System

Abstract

A system is provided.SOLUTION: This system includes a data collection means for acquiring the action history and task progress situation of a user, an AI analysis means for specifying an object requiring a remind on the basis of the acquired data, a mail preparation means for automatically generating a remind mail to the object person, and a transmission means for transmitting the prepared remind mail in proper timing.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In the past, sending and receiving reminder emails was done manually, which meant that senders had to spend time creating the emails and recipients had to deal with unnecessary emails, which was a burden on their work. There was also a risk that important information would be overlooked among the large number of reminder emails. This situation was a factor that reduced work efficiency. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system that includes a data collection means for acquiring a user's behavioral history and task progress status, an AI analysis means for identifying individuals who need reminders based on the acquired data, an email creation means for automatically generating reminder emails for the identified individuals, and a sending means for sending reminder emails at appropriate times. Furthermore, the system includes a schedule setting means for optimizing the timing of reminder email sending and a log recording means for recording the sending results, and a follow-up means for automatically generating and sending a follow-up email if the task is not completed after the reminder. This reduces the manpower and effort required for sending and receiving reminder emails, improving work efficiency.

[0006] "Data collection means" refers to devices or systems that have the function of acquiring information such as a user's behavior history and task progress.

[0007] "AI analysis means" refers to devices or systems that have the ability to use artificial intelligence technology to identify targets that require reminders based on acquired data.

[0008] "Email creation means" refers to a device or system that has the function of automatically generating reminder emails to specified recipients.

[0009] "Sending means" refers to a device or system that has the function of sending the created reminder email to the target person at the appropriate time.

[0010] The "schedule setting means" refers to a device or system that has the function of setting a sending plan to optimize the timing of sending reminder emails.

[0011] A "log recording means" is a device or system that has the function of recording the results of sent emails.

[0012] A "follow-up means" is a device or system that has the function of automatically generating and sending another reminder email if the task is not completed even after the reminder email has been sent. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0014] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0017] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0018] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0019] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0026] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0033] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0034] The present invention is a system for automating reminder emails, and a specific embodiment thereof will be described below.

[0035] Data collection

[0036] The server acquires user activity history and task progress status from a project management system, mail server, etc. This data collection is performed periodically, and the updated information is stored in a database. For example, the latest task status is saved in the database by a batch process scheduled every night.

[0037] AI-powered analysis

[0038] The server uses AI analytics to identify users who need reminders based on the collected data. This is done using machine learning models to make predictions based on each user's task completion status and past behavior. For example, it identifies users who have not yet completed a specific task that is due to be submitted.

[0039] Creating a reminder email

[0040] The server automatically generates reminder emails for the identified recipients. The email content is constructed using a template file, and important information such as the user name, task name, and deadline is dynamically embedded. For example, an email might be generated with the following content: "Dear [user name], today is the deadline for submitting your report."

[0041] Sending emails

[0042] The server sends the generated reminder email at an appropriate time. The sending timing is optimized using a schedule setting means, and is set to send, for example, one day before the submission deadline and in the morning of the day of the deadline. The server connects to the SMTP server and sends the email.

[0043] Follow-up

[0044] If the task is not completed after the reminder email is sent, the server automatically generates and sends a follow-up email. This increases the certainty of task completion. For example, if the task remains incomplete after the deadline, a follow-up email stating, "Submission is late. Please take immediate action." is sent.

[0045] Specific examples

[0046] As a specific example of use, consider the use in a company's project management system.

[0047] 1. Data collection

[0048] The server obtains the task completion status of each employee from the project management system and stores it in a database.

[0049] 2. AI-based analysis

[0050] The server analyzes the collected data using an AI model to identify employees who have tasks that are due soon but have not yet been completed.

[0051] 3. Create a reminder email

[0052] The server creates a reminder email for the identified employee, stating, "Dear [Employee Name], task [Task Name] for [Project Name] is incomplete. The deadline is [Date]."

[0053] 4. Sending emails

[0054] The server sends the created reminder email at an appropriate time, for example, the day before the submission deadline and in the morning of the deadline.

[0055] 5. Follow-up

[0056] If the task is not completed after the deadline, the server will send another follow-up email.

[0057] This system reduces the workload for both users and administrators and improves work efficiency.

[0058] The processing flow will be explained below.

[0059] Step 1:

[0060] The server acquires user activity history and task progress status from the project management system and mail server. This acquisition process is performed periodically, and a scheduled batch process is executed daily to acquire the latest data.

[0061] Step 2:

[0062] The server stores the acquired data in a database. The stored data shows the progress of each user's task in detail and is used for later analysis. For example, the user ID, task ID, deadline, progress status, etc. are saved in the database.

[0063] Step 3:

[0064] The server uses a query to extract data on people who need reminders from the database. For example, it executes an SQL query to extract "users who have tasks due the next day."

[0065] Step 4:

[0066] The server inputs the extracted data into an AI analysis model to identify those who need reminders. The AI ​​model uses machine learning models that have learned from past data to predict which users need reminders.

[0067] Step 5:

[0068] The server saves the analysis results in a database and updates the list of reminder recipients, ensuring the information is available for creating reminder emails in the next step.

[0069] Step 6:

[0070] The server loads the reminder email template and automatically generates emails by embedding individual information for each reminder recipient. For example, the template embeds parameters such as the user name, task name, and deadline date.

[0071] Step 7:

[0072] The server adds the generated reminder email to a sending queue and schedules it for sending. The schedule is set so that the email is sent at the optimal time, for example, the day before the deadline and in the morning of the deadline.

[0073] Step 8:

[0074] The server connects to the SMTP server and sends reminder emails according to the sending schedule. The sending result of each email is recorded in a log, and the success / failure is saved in a database.

[0075] Step 9:

[0076] The server monitors the sending results, and if the task is not completed by the deadline, it automatically generates a follow-up email and adds it to the sending queue. The follow-up email contains a message urging the user to complete the task again.

[0077] Step 10:

[0078] The server will send follow-up emails according to the schedule and again log the results, allowing for continuous follow-up until the task is completed.

[0079] This processing flow automates the sending and receiving of reminder emails, improving work efficiency.

[0080] Example 1

[0081] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0082] Conventional task management systems have problems such as users forgetting tasks or not receiving reminders to meet deadlines, resulting in reduced work efficiency. Manual reminders are time-consuming and difficult to send at the right time, so an automated reminder mechanism is needed. Furthermore, a system that can automatically send not only reminder emails but also follow-up emails is also needed.

[0083] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0084] In this invention, the server includes a data collection means for acquiring a user's behavioral history and task progress status, a machine learning model analysis means for identifying targets requiring reminders based on the acquired data, a template generation means for automatically generating reminder emails for targets, a sending means for sending the created reminder emails at an appropriate time, a follow-up means for automatically generating and sending a follow-up email if the task is not completed after sending, a batch processing means for periodically acquiring data, and a means for dynamically inserting information such as the user name, task name, and deadline into the content of the email to be sent. This encourages users to remember to complete tasks and improves work efficiency.

[0085] 1. "Data collection means" refers to a device or method for acquiring a user's behavioral history and task progress.

[0086] 2. "Machine learning model analysis means" means a device or method that uses a machine learning model to analyze acquired data and identify targets requiring reminders.

[0087] 3. "Template generation means" means a device or method that uses a template to automatically generate reminder emails to identified recipients.

[0088] 4. "Transmission means" means a device or method for sending the created reminder email at an appropriate time.

[0089] 5. "Follow-up means" means a device or method for automatically generating and sending a follow-up email if the task is not completed after sending.

[0090] 6. "Batch processing means" means a device or method that processes data in bulk to periodically obtain data.

[0091] 7. "Dynamic insertion means" means a device or method for automatically adding information such as user names, task names, and deadline dates to the content of emails being sent.

[0092] The present invention relates to a system for automating reminder emails, and specific embodiments thereof will be described below.

[0093] Data collection

[0094] The server obtains user activity history and task progress from a project management system (e.g., JIRA) or mail server (e.g., Exchange Server). This data collection is performed periodically by batch processing and stored in a database (e.g., MySQL) on the server. Specifically, the server sets up a Cron job every night to obtain task data from the project management system using an API request and store it in the database.

[0095] AI-powered analysis

[0096] The server analyzes the collected data using a machine learning model (e.g., Scikit-learn). The server uses a specific algorithm to analyze each user's task completion status and past behavioral history to identify users who need reminders. For example, the server uses the acquired task data to extract users who have tasks that are close to their submission deadline but have not yet been completed.

[0097] Creating a reminder email

[0098] The server automatically generates reminder emails for the identified recipients. Using a template engine (such as Jinja2), it dynamically inserts necessary information (such as user name, task name, deadline date, etc.) into the email content. Specifically, it generates an email with the content "Dear [user name], today is the deadline for submitting your report." This automatically creates a reminder email.

[0099] Sending emails

[0100] The server sends the generated reminder emails at the appropriate time. The sending timing is optimized based on the schedule settings, for example, sending them the day before the submission deadline and in the morning of the day itself. The server connects to an SMTP server (e.g., Postfix) to send the reminder email. The sending status is recorded in a log so that it can be checked later.

[0101] Follow-up

[0102] If the task is not completed even after sending the reminder email, the server automatically generates and sends another follow-up email. This ensures that the task is completed. For example, if the task is not completed even after the submission deadline, the server sends a follow-up email stating, "The submission is late. Please take immediate action."

[0103] Specific examples

[0104] 1. Data collection

[0105] The server obtains the task completion status of each user from the project management system and stores it in a database.

[0106] 2. AI-based analysis

[0107] The server analyzes the collected data using an AI model to identify users who have tasks that are due soon but have not yet been completed.

[0108] 3. Create a reminder email

[0109] The server creates a reminder email for the identified user with the following content: "Dear [user name], task [task name] for [project name] is incomplete. The deadline is [date]."

[0110] 4. Sending emails

[0111] The server sends the created reminder email at an appropriate time, for example, the day before the submission deadline and in the morning of the deadline.

[0112] 5. Follow-up

[0113] If the task is not completed after the deadline, the server will send another follow-up email.

