. The attribute information of the sender includes, for example, the sender's job title, relationship, etc. Some or all of the above-mentioned processing in the selection setting unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection setting unit can provide settings using an AI model that inputs attribute information data of the sender and outputs settings.

[0063] The selection setting unit can automatically present recommended settings based on the content of the contact during setup. For example, if the content of the contact is a business contact, the selection setting unit can recommend polite settings. Furthermore, if the content of the contact is a private topic, the selection setting unit can recommend casual settings. Furthermore, if the content of the contact is a question, the selection setting unit can recommend detailed settings. In this way, appropriate settings can be provided by automatically presenting recommended settings based on the content of the contact. The content of the contact includes, for example, text content, attachments, etc. Some or all of the above-described processing in the selection setting unit may be performed, for example, using AI, or may be performed without using AI. For example, the selection setting unit can present recommended settings using an AI model that inputs contact content data and outputs recommended settings.

[0064] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0065] When analyzing the content of a message, the analysis unit can perform the analysis while taking into account the attribute information of the sender of the message. For example, the importance of the message can be determined by taking into account the sender's job title or position. The content of the message can also be analyzed based on the sender's past contact history. Furthermore, the content of the message can be analyzed while taking into account the sender's relationships (boss, colleague, friend, etc.). By taking into account the attribute information of the sender of the message, the accuracy of the analysis is improved. The attribute information of the sender includes, for example, the sender's job title, relationships, etc. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can perform the analysis using an AI model that inputs the sender's attribute information data and outputs the analysis results.

[0066] When generating a summary, the summary generation unit can adjust the specificity of the summary based on the importance of the contact. For example, summaries of highly important contacts can be written in detail. Furthermore, summaries of low-importance contacts can be written concisely. Furthermore, summaries of medium-importance contacts can be written with a moderate level of detail. In this way, important contacts can be summarized in detail by adjusting the level of detail of the summary based on the importance of the contact. The importance of a contact includes, for example, urgency and the importance of the content. Some or all of the above-mentioned processing in the summary generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the summary generation unit can adjust the level of detail using an AI model that inputs contact importance data and outputs the level of detail of the summary.

[0067] The selection unit can analyze past reply history and suggest an optimal reply pattern. For example, it can prioritize suggesting reply patterns that the user has frequently used in the past. It can also suggest the most appropriate reply pattern from among the reply patterns the user has used in the past. Furthermore, it can suggest a reply pattern suitable for a specific situation based on the user's past reply history. In this way, it is possible to suggest an optimal reply pattern by analyzing the past reply history. The past reply history includes, for example, the content, frequency, and sender of replies. Some or all of the above-mentioned processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can suggest a reply pattern using an AI model that inputs past reply history data and outputs an optimal reply pattern.

[0068] When generating a reply, the reply generation unit can apply different reply algorithms depending on the category of the contact. For example, a detailed reply algorithm can be applied to work-related contacts. A concise reply algorithm can be applied to private contacts. Furthermore, an algorithm that omits replies can be applied to advertising or spam contacts. This allows an appropriate reply to be generated by applying the optimal reply algorithm depending on the category of the contact. Categories include, for example, business categories, technical categories, etc. Reply algorithms include, for example, template-based and generative models. Some or all of the above-mentioned processing in the reply generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the reply generation unit can apply an algorithm using an AI model that inputs contact category data and outputs a reply algorithm.

[0069] When sending, the sending unit can select a sending method by taking into account the attribute information of the sender of the message. For example, if the sender is a boss, a polite sending method can be selected. If the sender is a colleague, a normal sending method can be selected. Furthermore, if the sender is a friend, a casual sending method can be selected. In this way, an appropriate sending method can be selected by taking into account the attribute information of the sender of the message. The attribute information of the sender includes, for example, the sender's job title, relationship, etc. Some or all of the above-mentioned processing in the sending unit may be performed using, for example, AI, or may be performed without using AI. For example, the sending unit can select a sending method using an AI model that inputs attribute information data of the sender and outputs a sending method.

[0070] The processing flow of the first embodiment will be briefly explained below.

[0071] Step 1: The reader reads contacts. Contacts include emails, messages, notifications, etc. The reader can retrieve emails from the mail server, messages from the messaging app, and notifications from the notification system. The reader can also set the format of the contacts and the timing of reading. Step 2: The analysis unit uses natural language processing technology to analyze the content of the message read by the reading unit and determine the emotion and temperature. Emotions include positive, negative, neutral, etc., and temperature includes urgency, importance, etc. The analysis unit analyzes the content of the message using techniques such as morphological analysis, grammatical analysis, and semantic analysis. Step 3: The summary generator generates a concise summary based on the content analyzed by the analyzer. The summary is generated based on the length of the text and the importance of the information being summarized. The summary generator uses a generation AI to concisely summarize the content of the communication. Step 4: The selection unit provides an interface for the user to select a reply pattern. The interface may be a GUI, a CLI, a web interface, etc. The selection unit provides a button or a menu for the user to select a reply pattern. Step 5: The reply generator generates a reply based on the pattern selected by the selector. The reply includes grammar checks, content appropriateness checks, etc. The reply generator uses a generation AI to generate a reply based on the selected pattern. Step 6: The sender automatically sends the generated reply message. This includes confirming the timing and destination of the message. The sender can send emails through a mail server, messages through messaging apps, and notifications through a notification system.

[0072] (Example 2) A communication response automation system according to an embodiment of the present invention utilizes a generation AI to automate responses to emails, chats, and other communication tools sent to individuals. This system reads received messages, and the generation AI analyzes the content of the messages to determine their emotions (e.g., anger, sadness, etc.) and perceived tone. It then generates a short summary tailored to the situation. The user then views the generated summary and selects a reply pattern. Options include polite, normal, and casual. Once the user selects a reply pattern, the generation AI generates a reply based on that pattern and automatically sends it. Users can also choose between automated and semi-automated reply patterns for internal and external communications. This system significantly reduces the time it takes to reply. Users simply review the summary generated by the generation AI and select a reply pattern, saving time and effort. Furthermore, analyzing emotions and perceived tone enables appropriate replies and improves the quality of communication. For example, the system reads received emails, and the generation AI analyzes their contents to determine their emotions and perceived tone. The generation AI then generates a short summary based on the content. The user then views the summary and selects a reply pattern. Options include polite replies, normal replies, and casual replies. When the user selects a reply pattern, the generation AI generates a reply based on that pattern and sends it automatically. Users can also choose between automated and semi-automated replies for internal and external use. This allows the system to significantly reduce the time it takes to reply. Users only need to check the summary generated by the generation AI and select a reply pattern, saving them time. Analyzing emotions and feelings also enables appropriate replies, improving the quality of communication. This allows the communication response automation system to consistently perform everything from reading messages to automatically sending replies, significantly reducing the time it takes to reply.

