system

Abstract

We provide the system. [Solution] Means for receiving messages, A means for analyzing received messages based on natural language processing, A method for automatically generating reply text using a template based on the analysis results, A method for extracting tasks from messages, A means of saving the extracted tasks to a task management system, A means of notifying the user of the generated reply and extracted tasks, A system that includes a means of sending an automatic reply after user confirmation.

Description

Technical Field

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

Background Art

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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In conventional text-based business communication, a lot of time is spent. Especially when a reply is required, the user has to do it manually, which is a great burden. In addition, the received messages often lead not only to simple replies but also to schedule adjustments and task generation, and there is a lack of means for efficiently managing these. Therefore, there is a need for a system that can simultaneously achieve time savings and efficient task management.

Means for Solving the Problems

[0005] This invention provides a system that automatically receives messages, analyzes their content based on natural language processing, and automatically generates appropriate reply messages using templates. Furthermore, it extracts tasks from received messages and stores them in a task management system, enabling centralized management of messages and tasks. This system notifies the user of the generated reply messages and extracted tasks, and can automatically send replies after the user confirms them. This significantly reduces the user's workload, saving time and enabling efficient task management.

[0006] "Messages" refer to text-based business communications such as email and chat.

[0007] "Means of receiving" refers to the function that allows users to receive messages through their device.

[0008] "Natural language processing" refers to the technology that enables computers to understand and analyze human language.

[0009] "Means of analysis" refers to the function of analyzing received messages using a natural language processing engine and extracting important information.

[0010] A "template" refers to a standardized format for generating replies, or a pre-defined sentence structure.

[0011] "Methods for automatically generating reply messages" refers to a function that automatically generates appropriate reply messages using templates based on analysis results.

[0012] A "task" refers to an action, schedule, or work item extracted from a received message.

[0013] "Methods for extracting tasks" refers to a function that identifies action items and key phrases from the content of a message and automatically extracts tasks.

[0014] A "task management system" refers to a system for saving and managing extracted tasks.

[0015] "Means of saving" refers to the function of registering and recording extracted tasks in a task management system.

[0016] "Means of notifying the user" refers to a function that informs the user of the generated reply and extracted tasks.

[0017] "Method for sending automatic replies" refers to a function that automatically sends a reply message to the recipient after the user has confirmed it.

[0018] A "key phrase extraction algorithm" refers to a computational method for identifying and extracting important phrases within a message.

[0019] A "template engine" refers to a software component that dynamically generates replies and other text based on templates. [Brief explanation of the drawing]

[0020] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0021] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0022] First, the language used in the following description will be explained.

[0023] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0024] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0025] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0026] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0027] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0028] [First Embodiment]

[0029] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0030] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0031] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0032] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0033] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0034] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0035] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0036] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0038] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0039] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0040] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0041] This invention is a system designed to streamline text-based business communication and reduce user effort. The system includes processes such as message reception, content analysis, automatic generation of replies and tasks, user notifications, and automatic reply sending. Its specific operation is described below in natural language.

[0042] System Configuration

[0043] 1. Receiving a message

[0044] Users receive emails and chat messages on their devices. This receiving operation is performed through typical email clients and chat applications.

[0045] 2. Message Analysis

[0046] The received message is automatically sent from the terminal to the server. The server sends the message content to a natural language processing (NLP) engine for analysis.

[0047] 3. Automatic generation of reply messages

[0048] The server automatically generates a reply using a template engine based on the analysis results. The template engine generates an appropriate reply by filling in the necessary information based on a pre-configured template format.

[0049] Specific example:

[0050] Message received: "I'd like to schedule a meeting next Tuesday at 2 PM. Would that work for you?"

[0051] Automated reply: "Hello, thank you for contacting me. Tuesday at 2 PM next week is fine. Thank you."

[0052] 4. Task Extraction

[0053] The server extracts tasks from the received messages. A key phrase extraction algorithm is used to identify important action items, dates, times, and other relevant information.

[0054] Specific example:

[0055] Received message: "I would like to schedule a meeting for next Tuesday at 2 PM."

[0056] Extracted task: "Task: Schedule a meeting, Due date: Next Tuesday at 2 PM"

[0057] 5. Saving and managing tasks

[0058] The server stores the extracted tasks in a task management system. The task management system centrally manages information such as task deadlines, priorities, and assigned personnel, making it easy for users to access.

[0059] 6. User Notifications

[0060] The server notifies the terminal of the generated reply and extracted tasks. The user receives this notification and checks the reply and task details.

[0061] 7. Send automatic reply

[0062] The user reviews the reply message and task details, makes any necessary corrections, and then gives a confirmation signal. Based on this signal, the device automatically sends a reply message to the server, which then sends the reply to the recipient.

[0063] This system automates the entire process, from analyzing received messages and generating replies to extracting and managing tasks. This significantly reduces the time and effort users spend on daily business communication.

[0064] The following describes the processing flow.

[0065] Step 1: Receive message

[0066] Users receive emails and chat messages on their devices. These messages are received from mail servers and chat servers.

[0067] The terminal temporarily stores the received message and sends its contents to the server.

[0068] Step 2: Sending a message

[0069] The terminal sends the content of the received message to the server. The message is transferred to the server as text data.

[0070] Step 3: Message Analysis

[0071] The server sends the received message to a natural language processing (NLP) engine. The NLP engine analyzes the message content and extracts important information.

[0072] Specifically, the NLP engine identifies the date, time, location, and request from the message and outputs the analysis results.

[0073] Step 4: Generating a reply

[0074] The server generates a reply using a template engine based on the analysis results obtained from the NLP engine.

[0075] The template engine creates a reply by embedding the analysis results into a pre-prepared template.

[0076] Step 5: Task Extraction

[0077] The server uses a task engine to extract tasks from the message analysis results.

[0078] The task engine identifies action items and key phrases within a message and generates a task list.

[0079] Step 6: Save the task

[0080] The server saves the extracted tasks to the task management system.

[0081] A task management system centralizes task details (deadlines, priorities, etc.) and makes them easily accessible to users.

[0082] Step 7: User Notifications

[0083] The server notifies the terminal of the generated reply message and the extracted task content.

[0084] The user receives a notification on their device and checks the generated reply and task details.

[0085] Step 8: User verification and correction

[0086] The user reviews the generated reply and task details on their device and makes corrections if necessary.

[0087] Once the corrections are complete, the user enters a confirmation instruction into the terminal.

[0088] Step 9: Send automatic reply

[0089] When the terminal receives confirmation from the user, it sends that information to the server.

[0090] The server automatically sends the confirmed reply to the recipient.

[0091] Through the above processing steps, users can efficiently conduct text-based business communication without any extra effort.

[0092] (Example 1)

[0093] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0094] In business communication, responding to received messages and managing related tasks is time-consuming and laborious, reducing user efficiency. Furthermore, accurately analyzing message content and responding quickly and precisely is crucial for smooth business operations, but manual processes have limitations. Therefore, there is a need for systems that automate these processes and reduce user effort and time.

[0095] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0096] In this invention, the server includes means for receiving electronic communication messages using a personal terminal, means for transmitting the received electronic communication messages to a central processing unit for analysis, means for the central processing unit to analyze the message content using a natural language processing model, means for automatically generating a reply message using a predefined template based on the analysis results, means for extracting tasks from the electronic communication messages, means for storing the extracted tasks in a task management device, means for notifying the personal terminal of the automatically generated reply message and the extracted tasks, and means for sending an automatic reply message after user confirmation. This makes it possible to automate a series of processes from analyzing received messages to generating reply messages, extracting tasks, and managing them.

[0097] A "personal device" is an electronic device used by a user to receive and send emails and chat messages.

[0098] "Electronic communication messages" refer to digital text messages such as emails and chat messages that are sent and received via the internet or other communication networks.

[0099] A "central processing unit" is a computer server or cloud computing system that analyzes received electronic communication messages.

[0100] A "natural language processing model" is a machine learning model or algorithm that analyzes the content of an incoming message and understands and generates human language.

[0101] A "predefined template" is a pre-configured text format used when automatically generating reply messages.

[0102] A "template engine" is a software development tool that combines templates and dynamic data to generate content.

[0103] A "task management device" is software or a system used to manage and track extracted tasks.

[0104] A "key phrase extraction algorithm" is an algorithm used to identify important phrases and information from electronic communication messages.

[0105] An "automatic reply message" is a message that the system automatically sends after the user has reviewed or corrected something.

[0106] This invention is a system for streamlining text-based business communication and reducing user effort. The system includes processes for receiving messages, analyzing content, automatically generating replies and tasks, notifying users, and sending automatic replies.

[0107] System Configuration

[0108] Message received

[0109] Users receive emails and chat messages on their personal devices. This receiving operation is performed through common email and chat applications (e.g., Outlook, Slack) that process electronic communication messages.

[0110] Message Controller

[0111] Received electronic communication messages are automatically sent from the terminal to the central processing unit (CCU). The CCU (e.g., a cloud server) analyzes the message content using a natural language processing model (e.g., Google® Cloud NLP, Amazon Comprehend). The data analyzed by the NLP engine is processed in various ways, such as summarization, categorization, and sentiment analysis.

[0112] Automatically generate reply messages

[0113] The central processing unit automatically generates reply messages using a template engine (e.g., Mustache, Handlebars) based on the analysis results. Predefined templates contain the basic structure of appropriate reply messages, into which the analysis data is embedded.

[0114] Specific example:

[0115] Message received: "I'd like to schedule a meeting next Tuesday at 2 PM. Would that work for you?"

[0116] Automated reply: "Hello, thank you for contacting me. Tuesday at 2 PM next week is fine. Thank you."

[0117] Task extraction

[0118] The central processing unit extracts tasks from electronic communication messages. Key phrase extraction algorithms (e.g., TF-IDF, BERT) are used to identify important action items, dates, and times.

[0119] Specific example:

[0120] Received message: "I would like to schedule a meeting for next Tuesday at 2 PM."

[0121] Extracted task: "Task: Schedule a meeting, Due date: Next Tuesday at 2 PM"

[0122] Task saving and management

[0123] The central processing unit saves the extracted tasks to a task management system (e.g., Trello, Asana). The task management system centrally manages information such as task deadlines, priorities, and assignees, making it easily accessible to users.

[0124] User notifications

[0125] The central processing unit notifies the user's personal device of the generated reply and extracted tasks. The device then displays the generated content to the user via push notifications or in-app notifications.

[0126] Automatic reply sent

[0127] After the user reviews the reply and task details and makes any necessary corrections, the personal device sends a confirmation message. The device then sends this message to the central processing unit, which automatically sends a reply message to the recipient.

[0128] Example of a prompt

[0129] Message component:

[0130] The prompt text that users use to have a natural language processing engine parse their message:

[0131] Please analyze the following message: "I would like to schedule a meeting next Tuesday at 2 PM. Would that work for you?"

[0132] Reply text generation:

[0133] Prompts used to generate automated replies using a template engine:

[0134] "Please generate the following reply: Use the template 'Hello, thank you for contacting me. [Date and time] is fine. Thank you.' and fill in 'Next Tuesday at 2 PM' as the date and time."

[0135] This system automates a series of processes, from analyzing received messages and generating replies to extracting and managing tasks, allowing users to significantly reduce the time and effort spent on daily business communication.

[0136] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0137] Step 1:

[0138] A user receives electronic communication messages on their personal device. The device uses a common email client or chat application (e.g., Outlook, Slack) to receive new messages.

[0139] Input: New email or chat message

[0140] Output: Forward received messages to the server

[0141] Step 2:

[0142] The terminal automatically sends received electronic communication messages to the server. The terminal sends the received message information via the server's API endpoint.

[0143] Input: Received message sent from the device

[0144] Output: Preparing the server for message parsing

[0145] Step 3:

[0146] The server sends incoming messages to a natural language processing (NLP) engine for analysis. The server uses natural language processing models such as Google Cloud NLP or Amazon Comprehend to summarize the message content, analyze sentiment, and categorize it.

[0147] Input: Received message

[0148] Data processing: Analysis using an NLP engine (summarization, sentiment analysis, categorization).

[0149] Output: Analysis results (summary text, sentiment score, category information, etc.)

[0150] Step 4:

[0151] The server uses a template engine based on the analysis results to automatically generate a reply. The reply is created by embedding the necessary data (e.g., date and time, action item) into a predefined template.

[0152] Input: Analysis results and template

[0153] Data processing: Use a template engine to embed analysis results into a template.

[0154] Output: Automated reply

[0155] Specific examples of actions:

[0156] Template: "Hello, thank you for contacting me. [Date and time] is fine. Thank you."

[0157] Analysis result: "Date and time: Next Tuesday, 2 PM"

[0158] Generated reply: "Hello, thank you for contacting me. Tuesday at 2 PM next week is fine. Thank you."

[0159] Step 5:

[0160] The server extracts tasks from electronic communication messages. The server uses key phrase extraction algorithms (e.g., TF-IDF, BERT) to identify important action items, dates, and times from the messages.

[0161] Input: Received message

[0162] Data processing: Analysis using a key phrase extraction algorithm.

[0163] Output: Extracted tasks

[0164] Specific examples of actions:

[0165] Received message: "I would like to schedule a meeting for next Tuesday at 2 PM."

[0166] Extracted task: "Task: Schedule a meeting, Due date: Next Tuesday at 2 PM"

[0167] Step 6:

[0168] The server saves the extracted tasks to a task management system. The server uses task management tools such as Trello or Asana to centrally manage tasks.

[0169] Input: Extracted tasks

[0170] Data processing: Adding tasks to a task management system.

[0171] Output: Saved tasks

[0172] Step 7:

[0173] The server notifies the device of the generated reply and extracted tasks. The device then displays this information to the user via push notifications or in-app notifications.

[0174] Input: Auto-generated reply text, extracted tasks

[0175] Output: Notification to the user

[0176] Step 8:

[0177] The user reviews the reply and task details and makes corrections as needed. A confirmation message is sent from the terminal to the server.

[0178] Input: Instructions for user correction or confirmation.

[0179] Output: Confirmation complete

[0180] Step 9:

[0181] After the device receives confirmation, it automatically sends a reply message to the server. The server then forwards that message to the appropriate recipient.

[0182] Input: Confirmation complete instructions

[0183] Output: Automated reply message sent to the recipient

[0184] These steps automate the entire process, from receiving messages to generating and sending replies, and even managing tasks. This significantly improves the efficiency of users' business communications.

[0185] (Application Example 1)

[0186] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0187] In modern content delivery services, there is a demand for quick and accurate responses to user feedback and request messages. Furthermore, manually performing message analysis and task extraction is time-consuming and labor-intensive, hindering efficient work. Automating processes such as task management and reply generation is also required to reduce the burden on operators and enable faster responses. Current systems struggle to meet these requirements, resulting in limitations in improving the user experience.

[0188] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0189] In this invention, the server includes means for receiving messages, means for analyzing received messages based on natural language processing, means for automatically generating reply text using templates based on the analysis results, means for extracting tasks from messages, means for storing the extracted tasks in a task management system, means for notifying the user of the generated reply text and extracted tasks, means for sending an automatic reply after user confirmation, means for analyzing received feedback and requests and generating appropriate automatic reply texts, and means for extracting and managing tasks for content creation based on the task extraction results. This makes it possible to automate a series of processes from analyzing user messages and extracting tasks to task management and reply text generation, significantly reducing the burden on operators and enabling quick and efficient responses.

[0190] "Means of receiving messages" refers to the means of receiving messages sent by users via email, chat applications, etc.

[0191] Natural language processing is a set of techniques that use computers to understand, interpret, and manipulate human language, and is used to analyze the content of received messages.

[0192] "Methods for automatically generating reply text using templates" refer to methods for automatically generating appropriate reply text by filling in necessary information based on a pre-configured template format.

[0193] "Task extraction methods" refer to methods for identifying important action items, deadlines, etc., from the content of received messages using key phrase extraction algorithms, and extracting them as tasks.

[0194] A "task management system" is a system that stores and manages extracted tasks along with information such as deadlines, priorities, and assigned personnel, making them easily accessible to users.

[0195] "Means of notifying the user" refers to means of notifying the user's device of the generated reply message and the contents of the extracted tasks.

[0196] "Method for sending automatic replies" refers to a method for automatically sending a final reply after the user has reviewed and revised it.

[0197] "Means for analyzing feedback and requests" refers to methods for analyzing the content of user feedback and request messages.

[0198] "Means for extracting and managing tasks for content creation" refers to methods for identifying and managing the tasks necessary for content creation based on tasks extracted from received messages.

[0199] This invention provides a system that automates message processing in content distribution services, thereby reducing the burden on operators. This system includes a process that automatically analyzes received messages, generates replies, and extracts and manages tasks.

[0200] System Configuration

[0201] Message received

[0202] First, the system receives feedback and request messages sent by users via email or chat tools. This allows the system to incorporate messages from users.

[0203] Message Controller

[0204] Received messages are automatically sent from the terminal to the server. The server analyzes the message content using a natural language processing (NLP) engine (e.g., NLTK). At this stage, the message content is understood, and information necessary for generating replies and tasks is extracted.

[0205] Automatically generate reply messages

[0206] The server uses a template engine to generate an appropriate reply based on the analysis results. The template engine constructs the reply by embedding the analyzed information according to a pre-configured template format.

[0207] Task extraction and management

[0208] The server uses a key phrase extraction algorithm to extract tasks from messages. These extracted tasks are identified as action items and deadlines necessary for content creation. These tasks are stored in a task management system and centrally managed along with information such as deadlines, priorities, and assigned personnel.

[0209] User notifications and automatic reply sending

[0210] The server notifies the terminal of the generated reply and extracted tasks. The user receives this notification and reviews and modifies the reply and task details. After review, the terminal automatically sends a confirmation message to the server and sends the final reply message.

[0211] This makes it possible to automate a series of processes, from analyzing user messages and extracting tasks to managing tasks and generating replies, significantly reducing the burden on administrators and enabling quick and efficient responses.

[0212] Specific examples

[0213] For example, if a user sends a message saying, "I'd like to schedule a meeting next Friday at 3 PM to discuss new video content. Would that work for you?", the system will receive this message and automatically generate a reply like this:

[0214] "Hello, thank you for contacting me. Friday at 3 PM next week is fine. Thank you."

[0215] The extracted tasks also include items such as "Schedule a meeting about new video content, deadline: next Friday at 3 PM."

[0216] Example of a prompt

[0217] The following is an example of a specific prompt message:

[0218] Please generate a reply to the following message: "I would like to schedule a meeting next Friday at 3 PM to discuss new video content. Would that work for you?"

[0219] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0220] Step 1:

[0221] The device receives user feedback and request messages via email or chat tools. These messages are imported into the system in text format. The input is the user's message, and the output is the storage of the received message.

[0222] Step 2:

[0223] The terminal sends the received message to the server. Here, the received message data is transferred to the server. The input is the received message, and the output is the transfer of the message data to the server.

[0224] Step 3:

[0225] The server analyzes the content of received messages using a natural language processing (NLP) engine. Specifically, it uses a natural language processing library such as NLTK to tokenize the messages and extract key phrases. The input is the message data forwarded to the server, and the output is the analysis result.

[0226] Step 4:

[0227] The server automatically generates a reply based on the analysis results using a template engine. The template engine embeds the analyzed key phrases and time information into a pre-configured template to create an appropriate reply. The input is the analysis result, and the output is the automatically generated reply.

[0228] Step 5:

[0229] The server executes a keyphrase extraction algorithm to extract tasks from messages. The extracted tasks include important information such as action items and deadlines. The input is the parsing result, and the output is the extracted task information.

[0230] Step 6:

[0231] The server saves the extracted task information to the task management system. The task management system stores information such as deadlines, priorities, and assigned personnel in an easy-to-manage format. The input is the extracted task information, and the output is the tasks stored in the task management system.

[0232] Step 7:

[0233] The server notifies the terminal of the generated reply and extracted tasks. The terminal displays this information to the user and requests confirmation. The input is the automatically generated reply and extracted task information, and the output is the notification to the user.

[0234] Step 8:

[0235] The user checks the notification on their device and modifies the reply and task details as needed. The input is the notified reply and task information, and the output is the modified reply and task information.

[0236] Step 9:

[0237] User verification is complete, and the terminal sends a verification completion instruction to the server. The server sends a final reply message. The input is the verification completion instruction and the revised reply text, and the output is the sending of the final reply message.