[0114] Prompt Sentence Examples

[0115] Below are some example prompts to be input to the generative AI model:

[0116] Analyze user task data obtained from your project management system and identify users who have incomplete tasks with upcoming deadlines. Create templated reminder emails for those users and send them the day before and on the deadline. Also, send follow-up emails if the task is still incomplete after the deadline. Dynamically insert information such as the user name, task name, and due date into the reminder and follow-up emails.

[0117] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0118] Specific explanation of processing steps

[0119] Step 1: Collect data

[0120] The server periodically retrieves user action history and task progress from the project management system and mail server. The input data is task data retrieved from the project management system, and the output is updated task information stored in the database. Specifically, the server sets up a Cron job every night to execute batch processing. This process sends an API request to retrieve task data from the project management system and stores it in a MySQL database.

[0121] Step 2: AI analysis

[0122] The server analyzes all collected data using a machine learning model. The input data is task information stored in the database, and the output is a list of users who need reminders. Specifically, the server runs a Python script to read the necessary data from the database. It then inputs the data into a Scikit-learn model to generate a list of users who need reminders.

[0123] Step 3: Create a reminder email

[0124] The server uses a template engine to automatically generate reminder emails for the identified users. The input data is a list of users who need reminders and template information, and the output is the generated reminder email. Specifically, the server loads a Jinja2 template and dynamically embeds the user name and task information (task name, deadline date) into the template to generate the reminder email.

[0125] Step 4: Sending an email

[0126] The server sends the generated reminder email using an SMTP server. The input data is the generated reminder email and schedule information, and the output is the sent reminder email. Specifically, the server checks the sending timing based on the schedule settings, connects to the Postfix SMTP server, and sends the reminder email. The sending status is recorded in a log, making it possible to track it.

[0127] Step 5: Follow up

[0128] If the task is still incomplete after the reminder email is sent, the server automatically generates and sends another follow-up email. The input data is the task status data after submission, and the output is the follow-up email. Specifically, the server checks the database again after a certain period of time has passed and identifies users who have incomplete tasks. It then generates a follow-up email to that user stating, "Submission is late. Please take action as soon as possible," and sends it via the SMTP server.

[0129] Specific processing flow

[0130] Step 1:

[0131] The server runs a batch process every night by setting up a Cron job to retrieve task data from the project management system. The retrieved task data is obtained through an API request and stored in a MySQL database.

[0132] Step 2:

[0133] The server reads the task information stored in the database using a Python script and analyzes it using a machine learning model (Scikit-learn), which generates a list of users who need reminders.

[0134] Step 3:

[0135] The server uses the Jinja2 template engine to generate reminder emails for the identified users, dynamically populating the template with information such as the user name, task name, and due date to create the reminder email.

[0136] Step 4:

[0137] The server checks the schedule to send the generated reminder email, sends the reminder email using the Postfix SMTP server, and logs the delivery status.

[0138] Step 5:

[0139] After sending the reminder email, the server checks the database again to identify users with incomplete tasks. If necessary, it generates a follow-up email and sends it via the SMTP server with the message "Submission is late. Please take action as soon as possible."

[0140] (Application example 1)

[0141] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0142] In modern factories, worker task management is important, but it is difficult to grasp the progress of all workers in real time and provide appropriate reminders and follow-ups. To ensure that on-site workers complete their tasks at the appropriate time, an automated system that can provide immediate reminders is required. Furthermore, since reminders are sometimes not sent or notifications that are sent are ineffective, the importance of optimizing the timing of notifications and follow-ups is being questioned. Furthermore, conventional systems only notify workers via email, making it difficult to provide immediate notifications to workers who are working on-site.

[0143] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0144] In this invention, the server includes a data collection means for acquiring a user's behavioral history and task progress status, an AI analysis means for identifying individuals who need reminders based on the acquired data, a notification creation means for automatically generating reminder emails and real-time notifications for the individuals, and a transmission means for sending the created reminder emails and notifications at the appropriate time. This allows the progress of work in the factory to be grasped in real time, enabling reminders and follow-ups at the appropriate time. In addition, by using a wearable display device control means, on-site workers can be notified immediately, improving work efficiency.

[0145] The "data collection means" is a means for acquiring the behavioral history and task progress status of users and workers, and storing them in a database or the like.

[0146] "AI analysis methods" are methods that use machine learning models and artificial intelligence technology to analyze acquired data and identify targets that require reminders.

[0147] The "notification creation means" is a means for automatically generating reminder emails and real-time notifications for specified targets.

[0148] The "transmission means" refers to a means for sending the created reminder email or notification to the target person at an appropriate time.

[0149] A "scheduling means" is a means used to optimize the timing of sending reminder emails and notifications.

[0150] A "log recording means" is a means for recording the results of sent emails and notifications so that they can be referenced later.

[0151] The "follow-up method" is a method for automatically generating and sending a follow-up email or notification if the task is not completed after the reminder.

[0152] The "wearable display device control means" is a means for grasping the progress of work based on the acquired data and displaying reminders or follow-up notifications on the wearable display device (e.g., smart glasses).

[0153] The present invention is a system for automatically managing a user's behavior history and task progress, and sending reminder emails and real-time notifications. Specific embodiments of the system are described below.

[0154] First, the server plays an important role. This server has a means of collecting data to acquire the behavioral history and task progress of users and workers, and this data is stored in a database. This data collection is based on logs from sensors and robots installed in the factory, as well as input information from workers. Data is often collected in real time or periodically processed in batches.

[0155] Next, based on the collected data, the server's AI analysis method identifies those who need reminders. This AI analysis method uses machine learning models (e.g., RandomForestClassifier). Reminder emails and real-time notifications are automatically generated to provide appropriate reminders to the identified individuals. This notification creation method uses dynamic templates to automatically fill in important information such as user name, task name, and due date.

[0156] Reminder emails and notifications are sent at appropriate times. This sending method includes sending emails via a regular SMTP server or real-time notification functions using wearable display devices such as smart glasses. The sending timing is optimized by a scheduling method. For example, it can be set to match the user's work schedule, such as the day before the submission deadline or the morning of the deadline.

[0157] Furthermore, the results of the sent emails and notifications are recorded using a logging mechanism. This allows for future reference and serves as data for evaluating the effectiveness of the system. If the task is not completed after the reminder, the server's follow-up mechanism automatically generates and sends another follow-up email or notification. This improves the task completion rate.

[0158] Finally, it is important to have a wearable display control means to grasp the progress of work in the factory and notify workers immediately, which will allow real-time reminders and follow-ups at the workplace, greatly improving work efficiency.

[0159] Specific examples

[0160] For example, an example of use in a factory will be described.

[0161] 1. Data collection: The server collects real-time operational data from robots and sensors in the factory and stores it in a database.

[0162] 2. AI analysis: The server analyzes the collected data using an AI model (e.g., RandomForestClassifier) ​​to identify workers and tasks that require reminders.

[0163] 3. Creating and sending notifications: The server automatically generates reminder notifications for the identified workers and displays them on the smart glasses. The notification might say something like, "Worker B, the deadline for Task C is approaching. Please complete it as soon as possible."

[0164] 4. Follow-up: If the task is not completed after the reminder, a follow-up notification will be sent automatically.

[0165] Prompt Sentence Examples

[0166] Prompt Type: Industrial Task Management

[0167] Predictive Tasks: Forecast task progress and generate automatic reminders

[0168] Input data: {'worker_id': int, 'task_id': int, 'status': str, 'deadline': str}

[0169] Desired output: A list of tasks that need reminders

[0170] Example: Worker ID: 123 - Task ID: 789 is nearing its deadline.

[0171] In this way, the system can manage work progress within the factory in real time, send reminder notifications at appropriate times, and improve work efficiency.

[0172] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0173] Step 1:

[0174] The server collects work progress data from robots and sensors in the factory. This data collection is done in regular batch processing or in real time and stored in a database. For example, the location information of workers obtained from sensors and the operating hours of machines are stored in the database.

[0175] Input: Work progress data obtained from robots and sensors

[0176] Output: Working data stored in a database

[0177] Step 2:

[0178] The server inputs the stored data into an AI analysis method, which uses a machine learning model (e.g., RandomForestClassifier) ​​to identify workers and tasks that need reminding. The AI ​​model compares this data with past data and predicts who should be reminded based on certain criteria (e.g., tasks that are due soon but not completed).

[0179] Input: Working data stored in the database

[0180] Output: A list of workers and tasks that need reminding

[0181] Step 3:

[0182] The server automatically generates reminder notifications based on the workers and tasks identified by the AI ​​analysis method. The notification creation method uses templates to dynamically embed information such as the user name, task name, and deadline. For example, a notification might be created that reads, "Worker B, the deadline for Task C is approaching. Please complete it promptly."

[0183] Input: A list of workers and tasks that need reminding

[0184] Output: Reminder notification message

[0185] Step 4:

[0186] The server sends the created reminder notification at the appropriate time. The sending method includes email sending via an SMTP server and real-time notification using wearable display devices such as smart glasses. The notification timing is optimized by the schedule setting method. For example, notifications can be sent the day before the submission deadline or in the morning of the deadline.

[0187] Input: Reminder message

[0188] Output: Reminder sent

[0189] Step 5:

[0190] The server records the results of the sent reminders and notifications as a log. Using the log recording method, information such as the sending date and time, recipient, and notification content is saved in a database. This allows for future reference and can be used as data to evaluate the effectiveness of the system.

[0191] Input: Reminder notification information sent

[0192] Output: Log information recorded in the database

[0193] Step 6:

[0194] If the task is not completed after the reminder, the server automatically generates and sends another follow-up notification using the follow-up means. For example, a follow-up notification such as "Task C is not yet completed. Please take action immediately" can be generated and displayed on the worker's wearable display device at an appropriate time.

[0195] Input: Incomplete task information

[0196] Output: Follow-up notification message

[0197] Step 7:

[0198] The server notifies the on-site worker of the work progress in real time using the wearable display control means, which allows the worker wearing the smart glasses to receive immediate reminders and follow-up notifications, thereby improving work efficiency and increasing the task completion rate.

[0199] Input: Reminder notification message, Follow-up notification message

[0200] Output: Notifications displayed on wearable displays such as smart glasses

[0201] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0202] The present invention optimizes the content and sending timing of reminder emails according to the user's emotions by combining a system that automates reminder emails with an emotion engine that recognizes the user's emotions. Specific embodiments of this invention are described below.