[0073] A communication response automation system according to an embodiment includes a reading unit, an analysis unit, a summary generation unit, a selection unit, a reply generation unit, and a sending unit. The reading unit reads a message. The message may include, but is not limited to, an email, a message, or a notification. For example, the reading unit may obtain an email from a mail server, a message from a messaging app, or a notification from a notification system. The reading unit may also set the format of the message and the timing of the reading. For example, the reading unit may be configured to read messages during a specific time period. The analysis unit uses natural language processing technology to analyze the content of the message read by the reading unit and determine emotions and sentiments. Examples of emotions include, but are not limited to, positive, negative, neutral, etc. Examples of sentiments include, but are not limited to, urgency and importance. The analysis unit analyzes the content of the message using, for example, morphological analysis, grammatical analysis, semantic analysis, or other techniques. The summary generation unit generates a concise summary based on the content analyzed by the analysis unit. The summarization is performed based on, for example, the length of the text and the importance of the information to be summarized, but is not limited to these examples. The summary generation unit concisely summarizes the content of the communication using, for example, a generation AI. The selection unit provides an interface for the user to select a reply pattern. Examples of the interface include, but are not limited to, a GUI, a CLI, a web interface, etc. The selection unit provides, for example, a button or a menu for the user to select a reply pattern. The reply generation unit generates a reply message based on the pattern selected by the selection unit. Examples of the reply message include, but are not limited to, a grammar check and appropriateness of the content. The reply generation unit generates a reply message based on the selected pattern using, for example, a generation AI. The sending unit automatically sends the generated reply message. Examples of the sending include, but are not limited to, confirmation of the sending timing and the destination. The sending unit can, for example, send an email through a mail server, send a message through a messaging app, or send a notification through a notification system.As a result, the communication response automation system according to the embodiment can consistently perform processes from reading a message to automatically sending a reply, thereby significantly reducing the time it takes to reply.

[0074] The analysis unit can analyze emotions and feelings using natural language processing technology. Natural language processing technology includes, but is not limited to, morphological analysis, grammatical analysis, and semantic analysis. The analysis unit analyzes the content of the message using, for example, morphological analysis. For example, morphological analysis can divide the content of the message into words and analyze the meaning of each word. The analysis unit can also analyze the content of the message using grammatical analysis. For example, grammatical analysis can analyze the grammatical structure of the content of the message and understand the meaning of the sentence. The analysis unit can also analyze the content of the message using semantic analysis. For example, semantic analysis can analyze the meaning of the content of the message and understand the intent of the sentence. Thus, the use of natural language processing technology improves the analysis accuracy of emotions and feelings. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can analyze emotions and feelings using an AI model that inputs the content of the message and outputs emotions and feelings.

[0075] The summary generation unit can generate a concise summary based on the content analyzed by the analysis unit. A concise summary can be generated based on, for example, the length of the sentence or the importance of the information to be summarized, but is not limited to these examples. The summary generation unit can, for example, use a generation AI to concisely summarize the content of the communication. For example, the generation AI can input the content of the communication and output a concise summary. The summary generation unit can also use the generation AI to extract and summarize important parts of the content of the communication. For example, the generation AI can pick out particularly important information from the content of the communication and create a summary based on that information. This allows the user to quickly understand the content by generating a short summary. Some or all of the above-mentioned processing in the summary generation unit can be performed, for example, using AI, or can be performed without using AI. For example, the summary generation unit can generate a summary using an AI model that inputs the content of the communication and outputs a concise summary.

[0076] The selection unit can provide an interface for the user to select a reply pattern. Examples of interfaces include, but are not limited to, a GUI, a CLI, and a web interface. The selection unit can provide, for example, buttons and menus for the user to select a reply pattern. For example, a GUI interface provides buttons and menus that the user can operate visually. A CLI interface provides commands that the user can operate on a command line. A web interface provides buttons and menus that the user can operate through a web browser. This allows the user to easily select a reply pattern. Some or all of the above-described processing in the selection unit can be performed, for example, using AI or without AI. For example, the selection unit can select a reply pattern using an AI model that receives user operations as input and outputs a reply pattern.

[0077] The reply generation unit can generate a reply message based on the selected pattern. Examples of reply messages include, but are not limited to, grammar checks and content appropriateness checks. The reply generation unit can generate a reply message based on the selected pattern using, for example, a generation AI. For example, the generation AI can use the selected pattern as input and output a reply message. The reply generation unit can also generate a reply message while checking grammar using the generation AI. For example, the generation AI can check the grammar of the reply message and correct it to appropriate grammar. The reply generation unit can also generate a reply message while checking the appropriateness of the content using the generation AI. For example, the generation AI can check whether the content of the reply message is appropriate and correct inappropriate content. This allows an appropriate reply message to be generated based on the selected pattern. Some or all of the above-described processing in the reply generation unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the reply generation unit can generate a reply message using an AI model that uses the selected pattern as input and outputs a reply message.

[0078] The sending unit can automatically send the generated reply text. Examples of automatic sending include, but are not limited to, confirmation of the sending timing and the destination. For example, the sending unit can send an email through a mail server, a message through a messaging app, or a notification through a notification system. The sending unit can also set the sending timing. For example, the sending unit can set the reply text to be sent at a specific time period. The sending unit can also check the destination. For example, the sending unit can check whether the destination of the reply text is correct and prevent it from being sent to an incorrect destination. This reduces the effort required by automatically sending the generated reply text. Some or all of the above-described processing in the sending unit may be performed using, for example, AI, or may be performed without using AI. For example, the sending unit can automatically send the reply text using an AI model that receives the generated reply text as input and executes the transmission.

[0079] Furthermore, the communication response automation system includes a selection setting unit that provides settings for selecting automation or semi-automation for internal and external communications. The selection setting unit provides settings for selecting automation or semi-automation for internal and external communications. For example, the selection setting unit can select automation for internal communications and semi-automation for external communications. In the automation setting, all processes from reading the communication to sending the reply are performed automatically. On the other hand, in the semi-automation setting, reading the communication and generating a summary are performed automatically, and reply text is generated and sent after user confirmation. This allows appropriate automation settings to be selected for internal and external communications. Some or all of the above-described processing in the selection setting unit may be performed using, for example, AI, or may be performed without AI. For example, the selection setting unit can provide settings using an AI model that inputs attributes of the communication and outputs a setting for automation or semi-automation.

[0080] The reading unit can estimate the user's emotions and adjust the timing of message reading based on the estimated user emotions. For example, if the user is feeling stressed, the reading unit can delay message reading and wait until the user is relaxed. Also, if the user is relaxed, the reading unit can immediately read messages to encourage a quick response. Furthermore, if the user is busy, the reading unit can temporarily stop message reading and read them all at once later. This allows messages to be read at an appropriate time by adjusting the message reading timing according to the user's emotions. Emotion estimation is performed, for example, using an emotion analysis algorithm. The emotion analysis algorithm analyzes the user's facial expressions, voice, text, etc. to estimate the user's emotions. Some or all of the above-mentioned processing in the reading unit may be performed, for example, using AI, or may be performed without AI. For example, the reading unit can adjust the message reading timing using an AI model that inputs user emotion data and outputs the message reading timing.