[0238] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0239] This invention is a system designed to streamline text-based business communication and reduce user effort. The system combines message reception, content analysis, automatic generation of replies and tasks, user notifications, automatic reply sending, and an emotion engine that recognizes user sentiment. The specific operation of the entire system is described below.

[0240] System Configuration

[0241] 1. Receiving a message

[0242] Users receive emails and chat messages on their devices. This receiving operation is performed through common email clients and chat applications.

[0243] 2. Sending a message

[0244] The terminal automatically sends the content of the received message to the server. The message is transferred to the server as text data.

[0245] 3. Message Analysis

[0246] Received messages are analyzed by a natural language processing (NLP) engine on the server. This analysis extracts important information from the message, such as the date, time, location, and request.

[0247] 4. Emotion recognition

[0248] The server sends the analyzed message to the emotion engine, which evaluates the user's emotions. The emotion engine identifies emotions such as positive, negative, or neutral from the message.

[0249] Specific example:

[0250] Message received: "I'm very sorry to trouble you, but could I cancel tomorrow's meeting?"

[0251] Emotional engine evaluation: Negative

[0252] 5. Generating a reply

[0253] The server generates a reply using a template engine based on the results obtained from the NLP engine and the emotion engine. The template engine creates a reply with an appropriate tone, taking emotion evaluation into consideration.

[0254] Specific example:

[0255] Input: NLP analysis results, emotion assessment (negative)

[0256] output:

[0257] "Hello, thank you for your understanding regarding the cancellation of tomorrow's meeting. We will contact you later with a new date."

[0258] 6. Task Extraction

[0259] The server uses a task engine to extract tasks from the message analysis results. The task engine identifies action items and key phrases in the message and generates a task list.

[0260] Specific example:

[0261] Message received: "Please cancel tomorrow's meeting and reschedule it."

[0262] Extracted task: "Task: Schedule a new meeting, Deadline: Undetermined"

[0263] 7. Saving and managing tasks

[0264] The server stores the extracted tasks in a task management system. The task management system centrally manages detailed task information (deadlines, priorities, etc.) and makes it easily accessible to users.

[0265] 8. User Notifications

[0266] The server notifies the terminal of the generated reply and the extracted task content. The user receives this notification and checks the reply and task content.

[0267] 9. User verification and correction

[0268] The user reviews the generated reply and task details on their device and makes corrections if necessary. Once corrections are complete, the user enters a confirmation message into their device.

[0269] 10. Send automatic reply

[0270] When the terminal receives confirmation from the user, it sends that information to the server. The server automatically sends the confirmed reply to the recipient.

[0271] Through the processing steps described above, users can efficiently conduct text-based business communication without any hassle. Furthermore, the combination of emotion engines enables more appropriate and emotionally resonant replies.

[0272] The following describes the processing flow.

[0273] Step 1: Receive message

[0274] Users receive emails and chat messages on their devices. This receiving operation is performed through common email clients and chat applications.

[0275] Step 2: Send Message

[0276] The terminal automatically sends the content of the received message to the server. It is transferred to the server as text data.

[0277] Step 3: Message Analysis

[0278] The server sends the received message to a natural language processing (NLP) engine. The NLP engine analyzes the message content and extracts important information.

[0279] For example, the date, time, location, and details of the request will be specified.

[0280] Step 4: Emotion Recognition

[0281] The server sends the analyzed message to the sentiment engine to evaluate the user's sentiment. The sentiment engine identifies sentiments such as positive, negative, and neutral from the message.

[0282] As an example, a negative sentiment is identified from the expression "I'm very sorry to trouble you..." in the message.

[0283] Step 5: Reply message generation

[0284] The server uses the template engine to generate a reply message based on the results obtained from the NLP engine and the sentiment engine.

[0285] The template engine creates a reply message in an appropriate tone considering the analysis results and sentiment evaluation.

[0286] Step 6: Task extraction

[0287] The server extracts tasks from the message using the task engine. The task engine identifies action items and key phrases in the message and generates a task list.

[0288] As an example, the task "Task: Set a new meeting schedule" is extracted from the request "Please set a new schedule".

[0289] Step 7: Task saving

[0290] The server saves the extracted tasks to the task management system. The task management system centrally manages the detailed information of the tasks (due date, priority, etc.).

[0291] Step 8: User notification

[0292] The server notifies the terminal of the generated reply message and the content of the extracted tasks. The reply message and task details are displayed to the user.

[0293] Step 9: User verification and correction

[0294] The user reviews the generated reply and task details on their device. If necessary, the user modifies the reply and task.

[0295] The user enters confirmation instructions into the terminal.

[0296] Step 10: Send automatic reply

[0297] When the terminal receives confirmation from the user, it sends that information to the server.

[0298] The server automatically sends the confirmed reply to the recipient.

[0299] This process allows users to engage in efficient, emotionally sensitive, and effortless text-based business communication.

[0300] (Example 2)

[0301] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0302] In traditional text-based business communication, users had to spend considerable time analyzing received messages, drafting appropriate replies, and extracting and managing tasks. This manual process was time-consuming and labor-intensive, increasing the burden on users. Furthermore, it resulted in the generation of impersonal, mechanical replies that lacked emotional considerations, leading to a decline in communication quality.

[0303] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0304] In this invention, the server includes means for receiving a message, means for analyzing the received message based on natural language processing, means for recognizing emotion based on the analysis result, means for automatically generating a reply message using a template in consideration of the emotion evaluation, means for extracting a task from the message, means for storing the extracted task in a task management system, means for notifying the user of the generated reply message and the extracted task, and means for sending an automatic reply after the user's confirmation. Thereby, the user can perform message analysis, generation of an appropriate reply message, and task extraction and management in an integrated manner without much effort. Furthermore, the quality of communication can be improved by the reply message that takes emotion into consideration.

[0305] The "means for receiving a message" is a system component for the user to receive text-based messages such as e-mails and chat messages through a terminal.

[0306] The "means for analyzing based on natural language processing" is a system component including a natural language processing engine used to analyze the received message and extract important information (date and time, location, request items, etc.).

[0307] The "means for recognizing emotion" is a system component including an emotion engine for evaluating the user's emotion from the analyzed message and identifying emotions such as positive, negative, and neutral.

[0308] The "means for automatically generating a reply message using a template in consideration of the emotion evaluation" is a system component that automatically generates a reply message with an appropriate tone using a template engine based on the analysis result of natural language processing and the emotion evaluation.

[0309] The "means for extracting a task" is a system component including a task engine for extracting action items and key phrases from the analysis result of the message and identifying specific tasks.

[0310] "Means of saving to a task management system" refers to system components that include task management tools used to save and centrally manage extracted tasks.

[0311] "Means for notifying the user of the generated reply and extracted tasks" refers to system components for notifying the user's terminal of the content of the generated reply and tasks.

[0312] "Method for sending an automatic reply after user confirmation" refers to a system component that automatically sends a reply after the user has reviewed and corrected the generated reply text and task content.

[0313] This invention is a system designed to streamline text-based business communication and reduce the burden on users. Specifically, this system receives messages, analyzes their content, recognizes sentiment, automatically generates replies and tasks, notifies users, and sends automatic replies. The implementation method of this system is described below.

[0314] System configuration and operation

[0315] 1. Receiving a message

[0316] Users receive emails and chat messages using their devices (such as PCs and smartphones). Applications used include Outlook, Gmail, and Slack. When a user receives a new message, its content is saved on their device.

[0317] 2. Sending a message

[0318] The terminal sends the received message to the server. The message is transferred to the server in text data format. This process involves sending data via HTTP requests or WebSockets.

[0319] 3. Message Analysis

[0320] The server sends received messages to a natural language processing (NLP) engine for analysis. The NLP engine used may include the Google Cloud Natural Language API. Through analysis, important information (such as date, time, location, and request details) is extracted from the message.

[0321] 4. Emotion recognition

[0322] The server sends the analyzed message to an emotion recognition engine to evaluate the user's emotions. Engines used include IBM Watson® Tone Analyzer, which identifies emotions such as positive, negative, and neutral from the message.

[0323] Specific example:

[0324] Message received: "I'm very sorry to trouble you, but could I cancel tomorrow's meeting?"

[0325] Emotional engine evaluation: Negative

[0326] 5. Generating a reply

[0327] The server generates a reply using a template engine based on the results obtained from the NLP engine and the emotion engine. The template engine used is typically Handlebars.js, which generates a reply with an appropriate tone that takes emotion evaluation into account.

[0328] Specific example:

[0329] Input: NLP analysis results (request: meeting cancellation), emotion evaluation (negative)

[0330] Output: "Hello, thank you for your understanding regarding the cancellation of tomorrow's meeting. We will contact you later with a new date."

[0331] 6. Task Extraction

[0332] The server uses a task engine to extract tasks from the message analysis results. Task engines such as Apache® OpenNLP identify action items and key phrases within the message and generate a task list.

[0333] Specific example:

[0334] Message received: "Please cancel tomorrow's meeting and reschedule it."

[0335] Extracted task: "Task: Schedule a new meeting, Deadline: Undetermined"

[0336] 7. Saving and managing tasks

[0337] The server saves the extracted tasks to a task management system. Task management systems such as Trello or Asana are used to centrally manage detailed task information (deadlines, priorities, etc.).

[0338] 8. User Notifications

[0339] The server notifies the terminal of the generated reply and the extracted task content. The user receives this notification and checks the reply and task content.

[0340] 9. User verification and correction

[0341] The user reviews the generated reply and task details on their device and makes corrections if necessary. Once corrections are complete, the user enters a confirmation message into their device.

[0342] Specific example:

[0343] The user modifies the reply to "Thank you for your understanding" and clicks "Confirmation Complete".

[0344] 10. Send automatic reply

[0345] The terminal sends a confirmation message from the user to the server. The server then automatically sends a reply to the recipient based on the confirmed message.

[0346] Example of a prompt:

[0347] Message received: "I'm very sorry to trouble you, but could I cancel tomorrow's meeting?"

[0348] Emotional engine rating: "Negative"

[0349] NLP analysis result: "Cancellation request"

[0350] Prompt to input to the generating AI model: "The user's sentiment rating for this message has been determined to be negative. Please create a reply in an appropriate tone to address the cancellation request."

[0351] As described above, this system allows users to perform message analysis, generate appropriate replies, and extract and manage tasks in a unified manner without any extra effort. Furthermore, by utilizing the sentiment engine, it is possible to generate more appropriate and emotionally resonant replies.

[0352] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0353] Detailed explanation of the processing steps

[0354] Step 1: Receiving a message

[0355] The user receives emails and chat messages on their device.

[0356] input:

[0357] Email or chat message

[0358] Data processing:

[0359] none

[0360] output:

[0361] Received message data

[0362] Specific actions:

[0363] A user receives a new email using the Gmail application. For example, they receive an email that says, "I would like to cancel tomorrow's meeting."

[0364] Step 2: Sending a message

[0365] The terminal sends the received message to the server.

[0366] input:

[0367] Received message data

[0368] Data processing:

[0369] Convert the message to JSON format

[0370] output:

[0371] HTTP POST request to the server

[0372] Specific actions:

[0373] The terminal converts the received message into JSON format and sends it to the server as an HTTP POST request.

[0374] Step 3: Message Analysis

[0375] The server sends the received message to a natural language processing (NLP) engine for analysis.

[0376] input:

[0377] JSON data of the received message

[0378] Data processing:

[0379] Information extraction using natural language processing

[0380] output:

[0381] Analysis results (request details, date, time, location, etc.)

[0382] Specific actions:

[0383] The server uses an NLP engine (e.g., Google Cloud Natural Language API) to extract important information such as "cancellation of a meeting and scheduling of a new date."

[0384] Step 4: Emotion Recognition

[0385] The server sends the analyzed message to the emotion recognition engine, which then evaluates the user's emotions.

[0386] input:

[0387] Analyzed message data

[0388] Data processing:

[0389] sentiment analysis

[0390] output:

[0391] Emotional evaluation (positive, negative, neutral, etc.)

[0392] Specific actions:

[0393] The server uses an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to identify the emotion as "negative."

[0394] Step 5: Generating a reply

[0395] The server generates a reply using a template engine based on the NLP analysis results and sentiment evaluation.

[0396] input:

[0397] NLP analysis results, emotion evaluation

[0398] Data processing:

[0399] Generate reply text using a template engine.

[0400] output:

[0401] Generated reply

[0402] Specific actions:

[0403] The server uses the Handlebars.js template engine to generate a reply message that reads, "Hello, thank you for your understanding regarding the cancellation of tomorrow's meeting. We will contact you later with a new date."

[0404] Step 6: Task Extraction

[0405] The server uses a task engine to extract tasks from the message analysis results.

[0406] input:

[0407] NLP analysis results

[0408] Data processing:

[0409] Task extraction algorithm

[0410] output:

[0411] Extracted tasks

[0412] Specific actions:

[0413] The server uses Apache OpenNLP to extract a task called "Set up a new meeting" and sets its name to "Task: Set up a new meeting, Due date: Undetermined".

[0414] Step 7: Saving and managing tasks

[0415] The server saves the extracted tasks to the task management system.

[0416] input:

[0417] Extracted tasks

[0418] Data processing:

[0419] Save to task management system

[0420] output:

[0421] Tasks saved in the task management system

[0422] Specific actions:

[0423] The server uses the Trello API to save the extracted tasks as new cards.

[0424] Step 8: User Notifications

[0425] The server notifies the terminal of the generated reply message and the extracted task content.

[0426] input:

[0427] Generated reply text, extracted tasks

[0428] Data processing:

[0429] Generating push notifications

[0430] output:

[0431] Push notifications to your device

[0432] Specific actions:

[0433] The server sends a push notification to the device, and the user checks the "reply message" and "task details" on the screen.

[0434] Step 9: User verification and correction

[0435] The user reviews the generated reply and task details on their device and makes corrections if necessary.

[0436] input:

[0437] Generated reply text, extracted tasks

[0438] Data processing:

[0439] User modifications

[0440] output:

[0441] Revised reply, task

[0442] Specific actions:

[0443] The user modifies the reply to "Thank you for your understanding" and clicks "Confirmation Complete".

[0444] Step 10: Send automatic reply

[0445] The device sends a confirmation message from the user to the server and then sends a confirmed reply to the other party.

[0446] input:

[0447] Revised reply, user confirmation complete instruction

[0448] Data processing:

[0449] Sending a reply

[0450] output:

[0451] Reply sent to the recipient

[0452] Specific actions:

[0453] The terminal notifies the server that "confirmation complete," and the server sends a "confirmed reply" to the recipient as an email.

[0454] (Application Example 2)

[0455] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0456] In conventional factory robot systems, communication, reporting, and error message processing between robots were handled individually, resulting in difficulties in efficient operation. Furthermore, there was no system that could generate appropriate, emotion-based responses while reducing the burden on the user. Therefore, there was a need for a system that provides automated, advanced communication between robots and emotion-responsive response capabilities.

[0457] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving messages, means for analyzing the received messages based on natural language processing, means for automatically generating a reply using a template based on the analysis results, means for extracting tasks from messages, means for storing the extracted tasks in a task management system, means for notifying the user of the generated reply and extracted tasks, means for sending an automatic reply after user confirmation, means for evaluating emotions from the analyzed messages, means for selecting a reply template based on the evaluated emotions, means for factory robots to report status and request tasks from other robots and managers, and means for analyzing received error messages and performing automatic replies and task reassignments. This makes it possible to streamline communication between robots and realize appropriate responses based on emotions.

[0458] "Means of receiving messages" refers to the ability to electronically acquire messages from robots or users.

[0459] "Natural language processing" is a technology that analyzes received messages as text data and understands and processes their content.

[0460] "Method for automatically generating reply messages" refers to a function that automatically creates appropriate reply messages using templates based on analysis results.

[0461] "Methods for extracting tasks from messages" refers to a function that identifies and extracts specific work items or action items from the content of a message.

[0462] A "task management system" is a system for recording, monitoring, and managing extracted tasks.

[0463] "Means of notifying the user" refers to a function that informs the user of the generated reply and extracted tasks.

[0464] "Method for sending automatic replies" refers to a function that automatically sends a generated reply message to the recipient after user confirmation.

[0465] "Methods for evaluating emotions" refer to technologies that identify emotions such as positive and negative from analyzed messages.

[0466] The "means of selecting a reply template" refer to the function of selecting a template to generate a reply with an appropriate tone based on the evaluated emotion.

[0467] "Robot status reporting" refers to the act of a robot in a factory reporting its current status and work progress.

[0468] "A means of requesting tasks" refers to a function that allows a robot to request new tasks, repairs, or other tasks from other robots or administrators.

[0469] "Methods for analyzing error messages" refer to techniques for analyzing received error messages, understanding their content, and taking appropriate countermeasures.

[0470] "Means for task reassignment" refers to a function that redistributes tasks among robots and users based on analysis results.

[0471] This invention is a system for maximizing work efficiency by enabling robots in a factory to automatically communicate with other robots and managers. This system combines a natural language processing (NLP) engine, a sentiment evaluation engine, a template engine, a task management system, and other components. The detailed operation of the system is described below.

[0472] 1. Receiving a message

[0473] The server receives messages from robots within the factory, such as status reports, error messages, and task requests. These messages are then electronically incorporated into the system.

[0474] 2. Message Analysis

[0475] Received messages are analyzed by a natural language processing engine (NLP engine) on the server. This analysis extracts necessary information from the message (date and time, location, error details, request, etc.).

[0476] 3. Emotional evaluation

[0477] The analyzed message is sent to an emotion evaluation engine, where emotions such as positive, negative, or neutral are identified. For example, the message "The device has malfunctioned" is evaluated as negative.

[0478] 4. Generating a reply

[0479] The server generates a reply using a template engine based on the results obtained from the NLP engine and the sentiment evaluation engine. The template engine creates a reply with an appropriate tone based on the evaluated sentiment.

[0480] 5. Task Extraction

[0481] The server extracts tasks from the message analysis results. This task extraction uses a key phrase extraction algorithm to identify specific work items and action items.

[0482] 6. Saving and managing tasks

[0483] The extracted tasks are stored in a task management system. The task management system centralizes detailed task information, making it easy for robots and administrators to access and manage it.

[0484] 7. User notifications and automatic replies

[0485] The server notifies the user of the generated reply and the extracted task details. The user reviews this and makes any necessary corrections. Once final confirmation is complete, the server automatically sends the reply to the recipient.

[0486] Specific example

[0487] For example, if robot A sends the message "The device has malfunctioned. It needs repair," the server receives this message. The NLP engine analyzes the message and extracts the information "malfunction" and "repair needed." The sentiment evaluation engine evaluates this message as "negative." The server uses the template engine to generate a reply message saying "A problem has occurred. We will address it promptly." At the same time, a "repair task" is saved in the task management system.

[0488] Example of a prompt

[0489] Analyze the message "The device has malfunctioned. Repair is needed," perform a sentiment assessment, and generate an appropriate response.

[0490] This system streamlines communication between robots and enables responses based on appropriate emotions. This significantly reduces the burden on users and improves overall factory work efficiency.

[0491] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0492] Step 1:

[0493] The server receives messages from robots and administrators within the factory. These messages are sent in text format and are received by the server's receiving system. Input messages include robot status reports, error messages, and task requests. The text data of the received messages is stored on the server as output.

[0494] Step 2:

[0495] The server sends the received text data to a natural language processing (NLP) engine for message analysis. This NLP engine extracts important information such as the date and time, location, error details, and request details. The input is the text data of the received message, and the output is the analysis results.

[0496] Step 3:

[0497] The server sends the analysis results to the emotion evaluation engine, which evaluates the emotions from the message. The emotions evaluated include positive, negative, and neutral. The input for this step is the analysis results of the NLP engine, and the output is the emotion evaluation result.

[0498] Step 4:

[0499] The server automatically generates a reply using a template engine based on the sentiment evaluation results. The input is the sentiment evaluation results and analysis results, and the output is the generated reply. Specifically, the template engine selects an appropriate template and uses text generation AI to create the reply.

[0500] Step 5:

[0501] The server uses a key phrase extraction algorithm to extract tasks from the analysis results. The input is the analysis results of the NLP engine, and the output is a list of specific tasks. Specifically, it extracts repair tasks from the information "repair needed".