[0203] Data collection

[0204] The server periodically retrieves user activity history and task progress status from the project management system and mail server. This allows daily updated information to be stored in the database. For example, the latest task status is saved in the database by a batch process scheduled every night.

[0205] AI-powered analysis

[0206] The server uses AI analysis tools based on the collected data to identify users who need reminders. It also uses machine learning models to make predictions based on each user's task completion status and past behavioral history. For example, it identifies users who have not yet completed a specific task even though the deadline for its submission is approaching.

[0207] emotion recognition

[0208] The server uses an emotion engine to recognize the user's emotions. This emotion recognition is performed, for example, by analyzing the user's email text and voice data. The emotion engine evaluates the user's emotional state, taking into account factors such as the user's stress level and motivation.

[0209] Creating a reminder email

[0210] The server automatically generates reminder emails for identified recipients, with content customized according to the emotions recognized by the emotion engine. The template file is dynamically modified, so that if the user is feeling stressed, for example, an email is created with a gentle tone. An email is generated with the following content: "Dear [user name], I'm concerned about the progress of your task. Please let me know if you need any help."

[0211] Sending emails

[0212] The server adds the generated reminder email to a sending queue and sends it at an optimized timing based on the emotional state recognized by the emotion engine. For example, it sends the email when the user is relaxed, avoiding busy times.

[0213] Follow-up

[0214] If the task is not completed after the reminder email is sent, the server automatically generates a follow-up email and sends it again. The content and timing of the follow-up email are also customized based on information from the emotion engine. For example, if the task is not completed even after the deadline for submission, an appropriate follow-up will be performed depending on the user's status. An email may be sent stating, "Your submission is late, but please let us know if there are no particular problems."

[0215] Specific examples

[0216] As a specific example of use, consider the use in a company's project management system.

[0217] 1. Data collection

[0218] The server obtains the task completion status of each employee from the project management system and stores it in a database.

[0219] 2. AI-based analysis

[0220] The server analyzes the collected data using an AI model to identify employees who have tasks that are due soon but have not yet been completed.

[0221] 3. Emotion recognition

[0222] The server uses an emotion engine to recognize employees' emotional states from email text and voice data, and evaluates their stress and motivation.

[0223] 4. Create a reminder email

[0224] The server automatically generates reminder emails for identified employees based on their emotional state. For example, for an employee feeling stressed, the server creates a gentle email saying, "Please proceed without overdoing it."

[0225] 5. Sending emails

[0226] The server sends reminder emails at appropriate times, often during relaxing hours, taking into account the user's emotional state.

[0227] 6. Follow-up

[0228] The server sends follow-up emails if the task is still incomplete after the deadline, and the content is also adjusted to take into account the user's emotional state.

[0229] This system not only automates reminder emails, but also enables more personalized communication that takes users' emotions into consideration, which is expected to improve work efficiency and user satisfaction.

[0230] The processing flow will be explained below.

[0231] Step 1:

[0232] The server acquires user activity history and task progress from the project management system and mail server. This acquisition process is performed periodically, with daily scheduled batch processing. For example, data such as each user's task ID, progress, and deadline is acquired and stored in a database.

[0233] Step 2:

[0234] The server stores the collected data in a database, which records detailed task information for each user. The acquired data is organized according to a storage format for later analysis.

[0235] Step 3:

[0236] The server uses a query to extract data on users who need reminders from the database. For example, it executes an SQL query to extract users who have tasks due the next day.

[0237] Step 4:

[0238] The server inputs the extracted data into an AI analysis model to identify those who need reminders, and uses a machine learning model to predict candidates who need reminders based on each user's task completion status and past behavioral history.

[0239] Step 5:

[0240] The server saves the reminder recipients in the database based on the analysis results, and updates the list for creating reminder emails.

[0241] Step 6:

[0242] The server uses an emotion engine to recognize the user's emotions. For example, it analyzes past emails and voice data to assess the user's stress level and motivation. It may also use NLP (natural language processing) technology to analyze the text of emails.

[0243] Step 7:

[0244] The server automatically generates emotion-based reminder emails for the reminder recipients. It reads a template file and dynamically fills in parameters such as the user name, task name, and due date. It also customizes the email content based on the results of the emotion engine. For example, it generates a message like, "Dear [user name], I'm concerned about the progress of your task. Please let me know if you need any help."

[0245] Step 8:

[0246] The server adds the generated reminder email to a sending queue and schedules the sending based on the emotional state recognized by the emotion engine. For example, it schedules the email to be sent during a time when the user is relaxed.

[0247] Step 9:

[0248] The server connects to the SMTP server according to the sending schedule and sends the reminder email. The sending result is recorded in a log, and the success / failure information is saved in a database.

[0249] Step 10:

[0250] The server monitors the submission results and automatically generates a follow-up email and adds it to the submission queue if the task is not completed by the deadline. The content of the follow-up email is customized based on the evaluation results of the emotion engine. For example, it could say, "Your submission is late, but please let us know if there are no particular problems."

[0251] Step 11:

[0252] The server sends follow-up emails on a scheduled basis and again logs the results, allowing the effectiveness of the follow-up emails to be monitored and further follow-ups to be performed if necessary.

[0253] This specific processing flow automates the sending and receiving of reminder emails that take the user's emotions into consideration, thereby improving work efficiency and user satisfaction.

[0254] Example 2

[0255] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0256] Conventional reminder systems can create and send reminder emails based on the user's behavioral history and task progress, but it is difficult to set the optimal content and timing of the emails while taking the user's emotional state into account. As a result, problems arise, such as increased user stress and inappropriate follow-up. In particular, reminder emails can be counterproductive because they are insensitive to the user's emotions.

[0257] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a data collection means for acquiring a user's behavioral history and work progress status, an AI analysis means for identifying targets requiring reminders based on the acquired data, an email creation means for automatically generating reminder emails for the targets, a sending means for adding the generated reminder emails to a sending queue and sending them at an appropriate time, an emotion recognition means for recognizing the user's emotions, an email adjustment means for customizing the content of the reminder email according to the emotion recognized by the emotion recognition means, and a follow-up means for automatically generating and sending a follow-up email if the task is not completed even after sending. This makes it possible to optimize the content and sending timing of the reminder email taking the user's emotions into consideration.

[0258] A "user" is a person or organization that uses the system.

[0259] "Behavioral history" is a record of the operations and activities performed by a user.

[0260] "Work progress" is data on the progress of tasks and projects that a user is responsible for.

[0261] "Data collection means" refers to a mechanism or device for acquiring a user's behavior history and work progress.

[0262] "AI analysis methods" are methods that use artificial intelligence to analyze collected data and identify targets that require reminders.

[0263] A "reminder email" is an email sent to a user to encourage them to progress on a task or project.

[0264] "Email creation means" refers to a system or program for automatically generating reminder emails.

[0265] A "sending queue" is a temporary storage location or list of emails waiting to be sent.

[0266] "Transmission means" refers to the method or technology used to send reminder emails to users.

[0267] "Emotion recognition means" refers to a technology or system for determining a user's emotions or mental state.

[0268] The "email adjustment means" is a function for customizing the contents of the reminder email according to the user's emotions.

[0269] A "follow-up method" is a mechanism for sending another email if the task is not completed after the reminder email has been sent.

[0270] The system of the present invention acquires a user's behavior history and work progress, and takes the user's emotions into consideration when automatically generating and sending reminder emails. This system includes data collection means, AI analysis means, email creation means, email sending means, emotion recognition means, email adjustment means, and follow-up means.

[0271] An embodiment of this system will now be described in detail.

[0272] Data collection methods

[0273] The server periodically collects user activity history and work progress from the project management system and mail server. This is done by using automatic data acquisition via API or batch processing. For example, the latest task progress is stored in a database by batch processing scheduled overnight.

[0274] AI analysis means

[0275] The server analyzes the collected data using an AI model. It uses a machine learning algorithm to identify users who have incomplete tasks that are due soon. The AI ​​model makes predictions based on each user's task completion status and past behavioral history.

[0276] emotion recognition means

[0277] The server uses an emotion recognition engine to recognize the user's emotions, including natural language processing (NLP) and voice recognition technologies, to assess the user's stress level and motivation from the text of their emails and their voice data.

[0278] Email creation method

[0279] The server automatically generates reminder emails based on the emotions recognized by the emotion engine. This includes the ability to use template files to customize the content of emails depending on the user's emotional state. For example, a friendly email could be created that reads, "Dear [user name], I'm concerned about your task progress. Please let me know if you need any help."

[0280] Transmission method

[0281] The server adds the generated reminder email to a sending queue and sends it at the optimal time, which is set to a time when the user is relaxed.

[0282] Follow-up measures

[0283] If the task is not completed after the reminder email is sent, the server automatically generates and sends a follow-up email. This includes the ability to customize the content and timing of the email based on information obtained from the emotion engine. For example, an email could be sent with the following content: "Your submission is late, but please let us know if there are no particular problems."

[0284] Specific examples

[0285] As a specific example of use, consider using it in a company's project management system.

[0286] 1. Data collection: The server obtains the task completion status of each employee from the project management system API, and stores the progress status of each employee in a database.

[0287] 2. AI analysis: The server analyzes the collected data using an AI model to identify employees who have incomplete tasks that are due soon.

[0288] 3. Emotion recognition: The server uses an emotion engine to recognize employees' emotional states from email text and voice data, and evaluates their stress and motivation.

[0289] 4. Creating reminder emails: The server automatically generates reminder emails for identified employees according to their emotional state. For example, for an employee who is feeling stressed, the server creates a gentle email saying, "Please proceed without overdoing it."

[0290] 5. Sending emails: The server sends reminder emails at appropriate times, taking into account the user's emotional state and sending them during times when the user is relaxed.

[0291] 6. Follow-up: If the task is still incomplete after the deadline, the server will send a follow-up email. The content of the email will also be adjusted based on the user's emotional state.

[0292] Example prompt sentence:

[0293] "A system that retrieves the latest task data from a project management system, identifies users with incomplete tasks using an AI model, and generates and sends reminder emails based on their emotional state using an emotion engine."

[0294] This system goes beyond simply automating reminder emails, enabling more personalized communication that takes user emotions into account.