[0081] The reading unit can analyze past contact history and select an appropriate reading method. For example, the reading unit can prioritize reading contacts from contacts with whom the user has frequently communicated in the past. The reading unit can also prioritize reading contacts that the user has previously deemed important. Furthermore, the reading unit can filter contacts that the user has previously ignored and read only important contacts. This allows the optimal reading method to be selected by analyzing the past contact history. The past contact history includes, for example, the type, frequency, and content of contacts. Some or all of the above-described processing in the reading unit may be performed using, for example, AI, or may be performed without using AI. For example, the reading unit can select a reading method using an AI model that inputs past contact history data and outputs an appropriate reading method.

[0082] The reading unit can filter messages based on their importance when reading them. For example, the reading unit can prioritize reading messages with high importance and postpone reading messages with low importance. It can also automatically archive messages with low importance and display only messages with high importance. It can also temporarily hold messages with medium importance and read them all at once later. By filtering based on the importance of messages, important messages can be prioritized. The importance of messages includes, for example, urgency and the importance of the content. Some or all of the above-described processing in the reading unit can be performed using, for example, AI, or can be performed without AI. For example, the reading unit can perform filtering using an AI model that inputs message importance data and outputs filtering results.

[0083] The reading unit can estimate the user's emotions and determine the priority of messages to be read based on the estimated user emotions. For example, if the user is feeling stressed, the reading unit can postpone messages of lower importance. Furthermore, if the user is relaxed, the reading unit can read all messages evenly. Furthermore, if the user is busy, the reading unit can prioritize only messages of higher importance. This allows messages to be processed in an appropriate order by determining the priority of messages according to the user's emotions. The emotion estimation is performed, for example, using an emotion analysis algorithm. The emotion analysis algorithm analyzes the user's facial expressions, voice, text, etc. to estimate the user's emotions. Some or all of the above-described processing in the reading unit may be performed, for example, using AI, or may be performed without AI. For example, the reading unit can determine the priority using an AI model that inputs user emotion data and outputs the priority of messages.

[0084] When reading a message, the reading unit can prioritize reading highly relevant messages by taking into account attribute information of the message sender. For example, the reading unit can prioritize reading messages from senders with whom the user frequently communicates. The reading unit can also prioritize reading messages from senders that the user determines to be important. Furthermore, the reading unit can filter messages from senders that the user has previously ignored and read only messages from important senders. This allows highly relevant messages to be processed preferentially by taking into account attribute information of the message sender. The attribute information of the sender includes, for example, the sender's job title and relationship. Some or all of the above-described processing in the reading unit may be performed using, for example, AI, or may be performed without using AI. For example, the reading unit can read messages using an AI model that inputs attribute information data of the sender and outputs highly relevant messages.

[0085] When reading a contact, the reading unit can automatically categorize the contact based on its content. For example, the reading unit can automatically categorize work-related contacts into a "work" category. Furthermore, the reading unit can automatically categorize private contacts into a "private" category. Furthermore, the reading unit can automatically categorize advertising and spam contacts into a "spam" category. This makes it easier to manage contacts by automatically categorizing them based on their content. Examples of categorization include the type of content and importance. Some or all of the above-described processing in the reading unit may be performed using, for example, AI, or may be performed without using AI. For example, the reading unit can perform categorization using an AI model that receives contact content data as input and outputs categorization results.

[0086] The analysis unit can estimate the user's emotions and adjust the accuracy of the analysis based on the estimated user emotions. For example, if the user is feeling stressed, the analysis unit can increase the accuracy of the analysis to extract important information. Furthermore, if the user is relaxed, the analysis unit can return the accuracy of the analysis to normal. Furthermore, if the user is busy, the analysis unit can increase the accuracy of the analysis to quickly extract important information. This allows important information to be appropriately extracted by adjusting the accuracy of the analysis according to the user's emotions. Emotion estimation is performed, for example, using an emotion analysis algorithm. The emotion analysis algorithm analyzes the user's facial expressions, voice, text, etc. to estimate the user's emotions. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can adjust the accuracy of the analysis using an AI model that inputs user emotion data and outputs the accuracy of the analysis.

[0087] When analyzing the content of a communication, the analysis unit compares it with past communication content to improve the accuracy of the analysis. For example, the analysis unit can compare it with past communication content to identify similar communications and improve the accuracy of the analysis. Important keywords can also be extracted from past communication content and used in the analysis. Furthermore, the importance of a communication can be determined based on the past communication content to improve the accuracy of the analysis. Thus, by comparing it with past communication content, the accuracy of the analysis is improved. Past communication content includes, for example, the content, frequency, sender, etc. of the communication. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can improve the accuracy of the analysis using an AI model that inputs past communication content data and outputs analysis results.

[0088] When analyzing the content of a message, the analysis unit can perform the analysis while taking into consideration attribute information of the sender of the message. The analysis unit can determine the importance of the message, for example, by taking into consideration the sender's job title or position. The analysis unit can also analyze the content of the message based on the sender's past contact history. Furthermore, the analysis unit can analyze the content of the message while taking into consideration the sender's relationships (such as superior, colleague, or friend). This improves the accuracy of the analysis by taking into consideration the attribute information of the sender of the message. The attribute information of the sender includes, for example, the sender's job title and relationships. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can perform the analysis using an AI model that inputs attribute information data of the sender and outputs analysis results.

[0089] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is feeling stressed, the analysis unit can provide a simple, highly visible display method. Furthermore, if the user is relaxed, the analysis unit can provide a display method that includes detailed information. Furthermore, if the user is busy, the analysis unit can provide a display method that focuses on the main points. This improves visibility by adjusting the display method of the analysis results according to the user's emotions. The emotion estimation is performed, for example, using an emotion analysis algorithm. The emotion analysis algorithm analyzes the user's facial expressions, voice, text, etc. to estimate the user's emotions. Some or all of the above-described processing in the analysis unit may be performed, for example, using AI, or may be performed without AI. For example, the analysis unit can adjust the display method using an AI model that inputs user emotion data and outputs a display method.

[0090] When analyzing the content of a message, the analysis unit can determine the priority of analysis based on the time when the message was sent. For example, the analysis unit can prioritize analysis of messages sent most recently. Also, the analysis unit can postpone analysis of messages sent older than the current time. Furthermore, the analysis unit can prioritize analysis of messages sent during a specific time period (such as during business hours). In this way, by determining the priority of analysis based on the time when the message was sent, the most recent message can be processed preferentially. The time when the message was sent includes, for example, the date and time of sending and the frequency of sending. Some or all of the above-described processing by the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can determine the priority using an AI model that inputs sending time data and outputs the priority of analysis.

[0091] When analyzing the content of a communication, the analysis unit can improve the accuracy of the analysis by referring to literature related to the communication. For example, the analysis unit can improve the accuracy of the analysis by referring to literature related to the content of the communication. The analysis unit can also improve the accuracy of the analysis by referring to past emails and chats related to the content of the communication. Furthermore, the analysis unit can improve the accuracy of the analysis by referring to websites and articles related to the content of the communication. In this way, by referring to literature related to the communication, the accuracy of the analysis is improved. Related literature includes, for example, past research papers, technical documents, etc. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can improve the accuracy of the analysis by using an AI model that inputs related literature data and outputs analysis results.