[0502] Step 6:

[0503] The server saves the extracted tasks to the task management system. The input is a list of tasks, and the output is the tasks saved in the task management database. This allows for centralized management of detailed information for each task (deadline, priority, etc.).

[0504] Step 7:

[0505] The server notifies the user of the generated reply and extracted task content. The input is the reply and task list, and the output is a notification sent to the user's terminal. The user reviews this and makes corrections as needed.

[0506] Step 8:

[0507] The user reviews the reply and task details, makes any necessary corrections, and then performs a final check. The input is the user's corrections, and the output is the corrected reply and task list, which are sent to the server.

[0508] Step 9:

[0509] After user confirmation, the server automatically sends the generated reply to the recipient. The input is the reply confirmed by the user, and the output is the reply message sent to the recipient. This ensures that messages are processed at the appropriate time.

[0510] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0511] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0512] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0513] [Second Embodiment]

[0514] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0515] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0516] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0517] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0518] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0519] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0520] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0521] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0522] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0523] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0524] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0525] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0526] This invention is a system designed to streamline text-based business communication and reduce user effort. The system includes processes such as message reception, content analysis, automatic generation of replies and tasks, user notifications, and automatic reply sending. Its specific operation is described below in natural language.

[0527] System Configuration

[0528] 1. Receiving a message

[0529] Users receive emails and chat messages on their devices. This receiving operation is performed through typical email clients and chat applications.

[0530] 2. Message Analysis

[0531] The received message is automatically sent from the terminal to the server. The server sends the message content to a natural language processing (NLP) engine for analysis.

[0532] 3. Automatic generation of reply messages

[0533] The server automatically generates a reply using a template engine based on the analysis results. The template engine generates an appropriate reply by filling in the necessary information based on a pre-configured template format.

[0534] Specific example:

[0535] Message received: "I'd like to schedule a meeting next Tuesday at 2 PM. Would that work for you?"

[0536] Automated reply: "Hello, thank you for contacting me. Tuesday at 2 PM next week is fine. Thank you."

[0537] 4. Task Extraction

[0538] The server extracts tasks from the received messages. A key phrase extraction algorithm is used to identify important action items, dates, times, and other relevant information.

[0539] Specific example:

[0540] Received message: "I would like to schedule a meeting for next Tuesday at 2 PM."

[0541] Extracted task: "Task: Schedule a meeting, Due date: Next Tuesday at 2 PM"

[0542] 5. Saving and managing tasks

[0543] The server stores the extracted tasks in a task management system. The task management system centrally manages information such as task deadlines, priorities, and assigned personnel, making it easy for users to access.

[0544] 6. User Notifications

[0545] The server notifies the terminal of the generated reply and extracted tasks. The user receives this notification and checks the reply and task details.

[0546] 7. Send automatic reply

[0547] The user reviews the reply message and task details, makes any necessary corrections, and then gives a confirmation signal. Based on this signal, the device automatically sends a reply message to the server, which then sends the reply to the recipient.

[0548] This system automates the entire process, from analyzing received messages and generating replies to extracting and managing tasks. This significantly reduces the time and effort users spend on daily business communication.

[0549] The following describes the processing flow.

[0550] Step 1: Receive message

[0551] Users receive emails and chat messages on their devices. These messages are received from mail servers and chat servers.

[0552] The terminal temporarily stores the received message and sends its contents to the server.

[0553] Step 2: Sending a message

[0554] The terminal sends the content of the received message to the server. The message is transferred to the server as text data.

[0555] Step 3: Message Analysis

[0556] The server sends the received message to a natural language processing (NLP) engine. The NLP engine analyzes the message content and extracts important information.

[0557] Specifically, the NLP engine identifies the date, time, location, and request from the message and outputs the analysis results.

[0558] Step 4: Generating a reply

[0559] The server generates a reply using a template engine based on the analysis results obtained from the NLP engine.

[0560] The template engine creates a reply by embedding the analysis results into a pre-prepared template.

[0561] Step 5: Task Extraction

[0562] The server uses a task engine to extract tasks from the message analysis results.

[0563] The task engine identifies action items and key phrases within a message and generates a task list.

[0564] Step 6: Save the task

[0565] The server saves the extracted tasks to the task management system.

[0566] A task management system centralizes task details (deadlines, priorities, etc.) and makes them easily accessible to users.

[0567] Step 7: User Notifications

[0568] The server notifies the terminal of the generated reply message and the extracted task content.

[0569] The user receives a notification on their device and checks the generated reply and task details.

[0570] Step 8: User verification and correction

[0571] The user reviews the generated reply and task details on their device and makes corrections if necessary.

[0572] Once the corrections are complete, the user enters a confirmation instruction into the terminal.

[0573] Step 9: Send automatic reply

[0574] When the terminal receives confirmation from the user, it sends that information to the server.

[0575] The server automatically sends the confirmed reply to the recipient.

[0576] Through the above processing steps, users can efficiently conduct text-based business communication without any extra effort.

[0577] (Example 1)

[0578] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0579] In business communication, responding to received messages and managing related tasks is time-consuming and laborious, reducing user efficiency. Furthermore, accurately analyzing message content and responding quickly and precisely is crucial for smooth business operations, but manual processes have limitations. Therefore, there is a need for systems that automate these processes and reduce user effort and time.

[0580] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0581] In this invention, the server includes means for receiving electronic communication messages using a personal terminal, means for transmitting the received electronic communication messages to a central processing unit for analysis, means for the central processing unit to analyze the message content using a natural language processing model, means for automatically generating a reply message using a predefined template based on the analysis results, means for extracting tasks from the electronic communication messages, means for storing the extracted tasks in a task management device, means for notifying the personal terminal of the automatically generated reply message and the extracted tasks, and means for sending an automatic reply message after user confirmation. This makes it possible to automate a series of processes from analyzing received messages to generating reply messages, extracting tasks, and managing them.

[0582] A "personal device" is an electronic device used by a user to receive and send emails and chat messages.

[0583] "Electronic communication messages" refer to digital text messages such as emails and chat messages that are sent and received via the internet or other communication networks.

[0584] A "central processing unit" is a computer server or cloud computing system that analyzes received electronic communication messages.

[0585] A "natural language processing model" is a machine learning model or algorithm that analyzes the content of an incoming message and understands and generates human language.

[0586] A "predefined template" is a pre-configured text format used when automatically generating reply messages.

[0587] A "template engine" is a software development tool that combines templates and dynamic data to generate content.

[0588] A "task management device" is software or a system used to manage and track extracted tasks.

[0589] A "key phrase extraction algorithm" is an algorithm used to identify important phrases and information from electronic communication messages.

[0590] An "automatic reply message" is a message that the system automatically sends after the user has reviewed or corrected something.

[0591] This invention is a system for streamlining text-based business communication and reducing user effort. The system includes processes for receiving messages, analyzing content, automatically generating replies and tasks, notifying users, and sending automatic replies.

[0592] System Configuration

[0593] Message received

[0594] Users receive emails and chat messages on their personal devices. This receiving operation is performed through common email and chat applications (e.g., Outlook, Slack) that process electronic communication messages.

[0595] Message Controller

[0596] Received electronic communication messages are automatically sent from the terminal to the central processing unit (CCU). The CCU (e.g., a cloud server) analyzes the message content using a natural language processing model (e.g., Google Cloud NLP, Amazon Comprehend). The data analyzed by the NLP engine is processed in various ways, such as summarization, categorization, and sentiment analysis.

[0597] Automatically generate reply messages

[0598] The central processing unit automatically generates reply messages using a template engine (e.g., Mustache, Handlebars) based on the analysis results. Predefined templates contain the basic structure of appropriate reply messages, into which the analysis data is embedded.

[0599] Specific example:

[0600] Message received: "I'd like to schedule a meeting next Tuesday at 2 PM. Would that work for you?"

[0601] Automated reply: "Hello, thank you for contacting me. Tuesday at 2 PM next week is fine. Thank you."

[0602] Task extraction

[0603] The central processing unit extracts tasks from electronic communication messages. Key phrase extraction algorithms (e.g., TF-IDF, BERT) are used to identify important action items, dates, and times.

[0604] Specific example:

[0605] Received message: "I would like to schedule a meeting for next Tuesday at 2 PM."

[0606] Extracted task: "Task: Schedule a meeting, Due date: Next Tuesday at 2 PM"

[0607] Task saving and management

[0608] The central processing unit saves the extracted tasks to a task management system (e.g., Trello, Asana). The task management system centrally manages information such as task deadlines, priorities, and assignees, making it easily accessible to users.

[0609] User notifications

[0610] The central processing unit notifies the user's personal device of the generated reply and extracted tasks. The device then displays the generated content to the user via push notifications or in-app notifications.

[0611] Automatic reply sent

[0612] After the user reviews the reply and task details and makes any necessary corrections, the personal device sends a confirmation message. The device then sends this message to the central processing unit, which automatically sends a reply message to the recipient.

[0613] Example of a prompt

[0614] Message component:

[0615] The prompt text that users use to have a natural language processing engine parse their message:

[0616] Please analyze the following message: "I would like to schedule a meeting next Tuesday at 2 PM. Would that work for you?"

[0617] Reply text generation:

[0618] Prompts used to generate automated replies using a template engine:

[0619] "Please generate the following reply: Use the template 'Hello, thank you for contacting me. [Date and time] is fine. Thank you.' and fill in 'Next Tuesday at 2 PM' as the date and time."

[0620] This system automates a series of processes, from analyzing received messages and generating replies to extracting and managing tasks, allowing users to significantly reduce the time and effort spent on daily business communication.

[0621] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0622] Step 1:

[0623] A user receives electronic communication messages on their personal device. The device uses a common email client or chat application (e.g., Outlook, Slack) to receive new messages.

[0624] Input: New email or chat message

[0625] Output: Forward received messages to the server

[0626] Step 2:

[0627] The terminal automatically sends received electronic communication messages to the server. The terminal sends the received message information via the server's API endpoint.

[0628] Input: Received message sent from the device

[0629] Output: Preparing the server for message parsing

[0630] Step 3:

[0631] The server sends incoming messages to a natural language processing (NLP) engine for analysis. The server uses natural language processing models such as Google Cloud NLP or Amazon Comprehend to summarize the message content, analyze sentiment, and categorize it.

[0632] Input: Received message

[0633] Data processing: Analysis using an NLP engine (summarization, sentiment analysis, categorization).

[0634] Output: Analysis results (summary text, sentiment score, category information, etc.)

[0635] Step 4:

[0636] The server uses a template engine based on the analysis results to automatically generate a reply. The reply is created by embedding the necessary data (e.g., date and time, action item) into a predefined template.

[0637] Input: Analysis results and template

[0638] Data processing: Use a template engine to embed analysis results into a template.

[0639] Output: Automated reply

[0640] Specific examples of actions:

[0641] Template: "Hello, thank you for contacting me. [Date and time] is fine. Thank you."

[0642] Analysis result: "Date and time: Next Tuesday, 2 PM"

[0643] Generated reply: "Hello, thank you for contacting me. Tuesday at 2 PM next week is fine. Thank you."

[0644] Step 5:

[0645] The server extracts tasks from electronic communication messages. The server uses key phrase extraction algorithms (e.g., TF-IDF, BERT) to identify important action items, dates, and times from the messages.

[0646] Input: Received message

[0647] Data processing: Analysis using a key phrase extraction algorithm.

[0648] Output: Extracted tasks

[0649] Specific examples of actions:

[0650] Received message: "I would like to schedule a meeting for next Tuesday at 2 PM."

[0651] Extracted task: "Task: Schedule a meeting, Due date: Next Tuesday at 2 PM"

[0652] Step 6:

[0653] The server saves the extracted tasks to a task management system. The server uses task management tools such as Trello or Asana to centrally manage tasks.

[0654] Input: Extracted tasks

[0655] Data processing: Adding tasks to a task management system.

[0656] Output: Saved tasks

[0657] Step 7:

[0658] The server notifies the device of the generated reply and extracted tasks. The device then displays this information to the user via push notifications or in-app notifications.

[0659] Input: Auto-generated reply text, extracted tasks

[0660] Output: Notification to the user

[0661] Step 8:

[0662] The user reviews the reply and task details and makes corrections as needed. A confirmation message is sent from the terminal to the server.

[0663] Input: Instructions for user correction or confirmation.

[0664] Output: Confirmation complete

[0665] Step 9:

[0666] After the device receives confirmation, it automatically sends a reply message to the server. The server then forwards that message to the appropriate recipient.

[0667] Input: Confirmation complete instructions

[0668] Output: Automated reply message sent to the recipient

[0669] These steps automate the entire process, from receiving messages to generating and sending replies, and even managing tasks. This significantly improves the efficiency of users' business communications.

[0670] (Application Example 1)

[0671] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0672] In modern content delivery services, there is a demand for quick and accurate responses to user feedback and request messages. Furthermore, manually performing message analysis and task extraction is time-consuming and labor-intensive, hindering efficient work. Automating processes such as task management and reply generation is also required to reduce the burden on operators and enable faster responses. Current systems struggle to meet these requirements, resulting in limitations in improving the user experience.

[0673] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0674] In this invention, the server includes means for receiving messages, means for analyzing received messages based on natural language processing, means for automatically generating reply text using templates based on the analysis results, means for extracting tasks from messages, means for storing the extracted tasks in a task management system, means for notifying the user of the generated reply text and extracted tasks, means for sending an automatic reply after user confirmation, means for analyzing received feedback and requests and generating appropriate automatic reply texts, and means for extracting and managing tasks for content creation based on the task extraction results. This makes it possible to automate a series of processes from analyzing user messages and extracting tasks to task management and reply text generation, significantly reducing the burden on operators and enabling quick and efficient responses.

[0675] "Means of receiving messages" refers to the means of receiving messages sent by users via email, chat applications, etc.

[0676] Natural language processing is a set of techniques that use computers to understand, interpret, and manipulate human language, and is used to analyze the content of received messages.

[0677] "Methods for automatically generating reply text using templates" refer to methods for automatically generating appropriate reply text by filling in necessary information based on a pre-configured template format.

[0678] "Task extraction methods" refer to methods for identifying important action items, deadlines, etc., from the content of received messages using key phrase extraction algorithms, and extracting them as tasks.

[0679] A "task management system" is a system that stores and manages extracted tasks along with information such as deadlines, priorities, and assigned personnel, making them easily accessible to users.

[0680] "Means of notifying the user" refers to means of notifying the user's device of the generated reply message and the contents of the extracted tasks.

[0681] "Method for sending automatic replies" refers to a method for automatically sending a final reply after the user has reviewed and revised it.

[0682] "Means for analyzing feedback and requests" refers to methods for analyzing the content of user feedback and request messages.

[0683] "Means for extracting and managing tasks for content creation" refers to methods for identifying and managing the tasks necessary for content creation based on tasks extracted from received messages.

[0684] This invention provides a system that automates message processing in content distribution services, thereby reducing the burden on operators. This system includes a process that automatically analyzes received messages, generates replies, and extracts and manages tasks.

[0685] System Configuration

[0686] Message received

[0687] First, the system receives feedback and request messages sent by users via email or chat tools. This allows the system to incorporate messages from users.

[0688] Message Controller

[0689] Received messages are automatically sent from the terminal to the server. The server analyzes the message content using a natural language processing (NLP) engine (e.g., NLTK). At this stage, the message content is understood, and information necessary for generating replies and tasks is extracted.

[0690] Automatically generate reply messages

[0691] The server uses a template engine to generate an appropriate reply based on the analysis results. The template engine constructs the reply by embedding the analyzed information according to a pre-configured template format.

[0692] Task extraction and management

[0693] The server uses a key phrase extraction algorithm to extract tasks from messages. These extracted tasks are identified as action items and deadlines necessary for content creation. These tasks are stored in a task management system and centrally managed along with information such as deadlines, priorities, and assigned personnel.

[0694] User notifications and automatic reply sending

[0695] The server notifies the terminal of the generated reply and extracted tasks. The user receives this notification and reviews and modifies the reply and task details. After review, the terminal automatically sends a confirmation message to the server and sends the final reply message.

[0696] This makes it possible to automate a series of processes, from analyzing user messages and extracting tasks to managing tasks and generating replies, significantly reducing the burden on administrators and enabling quick and efficient responses.

[0697] Specific examples

[0698] For example, if a user sends a message saying, "I'd like to schedule a meeting next Friday at 3 PM to discuss new video content. Would that work for you?", the system will receive this message and automatically generate a reply like this:

[0699] "Hello, thank you for contacting me. Friday at 3 PM next week is fine. Thank you."

[0700] The extracted tasks also include items such as "Schedule a meeting about new video content, deadline: next Friday at 3 PM."

[0701] Example of a prompt

[0702] The following is an example of a specific prompt message:

[0703] Please generate a reply to the following message: "I would like to schedule a meeting next Friday at 3 PM to discuss new video content. Would that work for you?"

[0704] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0705] Step 1:

[0706] The device receives user feedback and request messages via email or chat tools. These messages are imported into the system in text format. The input is the user's message, and the output is the storage of the received message.

[0707] Step 2:

[0708] The terminal sends the received message to the server. Here, the received message data is transferred to the server. The input is the received message, and the output is the transfer of the message data to the server.

[0709] Step 3:

[0710] The server analyzes the content of received messages using a natural language processing (NLP) engine. Specifically, it uses a natural language processing library such as NLTK to tokenize the messages and extract key phrases. The input is the message data forwarded to the server, and the output is the analysis result.

[0711] Step 4:

[0712] The server automatically generates a reply based on the analysis results using a template engine. The template engine embeds the analyzed key phrases and time information into a pre-configured template to create an appropriate reply. The input is the analysis result, and the output is the automatically generated reply.

[0713] Step 5:

[0714] The server executes a keyphrase extraction algorithm to extract tasks from messages. The extracted tasks include important information such as action items and deadlines. The input is the parsing result, and the output is the extracted task information.

[0715] Step 6:

[0716] The server saves the extracted task information to the task management system. The task management system stores information such as deadlines, priorities, and assigned personnel in an easy-to-manage format. The input is the extracted task information, and the output is the tasks stored in the task management system.

[0717] Step 7:

[0718] The server notifies the terminal of the generated reply and extracted tasks. The terminal displays this information to the user and requests confirmation. The input is the automatically generated reply and extracted task information, and the output is the notification to the user.

[0719] Step 8:

[0720] The user checks the notification on their device and modifies the reply and task details as needed. The input is the notified reply and task information, and the output is the modified reply and task information.

[0721] Step 9:

[0722] User verification is complete, and the terminal sends a verification completion instruction to the server. The server sends a final reply message. The input is the verification completion instruction and the revised reply text, and the output is the sending of the final reply message.

[0723] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0724] This invention is a system designed to streamline text-based business communication and reduce user effort. The system combines message reception, content analysis, automatic generation of replies and tasks, user notifications, automatic reply sending, and an emotion engine that recognizes user sentiment. The specific operation of the entire system is described below.

[0725] System Configuration

[0726] 1. Receiving a message

[0727] Users receive emails and chat messages on their devices. This receiving operation is performed through common email clients and chat applications.

[0728] 2. Sending a message

[0729] The terminal automatically sends the content of the received message to the server. The message is transferred to the server as text data.

[0730] 3. Message Analysis

[0731] Received messages are analyzed by a natural language processing (NLP) engine on the server. This analysis extracts important information from the message, such as the date, time, location, and request.

[0732] 4. Emotion recognition

[0733] The server sends the analyzed message to the emotion engine, which evaluates the user's emotions. The emotion engine identifies emotions such as positive, negative, or neutral from the message.

[0734] Specific example:

[0735] Message received: "I'm very sorry to trouble you, but could I cancel tomorrow's meeting?"

[0736] Emotional engine evaluation: Negative

[0737] 5. Generating a reply

[0738] The server generates a reply using a template engine based on the results obtained from the NLP engine and the emotion engine. The template engine creates a reply with an appropriate tone, taking emotion evaluation into consideration.

[0739] Specific example:

[0740] Input: NLP analysis results, emotion assessment (negative)

[0741] output:

[0742] "Hello, thank you for your understanding regarding the cancellation of tomorrow's meeting. We will contact you later with a new date."

[0743] 6. Task Extraction

[0744] The server uses a task engine to extract tasks from the message analysis results. The task engine identifies action items and key phrases in the message and generates a task list.

[0745] Specific example:

[0746] Message received: "Please cancel tomorrow's meeting and reschedule it."