[0295] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0296] Step 1:

[0297] The server collects user activity history and work progress from the project management system and mail server. Inputs include data from the project management system's API and mail server. This data is periodically retrieved and stored in a database. For example, the latest task data and user activity logs are saved to the database by batch processing scheduled overnight.

[0298] Specific behavior:

[0299] Retrieving task data from a project management system's API

[0300] Collecting email logs from the email server

[0301] Store the collected data in a database

[0302] Step 2:

[0303] The server uses an AI model to analyze the collected data. The inputs include the task data and behavioral history collected in step 1. The AI ​​model analyzes users' task completion status and past behavioral history to identify users who need reminders. The output is a list of users who need reminders.

[0304] Specific behavior:

[0305] Input data collected from the database into the AI ​​model

[0306] Use machine learning algorithms to analyze incomplete tasks and behavioral history

[0307] Make a list of users who need reminders

[0308] Step 3:

[0309] The server uses an emotion recognition engine to recognize the user's emotions. Inputs include the user's email text and voice data. The emotion engine uses natural language processing (NLP) and voice analysis technologies to analyze the user's emotional state (e.g., stress level and motivation), and outputs the user's emotional state data.

[0310] Specific behavior:

[0311] Analyzing email text using natural language processing technology

[0312] Analyzing voice data using voice recognition technology

[0313] The emotion engine evaluates and outputs the user's emotional state.

[0314] Step 4:

[0315] The server automatically generates reminder emails based on the output of the emotion recognition engine. The input is a list of users who need reminding and their emotional state data. A template file is used to customize the email content according to the emotional state. The output is a customized reminder email.

[0316] Specific behavior:

[0317] Get the target users from the list of users who need to be reminded

[0318] Select and customize template files based on your emotional state

[0319] Generate customized reminder emails

[0320] Step 5:

[0321] The server adds the generated reminder email to the sending queue and sends it at the optimal time. The input is the customized reminder email and the user's appropriate sending timing data. The output is that the reminder email is sent.

[0322] Specific behavior:

[0323] Add the generated reminder email to the sending queue

[0324] Optimizing transmission timing based on the user's emotional state

[0325] Send reminders at the perfect time

[0326] Step 6:

[0327] If the task is not completed after the reminder email is sent, the server automatically generates and sends a follow-up email. The input is the task completion status data and emotional state data after the reminder email is sent. The output is the generation and sending of a follow-up email.

[0328] Specific behavior:

[0329] Check task completion status after sending a reminder email

[0330] Generate follow-up emails based on sentiment engine data when there are open tasks

[0331] Send a follow-up email

[0332] Through these steps, the system automatically generates and sends reminder emails that take the user's emotions into consideration, thereby improving work efficiency and user satisfaction.

[0333] (Application example 2)

[0334] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0335] Conventional reminder email systems send reminder emails based only on the user's behavioral history and task progress, and therefore are unable to take the user's emotional state into consideration. This has resulted in problems such as inappropriate reminders being sent based on the user's emotional state, and the effectiveness of reminders being insufficient. To solve this problem, the present invention aims to provide a system that recognizes the user's emotional state, automatically generates reminder emails based on the user's emotions, and sends them at the optimal time.

[0336] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a data collection means for acquiring the user's behavioral history and task progress status, an AI analysis means for identifying targets requiring reminders based on the acquired data, an emotion recognition means for recognizing the user's emotional state, an email creation means for automatically generating a reminder email according to the emotional state, and a sending means for sending the created reminder email at an appropriate time. This makes it possible to automatically generate a personalized reminder email that takes the user's emotional state into consideration and send it at the optimal time.

[0337] "User behavior history" refers to data such as the operations a user performs on the system, access history, and task progress.

[0338] "Task progress status" indicates information such as the current completion status, progress, and deadline of the task for which the user is responsible.

[0339] "Data collection means" refers to the technical means for acquiring data such as user behavior history and task progress on the system.

[0340] "AI analysis method" refers to an analysis technology that uses artificial intelligence to identify users who need reminders based on collected data.

[0341] "Emotion recognition means" refers to technology that analyzes a user's emotional state and evaluates their stress level, motivation, etc.

[0342] A "reminder email" refers to an email sent to a user to encourage them to progress with a task.

[0343] "Email creation means" refers to technology that automatically generates the content of reminder emails based on the user's emotional state.

[0344] "Transmission means" refers to a technology for sending the generated reminder email to the user at an appropriate time.

[0345] "Schedule setting means" refers to a technology that sets the optimal timing for sending reminder emails.

[0346] "Logging means" refers to technology for recording sent emails and their results.

[0347] "Follow-up measures" refer to technology that automatically generates and sends another email if the task is not completed after the reminder.

[0348] "Personalization" refers to optimizing content and services according to the individual characteristics and circumstances of the user.

[0349] The present invention is a system that recognizes a user's emotions and automatically generates and sends reminder emails according to the user's emotions. This system includes multifunctional technology that acquires the user's behavioral history and task progress, and optimizes the appropriate timing and content of reminders.

[0350] Collecting data on user behavior history and task progress

[0351] The server has a means of collecting data to acquire the user's behavioral history and task progress. For example, if a user adds a product to their cart on an online shopping site but leaves it unpurchased, that information is sent to the server. The server also collects information about the products the user has viewed and how frequently they have viewed them.

[0352] AI analysis to identify necessary reminders

[0353] The server uses AI analysis methods based on the collected data to identify users who need reminders. This process predicts whether a reminder to make a purchase is necessary based on, for example, the products the user has pending purchases or the pages they frequently visit. The artificial intelligence techniques used here include generative AI models.

[0354] Emotion evaluation of users using emotion recognition methods

[0355] The server uses emotion recognition techniques to recognize the user's emotional state. For example, it analyzes the context of the words used by the user in emails and chats to assess their stress level and motivation. Natural language processing technology and machine learning models are used for this emotion recognition.

[0356] Automatically generate reminder emails

[0357] The server automatically generates reminder emails according to the user's emotional state. The email creator adjusts the content based on the user's emotions. For example, for a user with low purchasing motivation, it generates a reminder email with the content "We will give you a limited-time discount coupon!"

[0358] Sending reminders and following up

[0359] The reminder email is sent to the user at an appropriate time by the server's sending means. For example, it is sent during a time period when the user is relaxing, taking into account the user's activity history. If the task is not completed after the reminder, another reminder email is automatically generated and sent using the follow-up means.

[0360] Examples and prompts

[0361] As a concrete example, consider the use of an online shopping site. If a user adds an item to their cart but holds off on purchasing, the emotion engine determines that the user is not highly motivated to purchase. In this situation, the reminder bot sends a reminder notification with a limited coupon during a relaxing time.

[0362] Here are some examples of prompts for generative AI models:

[0363] Customize the content of reminder emails based on the user's emotional state. A user has product A and product B in their cart. Their emotional state is low. What kind of reminder email should you create to encourage them to make a purchase?

[0364] In this way, by taking into account the user's emotional state and sending a personalized reminder email, it is possible to maximize the effectiveness of the reminder.

[0365] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0366] Step 1:

[0367] The server acquires the user's behavioral history and task progress. Specifically, it collects data such as the products the user viewed on the online shopping site, the products they added to their cart, and their purchase history. This data is stored in a database and used for later analysis.

[0368] Input: User behavior history, task progress data

[0369] Output: User behavior history and task progress stored in a database

[0370] Step 2:

[0371] The server uses AI analytics to identify users who need reminders based on the collected data, and uses a generative AI model to determine whether a particular user has left an item in their cart unpurchased.

[0372] Input: User behavior history and task progress stored in a database

[0373] Output: A list of users who need to be reminded

[0374] Step 3:

[0375] The server uses emotion recognition to recognize the user's emotional state, analyzing data such as email and chat messages and browsing history to assess the user's stress level and motivation.

[0376] Input: Email and chat text, browsing history

[0377] Output: User's emotional state (high motivation / low motivation, stress level, etc.)

[0378] Step 4:

[0379] The server automatically generates reminder emails based on the user's emotional state, using a generative AI model to create prompts tailored to the user's emotions and then constructing the email content accordingly.

[0380] Input: User's emotional state, prompt

[0381] Output: Reminder email content

[0382] Step 5:

[0383] The server then sends the created reminder email at the appropriate time, taking into account the user's behavioral history and emotional state, and sends the email at the optimal time, such as during a relaxed time.

[0384] Input: Reminder email content, user activity history

[0385] Output: Reminder email sent to user

[0386] Step 6:

[0387] If the user does not take action based on the reminder email, the server will automatically generate and send a follow-up email again, again using AI analysis methods to analyze the user's emotional state and customize the content of the follow-up email accordingly.

[0388] Input: Reminder email sending results, user behavior history

[0389] Output: Content and sending of follow-up email

[0390] This allows reminder emails and follow-up emails to be automatically generated and sent at the appropriate time, taking into account the user's emotional state.

[0391] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0392] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0393] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0394] [Second embodiment]

[0395] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0396] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0397] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0398] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0399] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0400] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0401] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0402] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0403] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0404] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0405] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0406] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0407] The present invention is a system for automating reminder emails, and a specific embodiment thereof will be described below.

[0408] Data collection

[0409] The server acquires user activity history and task progress status from a project management system, mail server, etc. This data collection is performed periodically, and the updated information is stored in a database. For example, the latest task status is saved in the database by a batch process scheduled every night.

[0410] AI-powered analysis

[0411] The server uses AI analytics to identify users who need reminders based on the collected data. This is done using machine learning models to make predictions based on each user's task completion status and past behavior. For example, it identifies users who have not yet completed a specific task that is due to be submitted.

[0412] Creating a reminder email

[0413] The server automatically generates reminder emails for the identified recipients. The email content is constructed using a template file, and important information such as the user name, task name, and deadline is dynamically embedded. For example, an email might be generated with the following content: "Dear [user name], today is the deadline for submitting your report."

[0414] Sending emails

[0415] The server sends the generated reminder email at an appropriate time. The sending timing is optimized using a schedule setting means, and is set to send, for example, one day before the submission deadline and in the morning of the day of the deadline. The server connects to the SMTP server and sends the email.

[0416] Follow-up

[0417] If the task is not completed after the reminder email is sent, the server automatically generates and sends a follow-up email. This increases the certainty of task completion. For example, if the task remains incomplete after the deadline, a follow-up email stating, "Submission is late. Please take immediate action." is sent.