[0092] The summary generation unit can estimate a user's emotions and adjust the presentation style of the summary based on the estimated user emotions. For example, if the user is stressed, the summary generation unit can generate a simple and to-the-point summary. If the user is relaxed, the summary generation unit can generate a detailed summary. Furthermore, if the user is busy, the summary generation unit can generate a short and to-the-point summary. This allows for the generation of an appropriate summary by adjusting the presentation style of the summary according to the user's emotions. The emotion estimation is performed, for example, using a sentiment analysis algorithm. The sentiment analysis algorithm analyzes the user's facial expressions, voice, text, etc. to estimate the user's emotions. Some or all of the above-described processing in the summary generation unit may be performed, for example, using AI, or may be performed without AI. For example, the summary generation unit can adjust the presentation style using an AI model that inputs user emotion data and outputs a summary presentation style.

[0093] The summary generation unit can adjust the specificity of the summary based on the importance of the contact when generating the summary. For example, the summary generation unit can describe summaries of highly important contacts in detail. Also, the summary generation unit can describe summaries of low-importance contacts in concise detail. Furthermore, the summary generation unit can describe summaries of medium-importance contacts with an appropriate level of detail. In this way, important contacts can be summarized in detail by adjusting the level of detail of the summary based on the importance of the contact. The importance of the contact includes, for example, urgency and the importance of the content. Some or all of the above-described processing in the summary generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the summary generation unit can adjust the level of detail using an AI model that inputs contact importance data and outputs the level of detail of the summary.

[0094] The summary generation unit can apply an appropriate summarization algorithm depending on the category of the contact when generating a summary. For example, the summary generation unit can apply a detailed summarization algorithm to work-related contacts. It can also apply a concise summarization algorithm to private contacts. It can also apply an algorithm that omits summarization to advertising or spam contacts. This allows an appropriate summary to be generated by applying the optimal summarization algorithm depending on the category of the contact. Examples of categories include business categories and technology categories. Examples of summarization algorithms include abstract summarization and extractive summarization. Some or all of the above-described processing in the summary generation unit may be performed using, for example, AI, or may be performed without AI. For example, the summary generation unit can apply an algorithm using an AI model that inputs contact category data and outputs a summarization algorithm.

[0095] The summary generation unit can estimate the user's emotions and adjust the length of the summary based on the estimated user emotions. For example, if the user is stressed, the summary generation unit can generate a short, concise summary. If the user is relaxed, the summary generation unit can generate a longer summary with detailed information. If the user is busy, the summary generation unit can generate a short, concise summary. By adjusting the length of the summary according to the user's emotions, a summary of an appropriate length can be generated. The emotion estimation is performed, for example, using a sentiment analysis algorithm. The sentiment analysis algorithm analyzes the user's facial expressions, voice, text, etc. to estimate the user's emotions. Some or all of the above-described processing in the summary generation unit may be performed, for example, using AI, or may be performed without AI. For example, the summary generation unit can adjust the length using an AI model that inputs user emotion data and outputs the length of the summary.

[0096] When generating summaries, the summary generation unit can determine the priority of summaries based on the transmission time of the messages. For example, the summary generation unit can prioritize summarizing messages that were sent most recently. Also, the summary generation unit can postpone the transmission of messages that were sent oldest. Furthermore, messages sent during a specific time period (such as during business hours) can be prioritized for summarization. In this way, by determining the priority of summaries based on the transmission time of the messages, the most recent messages can be prioritized for summarization. The transmission time includes, for example, the transmission date and time, the transmission frequency, etc. Some or all of the above-described processing in the summary generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the summary generation unit can determine the priority using an AI model that inputs transmission time data and outputs the priority of summaries.

[0097] The summary generation unit can adjust the order of summaries based on the relevance of the contacts when generating summaries. For example, the summary generation unit can prioritize summarizing highly relevant contacts. It can also postpone summarizing low-relevant contacts. It can also appropriately summarize medium-relevant contacts. This allows highly relevant contacts to be prioritized for summarization by adjusting the order of summaries based on the relevance of the contacts. Relevance includes, for example, similarity of content and relationships between senders. Some or all of the above-described processing in the summary generation unit may be performed using, for example, AI, or may be performed without AI. For example, the summary generation unit can adjust the order using an AI model that inputs contact relevance data and outputs the order of summaries.

[0098] The selection unit can estimate the user's emotions and adjust reply pattern options based on the estimated user emotions. For example, if the user is stressed, the selection unit can provide a simple and quick reply pattern. If the user is relaxed, the selection unit can provide a detailed reply pattern. If the user is busy, the selection unit can provide a short and to-the-point reply pattern. This allows appropriate reply patterns to be provided by adjusting the reply pattern options according to the user's emotions. The emotion estimation is performed, for example, using an emotion analysis algorithm. The emotion analysis algorithm analyzes the user's facial expressions, voice, text, etc. to estimate the user's emotions. Some or all of the above-described processing in the selection unit may be performed, for example, using AI, or may be performed without AI. For example, the selection unit can adjust the options using an AI model that inputs user emotion data and outputs reply pattern options.

[0099] The selection unit can analyze past reply history and suggest an optimal reply pattern. For example, the selection unit can prioritize and suggest reply patterns that the user has frequently used in the past. The selection unit can also suggest the most appropriate reply pattern from among the reply patterns the user has used in the past. Furthermore, the selection unit can suggest a reply pattern suitable for a specific situation based on the user's past reply history. This makes it possible to suggest an optimal reply pattern by analyzing the past reply history. The past reply history includes, for example, the content, frequency, and sender of replies. Some or all of the above-mentioned processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can suggest a reply pattern using an AI model that inputs past reply history data and outputs an optimal reply pattern.

[0100] When selecting a reply pattern, the selection unit can filter options based on the importance of the message. For example, the selection unit can prioritize providing a polite reply pattern for a message of high importance. Furthermore, the selection unit can prioritize providing a concise reply pattern for a message of low importance. Furthermore, the selection unit can provide a reply pattern with an appropriate level of detail for a message of medium importance. Thus, by filtering options based on the importance of the message, an appropriate reply pattern can be provided. The importance of the message includes, for example, urgency and the importance of the content. Some or all of the above-described processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can filter options using an AI model that inputs message importance data and outputs the filtering results.

[0101] The selection unit can estimate the user's emotions and adjust the display order of reply patterns based on the estimated user emotions. For example, if the user is stressed, the selection unit can display simple and quick reply patterns at the top. Furthermore, if the user is relaxed, the selection unit can display detailed reply patterns at the top. Furthermore, if the user is busy, the selection unit can display short and to-the-point reply patterns at the top. This allows appropriate reply patterns to be provided by adjusting the display order of reply patterns according to the user's emotions. The emotion estimation is performed, for example, using an emotion analysis algorithm. The emotion analysis algorithm analyzes the user's facial expressions, voice, text, etc. to estimate the user's emotions. Some or all of the above-described processing in the selection unit may be performed, for example, using AI, or may be performed without AI. For example, the selection unit can adjust the display order using an AI model that inputs user emotion data and outputs the display order of reply patterns.