[0747] Extracted task: "Task: Schedule a new meeting, Deadline: Undetermined"

[0748] 7. Saving and managing tasks

[0749] The server stores the extracted tasks in a task management system. The task management system centrally manages detailed task information (deadlines, priorities, etc.) and makes it easily accessible to users.

[0750] 8. User Notifications

[0751] The server notifies the terminal of the generated reply and the extracted task content. The user receives this notification and checks the reply and task content.

[0752] 9. User verification and correction

[0753] The user reviews the generated reply and task details on their device and makes corrections if necessary. Once corrections are complete, the user enters a confirmation message into their device.

[0754] 10. Send automatic reply

[0755] When the terminal receives confirmation from the user, it sends that information to the server. The server automatically sends the confirmed reply to the recipient.

[0756] Through the processing steps described above, users can efficiently conduct text-based business communication without any hassle. Furthermore, the combination of emotion engines enables more appropriate and emotionally resonant replies.

[0757] The following describes the processing flow.

[0758] Step 1: Receive message

[0759] Users receive emails and chat messages on their devices. This receiving operation is performed through common email clients and chat applications.

[0760] Step 2: Send Message

[0761] The terminal automatically sends the content of the received message to the server. It is transferred to the server as text data.

[0762] Step 3: Message Analysis

[0763] The server sends the received message to a natural language processing (NLP) engine. The NLP engine analyzes the message content and extracts important information.

[0764] For example, the date, time, location, and details of the request will be specified.

[0765] Step 4: Emotion Recognition

[0766] The server sends the analyzed message to the emotion engine, which evaluates the user's emotions. The emotion engine identifies emotions such as positive, negative, or neutral from the message.

[0767] For example, we can identify negative emotions from the phrase "I'm so sorry for the trouble..." in a message.

[0768] Step 5: Generate reply

[0769] The server uses a template engine to generate a reply based on the results obtained from the NLP engine and the emotion engine.

[0770] The template engine takes into account the analysis results and sentiment assessment to create a reply with an appropriate tone.

[0771] Step 6: Task Extraction

[0772] The server extracts tasks from the message using a task engine. The task engine identifies action items and key phrases within the message and generates a task list.

[0773] As an example, from a request that says "Please set a new date," we extract the task "Task: Set a new meeting."

[0774] Step 7: Save Task

[0775] The server saves the extracted tasks to the task management system. The task management system centrally manages detailed task information (deadlines, priorities, etc.).

[0776] Step 8: User Notifications

[0777] The server notifies the terminal of the generated reply and extracted task details. The user then sees the reply and task details.

[0778] Step 9: User verification and correction

[0779] The user reviews the generated reply and task details on their device. If necessary, the user modifies the reply and task.

[0780] The user enters confirmation instructions into the terminal.

[0781] Step 10: Send automatic reply

[0782] When the terminal receives confirmation from the user, it sends that information to the server.

[0783] The server automatically sends the confirmed reply to the recipient.

[0784] This process allows users to engage in efficient, emotionally sensitive, and effortless text-based business communication.

[0785] (Example 2)

[0786] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0787] In traditional text-based business communication, users had to spend considerable time analyzing received messages, drafting appropriate replies, and extracting and managing tasks. This manual process was time-consuming and labor-intensive, increasing the burden on users. Furthermore, it resulted in the generation of impersonal, mechanical replies that lacked emotional considerations, leading to a decline in communication quality.

[0788] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0789] In this invention, the server includes means for receiving messages, means for analyzing the received messages based on natural language processing, means for recognizing emotions based on the analysis results, means for automatically generating reply text using templates while considering emotion evaluation, means for extracting tasks from messages, means for storing the extracted tasks in a task management system, means for notifying the user of the generated reply text and extracted tasks, and means for sending an automatic reply after user confirmation. This allows the user to perform message analysis, generate appropriate reply texts, and extract and manage tasks in a unified manner without any effort. Furthermore, the quality of communication can be improved by providing reply texts that take emotions into consideration.

[0790] "Means for receiving messages" refers to system components that allow users to receive text-based messages, such as emails and chat messages, through their devices.

[0791] "Means for analysis based on natural language processing" refers to a system component that includes a natural language processing engine used to analyze received messages and extract important information (such as date and time, location, and requests).

[0792] "Means of recognizing emotions" refers to system components that include an emotion engine for evaluating the user's emotions from analyzed messages and identifying emotions such as positive, negative, or neutral.

[0793] "A means of automatically generating reply text using templates while considering sentiment evaluation" refers to a system component that automatically generates reply text with an appropriate tone using a template engine, based on the analysis results of natural language processing and sentiment evaluation.

[0794] "Means for extracting tasks" refers to system components that include a task engine for extracting action items and key phrases from the analysis results of messages and identifying specific tasks.

[0795] "Means of saving to a task management system" refers to system components that include task management tools used to save and centrally manage extracted tasks.

[0796] "Means for notifying the user of the generated reply and extracted tasks" refers to system components for notifying the user's terminal of the content of the generated reply and tasks.

[0797] "Method for sending an automatic reply after user confirmation" refers to a system component that automatically sends a reply after the user has reviewed and corrected the generated reply text and task content.

[0798] This invention is a system designed to streamline text-based business communication and reduce the burden on users. Specifically, this system receives messages, analyzes their content, recognizes sentiment, automatically generates replies and tasks, notifies users, and sends automatic replies. The implementation method of this system is described below.

[0799] System configuration and operation

[0800] 1. Receiving a message

[0801] Users receive emails and chat messages using their devices (such as PCs and smartphones). Applications used include Outlook, Gmail, and Slack. When a user receives a new message, its content is saved on their device.

[0802] 2. Sending a message

[0803] The terminal sends the received message to the server. The message is transferred to the server in text data format. This process involves sending data via HTTP requests or WebSockets.

[0804] 3. Message Analysis

[0805] The server sends received messages to a natural language processing (NLP) engine for analysis. The NLP engine used may include the Google Cloud Natural Language API. Through analysis, important information (such as date, time, location, and request details) is extracted from the message.

[0806] 4. Emotion recognition

[0807] The server sends the analyzed message to an emotion recognition engine to evaluate the user's emotions. Engines such as IBM Watson Tone Analyzer are used to identify emotions such as positive, negative, or neutral from the message.

[0808] Specific example:

[0809] Message received: "I'm very sorry to trouble you, but could I cancel tomorrow's meeting?"

[0810] Emotional engine evaluation: Negative

[0811] 5. Generating a reply

[0812] The server generates a reply using a template engine based on the results obtained from the NLP engine and the emotion engine. The template engine used is typically Handlebars.js, which generates a reply with an appropriate tone that takes emotion evaluation into account.

[0813] Specific example:

[0814] Input: NLP analysis results (request: meeting cancellation), emotion evaluation (negative)

[0815] Output: "Hello, thank you for your understanding regarding the cancellation of tomorrow's meeting. We will contact you later with a new date."

[0816] 6. Task Extraction

[0817] The server uses a task engine to extract tasks from the message analysis results. Task engines such as Apache OpenNLP identify action items and key phrases within the message and generate a task list.

[0818] Specific example:

[0819] Message received: "Please cancel tomorrow's meeting and reschedule it."

[0820] Extracted task: "Task: Schedule a new meeting, Deadline: Undetermined"

[0821] 7. Saving and managing tasks

[0822] The server saves the extracted tasks to a task management system. Task management systems such as Trello or Asana are used to centrally manage detailed task information (deadlines, priorities, etc.).

[0823] 8. User Notifications

[0824] The server notifies the terminal of the generated reply and the extracted task content. The user receives this notification and checks the reply and task content.

[0825] 9. User verification and correction

[0826] The user reviews the generated reply and task details on their device and makes corrections if necessary. Once corrections are complete, the user enters a confirmation message into their device.

[0827] Specific example:

[0828] The user modifies the reply to "Thank you for your understanding" and clicks "Confirmation Complete".

[0829] 10. Send automatic reply

[0830] The terminal sends a confirmation message from the user to the server. The server then automatically sends a reply to the recipient based on the confirmed message.

[0831] Example of a prompt:

[0832] Message received: "I'm very sorry to trouble you, but could I cancel tomorrow's meeting?"

[0833] Emotional engine rating: "Negative"

[0834] NLP analysis result: "Cancellation request"

[0835] Prompt to input to the generating AI model: "The user's sentiment rating for this message has been determined to be negative. Please create a reply in an appropriate tone to address the cancellation request."

[0836] As described above, this system allows users to perform message analysis, generate appropriate replies, and extract and manage tasks in a unified manner without any extra effort. Furthermore, by utilizing the sentiment engine, it is possible to generate more appropriate and emotionally resonant replies.

[0837] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0838] Detailed explanation of the processing steps

[0839] Step 1: Receiving a message

[0840] The user receives emails and chat messages on their device.

[0841] input:

[0842] Email or chat message

[0843] Data processing:

[0844] none

[0845] output:

[0846] Received message data

[0847] Specific actions:

[0848] A user receives a new email using the Gmail application. For example, they receive an email that says, "I would like to cancel tomorrow's meeting."

[0849] Step 2: Sending a message

[0850] The terminal sends the received message to the server.

[0851] input:

[0852] Received message data

[0853] Data processing:

[0854] Convert the message to JSON format

[0855] output:

[0856] HTTP POST request to the server

[0857] Specific actions:

[0858] The terminal converts the received message into JSON format and sends it to the server as an HTTP POST request.

[0859] Step 3: Message Analysis

[0860] The server sends the received message to a natural language processing (NLP) engine for analysis.

[0861] input:

[0862] JSON data of the received message

[0863] Data processing:

[0864] Information extraction using natural language processing

[0865] output:

[0866] Analysis results (request details, date, time, location, etc.)

[0867] Specific actions:

[0868] The server uses an NLP engine (e.g., Google Cloud Natural Language API) to extract important information such as "cancellation of a meeting and scheduling of a new date."

[0869] Step 4: Emotion Recognition

[0870] The server sends the analyzed message to the emotion recognition engine, which then evaluates the user's emotions.

[0871] input:

[0872] Analyzed message data

[0873] Data processing:

[0874] sentiment analysis

[0875] output:

[0876] Emotional evaluation (positive, negative, neutral, etc.)

[0877] Specific actions:

[0878] The server uses an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to identify the emotion as "negative."

[0879] Step 5: Generating a reply

[0880] The server generates a reply using a template engine based on the NLP analysis results and sentiment evaluation.

[0881] input:

[0882] NLP analysis results, emotion evaluation

[0883] Data processing:

[0884] Generate reply text using a template engine.

[0885] output:

[0886] Generated reply

[0887] Specific actions:

[0888] The server uses the Handlebars.js template engine to generate a reply message that reads, "Hello, thank you for your understanding regarding the cancellation of tomorrow's meeting. We will contact you later with a new date."

[0889] Step 6: Task Extraction

[0890] The server uses a task engine to extract tasks from the message analysis results.

[0891] input:

[0892] NLP analysis results

[0893] Data processing:

[0894] Task extraction algorithm

[0895] output:

[0896] Extracted tasks

[0897] Specific actions:

[0898] The server uses Apache OpenNLP to extract a task called "Set up a new meeting" and sets its name to "Task: Set up a new meeting, Due date: Undetermined".

[0899] Step 7: Saving and managing tasks

[0900] The server saves the extracted tasks to the task management system.

[0901] input:

[0902] Extracted tasks

[0903] Data processing:

[0904] Save to task management system

[0905] output:

[0906] Tasks saved in the task management system

[0907] Specific actions:

[0908] The server uses the Trello API to save the extracted tasks as new cards.

[0909] Step 8: User Notifications

[0910] The server notifies the terminal of the generated reply message and the extracted task content.

[0911] input:

[0912] Generated reply text, extracted tasks

[0913] Data processing:

[0914] Generating push notifications

[0915] output:

[0916] Push notifications to your device

[0917] Specific actions:

[0918] The server sends a push notification to the device, and the user checks the "reply message" and "task details" on the screen.

[0919] Step 9: User verification and correction

[0920] The user reviews the generated reply and task details on their device and makes corrections if necessary.

[0921] input:

[0922] Generated reply text, extracted tasks

[0923] Data processing:

[0924] User modifications

[0925] output:

[0926] Revised reply, task

[0927] Specific actions:

[0928] The user modifies the reply to "Thank you for your understanding" and clicks "Confirmation Complete".

[0929] Step 10: Send automatic reply

[0930] The device sends a confirmation message from the user to the server and then sends a confirmed reply to the other party.

[0931] input:

[0932] Revised reply, user confirmation complete instruction

[0933] Data processing:

[0934] Sending a reply

[0935] output:

[0936] Reply sent to the recipient

[0937] Specific actions:

[0938] The terminal notifies the server that "confirmation complete," and the server sends a "confirmed reply" to the recipient as an email.

[0939] (Application Example 2)

[0940] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0941] In conventional factory robot systems, communication, reporting, and error message processing between robots were handled individually, resulting in difficulties in efficient operation. Furthermore, there was no system that could generate appropriate, emotion-based responses while reducing the burden on the user. Therefore, there was a need for a system that provides automated, advanced communication between robots and emotion-responsive response capabilities.

[0942] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving messages, means for analyzing the received messages based on natural language processing, means for automatically generating a reply using a template based on the analysis results, means for extracting tasks from messages, means for storing the extracted tasks in a task management system, means for notifying the user of the generated reply and extracted tasks, means for sending an automatic reply after user confirmation, means for evaluating emotions from the analyzed messages, means for selecting a reply template based on the evaluated emotions, means for factory robots to report status and request tasks from other robots and managers, and means for analyzing received error messages and performing automatic replies and task reassignments. This makes it possible to streamline communication between robots and realize appropriate responses based on emotions.

[0943] "Means of receiving messages" refers to the ability to electronically acquire messages from robots or users.

[0944] "Natural language processing" is a technology that analyzes received messages as text data and understands and processes their content.

[0945] "Method for automatically generating reply messages" refers to a function that automatically creates appropriate reply messages using templates based on analysis results.

[0946] "Methods for extracting tasks from messages" refers to a function that identifies and extracts specific work items or action items from the content of a message.

[0947] A "task management system" is a system for recording, monitoring, and managing extracted tasks.

[0948] "Means of notifying the user" refers to a function that informs the user of the generated reply and extracted tasks.

[0949] "Method for sending automatic replies" refers to a function that automatically sends a generated reply message to the recipient after user confirmation.

[0950] "Methods for evaluating emotions" refer to technologies that identify emotions such as positive and negative from analyzed messages.

[0951] The "means of selecting a reply template" refer to the function of selecting a template to generate a reply with an appropriate tone based on the evaluated emotion.

[0952] "Robot status reporting" refers to the act of a robot in a factory reporting its current status and work progress.

[0953] "A means of requesting tasks" refers to a function that allows a robot to request new tasks, repairs, or other tasks from other robots or administrators.

[0954] "Methods for analyzing error messages" refer to techniques for analyzing received error messages, understanding their content, and taking appropriate countermeasures.

[0955] "Means for task reassignment" refers to a function that redistributes tasks among robots and users based on analysis results.

[0956] This invention is a system for maximizing work efficiency by enabling robots in a factory to automatically communicate with other robots and managers. This system combines a natural language processing (NLP) engine, a sentiment evaluation engine, a template engine, a task management system, and other components. The detailed operation of the system is described below.

[0957] 1. Receiving a message

[0958] The server receives messages from robots within the factory, such as status reports, error messages, and task requests. These messages are then electronically incorporated into the system.

[0959] 2. Message Analysis

[0960] Received messages are analyzed by a natural language processing engine (NLP engine) on the server. This analysis extracts necessary information from the message (date and time, location, error details, request, etc.).

[0961] 3. Emotional evaluation

[0962] The analyzed message is sent to an emotion evaluation engine, where emotions such as positive, negative, or neutral are identified. For example, the message "The device has malfunctioned" is evaluated as negative.

[0963] 4. Generating a reply

[0964] The server generates a reply using a template engine based on the results obtained from the NLP engine and the sentiment evaluation engine. The template engine creates a reply with an appropriate tone based on the evaluated sentiment.

[0965] 5. Task Extraction

[0966] The server extracts tasks from the message analysis results. This task extraction uses a key phrase extraction algorithm to identify specific work items and action items.

[0967] 6. Saving and managing tasks

[0968] The extracted tasks are stored in a task management system. The task management system centralizes detailed task information, making it easy for robots and administrators to access and manage it.

[0969] 7. User notifications and automatic replies

[0970] The server notifies the user of the generated reply and the extracted task details. The user reviews this and makes any necessary corrections. Once final confirmation is complete, the server automatically sends the reply to the recipient.

[0971] Specific example

[0972] For example, if robot A sends the message "The device has malfunctioned. It needs repair," the server receives this message. The NLP engine analyzes the message and extracts the information "malfunction" and "repair needed." The sentiment evaluation engine evaluates this message as "negative." The server uses the template engine to generate a reply message saying "A problem has occurred. We will address it promptly." At the same time, a "repair task" is saved in the task management system.

[0973] Example of a prompt

[0974] Analyze the message "The device has malfunctioned. Repair is needed," perform a sentiment assessment, and generate an appropriate response.

[0975] This system streamlines communication between robots and enables responses based on appropriate emotions. This significantly reduces the burden on users and improves overall factory work efficiency.

[0976] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0977] Step 1:

[0978] The server receives messages from robots and administrators within the factory. These messages are sent in text format and are received by the server's receiving system. Input messages include robot status reports, error messages, and task requests. The text data of the received messages is stored on the server as output.

[0979] Step 2:

[0980] The server sends the received text data to a natural language processing (NLP) engine for message analysis. This NLP engine extracts important information such as the date and time, location, error details, and request details. The input is the text data of the received message, and the output is the analysis results.

[0981] Step 3:

[0982] The server sends the analysis results to the emotion evaluation engine, which evaluates the emotions from the message. The emotions evaluated include positive, negative, and neutral. The input for this step is the analysis results of the NLP engine, and the output is the emotion evaluation result.

[0983] Step 4:

[0984] The server automatically generates a reply using a template engine based on the sentiment evaluation results. The input is the sentiment evaluation results and analysis results, and the output is the generated reply. Specifically, the template engine selects an appropriate template and uses text generation AI to create the reply.

[0985] Step 5:

[0986] The server uses a key phrase extraction algorithm to extract tasks from the analysis results. The input is the analysis results of the NLP engine, and the output is a list of specific tasks. Specifically, it extracts repair tasks from the information "repair needed".

[0987] Step 6:

[0988] The server saves the extracted tasks to the task management system. The input is a list of tasks, and the output is the tasks saved in the task management database. This allows for centralized management of detailed information for each task (deadline, priority, etc.).

[0989] Step 7:

[0990] The server notifies the user of the generated reply and extracted task content. The input is the reply and task list, and the output is a notification sent to the user's terminal. The user reviews this and makes corrections as needed.

[0991] Step 8:

[0992] The user reviews the reply and task details, makes any necessary corrections, and then performs a final check. The input is the user's corrections, and the output is the corrected reply and task list, which are sent to the server.

[0993] Step 9:

[0994] After user confirmation, the server automatically sends the generated reply to the recipient. The input is the reply confirmed by the user, and the output is the reply message sent to the recipient. This ensures that messages are processed at the appropriate time.

[0995] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0996] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0997] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0998] [Third Embodiment]

[0999] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[1000] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1001] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1002] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[1003] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1004] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1005] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1006] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1007] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1008] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1009] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1010] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[1011] This invention is a system designed to streamline text-based business communication and reduce user effort. The system includes processes such as message reception, content analysis, automatic generation of replies and tasks, user notifications, and automatic reply sending. Its specific operation is described below in natural language.

[1012] System Configuration

[1013] 1. Receiving a message

[1014] Users receive emails and chat messages on their devices. This receiving operation is performed through typical email clients and chat applications.

[1015] 2. Message Analysis

[1016] The received message is automatically sent from the terminal to the server. The server sends the message content to a natural language processing (NLP) engine for analysis.

[1017] 3. Automatic generation of reply messages

[1018] The server automatically generates a reply using a template engine based on the analysis results. The template engine generates an appropriate reply by filling in the necessary information based on a pre-configured template format.

[1019] Specific example:

[1020] Message received: "I'd like to schedule a meeting next Tuesday at 2 PM. Would that work for you?"

[1021] Automated reply: "Hello, thank you for contacting me. Tuesday at 2 PM next week is fine. Thank you."