[0418] Specific examples

[0419] As a specific example of use, consider the use in a company's project management system.

[0420] 1. Data collection

[0421] The server obtains the task completion status of each employee from the project management system and stores it in a database.

[0422] 2. AI-based analysis

[0423] The server analyzes the collected data using an AI model to identify employees who have tasks that are due soon but have not yet been completed.

[0424] 3. Create a reminder email

[0425] The server creates a reminder email for the identified employee, stating, "Dear [Employee Name], task [Task Name] for [Project Name] is incomplete. The deadline is [Date]."

[0426] 4. Sending emails

[0427] The server sends the created reminder email at an appropriate time, for example, the day before the submission deadline and in the morning of the deadline.

[0428] 5. Follow-up

[0429] If the task is not completed after the deadline, the server will send another follow-up email.

[0430] This system reduces the workload for both users and administrators and improves work efficiency.

[0431] The processing flow will be explained below.

[0432] Step 1:

[0433] The server acquires user activity history and task progress status from the project management system and mail server. This acquisition process is performed periodically, and a scheduled batch process is executed daily to acquire the latest data.

[0434] Step 2:

[0435] The server stores the acquired data in a database. The stored data shows the progress of each user's task in detail and is used for later analysis. For example, the user ID, task ID, deadline, progress status, etc. are saved in the database.

[0436] Step 3:

[0437] The server uses a query to extract data on people who need reminders from the database. For example, it executes an SQL query to extract "users who have tasks due the next day."

[0438] Step 4:

[0439] The server inputs the extracted data into an AI analysis model to identify those who need reminders. The AI ​​model uses machine learning models that have learned from past data to predict which users need reminders.

[0440] Step 5:

[0441] The server saves the analysis results in a database and updates the list of reminder recipients, ensuring the information is available for creating reminder emails in the next step.

[0442] Step 6:

[0443] The server loads the reminder email template and automatically generates emails by embedding individual information for each reminder recipient. For example, the template embeds parameters such as the user name, task name, and deadline date.

[0444] Step 7:

[0445] The server adds the generated reminder email to a sending queue and schedules it for sending. The schedule is set so that the email is sent at the optimal time, for example, the day before the deadline and in the morning of the deadline.

[0446] Step 8:

[0447] The server connects to the SMTP server and sends reminder emails according to the sending schedule. The sending result of each email is recorded in a log, and the success / failure is saved in a database.

[0448] Step 9:

[0449] The server monitors the sending results, and if the task is not completed by the deadline, it automatically generates a follow-up email and adds it to the sending queue. The follow-up email contains a message urging the user to complete the task again.

[0450] Step 10:

[0451] The server will send follow-up emails according to the schedule and again log the results, allowing for continuous follow-up until the task is completed.

[0452] This processing flow automates the sending and receiving of reminder emails, improving work efficiency.

[0453] Example 1

[0454] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0455] Conventional task management systems have problems such as users forgetting tasks or not receiving reminders to meet deadlines, resulting in reduced work efficiency. Manual reminders are time-consuming and difficult to send at the right time, so an automated reminder mechanism is needed. Furthermore, a system that can automatically send not only reminder emails but also follow-up emails is also needed.

[0456] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0457] In this invention, the server includes a data collection means for acquiring a user's behavioral history and task progress status, a machine learning model analysis means for identifying targets requiring reminders based on the acquired data, a template generation means for automatically generating reminder emails for targets, a sending means for sending the created reminder emails at an appropriate time, a follow-up means for automatically generating and sending a follow-up email if the task is not completed after sending, a batch processing means for periodically acquiring data, and a means for dynamically inserting information such as the user name, task name, and deadline into the content of the email to be sent. This encourages users to remember to complete tasks and improves work efficiency.

[0458] 1. "Data collection means" refers to a device or method for acquiring a user's behavioral history and task progress.

[0459] 2. "Machine learning model analysis means" means a device or method that uses a machine learning model to analyze acquired data and identify targets requiring reminders.

[0460] 3. "Template generation means" means a device or method that uses a template to automatically generate reminder emails to identified recipients.

[0461] 4. "Transmission means" means a device or method for sending the created reminder email at an appropriate time.

[0462] 5. "Follow-up means" means a device or method for automatically generating and sending a follow-up email if the task is not completed after sending.

[0463] 6. "Batch processing means" means a device or method that processes data in bulk to periodically obtain data.

[0464] 7. "Dynamic insertion means" means a device or method for automatically adding information such as user names, task names, and deadline dates to the content of emails being sent.

[0465] The present invention relates to a system for automating reminder emails, and specific embodiments thereof will be described below.

[0466] Data collection

[0467] The server obtains user activity history and task progress from a project management system (e.g., JIRA) or mail server (e.g., Exchange Server). This data collection is performed periodically by batch processing and stored in a database (e.g., MySQL) on the server. Specifically, the server sets up a Cron job every night to obtain task data from the project management system using an API request and store it in the database.

[0468] AI-powered analysis

[0469] The server analyzes the collected data using a machine learning model (e.g., Scikit-learn). The server uses a specific algorithm to analyze each user's task completion status and past behavioral history to identify users who need reminders. For example, the server uses the acquired task data to extract users who have tasks that are close to their submission deadline but have not yet been completed.

[0470] Creating a reminder email

[0471] The server automatically generates reminder emails for the identified recipients. Using a template engine (such as Jinja2), it dynamically inserts necessary information (such as user name, task name, deadline date, etc.) into the email content. Specifically, it generates an email with the content "Dear [user name], today is the deadline for submitting your report." This automatically creates a reminder email.

[0472] Sending emails

[0473] The server sends the generated reminder emails at the appropriate time. The sending timing is optimized based on the schedule settings, for example, sending them the day before the submission deadline and in the morning of the day itself. The server connects to an SMTP server (e.g., Postfix) to send the reminder email. The sending status is recorded in a log so that it can be checked later.

[0474] Follow-up

[0475] If the task is not completed even after sending the reminder email, the server automatically generates and sends another follow-up email. This ensures that the task is completed. For example, if the task is not completed even after the submission deadline, the server sends a follow-up email stating, "The submission is late. Please take immediate action."

[0476] Specific examples

[0477] 1. Data collection

[0478] The server obtains the task completion status of each user from the project management system and stores it in a database.

[0479] 2. AI-based analysis

[0480] The server analyzes the collected data using an AI model to identify users who have tasks that are due soon but have not yet been completed.

[0481] 3. Create a reminder email

[0482] The server creates a reminder email for the identified user with the following content: "Dear [user name], task [task name] for [project name] is incomplete. The deadline is [date]."

[0483] 4. Sending emails

[0484] The server sends the created reminder email at an appropriate time, for example, the day before the submission deadline and in the morning of the deadline.

[0485] 5. Follow-up

[0486] If the task is not completed after the deadline, the server will send another follow-up email.

[0487] Prompt Sentence Examples

[0488] Below are some example prompts to be input to the generative AI model:

[0489] Analyze user task data obtained from your project management system and identify users who have incomplete tasks with upcoming deadlines. Create templated reminder emails for those users and send them the day before and on the deadline. Also, send follow-up emails if the task is still incomplete after the deadline. Dynamically insert information such as the user name, task name, and due date into the reminder and follow-up emails.

[0490] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0491] Specific explanation of processing steps

[0492] Step 1: Collect data

[0493] The server periodically retrieves user action history and task progress from the project management system and mail server. The input data is task data retrieved from the project management system, and the output is updated task information stored in the database. Specifically, the server sets up a Cron job every night to execute batch processing. This process sends an API request to retrieve task data from the project management system and stores it in a MySQL database.

[0494] Step 2: AI analysis

[0495] The server analyzes all collected data using a machine learning model. The input data is task information stored in the database, and the output is a list of users who need reminders. Specifically, the server runs a Python script to read the necessary data from the database. It then inputs the data into a Scikit-learn model to generate a list of users who need reminders.

[0496] Step 3: Create a reminder email

[0497] The server uses a template engine to automatically generate reminder emails for the identified users. The input data is a list of users who need reminders and template information, and the output is the generated reminder email. Specifically, the server loads a Jinja2 template and dynamically embeds the user name and task information (task name, deadline date) into the template to generate the reminder email.

[0498] Step 4: Sending an email

[0499] The server sends the generated reminder email using an SMTP server. The input data is the generated reminder email and schedule information, and the output is the sent reminder email. Specifically, the server checks the sending timing based on the schedule settings, connects to the Postfix SMTP server, and sends the reminder email. The sending status is recorded in a log, making it possible to track it.

[0500] Step 5: Follow up

[0501] If the task is still incomplete after the reminder email is sent, the server automatically generates and sends another follow-up email. The input data is the task status data after submission, and the output is the follow-up email. Specifically, the server checks the database again after a certain period of time has passed and identifies users who have incomplete tasks. It then generates a follow-up email to that user stating, "Submission is late. Please take action as soon as possible," and sends it via the SMTP server.

[0502] Specific processing flow

[0503] Step 1:

[0504] The server runs a batch process every night by setting up a Cron job to retrieve task data from the project management system. The retrieved task data is obtained through an API request and stored in a MySQL database.

[0505] Step 2:

[0506] The server reads the task information stored in the database using a Python script and analyzes it using a machine learning model (Scikit-learn), which generates a list of users who need reminders.

[0507] Step 3:

[0508] The server uses the Jinja2 template engine to generate reminder emails for the identified users, dynamically populating the template with information such as the user name, task name, and due date to create the reminder email.

[0509] Step 4:

[0510] The server checks the schedule to send the generated reminder email, sends the reminder email using the Postfix SMTP server, and logs the delivery status.

[0511] Step 5:

[0512] After sending the reminder email, the server checks the database again to identify users with incomplete tasks. If necessary, it generates a follow-up email and sends it via the SMTP server with the message "Submission is late. Please take action as soon as possible."

[0513] (Application example 1)

[0514] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0515] In modern factories, worker task management is important, but it is difficult to grasp the progress of all workers in real time and provide appropriate reminders and follow-ups. To ensure that on-site workers complete their tasks at the appropriate time, an automated system that can provide immediate reminders is required. Furthermore, since reminders are sometimes not sent or notifications that are sent are ineffective, the importance of optimizing the timing of notifications and follow-ups is being questioned. Furthermore, conventional systems only notify workers via email, making it difficult to provide immediate notifications to workers who are working on-site.