[0102] When selecting a reply pattern, the selection unit can provide options by taking into consideration attribute information of the sender of the message. For example, if the sender is a boss, the selection unit can preferentially provide a polite reply pattern. Furthermore, if the sender is a colleague, the selection unit can preferentially provide a normal reply pattern. Furthermore, if the sender is a friend, the selection unit can preferentially provide a casual reply pattern. This allows an appropriate reply pattern to be provided by taking into consideration the attribute information of the sender of the message. The attribute information of the sender includes, for example, the sender's job title, relationship, etc. Some or all of the above-mentioned processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can provide options using an AI model that inputs attribute information data of the sender and outputs reply pattern options.

[0103] When selecting a reply pattern, the selection unit can automatically present a recommended pattern based on the content of the message. For example, if the content of the message is a business message, the selection unit can recommend a polite reply pattern. Furthermore, if the content of the message is a private topic, the selection unit can recommend a casual reply pattern. Furthermore, if the content of the message is a question, the selection unit can recommend a detailed reply pattern. In this way, by automatically presenting recommended patterns based on the content of the message, an appropriate reply pattern can be provided. The content of the message includes, for example, text content, attachments, etc. Some or all of the above-mentioned processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can present recommended patterns using an AI model that inputs message content data and outputs recommended patterns.

[0104] The reply generation unit can estimate the user's emotions and adjust the reply expression style based on the estimated user emotions. For example, if the user is stressed, the reply generation unit can generate a simple and quick reply. If the user is relaxed, the reply generation unit can generate a detailed reply. If the user is busy, the reply generation unit can generate a short and to-the-point reply. This allows for appropriate reply generation by adjusting the reply expression style according to the user's emotions. The emotion estimation is performed, for example, using a sentiment analysis algorithm. The sentiment analysis algorithm analyzes the user's facial expression, voice, text, etc. to estimate the user's emotions. Some or all of the above-described processing in the reply generation unit may be performed, for example, using AI, or may be performed without AI. For example, the reply generation unit can adjust the reply expression style using an AI model that inputs the user's emotional data and outputs the reply expression style.

[0105] When generating a reply, the reply generation unit can adjust the level of detail of the reply based on the importance of the message. For example, the reply generation unit can generate a detailed reply for a message of high importance. Furthermore, the reply generation unit can generate a concise reply for a message of low importance. Furthermore, the reply generation unit can generate a reply with an appropriate level of detail for a message of medium importance. By adjusting the level of detail of the reply based on the importance of the message, an appropriate reply can be generated for an important message. The importance of the message includes, for example, urgency and the importance of the content. Some or all of the above-described processing in the reply generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the reply generation unit can adjust the level of detail using an AI model that inputs message importance data and outputs the level of detail of the reply.

[0106] When generating a reply, the reply generation unit can apply different reply algorithms depending on the category of the contact. For example, the reply generation unit can apply a detailed reply algorithm to work-related contacts. Furthermore, the reply generation unit can apply a concise reply algorithm to private contacts. Furthermore, the reply generation unit can apply an algorithm that omits replies to advertising or spam contacts. This allows an appropriate reply to be generated by applying the optimal reply algorithm depending on the category of the contact. Categories include, for example, business categories, technical categories, etc. Reply algorithms include, for example, template-based, generative models, etc. Some or all of the above-mentioned processing in the reply generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the reply generation unit can apply an algorithm using an AI model that inputs contact category data and outputs a reply algorithm.

[0107] The reply generation unit can estimate the user's emotions and adjust the length of the reply based on the estimated user emotions. For example, if the user is stressed, the reply generation unit can generate a short, to-the-point reply. Furthermore, if the user is relaxed, the reply generation unit can generate a longer, detailed reply. Furthermore, if the user is busy, the reply generation unit can generate a short, to-the-point reply. By adjusting the length of the reply according to the user's emotions, a reply of an appropriate length can be generated. The emotion estimation is performed, for example, using a sentiment analysis algorithm. The sentiment analysis algorithm analyzes the user's facial expression, voice, text, etc. to estimate the user's emotions. Some or all of the above-described processing in the reply generation unit may be performed, for example, using AI, or may be performed without AI. For example, the reply generation unit can adjust the length using an AI model that inputs the user's emotion data and outputs the length of the reply.

[0108] When generating a reply message, the reply generation unit can determine the priority of the reply message based on the time when the message was sent. For example, the reply generation unit can prioritize the reply to a message sent most recently. Also, the reply generation unit can postpone messages sent earlier. Furthermore, messages sent during a specific time period (such as during business hours) can be prioritized for reply. In this way, by determining the priority of reply messages based on the time when the message was sent, it is possible to quickly reply to the most recent message. The time when the message was sent includes, for example, the date and time of sending and the frequency of sending. Some or all of the above-described processing in the reply generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the reply generation unit can determine the priority using an AI model that inputs sending time data and outputs the priority of the reply message.

[0109] When generating replies, the reply generation unit can adjust the order of replies based on the relevance of the messages. For example, the reply generation unit can prioritize replies to messages with high relevance. It can also postpone messages with low relevance. It can also appropriately reply to messages with medium relevance. By adjusting the order of replies based on the relevance of the messages, it is possible to prioritize replies to messages with high relevance. Relevance includes, for example, similarity of content, the relationship of the senders, etc. Some or all of the above-described processing in the reply generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the reply generation unit can adjust the order using an AI model that inputs message relevance data and outputs the order of replies.

[0110] The transmission unit can estimate the user's emotions and adjust the transmission timing based on the estimated user emotions. For example, if the user is feeling stressed, the transmission unit can delay transmission and wait until the user is relaxed. Alternatively, if the user is relaxed, the transmission unit can transmit immediately. Furthermore, if the user is busy, the transmission can be temporarily suspended and sent all at once later. This allows transmission at an appropriate time by adjusting the transmission timing according to the user's emotions. The emotion estimation is performed using, for example, an emotion analysis algorithm. The emotion analysis algorithm analyzes the user's facial expression, voice, text, etc. to estimate the user's emotions. Some or all of the above-described processing in the transmission unit may be performed using, for example, AI, or may be performed without AI. For example, the transmission unit can adjust the timing using an AI model that inputs user emotion data and outputs the transmission timing.

[0111] The transmitting unit can determine the priority of transmission based on the importance of the contact at the time of transmission. For example, the transmitting unit can prioritize transmission of contacts with high importance. Also, the transmitting unit can postpone transmission of contacts with low importance. Furthermore, the transmitting unit can appropriately transmit contacts with medium importance. In this way, by determining the priority of transmission based on the importance of the contact, important contacts can be transmitted with priority. The importance of the contact includes, for example, urgency and importance of the content. Some or all of the above-described processing in the transmitting unit may be performed using, for example, AI, or may be performed without using AI. For example, the transmitting unit can determine the priority using an AI model that inputs contact importance data and outputs transmission priority.