[1022] 4. Task Extraction

[1023] The server extracts tasks from the received messages. A key phrase extraction algorithm is used to identify important action items, dates, times, and other relevant information.

[1024] Specific example:

[1025] Received message: "I would like to schedule a meeting for next Tuesday at 2 PM."

[1026] Extracted task: "Task: Schedule a meeting, Due date: Next Tuesday at 2 PM"

[1027] 5. Saving and managing tasks

[1028] The server stores the extracted tasks in a task management system. The task management system centrally manages information such as task deadlines, priorities, and assigned personnel, making it easy for users to access.

[1029] 6. User Notifications

[1030] The server notifies the terminal of the generated reply and extracted tasks. The user receives this notification and checks the reply and task details.

[1031] 7. Send automatic reply

[1032] The user reviews the reply message and task details, makes any necessary corrections, and then gives a confirmation signal. Based on this signal, the device automatically sends a reply message to the server, which then sends the reply to the recipient.

[1033] This system automates the entire process, from analyzing received messages and generating replies to extracting and managing tasks. This significantly reduces the time and effort users spend on daily business communication.

[1034] The following describes the processing flow.

[1035] Step 1: Receive message

[1036] Users receive emails and chat messages on their devices. These messages are received from mail servers and chat servers.

[1037] The terminal temporarily stores the received message and sends its contents to the server.

[1038] Step 2: Sending a message

[1039] The terminal sends the content of the received message to the server. The message is transferred to the server as text data.

[1040] Step 3: Message Analysis

[1041] The server sends the received message to a natural language processing (NLP) engine. The NLP engine analyzes the message content and extracts important information.

[1042] Specifically, the NLP engine identifies the date, time, location, and request from the message and outputs the analysis results.

[1043] Step 4: Generating a reply

[1044] The server generates a reply using a template engine based on the analysis results obtained from the NLP engine.

[1045] The template engine creates a reply by embedding the analysis results into a pre-prepared template.

[1046] Step 5: Task Extraction

[1047] The server uses a task engine to extract tasks from the message analysis results.

[1048] The task engine identifies action items and key phrases within a message and generates a task list.

[1049] Step 6: Save the task

[1050] The server saves the extracted tasks to the task management system.

[1051] A task management system centralizes task details (deadlines, priorities, etc.) and makes them easily accessible to users.

[1052] Step 7: User Notifications

[1053] The server notifies the terminal of the generated reply message and the extracted task content.

[1054] The user receives a notification on their device and checks the generated reply and task details.

[1055] Step 8: User verification and correction

[1056] The user reviews the generated reply and task details on their device and makes corrections if necessary.

[1057] Once the corrections are complete, the user enters a confirmation instruction into the terminal.

[1058] Step 9: Send automatic reply

[1059] When the terminal receives confirmation from the user, it sends that information to the server.

[1060] The server automatically sends the confirmed reply to the recipient.

[1061] Through the above processing steps, users can efficiently conduct text-based business communication without any extra effort.

[1062] (Example 1)

[1063] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1064] In business communication, responding to received messages and managing related tasks is time-consuming and laborious, reducing user efficiency. Furthermore, accurately analyzing message content and responding quickly and precisely is crucial for smooth business operations, but manual processes have limitations. Therefore, there is a need for systems that automate these processes and reduce user effort and time.

[1065] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1066] In this invention, the server includes means for receiving electronic communication messages using a personal terminal, means for transmitting the received electronic communication messages to a central processing unit for analysis, means for the central processing unit to analyze the message content using a natural language processing model, means for automatically generating a reply message using a predefined template based on the analysis results, means for extracting tasks from the electronic communication messages, means for storing the extracted tasks in a task management device, means for notifying the personal terminal of the automatically generated reply message and the extracted tasks, and means for sending an automatic reply message after user confirmation. This makes it possible to automate a series of processes from analyzing received messages to generating reply messages, extracting tasks, and managing them.

[1067] A "personal device" is an electronic device used by a user to receive and send emails and chat messages.

[1068] "Electronic communication messages" refer to digital text messages such as emails and chat messages that are sent and received via the internet or other communication networks.

[1069] A "central processing unit" is a computer server or cloud computing system that analyzes received electronic communication messages.

[1070] A "natural language processing model" is a machine learning model or algorithm that analyzes the content of an incoming message and understands and generates human language.

[1071] A "predefined template" is a pre-configured text format used when automatically generating reply messages.

[1072] A "template engine" is a software development tool that combines templates and dynamic data to generate content.

[1073] A "task management device" is software or a system used to manage and track extracted tasks.

[1074] A "key phrase extraction algorithm" is an algorithm used to identify important phrases and information from electronic communication messages.

[1075] An "automatic reply message" is a message that the system automatically sends after the user has reviewed or corrected something.

[1076] This invention is a system for streamlining text-based business communication and reducing user effort. The system includes processes for receiving messages, analyzing content, automatically generating replies and tasks, notifying users, and sending automatic replies.

[1077] System Configuration

[1078] Message received

[1079] Users receive emails and chat messages on their personal devices. This receiving operation is performed through common email and chat applications (e.g., Outlook, Slack) that process electronic communication messages.

[1080] Message Controller

[1081] Received electronic communication messages are automatically sent from the terminal to the central processing unit (CCU). The CCU (e.g., a cloud server) analyzes the message content using a natural language processing model (e.g., Google Cloud NLP, Amazon Comprehend). The data analyzed by the NLP engine is processed in various ways, such as summarization, categorization, and sentiment analysis.

[1082] Automatically generate reply messages

[1083] The central processing unit automatically generates reply messages using a template engine (e.g., Mustache, Handlebars) based on the analysis results. Predefined templates contain the basic structure of appropriate reply messages, into which the analysis data is embedded.

[1084] Specific example:

[1085] Message received: "I'd like to schedule a meeting next Tuesday at 2 PM. Would that work for you?"

[1086] Automated reply: "Hello, thank you for contacting me. Tuesday at 2 PM next week is fine. Thank you."

[1087] Task extraction

[1088] The central processing unit extracts tasks from electronic communication messages. Key phrase extraction algorithms (e.g., TF-IDF, BERT) are used to identify important action items, dates, and times.

[1089] Specific example:

[1090] Received message: "I would like to schedule a meeting for next Tuesday at 2 PM."

[1091] Extracted task: "Task: Schedule a meeting, Due date: Next Tuesday at 2 PM"

[1092] Task saving and management

[1093] The central processing unit saves the extracted tasks to a task management system (e.g., Trello, Asana). The task management system centrally manages information such as task deadlines, priorities, and assignees, making it easily accessible to users.

[1094] User notifications

[1095] The central processing unit notifies the user's personal device of the generated reply and extracted tasks. The device then displays the generated content to the user via push notifications or in-app notifications.

[1096] Automatic reply sent

[1097] After the user reviews the reply and task details and makes any necessary corrections, the personal device sends a confirmation message. The device then sends this message to the central processing unit, which automatically sends a reply message to the recipient.

[1098] Example of a prompt

[1099] Message component:

[1100] The prompt text that users use to have a natural language processing engine parse their message:

[1101] Please analyze the following message: "I would like to schedule a meeting next Tuesday at 2 PM. Would that work for you?"

[1102] Reply text generation:

[1103] Prompts used to generate automated replies using a template engine:

[1104] "Please generate the following reply: Use the template 'Hello, thank you for contacting me. [Date and time] is fine. Thank you.' and fill in 'Next Tuesday at 2 PM' as the date and time."

[1105] This system automates a series of processes, from analyzing received messages and generating replies to extracting and managing tasks, allowing users to significantly reduce the time and effort spent on daily business communication.

[1106] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1107] Step 1:

[1108] A user receives electronic communication messages on their personal device. The device uses a common email client or chat application (e.g., Outlook, Slack) to receive new messages.

[1109] Input: New email or chat message

[1110] Output: Forward received messages to the server

[1111] Step 2:

[1112] The terminal automatically sends received electronic communication messages to the server. The terminal sends the received message information via the server's API endpoint.

[1113] Input: Received message sent from the device

[1114] Output: Preparing the server for message parsing

[1115] Step 3:

[1116] The server sends incoming messages to a natural language processing (NLP) engine for analysis. The server uses natural language processing models such as Google Cloud NLP or Amazon Comprehend to summarize the message content, analyze sentiment, and categorize it.

[1117] Input: Received message

[1118] Data processing: Analysis using an NLP engine (summarization, sentiment analysis, categorization).

[1119] Output: Analysis results (summary text, sentiment score, category information, etc.)

[1120] Step 4:

[1121] The server uses a template engine based on the analysis results to automatically generate a reply. The reply is created by embedding the necessary data (e.g., date and time, action item) into a predefined template.

[1122] Input: Analysis results and template

[1123] Data processing: Use a template engine to embed analysis results into a template.

[1124] Output: Automated reply

[1125] Specific examples of actions:

[1126] Template: "Hello, thank you for contacting me. [Date and time] is fine. Thank you."

[1127] Analysis result: "Date and time: Next Tuesday, 2 PM"

[1128] Generated reply: "Hello, thank you for contacting me. Tuesday at 2 PM next week is fine. Thank you."

[1129] Step 5:

[1130] The server extracts tasks from electronic communication messages. The server uses key phrase extraction algorithms (e.g., TF-IDF, BERT) to identify important action items, dates, and times from the messages.

[1131] Input: Received message

[1132] Data processing: Analysis using a key phrase extraction algorithm.

[1133] Output: Extracted tasks

[1134] Specific examples of actions:

[1135] Received message: "I would like to schedule a meeting for next Tuesday at 2 PM."

[1136] Extracted task: "Task: Schedule a meeting, Due date: Next Tuesday at 2 PM"

[1137] Step 6:

[1138] The server saves the extracted tasks to a task management system. The server uses task management tools such as Trello or Asana to centrally manage tasks.

[1139] Input: Extracted tasks

[1140] Data processing: Adding tasks to a task management system.

[1141] Output: Saved tasks

[1142] Step 7:

[1143] The server notifies the device of the generated reply and extracted tasks. The device then displays this information to the user via push notifications or in-app notifications.

[1144] Input: Auto-generated reply text, extracted tasks

[1145] Output: Notification to the user

[1146] Step 8:

[1147] The user reviews the reply and task details and makes corrections as needed. A confirmation message is sent from the terminal to the server.

[1148] Input: Instructions for user correction or confirmation.

[1149] Output: Confirmation complete

[1150] Step 9:

[1151] After the device receives confirmation, it automatically sends a reply message to the server. The server then forwards that message to the appropriate recipient.

[1152] Input: Confirmation complete instructions

[1153] Output: Automated reply message sent to the recipient

[1154] These steps automate the entire process, from receiving messages to generating and sending replies, and even managing tasks. This significantly improves the efficiency of users' business communications.

[1155] (Application Example 1)

[1156] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1157] In modern content delivery services, there is a demand for quick and accurate responses to user feedback and request messages. Furthermore, manually performing message analysis and task extraction is time-consuming and labor-intensive, hindering efficient work. Automating processes such as task management and reply generation is also required to reduce the burden on operators and enable faster responses. Current systems struggle to meet these requirements, resulting in limitations in improving the user experience.

[1158] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1159] In this invention, the server includes means for receiving messages, means for analyzing received messages based on natural language processing, means for automatically generating reply text using templates based on the analysis results, means for extracting tasks from messages, means for storing the extracted tasks in a task management system, means for notifying the user of the generated reply text and extracted tasks, means for sending an automatic reply after user confirmation, means for analyzing received feedback and requests and generating appropriate automatic reply texts, and means for extracting and managing tasks for content creation based on the task extraction results. This makes it possible to automate a series of processes from analyzing user messages and extracting tasks to task management and reply text generation, significantly reducing the burden on operators and enabling quick and efficient responses.

[1160] "Means of receiving messages" refers to the means of receiving messages sent by users via email, chat applications, etc.

[1161] Natural language processing is a set of techniques that use computers to understand, interpret, and manipulate human language, and is used to analyze the content of received messages.

[1162] "Methods for automatically generating reply text using templates" refer to methods for automatically generating appropriate reply text by filling in necessary information based on a pre-configured template format.

[1163] "Task extraction methods" refer to methods for identifying important action items, deadlines, etc., from the content of received messages using key phrase extraction algorithms, and extracting them as tasks.

[1164] A "task management system" is a system that stores and manages extracted tasks along with information such as deadlines, priorities, and assigned personnel, making them easily accessible to users.

[1165] "Means of notifying the user" refers to means of notifying the user's device of the generated reply message and the contents of the extracted tasks.

[1166] "Method for sending automatic replies" refers to a method for automatically sending a final reply after the user has reviewed and revised it.

[1167] "Means for analyzing feedback and requests" refers to methods for analyzing the content of user feedback and request messages.

[1168] "Means for extracting and managing tasks for content creation" refers to methods for identifying and managing the tasks necessary for content creation based on tasks extracted from received messages.

[1169] This invention provides a system that automates message processing in content distribution services, thereby reducing the burden on operators. This system includes a process that automatically analyzes received messages, generates replies, and extracts and manages tasks.

[1170] System Configuration

[1171] Message received

[1172] First, the system receives feedback and request messages sent by users via email or chat tools. This allows the system to incorporate messages from users.

[1173] Message Controller

[1174] Received messages are automatically sent from the terminal to the server. The server analyzes the message content using a natural language processing (NLP) engine (e.g., NLTK). At this stage, the message content is understood, and information necessary for generating replies and tasks is extracted.

[1175] Automatically generate reply messages

[1176] The server uses a template engine to generate an appropriate reply based on the analysis results. The template engine constructs the reply by embedding the analyzed information according to a pre-configured template format.

[1177] Task extraction and management

[1178] The server uses a key phrase extraction algorithm to extract tasks from messages. These extracted tasks are identified as action items and deadlines necessary for content creation. These tasks are stored in a task management system and centrally managed along with information such as deadlines, priorities, and assigned personnel.

[1179] User notifications and automatic reply sending

[1180] The server notifies the terminal of the generated reply and extracted tasks. The user receives this notification and reviews and modifies the reply and task details. After review, the terminal automatically sends a confirmation message to the server and sends the final reply message.

[1181] This makes it possible to automate a series of processes, from analyzing user messages and extracting tasks to managing tasks and generating replies, significantly reducing the burden on administrators and enabling quick and efficient responses.

[1182] Specific examples

[1183] For example, if a user sends a message saying, "I'd like to schedule a meeting next Friday at 3 PM to discuss new video content. Would that work for you?", the system will receive this message and automatically generate a reply like this:

[1184] "Hello, thank you for contacting me. Friday at 3 PM next week is fine. Thank you."

[1185] The extracted tasks also include items such as "Schedule a meeting about new video content, deadline: next Friday at 3 PM."

[1186] Example of a prompt

[1187] The following is an example of a specific prompt message:

[1188] Please generate a reply to the following message: "I would like to schedule a meeting next Friday at 3 PM to discuss new video content. Would that work for you?"

[1189] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1190] Step 1:

[1191] The device receives user feedback and request messages via email or chat tools. These messages are imported into the system in text format. The input is the user's message, and the output is the storage of the received message.

[1192] Step 2:

[1193] The terminal sends the received message to the server. Here, the received message data is transferred to the server. The input is the received message, and the output is the transfer of the message data to the server.

[1194] Step 3:

[1195] The server analyzes the content of received messages using a natural language processing (NLP) engine. Specifically, it uses a natural language processing library such as NLTK to tokenize the messages and extract key phrases. The input is the message data forwarded to the server, and the output is the analysis result.

[1196] Step 4:

[1197] The server automatically generates a reply based on the analysis results using a template engine. The template engine embeds the analyzed key phrases and time information into a pre-configured template to create an appropriate reply. The input is the analysis result, and the output is the automatically generated reply.

[1198] Step 5:

[1199] The server executes a keyphrase extraction algorithm to extract tasks from messages. The extracted tasks include important information such as action items and deadlines. The input is the parsing result, and the output is the extracted task information.

[1200] Step 6:

[1201] The server saves the extracted task information to the task management system. The task management system stores information such as deadlines, priorities, and assigned personnel in an easy-to-manage format. The input is the extracted task information, and the output is the tasks stored in the task management system.

[1202] Step 7:

[1203] The server notifies the terminal of the generated reply and extracted tasks. The terminal displays this information to the user and requests confirmation. The input is the automatically generated reply and extracted task information, and the output is the notification to the user.

[1204] Step 8:

[1205] The user checks the notification on their device and modifies the reply and task details as needed. The input is the notified reply and task information, and the output is the modified reply and task information.

[1206] Step 9:

[1207] User verification is complete, and the terminal sends a verification completion instruction to the server. The server sends a final reply message. The input is the verification completion instruction and the revised reply text, and the output is the sending of the final reply message.

[1208] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1209] This invention is a system designed to streamline text-based business communication and reduce user effort. The system combines message reception, content analysis, automatic generation of replies and tasks, user notifications, automatic reply sending, and an emotion engine that recognizes user sentiment. The specific operation of the entire system is described below.

[1210] System Configuration

[1211] 1. Receiving a message

[1212] Users receive emails and chat messages on their devices. This receiving operation is performed through common email clients and chat applications.

[1213] 2. Sending a message

[1214] The terminal automatically sends the content of the received message to the server. The message is transferred to the server as text data.

[1215] 3. Message Analysis

[1216] Received messages are analyzed by a natural language processing (NLP) engine on the server. This analysis extracts important information from the message, such as the date, time, location, and request.

[1217] 4. Emotion recognition

[1218] The server sends the analyzed message to the emotion engine, which evaluates the user's emotions. The emotion engine identifies emotions such as positive, negative, or neutral from the message.

[1219] Specific example:

[1220] Message received: "I'm very sorry to trouble you, but could I cancel tomorrow's meeting?"

[1221] Emotional engine evaluation: Negative

[1222] 5. Generating a reply

[1223] The server generates a reply using a template engine based on the results obtained from the NLP engine and the emotion engine. The template engine creates a reply with an appropriate tone, taking emotion evaluation into consideration.

[1224] Specific example:

[1225] Input: NLP analysis results, emotion assessment (negative)

[1226] output:

[1227] "Hello, thank you for your understanding regarding the cancellation of tomorrow's meeting. We will contact you later with a new date."

[1228] 6. Task Extraction

[1229] The server uses a task engine to extract tasks from the message analysis results. The task engine identifies action items and key phrases in the message and generates a task list.

[1230] Specific example:

[1231] Message received: "Please cancel tomorrow's meeting and reschedule it."

[1232] Extracted task: "Task: Schedule a new meeting, Deadline: Undetermined"

[1233] 7. Saving and managing tasks

[1234] The server stores the extracted tasks in a task management system. The task management system centrally manages detailed task information (deadlines, priorities, etc.) and makes it easily accessible to users.

[1235] 8. User Notifications

[1236] The server notifies the terminal of the generated reply and the extracted task content. The user receives this notification and checks the reply and task content.

[1237] 9. User verification and correction

[1238] The user reviews the generated reply and task details on their device and makes corrections if necessary. Once corrections are complete, the user enters a confirmation message into their device.

[1239] 10. Send automatic reply

[1240] When the terminal receives confirmation from the user, it sends that information to the server. The server automatically sends the confirmed reply to the recipient.

[1241] Through the processing steps described above, users can efficiently conduct text-based business communication without any hassle. Furthermore, the combination of emotion engines enables more appropriate and emotionally resonant replies.

[1242] The following describes the processing flow.

[1243] Step 1: Receive message

[1244] Users receive emails and chat messages on their devices. This receiving operation is performed through common email clients and chat applications.

[1245] Step 2: Send Message

[1246] The terminal automatically sends the content of the received message to the server. It is transferred to the server as text data.

[1247] Step 3: Message Analysis

[1248] The server sends the received message to a natural language processing (NLP) engine. The NLP engine analyzes the message content and extracts important information.

[1249] For example, the date, time, location, and details of the request will be specified.

[1250] Step 4: Emotion Recognition

[1251] The server sends the analyzed message to the emotion engine, which evaluates the user's emotions. The emotion engine identifies emotions such as positive, negative, or neutral from the message.

[1252] For example, we can identify negative emotions from the phrase "I'm so sorry for the trouble..." in a message.

[1253] Step 5: Generate reply

[1254] The server uses a template engine to generate a reply based on the results obtained from the NLP engine and the emotion engine.