[0516] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0517] In this invention, the server includes a data collection means for acquiring a user's behavioral history and task progress status, an AI analysis means for identifying individuals who need reminders based on the acquired data, a notification creation means for automatically generating reminder emails and real-time notifications for the individuals, and a transmission means for sending the created reminder emails and notifications at the appropriate time. This allows the progress of work in the factory to be grasped in real time, enabling reminders and follow-ups at the appropriate time. In addition, by using a wearable display device control means, on-site workers can be notified immediately, improving work efficiency.

[0518] The "data collection means" is a means for acquiring the behavioral history and task progress status of users and workers, and storing them in a database or the like.

[0519] "AI analysis methods" are methods that use machine learning models and artificial intelligence technology to analyze acquired data and identify targets that require reminders.

[0520] The "notification creation means" is a means for automatically generating reminder emails and real-time notifications for specified targets.

[0521] The "transmission means" refers to a means for sending the created reminder email or notification to the target person at an appropriate time.

[0522] A "scheduling means" is a means used to optimize the timing of sending reminder emails and notifications.

[0523] A "log recording means" is a means for recording the results of sent emails and notifications so that they can be referenced later.

[0524] The "follow-up method" is a method for automatically generating and sending a follow-up email or notification if the task is not completed after the reminder.

[0525] The "wearable display device control means" is a means for grasping the progress of work based on the acquired data and displaying reminders or follow-up notifications on the wearable display device (e.g., smart glasses).

[0526] The present invention is a system for automatically managing a user's behavior history and task progress, and sending reminder emails and real-time notifications. Specific embodiments of the system are described below.

[0527] First, the server plays an important role. This server has a means of collecting data to acquire the behavioral history and task progress of users and workers, and this data is stored in a database. This data collection is based on logs from sensors and robots installed in the factory, as well as input information from workers. Data is often collected in real time or periodically processed in batches.

[0528] Next, based on the collected data, the server's AI analysis method identifies those who need reminders. This AI analysis method uses machine learning models (e.g., RandomForestClassifier). Reminder emails and real-time notifications are automatically generated to provide appropriate reminders to the identified individuals. This notification creation method uses dynamic templates to automatically fill in important information such as user name, task name, and due date.

[0529] Reminder emails and notifications are sent at appropriate times. This sending method includes sending emails via a regular SMTP server or real-time notification functions using wearable display devices such as smart glasses. The sending timing is optimized by a scheduling method. For example, it can be set to match the user's work schedule, such as the day before the submission deadline or the morning of the deadline.

[0530] Furthermore, the results of the sent emails and notifications are recorded using a logging mechanism. This allows for future reference and serves as data for evaluating the effectiveness of the system. If the task is not completed after the reminder, the server's follow-up mechanism automatically generates and sends another follow-up email or notification. This improves the task completion rate.

[0531] Finally, it is important to have a wearable display control means to grasp the progress of work in the factory and notify workers immediately, which will allow real-time reminders and follow-ups at the workplace, greatly improving work efficiency.

[0532] Specific examples

[0533] For example, an example of use in a factory will be described.

[0534] 1. Data collection: The server collects real-time operational data from robots and sensors in the factory and stores it in a database.

[0535] 2. AI analysis: The server analyzes the collected data using an AI model (e.g., RandomForestClassifier) ​​to identify workers and tasks that require reminders.

[0536] 3. Creating and sending notifications: The server automatically generates reminder notifications for the identified workers and displays them on the smart glasses. The notification might say something like, "Worker B, the deadline for Task C is approaching. Please complete it as soon as possible."

[0537] 4. Follow-up: If the task is not completed after the reminder, a follow-up notification will be sent automatically.

[0538] Prompt Sentence Examples

[0539] Prompt Type: Industrial Task Management

[0540] Predictive Tasks: Forecast task progress and generate automatic reminders

[0541] Input data: {'worker_id': int, 'task_id': int, 'status': str, 'deadline': str}

[0542] Desired output: A list of tasks that need reminders

[0543] Example: Worker ID: 123 - Task ID: 789 is nearing its deadline.

[0544] In this way, the system can manage work progress within the factory in real time, send reminder notifications at appropriate times, and improve work efficiency.

[0545] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0546] Step 1:

[0547] The server collects work progress data from robots and sensors in the factory. This data collection is done in regular batch processing or in real time and stored in a database. For example, the location information of workers obtained from sensors and the operating hours of machines are stored in the database.

[0548] Input: Work progress data obtained from robots and sensors

[0549] Output: Working data stored in a database

[0550] Step 2:

[0551] The server inputs the stored data into an AI analysis method, which uses a machine learning model (e.g., RandomForestClassifier) ​​to identify workers and tasks that need reminding. The AI ​​model compares this data with past data and predicts who should be reminded based on certain criteria (e.g., tasks that are due soon but not completed).

[0552] Input: Working data stored in the database

[0553] Output: A list of workers and tasks that need reminding

[0554] Step 3:

[0555] The server automatically generates reminder notifications based on the workers and tasks identified by the AI ​​analysis method. The notification creation method uses templates to dynamically embed information such as the user name, task name, and deadline. For example, a notification might be created that reads, "Worker B, the deadline for Task C is approaching. Please complete it promptly."

[0556] Input: A list of workers and tasks that need reminding

[0557] Output: Reminder notification message

[0558] Step 4:

[0559] The server sends the created reminder notification at the appropriate time. The sending method includes email sending via an SMTP server and real-time notification using wearable display devices such as smart glasses. The notification timing is optimized by the schedule setting method. For example, notifications can be sent the day before the submission deadline or in the morning of the deadline.

[0560] Input: Reminder message

[0561] Output: Reminder sent

[0562] Step 5:

[0563] The server records the results of the sent reminders and notifications as a log. Using the log recording method, information such as the sending date and time, recipient, and notification content is saved in a database. This allows for future reference and can be used as data to evaluate the effectiveness of the system.

[0564] Input: Reminder notification information sent

[0565] Output: Log information recorded in the database

[0566] Step 6:

[0567] If the task is not completed after the reminder, the server automatically generates and sends another follow-up notification using the follow-up means. For example, a follow-up notification such as "Task C is not yet completed. Please take action immediately" can be generated and displayed on the worker's wearable display device at an appropriate time.

[0568] Input: Incomplete task information

[0569] Output: Follow-up notification message

[0570] Step 7:

[0571] The server notifies the on-site worker of the work progress in real time using the wearable display control means, which allows the worker wearing the smart glasses to receive immediate reminders and follow-up notifications, thereby improving work efficiency and increasing the task completion rate.

[0572] Input: Reminder notification message, Follow-up notification message

[0573] Output: Notifications displayed on wearable displays such as smart glasses

[0574] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0575] The present invention optimizes the content and sending timing of reminder emails according to the user's emotions by combining a system that automates reminder emails with an emotion engine that recognizes the user's emotions. Specific embodiments of this invention are described below.

[0576] Data collection

[0577] The server periodically retrieves user activity history and task progress status from the project management system and mail server. This allows daily updated information to be stored in the database. For example, the latest task status is saved in the database by a batch process scheduled every night.

[0578] AI-powered analysis

[0579] The server uses AI analysis tools based on the collected data to identify users who need reminders. It also uses machine learning models to make predictions based on each user's task completion status and past behavioral history. For example, it identifies users who have not yet completed a specific task even though the deadline for its submission is approaching.

[0580] emotion recognition

[0581] The server uses an emotion engine to recognize the user's emotions. This emotion recognition is performed, for example, by analyzing the user's email text and voice data. The emotion engine evaluates the user's emotional state, taking into account factors such as the user's stress level and motivation.

[0582] Creating a reminder email

[0583] The server automatically generates reminder emails for identified recipients, with content customized according to the emotions recognized by the emotion engine. The template file is dynamically modified, so that if the user is feeling stressed, for example, an email is created with a gentle tone. An email is generated with the following content: "Dear [user name], I'm concerned about the progress of your task. Please let me know if you need any help."

[0584] Sending emails

[0585] The server adds the generated reminder email to a sending queue and sends it at an optimized timing based on the emotional state recognized by the emotion engine. For example, it sends the email when the user is relaxed, avoiding busy times.

[0586] Follow-up

[0587] If the task is not completed after the reminder email is sent, the server automatically generates a follow-up email and sends it again. The content and timing of the follow-up email are also customized based on information from the emotion engine. For example, if the task is not completed even after the deadline for submission, an appropriate follow-up will be performed depending on the user's status. An email may be sent stating, "Your submission is late, but please let us know if there are no particular problems."

[0588] Specific examples

[0589] As a specific example of use, consider the use in a company's project management system.

[0590] 1. Data collection

[0591] The server obtains the task completion status of each employee from the project management system and stores it in a database.

[0592] 2. AI-based analysis

[0593] The server analyzes the collected data using an AI model to identify employees who have tasks that are due soon but have not yet been completed.

[0594] 3. Emotion recognition

[0595] The server uses an emotion engine to recognize employees' emotional states from email text and voice data, and evaluates their stress and motivation.

[0596] 4. Create a reminder email

[0597] The server automatically generates reminder emails for identified employees based on their emotional state. For example, for an employee feeling stressed, the server creates a gentle email saying, "Please proceed without overdoing it."

[0598] 5. Sending emails

[0599] The server sends reminder emails at appropriate times, often during relaxing hours, taking into account the user's emotional state.

[0600] 6. Follow-up

[0601] The server sends follow-up emails if the task is still incomplete after the deadline, and the content is also adjusted to take into account the user's emotional state.

[0602] This system not only automates reminder emails, but also enables more personalized communication that takes users' emotions into consideration, which is expected to improve work efficiency and user satisfaction.

[0603] The processing flow will be explained below.

[0604] Step 1:

[0605] The server acquires user activity history and task progress from the project management system and mail server. This acquisition process is performed periodically, with daily scheduled batch processing. For example, data such as each user's task ID, progress, and deadline is acquired and stored in a database.

[0606] Step 2:

[0607] The server stores the collected data in a database, which records detailed task information for each user. The acquired data is organized according to a storage format for later analysis.