[0112] When sending, the sending unit can select a sending method by taking into account attribute information of the sender of the message. For example, if the sender is a boss, the sending unit can select a polite sending method. If the sender is a colleague, the sending unit can select a normal sending method. Furthermore, if the sender is a friend, the sending unit can select a casual sending method. This allows an appropriate sending method to be selected by taking into account attribute information of the sender of the message. Attribute information of the sender includes, for example, the sender's job title, relationship, etc. Some or all of the above-mentioned processing in the sending unit may be performed using, for example, AI, or may be performed without using AI. For example, the sending unit can select a sending method using an AI model that inputs attribute information data of the sender and outputs a sending method.

[0113] The transmission unit can estimate the user's emotions and adjust the confirmation procedure for transmission based on the estimated user's emotions. For example, the transmission unit can provide a brief confirmation procedure when the user is stressed. Furthermore, the transmission unit can provide a detailed confirmation procedure when the user is relaxed. Furthermore, the transmission unit can provide a quick confirmation procedure when the user is busy. This allows the transmission confirmation procedure to be adjusted according to the user's emotions, thereby providing an appropriate confirmation procedure. The emotion estimation is performed, for example, using an emotion analysis algorithm. The emotion analysis algorithm analyzes the user's facial expression, voice, text, etc. to estimate the user's emotions. Some or all of the above-described processing in the transmission unit may be performed, for example, using AI, or may be performed without using AI. For example, the transmission unit can adjust the confirmation procedure using an AI model that inputs user emotion data and outputs a confirmation procedure.

[0114] At the time of transmission, the transmission unit can determine the priority of transmission based on the transmission time of the message. For example, the transmission unit can prioritize transmission of a message that was sent most recently. Also, the transmission unit can postpone transmission of a message that was sent older. Furthermore, the transmission unit can prioritize transmission of messages sent during a specific time period (such as during business hours). In this way, by determining the priority of transmission based on the transmission time of the message, the most recent message can be sent preferentially. The transmission time includes, for example, the transmission date and time, the transmission frequency, etc. Some or all of the above-described processing in the transmission unit may be performed using, for example, AI, or may be performed without using AI. For example, the transmission unit can determine the priority using an AI model that inputs transmission time data and outputs the transmission priority.

[0115] The sending unit can improve the accuracy of the transmission by referring to literature related to the message at the time of transmission. For example, the sending unit can improve the accuracy of the transmission by referring to literature related to the content of the message. The sending unit can also improve the accuracy of the transmission by referring to past emails or chats related to the content of the message. Furthermore, the sending unit can improve the accuracy of the transmission by referring to websites or articles related to the content of the message. In this way, the accuracy of the transmission is improved by referring to literature related to the message. Related literature includes, for example, past research papers, technical documents, etc. Some or all of the above-described processing in the sending unit may be performed using, for example, AI, or may be performed without using AI. For example, the sending unit can improve the accuracy by using an AI model that inputs related literature data and outputs the accuracy of the transmission.

[0116] The selection and setting unit can estimate a user's emotions and adjust the automated and semi-automated settings based on the estimated user emotions. For example, if the user is stressed, the selection and setting unit can prioritize the automated settings and minimize manual operation. Furthermore, if the user is relaxed, the selection and setting unit can provide the semi-automated settings and allow user intervention. Furthermore, if the user is busy, the selection and setting unit can prioritize the automated settings and enable a quick response. This allows appropriate settings to be provided by adjusting the automated and semi-automated settings according to the user's emotions. The emotion estimation is performed, for example, using an emotion analysis algorithm. The emotion analysis algorithm analyzes the user's facial expressions, voice, text, etc. to estimate the user's emotions. Some or all of the above-described processing in the selection and setting unit may be performed, for example, using AI or without AI. For example, the selection and setting unit can adjust the settings using an AI model that inputs user emotion data and outputs automated and semi-automated settings.

[0117] The selection and setting unit can analyze past setting history and suggest optimal settings. For example, the selection and setting unit can prioritize and suggest settings that the user has frequently used in the past. Furthermore, the selection and setting unit can suggest the most appropriate settings from among the settings that the user has used in the past. Furthermore, the selection and setting unit can suggest settings suitable for a specific situation based on the user's past setting history. In this way, optimal settings can be suggested by analyzing the past setting history. The past setting history includes, for example, the type of setting, frequency, and success stories. Some or all of the above-mentioned processing in the selection and setting unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection and setting unit can suggest settings using an AI model that inputs past setting history data and outputs optimal settings.

[0118] During setup, the selection setting unit can filter automation and semi-automation options based on the importance of the contact. For example, the selection setting unit can prioritize providing an automation setting for contacts with high importance. Furthermore, the selection setting unit can prioritize providing a semi-automation setting for contacts with low importance. Furthermore, for contacts with medium importance, it can provide appropriate automation and semi-automation settings. Thus, by filtering the automation and semi-automation options based on the importance of the contact, appropriate settings can be provided. The importance of the contact includes, for example, urgency and the importance of the content. Some or all of the above-described processing in the selection setting unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection setting unit can filter the options using an AI model that inputs contact importance data and outputs the filtering results.

[0119] The selection setting unit can estimate the user's emotions and adjust the display order of settings based on the estimated user emotions. For example, if the user is stressed, the selection setting unit can display simple and quick settings at the top. Furthermore, if the user is relaxed, the selection setting unit can display detailed settings at the top. Furthermore, if the user is busy, the selection setting unit can display short and concise settings at the top. This allows appropriate settings to be provided by adjusting the display order of settings according to the user's emotions. The emotion estimation is performed, for example, using an emotion analysis algorithm. The emotion analysis algorithm analyzes the user's facial expressions, voice, text, etc. to estimate the user's emotions. Some or all of the above-described processing in the selection setting unit may be performed, for example, using AI, or may be performed without AI. For example, the selection setting unit can adjust the display order using an AI model that inputs user emotion data and outputs the display order of settings.

[0120] The selection setting unit can provide settings taking into consideration attribute information of the sender of the contact when setting the settings. For example, if the sender is a boss, the selection setting unit can provide a polite setting preferentially. If the sender is a colleague, the selection setting unit can provide a normal setting preferentially. If the sender is a friend, the selection setting unit can provide a casual setting preferentially. This allows appropriate settings to be provided by taking into consideration the attribute information of the sender of the contact. The attribute information of the sender includes, for example, the sender's job title, relationship, etc. Some or all of the above-mentioned processing in the selection setting unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection setting unit can provide settings using an AI model that inputs attribute information data of the sender and outputs settings.