[1255] The template engine takes into account the analysis results and sentiment assessment to create a reply with an appropriate tone.

[1256] Step 6: Task Extraction

[1257] The server extracts tasks from the message using a task engine. The task engine identifies action items and key phrases within the message and generates a task list.

[1258] As an example, from a request that says "Please set a new date," we extract the task "Task: Set a new meeting."

[1259] Step 7: Save Task

[1260] The server saves the extracted tasks to the task management system. The task management system centrally manages detailed task information (deadlines, priorities, etc.).

[1261] Step 8: User Notifications

[1262] The server notifies the terminal of the generated reply and extracted task details. The user then sees the reply and task details.

[1263] Step 9: User verification and correction

[1264] The user reviews the generated reply and task details on their device. If necessary, the user modifies the reply and task.

[1265] The user enters confirmation instructions into the terminal.

[1266] Step 10: Send automatic reply

[1267] When the terminal receives confirmation from the user, it sends that information to the server.

[1268] The server automatically sends the confirmed reply to the recipient.

[1269] This process allows users to engage in efficient, emotionally sensitive, and effortless text-based business communication.

[1270] (Example 2)

[1271] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1272] In traditional text-based business communication, users had to spend considerable time analyzing received messages, drafting appropriate replies, and extracting and managing tasks. This manual process was time-consuming and labor-intensive, increasing the burden on users. Furthermore, it resulted in the generation of impersonal, mechanical replies that lacked emotional considerations, leading to a decline in communication quality.

[1273] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1274] In this invention, the server includes means for receiving messages, means for analyzing the received messages based on natural language processing, means for recognizing emotions based on the analysis results, means for automatically generating reply text using templates while considering emotion evaluation, means for extracting tasks from messages, means for storing the extracted tasks in a task management system, means for notifying the user of the generated reply text and extracted tasks, and means for sending an automatic reply after user confirmation. This allows the user to perform message analysis, generate appropriate reply texts, and extract and manage tasks in a unified manner without any effort. Furthermore, the quality of communication can be improved by providing reply texts that take emotions into consideration.

[1275] "Means for receiving messages" refers to system components that allow users to receive text-based messages, such as emails and chat messages, through their devices.

[1276] "Means for analysis based on natural language processing" refers to a system component that includes a natural language processing engine used to analyze received messages and extract important information (such as date and time, location, and requests).

[1277] "Means of recognizing emotions" refers to system components that include an emotion engine for evaluating the user's emotions from analyzed messages and identifying emotions such as positive, negative, or neutral.

[1278] "A means of automatically generating reply text using templates while considering sentiment evaluation" refers to a system component that automatically generates reply text with an appropriate tone using a template engine, based on the analysis results of natural language processing and sentiment evaluation.

[1279] "Means for extracting tasks" refers to system components that include a task engine for extracting action items and key phrases from the analysis results of messages and identifying specific tasks.

[1280] "Means of saving to a task management system" refers to system components that include task management tools used to save and centrally manage extracted tasks.

[1281] "Means for notifying the user of the generated reply and extracted tasks" refers to system components for notifying the user's terminal of the content of the generated reply and tasks.

[1282] "Method for sending an automatic reply after user confirmation" refers to a system component that automatically sends a reply after the user has reviewed and corrected the generated reply text and task content.

[1283] This invention is a system designed to streamline text-based business communication and reduce the burden on users. Specifically, this system receives messages, analyzes their content, recognizes sentiment, automatically generates replies and tasks, notifies users, and sends automatic replies. The implementation method of this system is described below.

[1284] System configuration and operation

[1285] 1. Receiving a message

[1286] Users receive emails and chat messages using their devices (such as PCs and smartphones). Applications used include Outlook, Gmail, and Slack. When a user receives a new message, its content is saved on their device.

[1287] 2. Sending a message

[1288] The terminal sends the received message to the server. The message is transferred to the server in text data format. This process involves sending data via HTTP requests or WebSockets.

[1289] 3. Message Analysis

[1290] The server sends received messages to a natural language processing (NLP) engine for analysis. The NLP engine used may include the Google Cloud Natural Language API. Through analysis, important information (such as date, time, location, and request details) is extracted from the message.

[1291] 4. Emotion recognition

[1292] The server sends the analyzed message to an emotion recognition engine to evaluate the user's emotions. Engines such as IBM Watson Tone Analyzer are used to identify emotions such as positive, negative, or neutral from the message.

[1293] Specific example:

[1294] Message received: "I'm very sorry to trouble you, but could I cancel tomorrow's meeting?"

[1295] Emotional engine evaluation: Negative

[1296] 5. Generating a reply

[1297] The server generates a reply using a template engine based on the results obtained from the NLP engine and the emotion engine. The template engine used is typically Handlebars.js, which generates a reply with an appropriate tone that takes emotion evaluation into account.

[1298] Specific example:

[1299] Input: NLP analysis results (request: meeting cancellation), emotion evaluation (negative)

[1300] Output: "Hello, thank you for your understanding regarding the cancellation of tomorrow's meeting. We will contact you later with a new date."

[1301] 6. Task Extraction

[1302] The server uses a task engine to extract tasks from the message analysis results. Task engines such as Apache OpenNLP identify action items and key phrases within the message and generate a task list.

[1303] Specific example:

[1304] Message received: "Please cancel tomorrow's meeting and reschedule it."

[1305] Extracted task: "Task: Schedule a new meeting, Deadline: Undetermined"

[1306] 7. Saving and managing tasks

[1307] The server saves the extracted tasks to a task management system. Task management systems such as Trello or Asana are used to centrally manage detailed task information (deadlines, priorities, etc.).

[1308] 8. User Notifications

[1309] The server notifies the terminal of the generated reply and the extracted task content. The user receives this notification and checks the reply and task content.

[1310] 9. User verification and correction

[1311] The user reviews the generated reply and task details on their device and makes corrections if necessary. Once corrections are complete, the user enters a confirmation message into their device.

[1312] Specific example:

[1313] The user modifies the reply to "Thank you for your understanding" and clicks "Confirmation Complete".

[1314] 10. Send automatic reply

[1315] The terminal sends a confirmation message from the user to the server. The server then automatically sends a reply to the recipient based on the confirmed message.

[1316] Example of a prompt:

[1317] Message received: "I'm very sorry to trouble you, but could I cancel tomorrow's meeting?"

[1318] Emotional engine rating: "Negative"

[1319] NLP analysis result: "Cancellation request"

[1320] Prompt to input to the generating AI model: "The user's sentiment rating for this message has been determined to be negative. Please create a reply in an appropriate tone to address the cancellation request."

[1321] As described above, this system allows users to perform message analysis, generate appropriate replies, and extract and manage tasks in a unified manner without any extra effort. Furthermore, by utilizing the sentiment engine, it is possible to generate more appropriate and emotionally resonant replies.

[1322] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1323] Detailed explanation of the processing steps

[1324] Step 1: Receiving a message

[1325] The user receives emails and chat messages on their device.

[1326] input:

[1327] Email or chat message

[1328] Data processing:

[1329] none

[1330] output:

[1331] Received message data

[1332] Specific actions:

[1333] A user receives a new email using the Gmail application. For example, they receive an email that says, "I would like to cancel tomorrow's meeting."

[1334] Step 2: Sending a message

[1335] The terminal sends the received message to the server.

[1336] input:

[1337] Received message data

[1338] Data processing:

[1339] Convert the message to JSON format

[1340] output:

[1341] HTTP POST request to the server

[1342] Specific actions:

[1343] The terminal converts the received message into JSON format and sends it to the server as an HTTP POST request.

[1344] Step 3: Message Analysis

[1345] The server sends the received message to a natural language processing (NLP) engine for analysis.

[1346] input:

[1347] JSON data of the received message

[1348] Data processing:

[1349] Information extraction using natural language processing

[1350] output:

[1351] Analysis results (request details, date, time, location, etc.)

[1352] Specific actions:

[1353] The server uses an NLP engine (e.g., Google Cloud Natural Language API) to extract important information such as "cancellation of a meeting and scheduling of a new date."

[1354] Step 4: Emotion Recognition

[1355] The server sends the analyzed message to the emotion recognition engine, which then evaluates the user's emotions.

[1356] input:

[1357] Analyzed message data

[1358] Data processing:

[1359] sentiment analysis

[1360] output:

[1361] Emotional evaluation (positive, negative, neutral, etc.)

[1362] Specific actions:

[1363] The server uses an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to identify the emotion as "negative."

[1364] Step 5: Generating a reply

[1365] The server generates a reply using a template engine based on the NLP analysis results and sentiment evaluation.

[1366] input:

[1367] NLP analysis results, emotion evaluation

[1368] Data processing:

[1369] Generate reply text using a template engine.

[1370] output:

[1371] Generated reply

[1372] Specific actions:

[1373] The server uses the Handlebars.js template engine to generate a reply message that reads, "Hello, thank you for your understanding regarding the cancellation of tomorrow's meeting. We will contact you later with a new date."

[1374] Step 6: Task Extraction

[1375] The server uses a task engine to extract tasks from the message analysis results.

[1376] input:

[1377] NLP analysis results

[1378] Data processing:

[1379] Task extraction algorithm

[1380] output:

[1381] Extracted tasks

[1382] Specific actions:

[1383] The server uses Apache OpenNLP to extract a task called "Set up a new meeting" and sets its name to "Task: Set up a new meeting, Due date: Undetermined".

[1384] Step 7: Saving and managing tasks

[1385] The server saves the extracted tasks to the task management system.

[1386] input:

[1387] Extracted tasks

[1388] Data processing:

[1389] Save to task management system

[1390] output:

[1391] Tasks saved in the task management system

[1392] Specific actions:

[1393] The server uses the Trello API to save the extracted tasks as new cards.

[1394] Step 8: User Notifications

[1395] The server notifies the terminal of the generated reply message and the extracted task content.

[1396] input:

[1397] Generated reply text, extracted tasks

[1398] Data processing:

[1399] Generating push notifications

[1400] output:

[1401] Push notifications to your device

[1402] Specific actions:

[1403] The server sends a push notification to the device, and the user checks the "reply message" and "task details" on the screen.

[1404] Step 9: User verification and correction

[1405] The user reviews the generated reply and task details on their device and makes corrections if necessary.

[1406] input:

[1407] Generated reply text, extracted tasks

[1408] Data processing:

[1409] User modifications

[1410] output:

[1411] Revised reply, task

[1412] Specific actions:

[1413] The user modifies the reply to "Thank you for your understanding" and clicks "Confirmation Complete".

[1414] Step 10: Send automatic reply

[1415] The device sends a confirmation message from the user to the server and then sends a confirmed reply to the other party.

[1416] input:

[1417] Revised reply, user confirmation complete instruction

[1418] Data processing:

[1419] Sending a reply

[1420] output:

[1421] Reply sent to the recipient

[1422] Specific actions:

[1423] The terminal notifies the server that "confirmation complete," and the server sends a "confirmed reply" to the recipient as an email.

[1424] (Application Example 2)

[1425] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1426] In conventional factory robot systems, communication, reporting, and error message processing between robots were handled individually, resulting in difficulties in efficient operation. Furthermore, there was no system that could generate appropriate, emotion-based responses while reducing the burden on the user. Therefore, there was a need for a system that provides automated, advanced communication between robots and emotion-responsive response capabilities.

[1427] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving messages, means for analyzing the received messages based on natural language processing, means for automatically generating a reply using a template based on the analysis results, means for extracting tasks from messages, means for storing the extracted tasks in a task management system, means for notifying the user of the generated reply and extracted tasks, means for sending an automatic reply after user confirmation, means for evaluating emotions from the analyzed messages, means for selecting a reply template based on the evaluated emotions, means for factory robots to report status and request tasks from other robots and managers, and means for analyzing received error messages and performing automatic replies and task reassignments. This makes it possible to streamline communication between robots and realize appropriate responses based on emotions.

[1428] "Means of receiving messages" refers to the ability to electronically acquire messages from robots or users.

[1429] "Natural language processing" is a technology that analyzes received messages as text data and understands and processes their content.

[1430] "Method for automatically generating reply messages" refers to a function that automatically creates appropriate reply messages using templates based on analysis results.

[1431] "Methods for extracting tasks from messages" refers to a function that identifies and extracts specific work items or action items from the content of a message.

[1432] A "task management system" is a system for recording, monitoring, and managing extracted tasks.

[1433] "Means of notifying the user" refers to a function that informs the user of the generated reply and extracted tasks.

[1434] "Method for sending automatic replies" refers to a function that automatically sends a generated reply message to the recipient after user confirmation.

[1435] "Methods for evaluating emotions" refer to technologies that identify emotions such as positive and negative from analyzed messages.

[1436] The "means of selecting a reply template" refer to the function of selecting a template to generate a reply with an appropriate tone based on the evaluated emotion.

[1437] "Robot status reporting" refers to the act of a robot in a factory reporting its current status and work progress.

[1438] "A means of requesting tasks" refers to a function that allows a robot to request new tasks, repairs, or other tasks from other robots or administrators.

[1439] "Methods for analyzing error messages" refer to techniques for analyzing received error messages, understanding their content, and taking appropriate countermeasures.

[1440] "Means for task reassignment" refers to a function that redistributes tasks among robots and users based on analysis results.

[1441] This invention is a system for maximizing work efficiency by enabling robots in a factory to automatically communicate with other robots and managers. This system combines a natural language processing (NLP) engine, a sentiment evaluation engine, a template engine, a task management system, and other components. The detailed operation of the system is described below.

[1442] 1. Receiving a message

[1443] The server receives messages from robots within the factory, such as status reports, error messages, and task requests. These messages are then electronically incorporated into the system.

[1444] 2. Message Analysis

[1445] Received messages are analyzed by a natural language processing engine (NLP engine) on the server. This analysis extracts necessary information from the message (date and time, location, error details, request, etc.).

[1446] 3. Emotional evaluation

[1447] The analyzed message is sent to an emotion evaluation engine, where emotions such as positive, negative, or neutral are identified. For example, the message "The device has malfunctioned" is evaluated as negative.

[1448] 4. Generating a reply

[1449] The server generates a reply using a template engine based on the results obtained from the NLP engine and the sentiment evaluation engine. The template engine creates a reply with an appropriate tone based on the evaluated sentiment.

[1450] 5. Task Extraction

[1451] The server extracts tasks from the message analysis results. This task extraction uses a key phrase extraction algorithm to identify specific work items and action items.

[1452] 6. Saving and managing tasks

[1453] The extracted tasks are stored in a task management system. The task management system centralizes detailed task information, making it easy for robots and administrators to access and manage it.

[1454] 7. User notifications and automatic replies

[1455] The server notifies the user of the generated reply and the extracted task details. The user reviews this and makes any necessary corrections. Once final confirmation is complete, the server automatically sends the reply to the recipient.

[1456] Specific example

[1457] For example, if robot A sends the message "The device has malfunctioned. It needs repair," the server receives this message. The NLP engine analyzes the message and extracts the information "malfunction" and "repair needed." The sentiment evaluation engine evaluates this message as "negative." The server uses the template engine to generate a reply message saying "A problem has occurred. We will address it promptly." At the same time, a "repair task" is saved in the task management system.

[1458] Example of a prompt

[1459] Analyze the message "The device has malfunctioned. Repair is needed," perform a sentiment assessment, and generate an appropriate response.

[1460] This system streamlines communication between robots and enables responses based on appropriate emotions. This significantly reduces the burden on users and improves overall factory work efficiency.

[1461] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1462] Step 1:

[1463] The server receives messages from robots and administrators within the factory. These messages are sent in text format and are received by the server's receiving system. Input messages include robot status reports, error messages, and task requests. The text data of the received messages is stored on the server as output.

[1464] Step 2:

[1465] The server sends the received text data to a natural language processing (NLP) engine for message analysis. This NLP engine extracts important information such as the date and time, location, error details, and request details. The input is the text data of the received message, and the output is the analysis results.

[1466] Step 3:

[1467] The server sends the analysis results to the emotion evaluation engine, which evaluates the emotions from the message. The emotions evaluated include positive, negative, and neutral. The input for this step is the analysis results of the NLP engine, and the output is the emotion evaluation result.

[1468] Step 4:

[1469] The server automatically generates a reply using a template engine based on the sentiment evaluation results. The input is the sentiment evaluation results and analysis results, and the output is the generated reply. Specifically, the template engine selects an appropriate template and uses text generation AI to create the reply.

[1470] Step 5:

[1471] The server uses a key phrase extraction algorithm to extract tasks from the analysis results. The input is the analysis results of the NLP engine, and the output is a list of specific tasks. Specifically, it extracts repair tasks from the information "repair needed".

[1472] Step 6:

[1473] The server saves the extracted tasks to the task management system. The input is a list of tasks, and the output is the tasks saved in the task management database. This allows for centralized management of detailed information for each task (deadline, priority, etc.).

[1474] Step 7:

[1475] The server notifies the user of the generated reply and extracted task content. The input is the reply and task list, and the output is a notification sent to the user's terminal. The user reviews this and makes corrections as needed.

[1476] Step 8:

[1477] The user reviews the reply and task details, makes any necessary corrections, and then performs a final check. The input is the user's corrections, and the output is the corrected reply and task list, which are sent to the server.

[1478] Step 9:

[1479] After user confirmation, the server automatically sends the generated reply to the recipient. The input is the reply confirmed by the user, and the output is the reply message sent to the recipient. This ensures that messages are processed at the appropriate time.

[1480] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1481] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1482] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1483] [Fourth Embodiment]

[1484] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1485] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1486] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1487] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1488] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1489] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1490] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1491] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1492] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1493] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1494] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1495] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1496] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1497] This invention is a system designed to streamline text-based business communication and reduce user effort. The system includes processes such as message reception, content analysis, automatic generation of replies and tasks, user notifications, and automatic reply sending. Its specific operation is described below in natural language.

[1498] System Configuration

[1499] 1. Receiving a message

[1500] Users receive emails and chat messages on their devices. This receiving operation is performed through typical email clients and chat applications.

[1501] 2. Message Analysis

[1502] The received message is automatically sent from the terminal to the server. The server sends the message content to a natural language processing (NLP) engine for analysis.

[1503] 3. Automatic generation of reply messages

[1504] The server automatically generates a reply using a template engine based on the analysis results. The template engine generates an appropriate reply by filling in the necessary information based on a pre-configured template format.

[1505] Specific example:

[1506] Message received: "I'd like to schedule a meeting next Tuesday at 2 PM. Would that work for you?"

[1507] Automated reply: "Hello, thank you for contacting me. Tuesday at 2 PM next week is fine. Thank you."

[1508] 4. Task Extraction

[1509] The server extracts tasks from the received messages. A key phrase extraction algorithm is used to identify important action items, dates, times, and other relevant information.

[1510] Specific example:

[1511] Received message: "I would like to schedule a meeting for next Tuesday at 2 PM."

[1512] Extracted task: "Task: Schedule a meeting, Due date: Next Tuesday at 2 PM"

[1513] 5. Saving and managing tasks

[1514] The server stores the extracted tasks in a task management system. The task management system centrally manages information such as task deadlines, priorities, and assigned personnel, making it easy for users to access.

[1515] 6. User Notifications

[1516] The server notifies the terminal of the generated reply and extracted tasks. The user receives this notification and checks the reply and task details.

[1517] 7. Send automatic reply

[1518] The user reviews the reply message and task details, makes any necessary corrections, and then gives a confirmation signal. Based on this signal, the device automatically sends a reply message to the server, which then sends the reply to the recipient.

[1519] This system automates the entire process, from analyzing received messages and generating replies to extracting and managing tasks. This significantly reduces the time and effort users spend on daily business communication.

[1520] The following describes the processing flow.

[1521] Step 1: Receive message

[1522] Users receive emails and chat messages on their devices. These messages are received from mail servers and chat servers.

[1523] The terminal temporarily stores the received message and sends its contents to the server.

[1524] Step 2: Sending a message

[1525] The terminal sends the content of the received message to the server. The message is transferred to the server as text data.

[1526] Step 3: Message Analysis

[1527] The server sends the received message to a natural language processing (NLP) engine. The NLP engine analyzes the message content and extracts important information.

[1528] Specifically, the NLP engine identifies the date, time, location, and request from the message and outputs the analysis results.

[1529] Step 4: Generating a reply

[1530] The server generates a reply using a template engine based on the analysis results obtained from the NLP engine.