[0608] Step 3:

[0609] The server uses a query to extract data on users who need reminders from the database. For example, it executes an SQL query to extract users who have tasks due the next day.

[0610] Step 4:

[0611] The server inputs the extracted data into an AI analysis model to identify those who need reminders, and uses a machine learning model to predict candidates who need reminders based on each user's task completion status and past behavioral history.

[0612] Step 5:

[0613] The server saves the reminder recipients in the database based on the analysis results, and updates the list for creating reminder emails.

[0614] Step 6:

[0615] The server uses an emotion engine to recognize the user's emotions. For example, it analyzes past emails and voice data to assess the user's stress level and motivation. It may also use NLP (natural language processing) technology to analyze the text of emails.

[0616] Step 7:

[0617] The server automatically generates emotion-based reminder emails for the reminder recipients. It reads a template file and dynamically fills in parameters such as the user name, task name, and due date. It also customizes the email content based on the results of the emotion engine. For example, it generates a message like, "Dear [user name], I'm concerned about the progress of your task. Please let me know if you need any help."

[0618] Step 8:

[0619] The server adds the generated reminder email to a sending queue and schedules the sending based on the emotional state recognized by the emotion engine. For example, it schedules the email to be sent during a time when the user is relaxed.

[0620] Step 9:

[0621] The server connects to the SMTP server according to the sending schedule and sends the reminder email. The sending result is recorded in a log, and the success / failure information is saved in a database.

[0622] Step 10:

[0623] The server monitors the submission results and automatically generates a follow-up email and adds it to the submission queue if the task is not completed by the deadline. The content of the follow-up email is customized based on the evaluation results of the emotion engine. For example, it could say, "Your submission is late, but please let us know if there are no particular problems."

[0624] Step 11:

[0625] The server sends follow-up emails on a scheduled basis and again logs the results, allowing the effectiveness of the follow-up emails to be monitored and further follow-ups to be performed if necessary.

[0626] This specific processing flow automates the sending and receiving of reminder emails that take the user's emotions into consideration, thereby improving work efficiency and user satisfaction.

[0627] Example 2

[0628] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0629] Conventional reminder systems can create and send reminder emails based on the user's behavioral history and task progress, but it is difficult to set the optimal content and timing of the emails while taking the user's emotional state into account. As a result, problems arise, such as increased user stress and inappropriate follow-up. In particular, reminder emails can be counterproductive because they are insensitive to the user's emotions.

[0630] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a data collection means for acquiring a user's behavioral history and work progress status, an AI analysis means for identifying targets requiring reminders based on the acquired data, an email creation means for automatically generating reminder emails for the targets, a sending means for adding the generated reminder emails to a sending queue and sending them at an appropriate time, an emotion recognition means for recognizing the user's emotions, an email adjustment means for customizing the content of the reminder email according to the emotion recognized by the emotion recognition means, and a follow-up means for automatically generating and sending a follow-up email if the task is not completed even after sending. This makes it possible to optimize the content and sending timing of the reminder email taking the user's emotions into consideration.

[0631] A "user" is a person or organization that uses the system.

[0632] "Behavioral history" is a record of the operations and activities performed by a user.

[0633] "Work progress" is data on the progress of tasks and projects that a user is responsible for.

[0634] "Data collection means" refers to a mechanism or device for acquiring a user's behavior history and work progress.

[0635] "AI analysis methods" are methods that use artificial intelligence to analyze collected data and identify targets that require reminders.

[0636] A "reminder email" is an email sent to a user to encourage them to progress on a task or project.

[0637] "Email creation means" refers to a system or program for automatically generating reminder emails.

[0638] A "sending queue" is a temporary storage location or list of emails waiting to be sent.

[0639] "Transmission means" refers to the method or technology used to send reminder emails to users.

[0640] "Emotion recognition means" refers to a technology or system for determining a user's emotions or mental state.

[0641] The "email adjustment means" is a function for customizing the contents of the reminder email according to the user's emotions.

[0642] A "follow-up method" is a mechanism for sending another email if the task is not completed after the reminder email has been sent.

[0643] The system of the present invention acquires a user's behavior history and work progress, and takes the user's emotions into consideration when automatically generating and sending reminder emails. This system includes data collection means, AI analysis means, email creation means, email sending means, emotion recognition means, email adjustment means, and follow-up means.

[0644] An embodiment of this system will now be described in detail.

[0645] Data collection methods

[0646] The server periodically collects user activity history and work progress from the project management system and mail server. This is done by using automatic data acquisition via API or batch processing. For example, the latest task progress is stored in a database by batch processing scheduled overnight.

[0647] AI analysis means

[0648] The server analyzes the collected data using an AI model. It uses a machine learning algorithm to identify users who have incomplete tasks that are due soon. The AI ​​model makes predictions based on each user's task completion status and past behavioral history.

[0649] emotion recognition means

[0650] The server uses an emotion recognition engine to recognize the user's emotions, including natural language processing (NLP) and voice recognition technologies, to assess the user's stress level and motivation from the text of their emails and their voice data.

[0651] Email creation method

[0652] The server automatically generates reminder emails based on the emotions recognized by the emotion engine. This includes the ability to use template files to customize the content of emails depending on the user's emotional state. For example, a friendly email could be created that reads, "Dear [user name], I'm concerned about your task progress. Please let me know if you need any help."

[0653] Transmission method

[0654] The server adds the generated reminder email to a sending queue and sends it at the optimal time, which is set to a time when the user is relaxed.

[0655] Follow-up measures

[0656] If the task is not completed after the reminder email is sent, the server automatically generates and sends a follow-up email. This includes the ability to customize the content and timing of the email based on information obtained from the emotion engine. For example, an email could be sent with the following content: "Your submission is late, but please let us know if there are no particular problems."

[0657] Specific examples

[0658] As a specific example of use, consider using it in a company's project management system.

[0659] 1. Data collection: The server obtains the task completion status of each employee from the project management system API, and stores the progress status of each employee in a database.

[0660] 2. AI analysis: The server analyzes the collected data using an AI model to identify employees who have incomplete tasks that are due soon.

[0661] 3. Emotion recognition: The server uses an emotion engine to recognize employees' emotional states from email text and voice data, and evaluates their stress and motivation.

[0662] 4. Creating reminder emails: The server automatically generates reminder emails for identified employees according to their emotional state. For example, for an employee who is feeling stressed, the server creates a gentle email saying, "Please proceed without overdoing it."

[0663] 5. Sending emails: The server sends reminder emails at appropriate times, taking into account the user's emotional state and sending them during times when the user is relaxed.

[0664] 6. Follow-up: If the task is still incomplete after the deadline, the server will send a follow-up email. The content of the email will also be adjusted based on the user's emotional state.

[0665] Example prompt sentence:

[0666] "A system that retrieves the latest task data from a project management system, identifies users with incomplete tasks using an AI model, and generates and sends reminder emails based on their emotional state using an emotion engine."

[0667] This system goes beyond simply automating reminder emails, enabling more personalized communication that takes user emotions into account.

[0668] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0669] Step 1:

[0670] The server collects user activity history and work progress from the project management system and mail server. Inputs include data from the project management system's API and mail server. This data is periodically retrieved and stored in a database. For example, the latest task data and user activity logs are saved to the database by batch processing scheduled overnight.

[0671] Specific behavior:

[0672] Retrieving task data from a project management system's API

[0673] Collecting email logs from the email server

[0674] Store the collected data in a database

[0675] Step 2:

[0676] The server uses an AI model to analyze the collected data. The inputs include the task data and behavioral history collected in step 1. The AI ​​model analyzes users' task completion status and past behavioral history to identify users who need reminders. The output is a list of users who need reminders.

[0677] Specific behavior:

[0678] Input data collected from the database into the AI ​​model

[0679] Use machine learning algorithms to analyze incomplete tasks and behavioral history

[0680] Make a list of users who need reminders

[0681] Step 3:

[0682] The server uses an emotion recognition engine to recognize the user's emotions. Inputs include the user's email text and voice data. The emotion engine uses natural language processing (NLP) and voice analysis technologies to analyze the user's emotional state (e.g., stress level and motivation), and outputs the user's emotional state data.

[0683] Specific behavior:

[0684] Analyzing email text using natural language processing technology

[0685] Analyzing voice data using voice recognition technology

[0686] The emotion engine evaluates and outputs the user's emotional state.

[0687] Step 4:

[0688] The server automatically generates reminder emails based on the output of the emotion recognition engine. The input is a list of users who need reminding and their emotional state data. A template file is used to customize the email content according to the emotional state. The output is a customized reminder email.

[0689] Specific behavior:

[0690] Get the target users from the list of users who need to be reminded

[0691] Select and customize template files based on your emotional state

[0692] Generate customized reminder emails

[0693] Step 5:

[0694] The server adds the generated reminder email to the sending queue and sends it at the optimal time. The input is the customized reminder email and the user's appropriate sending timing data. The output is that the reminder email is sent.

[0695] Specific behavior:

[0696] Add the generated reminder email to the sending queue

[0697] Optimizing transmission timing based on the user's emotional state

[0698] Send reminders at the perfect time

[0699] Step 6:

[0700] If the task is not completed after the reminder email is sent, the server automatically generates and sends a follow-up email. The input is the task completion status data and emotional state data after the reminder email is sent. The output is the generation and sending of a follow-up email.

[0701] Specific behavior:

[0702] Check task completion status after sending a reminder email

[0703] Generate follow-up emails based on sentiment engine data when there are open tasks

[0704] Send a follow-up email

[0705] Through these steps, the system automatically generates and sends reminder emails that take the user's emotions into consideration, thereby improving work efficiency and user satisfaction.

[0706] (Application example 2)

[0707] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0708] Conventional reminder email systems send reminder emails based only on the user's behavioral history and task progress, and therefore are unable to take the user's emotional state into consideration. This has resulted in problems such as inappropriate reminders being sent based on the user's emotional state, and the effectiveness of reminders being insufficient. To solve this problem, the present invention aims to provide a system that recognizes the user's emotional state, automatically generates reminder emails based on the user's emotions, and sends them at the optimal time.