[0121] The selection setting unit can automatically present recommended settings based on the content of the contact during setup. For example, if the content of the contact is a business contact, the selection setting unit can recommend polite settings. Furthermore, if the content of the contact is a private topic, the selection setting unit can recommend casual settings. Furthermore, if the content of the contact is a question, the selection setting unit can recommend detailed settings. In this way, appropriate settings can be provided by automatically presenting recommended settings based on the content of the contact. The content of the contact includes, for example, text content, attachments, etc. Some or all of the above-described processing in the selection setting unit may be performed, for example, using AI, or may be performed without using AI. For example, the selection setting unit can present recommended settings using an AI model that inputs contact content data and outputs recommended settings. === Hard Collateral 1-1 === Each of the multiple elements, including the above-mentioned reading unit, analysis unit, summary generation unit, selection unit, reply generation unit, transmission unit, selection setting unit, and emotion estimation unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reading unit is realized by the computer 36 of the smart device 14 and acquires messages from a mail server or a messaging app. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the content of the messages using natural language processing technology. The summary generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a concise summary using a generation AI. The selection unit is realized by the control unit 46A of the smart device 14 and provides an interface for the user to select a reply pattern. The reply generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a reply message based on the selected pattern. The transmission unit is realized by the communication I / F 44 of the smart device 14 and automatically transmits the generated reply message. The selection setting unit is realized by the specific processing unit 290 of the data processing device 12, and provides settings for selecting automation or semi-automation for internal and external use. The emotion estimation unit is realized by the specific processing unit 290 of the data processing device 12, and estimates the user's emotion and adjusts the timing of message reading. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned reading unit, analysis unit, summary generation unit, selection unit, reply generation unit, transmission unit, selection setting unit, and emotion estimation unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reading unit is realized by the computer 36 of the smart glasses 214 and acquires messages from a mail server or a messaging app. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the content of the messages using natural language processing technology. The summary generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a concise summary using a generation AI. The selection unit is realized by the control unit 46A of the smart glasses 214 and provides an interface for the user to select a reply pattern. The reply generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a reply sentence based on the selected pattern. The transmission unit is realized by the communication I / F 44 of the smart glasses 214 and automatically transmits the generated reply sentence. The selection setting unit is realized by the specific processing unit 290 of the data processing device 12, and provides settings for selecting automation or semi-automation for internal and external use. The emotion estimation unit is realized by the specific processing unit 290 of the data processing device 12, and estimates the user's emotion and adjusts the timing of message reading. === Hard Collateral 1-3 === Each of the multiple elements, including the above-mentioned reading unit, analysis unit, summary generation unit, selection unit, reply generation unit, transmission unit, selection setting unit, and emotion estimation unit, is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the reading unit is realized by the computer 36 of the headset type terminal 314 and acquires messages from a mail server or a messaging app. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the content of the messages using natural language processing technology. The summary generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a concise summary using a generation AI. The selection unit is realized by the control unit 46A of the headset type terminal 314 and provides an interface for the user to select a reply pattern. The reply generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a reply message based on the selected pattern. The transmission unit is realized by the communication I / F 44 of the headset type terminal 314 and automatically transmits the generated reply message. The selection setting unit is realized by the specific processing unit 290 of the data processing device 12, and provides settings for selecting automation or semi-automation for internal and external use. The emotion estimation unit is realized by the specific processing unit 290 of the data processing device 12, and estimates the user's emotion and adjusts the timing of message reading. === Hard Collateral 1-4 === Each of the multiple elements, including the reading unit, analysis unit, summary generation unit, selection unit, reply generation unit, transmission unit, selection setting unit, and emotion estimation unit, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reading unit is realized by the computer 36 of the robot 414 and acquires messages from a mail server or a messaging app. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the content of the messages using natural language processing technology. The summary generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a concise summary using a generation AI. The selection unit is realized by the control unit 46A of the robot 414 and provides an interface for the user to select a reply pattern. The reply generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a reply message based on the selected pattern. The transmission unit is realized by the communication I / F 44 of the robot 414 and automatically transmits the generated reply message. The selection setting unit is realized by the specific processing unit 290 of the data processing device 12, and provides settings for selecting automation or semi-automation for internal and external use. The emotion estimation unit is realized by the specific processing unit 290 of the data processing device 12, and estimates the user's emotion and adjusts the timing of message reading.

[0122] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0123] When analyzing the content of a message, the analysis unit can perform the analysis while taking into account the attribute information of the sender of the message. For example, the importance of the message can be determined by taking into account the sender's job title or position. The content of the message can also be analyzed based on the sender's past contact history. Furthermore, the content of the message can be analyzed while taking into account the sender's relationships (boss, colleague, friend, etc.). By taking into account the attribute information of the sender of the message, the accuracy of the analysis is improved. The attribute information of the sender includes, for example, the sender's job title, relationships, etc. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can perform the analysis using an AI model that inputs the sender's attribute information data and outputs the analysis results.

[0124] When generating a summary, the summary generation unit can adjust the specificity of the summary based on the importance of the contact. For example, summaries of highly important contacts can be written in detail. Furthermore, summaries of low-importance contacts can be written concisely. Furthermore, summaries of medium-importance contacts can be written with a moderate level of detail. In this way, important contacts can be summarized in detail by adjusting the level of detail of the summary based on the importance of the contact. The importance of a contact includes, for example, urgency and the importance of the content. Some or all of the above-mentioned processing in the summary generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the summary generation unit can adjust the level of detail using an AI model that inputs contact importance data and outputs the level of detail of the summary.

[0125] The selection unit can analyze past reply history and suggest an optimal reply pattern. For example, it can prioritize suggesting reply patterns that the user has frequently used in the past. It can also suggest the most appropriate reply pattern from among the reply patterns the user has used in the past. Furthermore, it can suggest a reply pattern suitable for a specific situation based on the user's past reply history. In this way, it is possible to suggest an optimal reply pattern by analyzing the past reply history. The past reply history includes, for example, the content, frequency, and sender of replies. Some or all of the above-mentioned processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can suggest a reply pattern using an AI model that inputs past reply history data and outputs an optimal reply pattern.

[0126] When generating a reply, the reply generation unit can apply different reply algorithms depending on the category of the contact. For example, a detailed reply algorithm can be applied to work-related contacts. A concise reply algorithm can be applied to private contacts. Furthermore, an algorithm that omits replies can be applied to advertising or spam contacts. This allows an appropriate reply to be generated by applying the optimal reply algorithm depending on the category of the contact. Categories include, for example, business categories, technical categories, etc. Reply algorithms include, for example, template-based and generative models. Some or all of the above-mentioned processing in the reply generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the reply generation unit can apply an algorithm using an AI model that inputs contact category data and outputs a reply algorithm.

[0127] When sending, the sending unit can select a sending method by taking into account the attribute information of the sender of the message. For example, if the sender is a boss, a polite sending method can be selected. If the sender is a colleague, a normal sending method can be selected. Furthermore, if the sender is a friend, a casual sending method can be selected. In this way, an appropriate sending method can be selected by taking into account the attribute information of the sender of the message. The attribute information of the sender includes, for example, the sender's job title, relationship, etc. Some or all of the above-mentioned processing in the sending unit may be performed using, for example, AI, or may be performed without using AI. For example, the sending unit can select a sending method using an AI model that inputs attribute information data of the sender and outputs a sending method.