[1531] The template engine creates a reply by embedding the analysis results into a pre-prepared template.

[1532] Step 5: Task Extraction

[1533] The server uses a task engine to extract tasks from the message analysis results.

[1534] The task engine identifies action items and key phrases within a message and generates a task list.

[1535] Step 6: Save the task

[1536] The server saves the extracted tasks to the task management system.

[1537] A task management system centralizes task details (deadlines, priorities, etc.) and makes them easily accessible to users.

[1538] Step 7: User Notifications

[1539] The server notifies the terminal of the generated reply message and the extracted task content.

[1540] The user receives a notification on their device and checks the generated reply and task details.

[1541] Step 8: User verification and correction

[1542] The user reviews the generated reply and task details on their device and makes corrections if necessary.

[1543] Once the corrections are complete, the user enters a confirmation instruction into the terminal.

[1544] Step 9: Send automatic reply

[1545] When the terminal receives confirmation from the user, it sends that information to the server.

[1546] The server automatically sends the confirmed reply to the recipient.

[1547] Through the above processing steps, users can efficiently conduct text-based business communication without any extra effort.

[1548] (Example 1)

[1549] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1550] In business communication, responding to received messages and managing related tasks is time-consuming and laborious, reducing user efficiency. Furthermore, accurately analyzing message content and responding quickly and precisely is crucial for smooth business operations, but manual processes have limitations. Therefore, there is a need for systems that automate these processes and reduce user effort and time.

[1551] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1552] In this invention, the server includes means for receiving electronic communication messages using a personal terminal, means for transmitting the received electronic communication messages to a central processing unit for analysis, means for the central processing unit to analyze the message content using a natural language processing model, means for automatically generating a reply message using a predefined template based on the analysis results, means for extracting tasks from the electronic communication messages, means for storing the extracted tasks in a task management device, means for notifying the personal terminal of the automatically generated reply message and the extracted tasks, and means for sending an automatic reply message after user confirmation. This makes it possible to automate a series of processes from analyzing received messages to generating reply messages, extracting tasks, and managing them.

[1553] A "personal device" is an electronic device used by a user to receive and send emails and chat messages.

[1554] "Electronic communication messages" refer to digital text messages such as emails and chat messages that are sent and received via the internet or other communication networks.

[1555] A "central processing unit" is a computer server or cloud computing system that analyzes received electronic communication messages.

[1556] A "natural language processing model" is a machine learning model or algorithm that analyzes the content of an incoming message and understands and generates human language.

[1557] A "predefined template" is a pre-configured text format used when automatically generating reply messages.

[1558] A "template engine" is a software development tool that combines templates and dynamic data to generate content.

[1559] A "task management device" is software or a system used to manage and track extracted tasks.

[1560] A "key phrase extraction algorithm" is an algorithm used to identify important phrases and information from electronic communication messages.

[1561] An "automatic reply message" is a message that the system automatically sends after the user has reviewed or corrected something.

[1562] This invention is a system for streamlining text-based business communication and reducing user effort. The system includes processes for receiving messages, analyzing content, automatically generating replies and tasks, notifying users, and sending automatic replies.

[1563] System Configuration

[1564] Message received

[1565] Users receive emails and chat messages on their personal devices. This receiving operation is performed through common email and chat applications (e.g., Outlook, Slack) that process electronic communication messages.

[1566] Message Controller

[1567] Received electronic communication messages are automatically sent from the terminal to the central processing unit (CCU). The CCU (e.g., a cloud server) analyzes the message content using a natural language processing model (e.g., Google Cloud NLP, Amazon Comprehend). The data analyzed by the NLP engine is processed in various ways, such as summarization, categorization, and sentiment analysis.

[1568] Automatically generate reply messages

[1569] The central processing unit automatically generates reply messages using a template engine (e.g., Mustache, Handlebars) based on the analysis results. Predefined templates contain the basic structure of appropriate reply messages, into which the analysis data is embedded.

[1570] Specific example:

[1571] Message received: "I'd like to schedule a meeting next Tuesday at 2 PM. Would that work for you?"

[1572] Automated reply: "Hello, thank you for contacting me. Tuesday at 2 PM next week is fine. Thank you."

[1573] Task extraction

[1574] The central processing unit extracts tasks from electronic communication messages. Key phrase extraction algorithms (e.g., TF-IDF, BERT) are used to identify important action items, dates, and times.

[1575] Specific example:

[1576] Received message: "I would like to schedule a meeting for next Tuesday at 2 PM."

[1577] Extracted task: "Task: Schedule a meeting, Due date: Next Tuesday at 2 PM"

[1578] Task saving and management

[1579] The central processing unit saves the extracted tasks to a task management system (e.g., Trello, Asana). The task management system centrally manages information such as task deadlines, priorities, and assignees, making it easily accessible to users.

[1580] User notifications

[1581] The central processing unit notifies the user's personal device of the generated reply and extracted tasks. The device then displays the generated content to the user via push notifications or in-app notifications.

[1582] Automatic reply sent

[1583] After the user reviews the reply and task details and makes any necessary corrections, the personal device sends a confirmation message. The device then sends this message to the central processing unit, which automatically sends a reply message to the recipient.

[1584] Example of a prompt

[1585] Message component:

[1586] The prompt text that users use to have a natural language processing engine parse their message:

[1587] Please analyze the following message: "I would like to schedule a meeting next Tuesday at 2 PM. Would that work for you?"

[1588] Reply text generation:

[1589] Prompts used to generate automated replies using a template engine:

[1590] "Please generate the following reply: Use the template 'Hello, thank you for contacting me. [Date and time] is fine. Thank you.' and fill in 'Next Tuesday at 2 PM' as the date and time."

[1591] This system automates a series of processes, from analyzing received messages and generating replies to extracting and managing tasks, allowing users to significantly reduce the time and effort spent on daily business communication.

[1592] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1593] Step 1:

[1594] A user receives electronic communication messages on their personal device. The device uses a common email client or chat application (e.g., Outlook, Slack) to receive new messages.

[1595] Input: New email or chat message

[1596] Output: Forward received messages to the server

[1597] Step 2:

[1598] The terminal automatically sends received electronic communication messages to the server. The terminal sends the received message information via the server's API endpoint.

[1599] Input: Received message sent from the device

[1600] Output: Preparing the server for message parsing

[1601] Step 3:

[1602] The server sends incoming messages to a natural language processing (NLP) engine for analysis. The server uses natural language processing models such as Google Cloud NLP or Amazon Comprehend to summarize the message content, analyze sentiment, and categorize it.

[1603] Input: Received message

[1604] Data processing: Analysis using an NLP engine (summarization, sentiment analysis, categorization).

[1605] Output: Analysis results (summary text, sentiment score, category information, etc.)

[1606] Step 4:

[1607] The server uses a template engine based on the analysis results to automatically generate a reply. The reply is created by embedding the necessary data (e.g., date and time, action item) into a predefined template.

[1608] Input: Analysis results and template

[1609] Data processing: Use a template engine to embed analysis results into a template.

[1610] Output: Automated reply

[1611] Specific examples of actions:

[1612] Template: "Hello, thank you for contacting me. [Date and time] is fine. Thank you."

[1613] Analysis result: "Date and time: Next Tuesday, 2 PM"

[1614] Generated reply: "Hello, thank you for contacting me. Tuesday at 2 PM next week is fine. Thank you."

[1615] Step 5:

[1616] The server extracts tasks from electronic communication messages. The server uses key phrase extraction algorithms (e.g., TF-IDF, BERT) to identify important action items, dates, and times from the messages.

[1617] Input: Received message

[1618] Data processing: Analysis using a key phrase extraction algorithm.

[1619] Output: Extracted tasks

[1620] Specific examples of actions:

[1621] Received message: "I would like to schedule a meeting for next Tuesday at 2 PM."

[1622] Extracted task: "Task: Schedule a meeting, Due date: Next Tuesday at 2 PM"

[1623] Step 6:

[1624] The server saves the extracted tasks to a task management system. The server uses task management tools such as Trello or Asana to centrally manage tasks.

[1625] Input: Extracted tasks

[1626] Data processing: Adding tasks to a task management system.

[1627] Output: Saved tasks

[1628] Step 7:

[1629] The server notifies the device of the generated reply and extracted tasks. The device then displays this information to the user via push notifications or in-app notifications.

[1630] Input: Auto-generated reply text, extracted tasks

[1631] Output: Notification to the user

[1632] Step 8:

[1633] The user reviews the reply and task details and makes corrections as needed. A confirmation message is sent from the terminal to the server.

[1634] Input: Instructions for user correction or confirmation.

[1635] Output: Confirmation complete

[1636] Step 9:

[1637] After the device receives confirmation, it automatically sends a reply message to the server. The server then forwards that message to the appropriate recipient.

[1638] Input: Confirmation complete instructions

[1639] Output: Automated reply message sent to the recipient

[1640] These steps automate the entire process, from receiving messages to generating and sending replies, and even managing tasks. This significantly improves the efficiency of users' business communications.

[1641] (Application Example 1)

[1642] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1643] In modern content delivery services, there is a demand for quick and accurate responses to user feedback and request messages. Furthermore, manually performing message analysis and task extraction is time-consuming and labor-intensive, hindering efficient work. Automating processes such as task management and reply generation is also required to reduce the burden on operators and enable faster responses. Current systems struggle to meet these requirements, resulting in limitations in improving the user experience.

[1644] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1645] In this invention, the server includes means for receiving messages, means for analyzing received messages based on natural language processing, means for automatically generating reply text using templates based on the analysis results, means for extracting tasks from messages, means for storing the extracted tasks in a task management system, means for notifying the user of the generated reply text and extracted tasks, means for sending an automatic reply after user confirmation, means for analyzing received feedback and requests and generating appropriate automatic reply texts, and means for extracting and managing tasks for content creation based on the task extraction results. This makes it possible to automate a series of processes from analyzing user messages and extracting tasks to task management and reply text generation, significantly reducing the burden on operators and enabling quick and efficient responses.

[1646] "Means of receiving messages" refers to the means of receiving messages sent by users via email, chat applications, etc.

[1647] Natural language processing is a set of techniques that use computers to understand, interpret, and manipulate human language, and is used to analyze the content of received messages.

[1648] "Methods for automatically generating reply text using templates" refer to methods for automatically generating appropriate reply text by filling in necessary information based on a pre-configured template format.

[1649] "Task extraction methods" refer to methods for identifying important action items, deadlines, etc., from the content of received messages using key phrase extraction algorithms, and extracting them as tasks.

[1650] A "task management system" is a system that stores and manages extracted tasks along with information such as deadlines, priorities, and assigned personnel, making them easily accessible to users.

[1651] "Means of notifying the user" refers to means of notifying the user's device of the generated reply message and the contents of the extracted tasks.

[1652] "Method for sending automatic replies" refers to a method for automatically sending a final reply after the user has reviewed and revised it.

[1653] "Means for analyzing feedback and requests" refers to methods for analyzing the content of user feedback and request messages.

[1654] "Means for extracting and managing tasks for content creation" refers to methods for identifying and managing the tasks necessary for content creation based on tasks extracted from received messages.

[1655] This invention provides a system that automates message processing in content distribution services, thereby reducing the burden on operators. This system includes a process that automatically analyzes received messages, generates replies, and extracts and manages tasks.

[1656] System Configuration

[1657] Message received

[1658] First, the system receives feedback and request messages sent by users via email or chat tools. This allows the system to incorporate messages from users.

[1659] Message Controller

[1660] Received messages are automatically sent from the terminal to the server. The server analyzes the message content using a natural language processing (NLP) engine (e.g., NLTK). At this stage, the message content is understood, and information necessary for generating replies and tasks is extracted.

[1661] Automatically generate reply messages

[1662] The server uses a template engine to generate an appropriate reply based on the analysis results. The template engine constructs the reply by embedding the analyzed information according to a pre-configured template format.

[1663] Task extraction and management

[1664] The server uses a key phrase extraction algorithm to extract tasks from messages. These extracted tasks are identified as action items and deadlines necessary for content creation. These tasks are stored in a task management system and centrally managed along with information such as deadlines, priorities, and assigned personnel.

[1665] User notifications and automatic reply sending

[1666] The server notifies the terminal of the generated reply and extracted tasks. The user receives this notification and reviews and modifies the reply and task details. After review, the terminal automatically sends a confirmation message to the server and sends the final reply message.

[1667] This makes it possible to automate a series of processes, from analyzing user messages and extracting tasks to managing tasks and generating replies, significantly reducing the burden on administrators and enabling quick and efficient responses.

[1668] Specific examples

[1669] For example, if a user sends a message saying, "I'd like to schedule a meeting next Friday at 3 PM to discuss new video content. Would that work for you?", the system will receive this message and automatically generate a reply like this:

[1670] "Hello, thank you for contacting me. Friday at 3 PM next week is fine. Thank you."

[1671] The extracted tasks also include items such as "Schedule a meeting about new video content, deadline: next Friday at 3 PM."

[1672] Example of a prompt

[1673] The following is an example of a specific prompt message:

[1674] Please generate a reply to the following message: "I would like to schedule a meeting next Friday at 3 PM to discuss new video content. Would that work for you?"

[1675] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1676] Step 1:

[1677] The device receives user feedback and request messages via email or chat tools. These messages are imported into the system in text format. The input is the user's message, and the output is the storage of the received message.

[1678] Step 2:

[1679] The terminal sends the received message to the server. Here, the received message data is transferred to the server. The input is the received message, and the output is the transfer of the message data to the server.

[1680] Step 3:

[1681] The server analyzes the content of received messages using a natural language processing (NLP) engine. Specifically, it uses a natural language processing library such as NLTK to tokenize the messages and extract key phrases. The input is the message data forwarded to the server, and the output is the analysis result.

[1682] Step 4:

[1683] The server automatically generates a reply based on the analysis results using a template engine. The template engine embeds the analyzed key phrases and time information into a pre-configured template to create an appropriate reply. The input is the analysis result, and the output is the automatically generated reply.

[1684] Step 5:

[1685] The server executes a keyphrase extraction algorithm to extract tasks from messages. The extracted tasks include important information such as action items and deadlines. The input is the parsing result, and the output is the extracted task information.

[1686] Step 6:

[1687] The server saves the extracted task information to the task management system. The task management system stores information such as deadlines, priorities, and assigned personnel in an easy-to-manage format. The input is the extracted task information, and the output is the tasks stored in the task management system.

[1688] Step 7:

[1689] The server notifies the terminal of the generated reply and extracted tasks. The terminal displays this information to the user and requests confirmation. The input is the automatically generated reply and extracted task information, and the output is the notification to the user.

[1690] Step 8:

[1691] The user checks the notification on their device and modifies the reply and task details as needed. The input is the notified reply and task information, and the output is the modified reply and task information.

[1692] Step 9:

[1693] User verification is complete, and the terminal sends a verification completion instruction to the server. The server sends a final reply message. The input is the verification completion instruction and the revised reply text, and the output is the sending of the final reply message.

[1694] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1695] This invention is a system designed to streamline text-based business communication and reduce user effort. The system combines message reception, content analysis, automatic generation of replies and tasks, user notifications, automatic reply sending, and an emotion engine that recognizes user sentiment. The specific operation of the entire system is described below.

[1696] System Configuration

[1697] 1. Receiving a message

[1698] Users receive emails and chat messages on their devices. This receiving operation is performed through common email clients and chat applications.

[1699] 2. Sending a message

[1700] The terminal automatically sends the content of the received message to the server. The message is transferred to the server as text data.

[1701] 3. Message Analysis

[1702] Received messages are analyzed by a natural language processing (NLP) engine on the server. This analysis extracts important information from the message, such as the date, time, location, and request.

[1703] 4. Emotion recognition

[1704] The server sends the analyzed message to the emotion engine, which evaluates the user's emotions. The emotion engine identifies emotions such as positive, negative, or neutral from the message.

[1705] Specific example:

[1706] Message received: "I'm very sorry to trouble you, but could I cancel tomorrow's meeting?"

[1707] Emotional engine evaluation: Negative

[1708] 5. Generating a reply

[1709] The server generates a reply using a template engine based on the results obtained from the NLP engine and the emotion engine. The template engine creates a reply with an appropriate tone, taking emotion evaluation into consideration.

[1710] Specific example:

[1711] Input: NLP analysis results, emotion assessment (negative)

[1712] output:

[1713] "Hello, thank you for your understanding regarding the cancellation of tomorrow's meeting. We will contact you later with a new date."

[1714] 6. Task Extraction

[1715] The server uses a task engine to extract tasks from the message analysis results. The task engine identifies action items and key phrases in the message and generates a task list.

[1716] Specific example:

[1717] Message received: "Please cancel tomorrow's meeting and reschedule it."

[1718] Extracted task: "Task: Schedule a new meeting, Deadline: Undetermined"

[1719] 7. Saving and managing tasks

[1720] The server stores the extracted tasks in a task management system. The task management system centrally manages detailed task information (deadlines, priorities, etc.) and makes it easily accessible to users.

[1721] 8. User Notifications

[1722] The server notifies the terminal of the generated reply and the extracted task content. The user receives this notification and checks the reply and task content.

[1723] 9. User verification and correction

[1724] The user reviews the generated reply and task details on their device and makes corrections if necessary. Once corrections are complete, the user enters a confirmation message into their device.

[1725] 10. Send automatic reply

[1726] When the terminal receives confirmation from the user, it sends that information to the server. The server automatically sends the confirmed reply to the recipient.

[1727] Through the processing steps described above, users can efficiently conduct text-based business communication without any hassle. Furthermore, the combination of emotion engines enables more appropriate and emotionally resonant replies.

[1728] The following describes the processing flow.

[1729] Step 1: Receive message

[1730] Users receive emails and chat messages on their devices. This receiving operation is performed through common email clients and chat applications.

[1731] Step 2: Send Message

[1732] The terminal automatically sends the content of the received message to the server. It is transferred to the server as text data.

[1733] Step 3: Message Analysis

[1734] The server sends the received message to a natural language processing (NLP) engine. The NLP engine analyzes the message content and extracts important information.

[1735] For example, the date, time, location, and details of the request will be specified.

[1736] Step 4: Emotion Recognition

[1737] The server sends the analyzed message to the emotion engine, which evaluates the user's emotions. The emotion engine identifies emotions such as positive, negative, or neutral from the message.

[1738] For example, we can identify negative emotions from the phrase "I'm so sorry for the trouble..." in a message.

[1739] Step 5: Generate reply

[1740] The server uses a template engine to generate a reply based on the results obtained from the NLP engine and the emotion engine.

[1741] The template engine takes into account the analysis results and sentiment assessment to create a reply with an appropriate tone.

[1742] Step 6: Task Extraction

[1743] The server extracts tasks from the message using a task engine. The task engine identifies action items and key phrases within the message and generates a task list.

[1744] As an example, from a request that says "Please set a new date," we extract the task "Task: Set a new meeting."

[1745] Step 7: Save Task

[1746] The server saves the extracted tasks to the task management system. The task management system centrally manages detailed task information (deadlines, priorities, etc.).

[1747] Step 8: User Notifications

[1748] The server notifies the terminal of the generated reply and extracted task details. The user then sees the reply and task details.

[1749] Step 9: User verification and correction

[1750] The user reviews the generated reply and task details on their device. If necessary, the user modifies the reply and task.

[1751] The user enters confirmation instructions into the terminal.

[1752] Step 10: Send automatic reply

[1753] When the terminal receives confirmation from the user, it sends that information to the server.

[1754] The server automatically sends the confirmed reply to the recipient.

[1755] This process allows users to engage in efficient, emotionally sensitive, and effortless text-based business communication.

[1756] (Example 2)

[1757] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1758] In traditional text-based business communication, users had to spend considerable time analyzing received messages, drafting appropriate replies, and extracting and managing tasks. This manual process was time-consuming and labor-intensive, increasing the burden on users. Furthermore, it resulted in the generation of impersonal, mechanical replies that lacked emotional considerations, leading to a decline in communication quality.

[1759] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1760] In this invention, the server includes means for receiving messages, means for analyzing the received messages based on natural language processing, means for recognizing emotions based on the analysis results, means for automatically generating reply text using templates while considering emotion evaluation, means for extracting tasks from messages, means for storing the extracted tasks in a task management system, means for notifying the user of the generated reply text and extracted tasks, and means for sending an automatic reply after user confirmation. This allows the user to perform message analysis, generate appropriate reply texts, and extract and manage tasks in a unified manner without any effort. Furthermore, the quality of communication can be improved by providing reply texts that take emotions into consideration.

[1761] "Means for receiving messages" refers to system components that allow users to receive text-based messages, such as emails and chat messages, through their devices.

[1762] "Means for analysis based on natural language processing" refers to a system component that includes a natural language processing engine used to analyze received messages and extract important information (such as date and time, location, and requests).

[1763] "Means of recognizing emotions" refers to system components that include an emotion engine for evaluating the user's emotions from analyzed messages and identifying emotions such as positive, negative, or neutral.

[1764] "A means of automatically generating reply text using templates while considering sentiment evaluation" refers to a system component that automatically generates reply text with an appropriate tone using a template engine, based on the analysis results of natural language processing and sentiment evaluation.

[1765] "Means for extracting tasks" refers to system components that include a task engine for extracting action items and key phrases from the analysis results of messages and identifying specific tasks.

[1766] "Means of saving to a task management system" refers to system components that include task management tools used to save and centrally manage extracted tasks.

[1767] "Means for notifying the user of the generated reply and extracted tasks" refers to system components for notifying the user's terminal of the content of the generated reply and tasks.

[1768] "Method for sending an automatic reply after user confirmation" refers to a system component that automatically sends a reply after the user has reviewed and corrected the generated reply text and task content.

[1769] This invention is a system designed to streamline text-based business communication and reduce the burden on users. Specifically, this system receives messages, analyzes their content, recognizes sentiment, automatically generates replies and tasks, notifies users, and sends automatic replies. The implementation method of this system is described below.

[1770] System configuration and operation

[1771] 1. Receiving a message

[1772] Users receive emails and chat messages using their devices (such as PCs and smartphones). Applications used include Outlook, Gmail, and Slack. When a user receives a new message, its content is saved on their device.

[1773] 2. Sending a message

[1774] The terminal sends the received message to the server. The message is transferred to the server in text data format. This process involves sending data via HTTP requests or WebSockets.

[1775] 3. Message Analysis

[1776] The server sends received messages to a natural language processing (NLP) engine for analysis. The NLP engine used may include the Google Cloud Natural Language API. Through analysis, important information (such as date, time, location, and request details) is extracted from the message.

[1777] 4. Emotion recognition

[1778] The server sends the analyzed message to an emotion recognition engine to evaluate the user's emotions. Engines such as IBM Watson Tone Analyzer are used to identify emotions such as positive, negative, or neutral from the message.

[1779] Specific example:

[1780] Message received: "I'm very sorry to trouble you, but could I cancel tomorrow's meeting?"

[1781] Emotional engine evaluation: Negative

[1782] 5. Generating a reply

[1783] The server generates a reply using a template engine based on the results obtained from the NLP engine and the emotion engine. The template engine used is typically Handlebars.js, which generates a reply with an appropriate tone that takes emotion evaluation into account.

[1784] Specific example:

[1785] Input: NLP analysis results (request: meeting cancellation), emotion evaluation (negative)

[1786] Output: "Hello, thank you for your understanding regarding the cancellation of tomorrow's meeting. We will contact you later with a new date."

[1787] 6. Task Extraction

[1788] The server uses a task engine to extract tasks from the message analysis results. Task engines such as Apache OpenNLP identify action items and key phrases within the message and generate a task list.

[1789] Specific example:

[1790] Message received: "Please cancel tomorrow's meeting and reschedule it."

[1791] Extracted task: "Task: Schedule a new meeting, Deadline: Undetermined"

[1792] 7. Saving and managing tasks

[1793] The server saves the extracted tasks to a task management system. Task management systems such as Trello or Asana are used to centrally manage detailed task information (deadlines, priorities, etc.).

[1794] 8. User Notifications

[1795] The server notifies the terminal of the generated reply and the extracted task content. The user receives this notification and checks the reply and task content.

[1796] 9. User verification and correction

[1797] The user reviews the generated reply and task details on their device and makes corrections if necessary. Once corrections are complete, the user enters a confirmation message into their device.

[1798] Specific example:

[1799] The user modifies the reply to "Thank you for your understanding" and clicks "Confirmation Complete".

[1800] 10. Send automatic reply

[1801] The terminal sends a confirmation message from the user to the server. The server then automatically sends a reply to the recipient based on the confirmed message.

[1802] Example of a prompt:

[1803] Message received: "I'm very sorry to trouble you, but could I cancel tomorrow's meeting?"

[1804] Emotional engine rating: "Negative"

[1805] NLP analysis result: "Cancellation request"

[1806] Prompt to input to the generating AI model: "The user's sentiment rating for this message has been determined to be negative. Please create a reply in an appropriate tone to address the cancellation request."

[1807] As described above, this system allows users to perform message analysis, generate appropriate replies, and extract and manage tasks in a unified manner without any extra effort. Furthermore, by utilizing the sentiment engine, it is possible to generate more appropriate and emotionally resonant replies.

[1808] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1809] Detailed explanation of the processing steps

[1810] Step 1: Receiving a message

[1811] The user receives emails and chat messages on their device.

[1812] input:

[1813] Email or chat message

[1814] Data processing:

[1815] none

[1816] output:

[1817] Received message data

[1818] Specific actions:

[1819] A user receives a new email using the Gmail application. For example, they receive an email that says, "I would like to cancel tomorrow's meeting."

[1820] Step 2: Sending a message

[1821] The terminal sends the received message to the server.

[1822] input:

[1823] Received message data

[1824] Data processing:

[1825] Convert the message to JSON format

[1826] output:

[1827] HTTP POST request to the server

[1828] Specific actions:

[1829] The terminal converts the received message into JSON format and sends it to the server as an HTTP POST request.

[1830] Step 3: Message Analysis

[1831] The server sends the received message to a natural language processing (NLP) engine for analysis.

[1832] input:

[1833] JSON data of the received message

[1834] Data processing:

[1835] Information extraction using natural language processing

[1836] output:

[1837] Analysis results (request details, date, time, location, etc.)

[1838] Specific actions:

[1839] The server uses an NLP engine (e.g., Google Cloud Natural Language API) to extract important information such as "cancellation of a meeting and scheduling of a new date."

[1840] Step 4: Emotion Recognition

[1841] The server sends the analyzed message to the emotion recognition engine, which then evaluates the user's emotions.

[1842] input:

[1843] Analyzed message data

[1844] Data processing:

[1845] sentiment analysis

[1846] output:

[1847] Emotional evaluation (positive, negative, neutral, etc.)

[1848] Specific actions:

[1849] The server uses an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to identify the emotion as "negative."

[1850] Step 5: Generating a reply

[1851] The server generates a reply using a template engine based on the NLP analysis results and sentiment evaluation.

[1852] input:

[1853] NLP analysis results, emotion evaluation

[1854] Data processing:

[1855] Generate reply text using a template engine.

[1856] output:

[1857] Generated reply

[1858] Specific actions:

[1859] The server uses the Handlebars.js template engine to generate a reply message that reads, "Hello, thank you for your understanding regarding the cancellation of tomorrow's meeting. We will contact you later with a new date."

[1860] Step 6: Task Extraction

[1861] The server uses a task engine to extract tasks from the message analysis results.

[1862] input:

[1863] NLP analysis results

[1864] Data processing:

[1865] Task extraction algorithm

[1866] output:

[1867] Extracted tasks

[1868] Specific actions:

[1869] The server uses Apache OpenNLP to extract a task called "Set up a new meeting" and sets its name to "Task: Set up a new meeting, Due date: Undetermined".

[1870] Step 7: Saving and managing tasks

[1871] The server saves the extracted tasks to the task management system.

[1872] input:

[1873] Extracted tasks

[1874] Data processing:

[1875] Save to task management system

[1876] output:

[1877] Tasks saved in the task management system

[1878] Specific actions:

[1879] The server uses the Trello API to save the extracted tasks as new cards.

[1880] Step 8: User Notifications

[1881] The server notifies the terminal of the generated reply message and the extracted task content.

[1882] input:

[1883] Generated reply text, extracted tasks

[1884] Data processing:

[1885] Generating push notifications

[1886] output:

[1887] Push notifications to your device

[1888] Specific actions:

[1889] The server sends a push notification to the device, and the user checks the "reply message" and "task details" on the screen.

[1890] Step 9: User verification and correction

[1891] The user reviews the generated reply and task details on their device and makes corrections if necessary.

[1892] input:

[1893] Generated reply text, extracted tasks

[1894] Data processing:

[1895] User modifications

[1896] output:

[1897] Revised reply, task

[1898] Specific actions:

[1899] The user modifies the reply to "Thank you for your understanding" and clicks "Confirmation Complete".

[1900] Step 10: Send automatic reply

[1901] The device sends a confirmation message from the user to the server and then sends a confirmed reply to the other party.

[1902] input:

[1903] Revised reply, user confirmation complete instruction

[1904] Data processing:

[1905] Sending a reply

[1906] output:

[1907] Reply sent to the recipient

[1908] Specific actions:

[1909] The terminal notifies the server that "confirmation complete," and the server sends a "confirmed reply" to the recipient as an email.

[1910] (Application Example 2)

[1911] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1912] In conventional factory robot systems, communication, reporting, and error message processing between robots were handled individually, resulting in difficulties in efficient operation. Furthermore, there was no system that could generate appropriate, emotion-based responses while reducing the burden on the user. Therefore, there was a need for a system that provides automated, advanced communication between robots and emotion-responsive response capabilities.

[1913] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving messages, means for analyzing the received messages based on natural language processing, means for automatically generating a reply using a template based on the analysis results, means for extracting tasks from messages, means for storing the extracted tasks in a task management system, means for notifying the user of the generated reply and extracted tasks, means for sending an automatic reply after user confirmation, means for evaluating emotions from the analyzed messages, means for selecting a reply template based on the evaluated emotions, means for factory robots to report status and request tasks from other robots and managers, and means for analyzing received error messages and performing automatic replies and task reassignments. This makes it possible to streamline communication between robots and realize appropriate responses based on emotions.

[1914] "Means of receiving messages" refers to the ability to electronically acquire messages from robots or users.

[1915] "Natural language processing" is a technology that analyzes received messages as text data and understands and processes their content.

[1916] "Method for automatically generating reply messages" refers to a function that automatically creates appropriate reply messages using templates based on analysis results.

[1917] "Methods for extracting tasks from messages" refers to a function that identifies and extracts specific work items or action items from the content of a message.

[1918] A "task management system" is a system for recording, monitoring, and managing extracted tasks.

[1919] "Means of notifying the user" refers to a function that informs the user of the generated reply and extracted tasks.

[1920] "Method for sending automatic replies" refers to a function that automatically sends a generated reply message to the recipient after user confirmation.

[1921] "Methods for evaluating emotions" refer to technologies that identify emotions such as positive and negative from analyzed messages.

[1922] The "means of selecting a reply template" refer to the function of selecting a template to generate a reply with an appropriate tone based on the evaluated emotion.

[1923] "Robot status reporting" refers to the act of a robot in a factory reporting its current status and work progress.

[1924] "A means of requesting tasks" refers to a function that allows a robot to request new tasks, repairs, or other tasks from other robots or administrators.

[1925] "Methods for analyzing error messages" refer to techniques for analyzing received error messages, understanding their content, and taking appropriate countermeasures.

[1926] "Means for task reassignment" refers to a function that redistributes tasks among robots and users based on analysis results.

[1927] This invention is a system for maximizing work efficiency by enabling robots in a factory to automatically communicate with other robots and managers. This system combines a natural language processing (NLP) engine, a sentiment evaluation engine, a template engine, a task management system, and other components. The detailed operation of the system is described below.

[1928] 1. Receiving a message

[1929] The server receives messages from robots within the factory, such as status reports, error messages, and task requests. These messages are then electronically incorporated into the system.

[1930] 2. Message Analysis

[1931] Received messages are analyzed by a natural language processing engine (NLP engine) on the server. This analysis extracts necessary information from the message (date and time, location, error details, request, etc.).

[1932] 3. Emotional evaluation

[1933] The analyzed message is sent to an emotion evaluation engine, where emotions such as positive, negative, or neutral are identified. For example, the message "The device has malfunctioned" is evaluated as negative.

[1934] 4. Generating a reply

[1935] The server generates a reply using a template engine based on the results obtained from the NLP engine and the sentiment evaluation engine. The template engine creates a reply with an appropriate tone based on the evaluated sentiment.

[1936] 5. Task Extraction

[1937] The server extracts tasks from the message analysis results. This task extraction uses a key phrase extraction algorithm to identify specific work items and action items.

[1938] 6. Saving and managing tasks

[1939] The extracted tasks are stored in a task management system. The task management system centralizes detailed task information, making it easy for robots and administrators to access and manage it.

[1940] 7. User notifications and automatic replies

[1941] The server notifies the user of the generated reply and the extracted task details. The user reviews this and makes any necessary corrections. Once final confirmation is complete, the server automatically sends the reply to the recipient.

[1942] Specific example

[1943] For example, if robot A sends the message "The device has malfunctioned. It needs repair," the server receives this message. The NLP engine analyzes the message and extracts the information "malfunction" and "repair needed." The sentiment evaluation engine evaluates this message as "negative." The server uses the template engine to generate a reply message saying "A problem has occurred. We will address it promptly." At the same time, a "repair task" is saved in the task management system.

[1944] Example of a prompt

[1945] Analyze the message "The device has malfunctioned. Repair is needed," perform a sentiment assessment, and generate an appropriate response.

[1946] This system streamlines communication between robots and enables responses based on appropriate emotions. This significantly reduces the burden on users and improves overall factory work efficiency.

[1947] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1948] Step 1:

[1949] The server receives messages from robots and administrators within the factory. These messages are sent in text format and are received by the server's receiving system. Input messages include robot status reports, error messages, and task requests. The text data of the received messages is stored on the server as output.

[1950] Step 2:

[1951] The server sends the received text data to a natural language processing (NLP) engine for message analysis. This NLP engine extracts important information such as the date and time, location, error details, and request details. The input is the text data of the received message, and the output is the analysis results.

[1952] Step 3:

[1953] The server sends the analysis results to the emotion evaluation engine, which evaluates the emotions from the message. The emotions evaluated include positive, negative, and neutral. The input for this step is the analysis results of the NLP engine, and the output is the emotion evaluation result.

[1954] Step 4:

[1955] The server automatically generates a reply using a template engine based on the sentiment evaluation results. The input is the sentiment evaluation results and analysis results, and the output is the generated reply. Specifically, the template engine selects an appropriate template and uses text generation AI to create the reply.

[1956] Step 5:

[1957] The server uses a key phrase extraction algorithm to extract tasks from the analysis results. The input is the analysis results of the NLP engine, and the output is a list of specific tasks. Specifically, it extracts repair tasks from the information "repair needed".

[1958] Step 6:

[1959] The server saves the extracted tasks to the task management system. The input is a list of tasks, and the output is the tasks saved in the task management database. This allows for centralized management of detailed information for each task (deadline, priority, etc.).

[1960] Step 7:

[1961] The server notifies the user of the generated reply and extracted task content. The input is the reply and task list, and the output is a notification sent to the user's terminal. The user reviews this and makes corrections as needed.

[1962] Step 8:

[1963] The user reviews the reply and task details, makes any necessary corrections, and then performs a final check. The input is the user's corrections, and the output is the corrected reply and task list, which are sent to the server.

[1964] Step 9:

[1965] After user confirmation, the server automatically sends the generated reply to the recipient. The input is the reply confirmed by the user, and the output is the reply message sent to the recipient. This ensures that messages are processed at the appropriate time.

[1966] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1967] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1968] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1969] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1970] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1971] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1972] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1973] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1974] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1975] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1976] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1977] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1978] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1979] 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.

[1980] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1981] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1982] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1983] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1984] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1985] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1986] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1987] The following is further disclosed regarding the embodiments described above.

[1988] (Claim 1)

[1989] A means of receiving a message,

[1990] A means for analyzing received messages based on natural language processing,

[1991] A method for automatically generating reply text using a template based on the analysis results,

[1992] A method for extracting tasks from messages,

[1993] A means of saving the extracted tasks to a task management system,

[1994] A means of notifying the user of the generated reply and extracted tasks,

[1995] A system that includes a means of sending an automatic reply after user confirmation.

[1996] (Claim 2)

[1997] The system according to claim 1, comprising means of using a key phrase extraction algorithm for task extraction.

[1998] (Claim 3)

[1999] The system according to claim 1, comprising means for generating a reply using a template engine.

[2000] "Example 1"

[2001] (Claim 1)

[2002] A means of receiving electronic communication messages using a personal terminal,

[2003] A means for transmitting received electronic communication messages to a central processing unit for analysis,

[2004] A means by which a central processing unit analyzes message content using a natural language processing model,

[2005] A means for automatically generating a reply using a predefined template based on the analysis results,

[2006] A means of extracting tasks from electronic communication messages,

[2007] Means for saving extracted tasks to a task management device,

[2008] A means of notifying a personal device of automatically generated reply messages and extracted tasks,

[2009] A system that includes a means of sending an automatic reply message after user confirmation.

[2010] (Claim 2)

[2011] The system according to claim 1, comprising means for extracting tasks using a key phrase extraction algorithm.

[2012] (Claim 3)

[2013] The system according to claim 1, comprising means for generating an automated reply using a template engine.

[2014] "Application Example 1"

[2015] (Claim 1)

[2016] A means of receiving a message,

[2017] A means for analyzing received messages based on natural language processing,

[2018] A method for automatically generating reply text using a template based on the analysis results,

[2019] A method for extracting tasks from messages,

[2020] A means of saving the extracted tasks to a task management system,

[2021] A means of notifying the user of the generated reply and extracted tasks,

[2022] A means of sending an automatic reply after user confirmation,

[2023] A means of analyzing received feedback and requests and generating appropriate automated replies,

[2024] A means of extracting and managing tasks for content creation based on the task extraction results,

[2025] A system that includes this.

[2026] (Claim 2)

[2027] The system according to claim 1, comprising means of using a key phrase extraction algorithm for task extraction.

[2028] (Claim 3)

[2029] The system according to claim 1, comprising means for generating a reply using a template engine.

[2030] "Example 2 of combining an emotion engine"

[2031] (Claim 1)

[2032] A means of receiving a message,

[2033] A means for analyzing received messages based on natural language processing,

[2034] A means of recognizing emotions based on the analysis results,

[2035] A method for automatically generating reply text using templates while taking sentiment evaluation into consideration,

[2036] A method for extracting tasks from messages,

[2037] A means of saving the extracted tasks to a task management system,

[2038] A means of notifying the user of the generated reply and extracted tasks,

[2039] A system that includes a means of sending an automatic reply after user confirmation.

[2040] (Claim 2)

[2041] The system according to claim 1, comprising means of using a key phrase extraction algorithm for task extraction.

[2042] (Claim 3)

[2043] The system according to claim 1, comprising means for generating a reply using a template engine.

[2044] "Application example 2 when combining with an emotional engine"

[2045] (Claim 1)

[2046] A means of receiving a message,

[2047] A means for analyzing received messages based on natural language processing,

[2048] A method for automatically generating reply text using a template based on the analysis results,

[2049] A method for extracting tasks from messages,

[2050] A means of saving the extracted tasks to a task management system,

[2051] A means of notifying the user of the generated reply and extracted tasks,

[2052] A means of sending an automatic reply after user confirmation,

[2053] A means of evaluating emotions from analyzed messages,

[2054] A means of selecting a reply template based on the evaluated emotions,

[2055] A means for robots within a factory to report their status and request tasks from other robots or managers,

[2056] A system that includes means to analyze received error messages and perform automatic replies or task reassignments.

[2057] (Claim 2)

[2058] The system according to claim 1, comprising means of using a key phrase extraction algorithm for task extraction.

[2059] (Claim 3)

[2060] The system according to claim 1, comprising means for generating a reply using a template engine. [Explanation of Symbols]

[2061] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of receiving a message, A means for analyzing received messages based on natural language processing, A method for automatically generating reply text using a template based on the analysis results, A method for extracting tasks from messages, A means of saving the extracted tasks to a task management system, A means of notifying the user of the generated reply and extracted tasks, A system that includes a means of sending an automatic reply after user confirmation.

2. The system according to claim 1, comprising means of using a key phrase extraction algorithm for task extraction.

3. The system according to claim 1, comprising means for generating a reply using a template engine.

Images