[0128] The reading unit can estimate the user's emotions and adjust the timing of message reading based on the estimated user emotions. For example, if the user is feeling stressed, the reading unit can delay message reading and wait until the user is relaxed. Also, if the user is relaxed, the reading unit can immediately read messages to encourage a quick response. Furthermore, if the user is busy, the reading unit can temporarily stop message reading and read them all at once later. This allows messages to be read at an appropriate time by adjusting the message reading timing according to the user's emotions. Emotion estimation is performed, for example, using an emotion analysis algorithm. The emotion analysis algorithm analyzes the user's facial expressions, voice, text, etc. to estimate the user's emotions. Some or all of the above-mentioned processing in the reading unit may be performed, for example, using AI, or may be performed without AI. For example, the reading unit can adjust the message reading timing using an AI model that inputs user emotion data and outputs the message reading timing.

[0129] The analysis unit can estimate the user's emotions and adjust the accuracy of the analysis based on the estimated user emotions. For example, if the user is feeling stressed, the analysis unit can increase the accuracy of the analysis to extract important information. Furthermore, if the user is relaxed, the analysis unit can return the accuracy of the analysis to normal. Furthermore, if the user is busy, the analysis unit can increase the accuracy of the analysis to quickly extract important information. This allows important information to be appropriately extracted by adjusting the accuracy of the analysis according to the user's emotions. Emotion estimation is performed, for example, using an emotion analysis algorithm. The emotion analysis algorithm analyzes the user's facial expressions, voice, text, etc. to estimate the user's emotions. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can adjust the accuracy of the analysis using an AI model that inputs user emotion data and outputs the accuracy of the analysis.

[0130] The summary generation unit can estimate a user's emotions and adjust the presentation style of the summary based on the estimated user emotions. For example, if the user is stressed, the summary generation unit can generate a simple and to-the-point summary. If the user is relaxed, the summary generation unit can generate a detailed summary. Furthermore, if the user is busy, the summary generation unit can generate a short and to-the-point summary. This allows for the generation of an appropriate summary by adjusting the presentation style of the summary according to the user's emotions. The emotion estimation is performed, for example, using a sentiment analysis algorithm. The sentiment analysis algorithm analyzes the user's facial expressions, voice, text, etc. to estimate the user's emotions. Some or all of the above-described processing in the summary generation unit may be performed, for example, using AI, or may be performed without AI. For example, the summary generation unit can adjust the presentation style using an AI model that inputs user emotion data and outputs a summary presentation style.

[0131] The selection unit can estimate the user's emotions and adjust reply pattern options based on the estimated user emotions. For example, if the user is stressed, the selection unit can provide a simple and quick reply pattern. If the user is relaxed, the selection unit can provide a detailed reply pattern. If the user is busy, the selection unit can provide a short and to-the-point reply pattern. This allows appropriate reply patterns to be provided by adjusting the reply pattern options according to the user's emotions. The emotion estimation is performed, for example, using an emotion analysis algorithm. The emotion analysis algorithm analyzes the user's facial expressions, voice, text, etc. to estimate the user's emotions. Some or all of the above-described processing in the selection unit may be performed, for example, using AI, or may be performed without AI. For example, the selection unit can adjust the options using an AI model that inputs user emotion data and outputs reply pattern options.

[0132] The transmission unit can estimate the user's emotions and adjust the transmission timing based on the estimated user emotions. For example, if the user is feeling stressed, the transmission unit can delay transmission and wait until the user is relaxed. Alternatively, if the user is relaxed, the transmission unit can transmit immediately. Furthermore, if the user is busy, the transmission can be temporarily suspended and sent all at once later. This allows transmission at an appropriate time by adjusting the transmission timing according to the user's emotions. The emotion estimation is performed using, for example, an emotion analysis algorithm. The emotion analysis algorithm analyzes the user's facial expression, voice, text, etc. to estimate the user's emotions. Some or all of the above-described processing in the transmission unit may be performed using, for example, AI, or may be performed without AI. For example, the transmission unit can adjust the timing using an AI model that inputs user emotion data and outputs the transmission timing.

[0133] The processing flow of the second embodiment will be briefly explained below.

[0134] Step 1: The reader reads contacts. Contacts include emails, messages, notifications, etc. The reader can retrieve emails from the mail server, messages from the messaging app, and notifications from the notification system. The reader can also set the format of the contacts and the timing of reading. Step 2: The analysis unit uses natural language processing technology to analyze the content of the message read by the reading unit and determine the emotion and temperature. Emotions include positive, negative, neutral, etc., and temperature includes urgency, importance, etc. The analysis unit analyzes the content of the message using techniques such as morphological analysis, grammatical analysis, and semantic analysis. Step 3: The summary generator generates a concise summary based on the content analyzed by the analyzer. The summary is generated based on the length of the text and the importance of the information being summarized. The summary generator uses a generation AI to concisely summarize the content of the communication. Step 4: The selection unit provides an interface for the user to select a reply pattern. The interface may be a GUI, a CLI, a web interface, etc. The selection unit provides a button or a menu for the user to select a reply pattern. Step 5: The reply generator generates a reply based on the pattern selected by the selector. The reply includes grammar checks, content appropriateness checks, etc. The reply generator uses a generation AI to generate a reply based on the selected pattern. Step 6: The sender automatically sends the generated reply message. This includes confirming the timing and destination of the message. The sender can send emails through a mail server, messages through messaging apps, and notifications through a notification system.

[0135] 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.

[0136] 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 the generative AI include a neural network (NN) and a neural network (NN). 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 (e.g., still image data or video data). 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 one or more data formats of voice data, text data, image data, etc. 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 may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0137] 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.

[0138] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0139] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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).

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0153] 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.

[0154] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0155] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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).

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0169] 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.

[0170] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0171] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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).

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0186] 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.

[0187] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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).

[0192] 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.

[0193] 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."

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] [Explanation of symbols]

[0207] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a reading unit for reading the contact; an analysis unit that analyzes the content of the message read by the reading unit and determines emotions and feelings; a summary generation unit that generates a summary based on the content analyzed by the analysis unit; a selection unit that selects a reply pattern based on the summary generated by the summary generation unit; a reply generation unit that generates a reply message based on the pattern selected by the selection unit; a sending unit that automatically sends the reply message generated by the reply generating unit; Equipped with A system characterized by:

2. The analysis unit Analyzing emotions and feelings using natural language processing technology 2. The system of claim 1.

3. The summary generation unit generating a concise summary based on the content analyzed by the analysis unit; 2. The system of claim 1.

4. The selection unit Provides an interface for users to select a reply pattern 2. The system of claim 1.

5. The reply generation unit Generate a reply based on the selected pattern 2. The system of claim 1.

6. The transmission unit Automatically send generated replies 2. The system of claim 1.

7. Equipped with a selection setting section that provides settings for selecting automation or semi-automation for internal and external use 2. The system of claim 1.

8. The reading unit Infer user sentiment and adjust communication loading times based on the estimated user sentiment 2. The system of claim 1.

Images