[0709] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a data collection means for acquiring the user's behavioral history and task progress status, an AI analysis means for identifying targets requiring reminders based on the acquired data, an emotion recognition means for recognizing the user's emotional state, an email creation means for automatically generating a reminder email according to the emotional state, and a sending means for sending the created reminder email at an appropriate time. This makes it possible to automatically generate a personalized reminder email that takes the user's emotional state into consideration and send it at the optimal time.

[0710] "User behavior history" refers to data such as the operations a user performs on the system, access history, and task progress.

[0711] "Task progress status" indicates information such as the current completion status, progress, and deadline of the task for which the user is responsible.

[0712] "Data collection means" refers to the technical means for acquiring data such as user behavior history and task progress on the system.

[0713] "AI analysis method" refers to an analysis technology that uses artificial intelligence to identify users who need reminders based on collected data.

[0714] "Emotion recognition means" refers to technology that analyzes a user's emotional state and evaluates their stress level, motivation, etc.

[0715] A "reminder email" refers to an email sent to a user to encourage them to progress with a task.

[0716] "Email creation means" refers to technology that automatically generates the content of reminder emails based on the user's emotional state.

[0717] "Transmission means" refers to a technology for sending the generated reminder email to the user at an appropriate time.

[0718] "Schedule setting means" refers to a technology that sets the optimal timing for sending reminder emails.

[0719] "Logging means" refers to technology for recording sent emails and their results.

[0720] "Follow-up measures" refer to technology that automatically generates and sends another email if the task is not completed after the reminder.

[0721] "Personalization" refers to optimizing content and services according to the individual characteristics and circumstances of the user.

[0722] The present invention is a system that recognizes a user's emotions and automatically generates and sends reminder emails according to the user's emotions. This system includes multifunctional technology that acquires the user's behavioral history and task progress, and optimizes the appropriate timing and content of reminders.

[0723] Collecting data on user behavior history and task progress

[0724] The server has a means of collecting data to acquire the user's behavioral history and task progress. For example, if a user adds a product to their cart on an online shopping site but leaves it unpurchased, that information is sent to the server. The server also collects information about the products the user has viewed and how frequently they have viewed them.

[0725] AI analysis to identify necessary reminders

[0726] The server uses AI analysis methods based on the collected data to identify users who need reminders. This process predicts whether a reminder to make a purchase is necessary based on, for example, the products the user has pending purchases or the pages they frequently visit. The artificial intelligence techniques used here include generative AI models.

[0727] Emotion evaluation of users using emotion recognition methods

[0728] The server uses emotion recognition techniques to recognize the user's emotional state. For example, it analyzes the context of the words used by the user in emails and chats to assess their stress level and motivation. Natural language processing technology and machine learning models are used for this emotion recognition.

[0729] Automatically generate reminder emails

[0730] The server automatically generates reminder emails according to the user's emotional state. The email creator adjusts the content based on the user's emotions. For example, for a user with low purchasing motivation, it generates a reminder email with the content "We will give you a limited-time discount coupon!"

[0731] Sending reminders and following up

[0732] The reminder email is sent to the user at an appropriate time by the server's sending means. For example, it is sent during a time period when the user is relaxing, taking into account the user's activity history. If the task is not completed after the reminder, another reminder email is automatically generated and sent using the follow-up means.

[0733] Examples and prompts

[0734] As a concrete example, consider the use of an online shopping site. If a user adds an item to their cart but holds off on purchasing, the emotion engine determines that the user is not highly motivated to purchase. In this situation, the reminder bot sends a reminder notification with a limited coupon during a relaxing time.

[0735] Here are some examples of prompts for generative AI models:

[0736] Customize the content of reminder emails based on the user's emotional state. A user has product A and product B in their cart. Their emotional state is low. What kind of reminder email should you create to encourage them to make a purchase?

[0737] In this way, by taking into account the user's emotional state and sending a personalized reminder email, it is possible to maximize the effectiveness of the reminder.

[0738] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0739] Step 1:

[0740] The server acquires the user's behavioral history and task progress. Specifically, it collects data such as the products the user viewed on the online shopping site, the products they added to their cart, and their purchase history. This data is stored in a database and used for later analysis.

[0741] Input: User behavior history, task progress data

[0742] Output: User behavior history and task progress stored in a database

[0743] Step 2:

[0744] The server uses AI analytics to identify users who need reminders based on the collected data, and uses a generative AI model to determine whether a particular user has left an item in their cart unpurchased.

[0745] Input: User behavior history and task progress stored in a database

[0746] Output: A list of users who need to be reminded

[0747] Step 3:

[0748] The server uses emotion recognition to recognize the user's emotional state, analyzing data such as email and chat messages and browsing history to assess the user's stress level and motivation.

[0749] Input: Email and chat text, browsing history

[0750] Output: User's emotional state (high motivation / low motivation, stress level, etc.)

[0751] Step 4:

[0752] The server automatically generates reminder emails based on the user's emotional state, using a generative AI model to create prompts tailored to the user's emotions and then constructing the email content accordingly.

[0753] Input: User's emotional state, prompt

[0754] Output: Reminder email content

[0755] Step 5:

[0756] The server then sends the created reminder email at the appropriate time, taking into account the user's behavioral history and emotional state, and sends the email at the optimal time, such as during a relaxed time.

[0757] Input: Reminder email content, user activity history

[0758] Output: Reminder email sent to user

[0759] Step 6:

[0760] If the user does not take action based on the reminder email, the server will automatically generate and send a follow-up email again, again using AI analysis methods to analyze the user's emotional state and customize the content of the follow-up email accordingly.

[0761] Input: Reminder email sending results, user behavior history

[0762] Output: Content and sending of follow-up email

[0763] This allows reminder emails and follow-up emails to be automatically generated and sent at the appropriate time, taking into account the user's emotional state.

[0764] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0765] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0766] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0767] [Third embodiment]

[0768] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0769] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0770] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0771] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0772] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0773] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0774] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0775] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0776] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0777] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0778] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0779] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0780] The present invention is a system for automating reminder emails, and a specific embodiment thereof will be described below.

[0781] Data collection

[0782] The server acquires user activity history and task progress status from a project management system, mail server, etc. This data collection is performed periodically, and the updated information is stored in a database. For example, the latest task status is saved in the database by a batch process scheduled every night.

[0783] AI-powered analysis

[0784] The server uses AI analytics to identify users who need reminders based on the collected data. This is done using machine learning models to make predictions based on each user's task completion status and past behavior. For example, it identifies users who have not yet completed a specific task that is due to be submitted.

[0785] Creating a reminder email

[0786] The server automatically generates reminder emails for the identified recipients. The email content is constructed using a template file, and important information such as the user name, task name, and deadline is dynamically embedded. For example, an email might be generated with the following content: "Dear [user name], today is the deadline for submitting your report."

[0787] Sending emails

[0788] The server sends the generated reminder email at an appropriate time. The sending timing is optimized using a schedule setting means, and is set to send, for example, one day before the submission deadline and in the morning of the day of the deadline. The server connects to the SMTP server and sends the email.

[0789] Follow-up

[0790] If the task is not completed after the reminder email is sent, the server automatically generates and sends a follow-up email. This increases the certainty of task completion. For example, if the task remains incomplete after the deadline, a follow-up email stating, "Submission is late. Please take immediate action." is sent.

[0791] Specific examples

[0792] As a specific example of use, consider the use in a company's project management system.

[0793] 1. Data collection

[0794] The server obtains the task completion status of each employee from the project management system and stores it in a database.

[0795] 2. AI-based analysis

[0796] The server analyzes the collected data using an AI model to identify employees who have tasks that are due soon but have not yet been completed.

[0797] 3. Create a reminder email

[0798] The server creates a reminder email for the identified employee, stating, "Dear [Employee Name], task [Task Name] for [Project Name] is incomplete. The deadline is [Date]."

[0799] 4. Sending emails

[0800] The server sends the created reminder email at an appropriate time, for example, the day before the submission deadline and in the morning of the deadline.

[0801] 5. Follow-up

[0802] If the task is not completed after the deadline, the server will send another follow-up email.

[0803] This system reduces the workload for both users and administrators and improves work efficiency.

[0804] The processing flow will be explained below.

[0805] Step 1:

[0806] The server acquires user activity history and task progress status from the project management system and mail server. This acquisition process is performed periodically, and a scheduled batch process is executed daily to acquire the latest data.

[0807] Step 2:

[0808] The server stores the acquired data in a database. The stored data shows the progress of each user's task in detail and is used for later analysis. For example, the user ID, task ID, deadline, progress status, etc. are saved in the database.

[0809] Step 3:

[0810] The server uses a query to extract data on people who need reminders from the database. For example, it executes an SQL query to extract "users who have tasks due the next day."

[0811] Step 4:

[0812] The server inputs the extracted data into an AI analysis model to identify those who need reminders. The AI ​​model uses machine learning models that have learned from past data to predict which users need reminders.

[0813] Step 5:

[0814] The server saves the analysis results in a database and updates the list of reminder recipients, ensuring the information is available for creating reminder emails in the next step.

[0815] Step 6:

[0816] The server loads the reminder email template and automatically generates emails by embedding individual information for each reminder recipient. For example, the template embeds parameters such as the user name, task name, and deadline date.

[0817] Step 7:

[0818] The server adds the generated reminder email to a sending queue and schedules it for sending. The schedule is set so that the email is sent at the optimal time, for example, the day before the deadline and in the morning of the deadline.

[0819] Step 8:

[0820] The server connects to the SMTP server and sends reminder emails according to the sending schedule. The sending result of each email is recorded in a log, and the success / failure is saved in a database.

[0821] Step 9:

[0822] The server monitors the sending results, and if the task is not completed by the deadline, it automatically generates a follow-up email and adds it to the sending queue. The follow-up email contains a message urging the user to complete the task again.

[0823] Step 10:

[0824] The server will send follow-up emails according to the schedule and again log the results, allowing for continuous follow-up until the task is completed.

[0825] This processing flow automates the sending and receiving of reminder emails, improving work efficiency.

[0826] Example 1

[0827] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0828] Conventional task management systems have problems such as users forgetting tasks or not receiving reminders to meet deadlines, resulting in reduced work efficiency. Manual reminders are time-consuming and difficult to send at the right time, so an automated reminder mechanism is needed. Furthermore, a system that can automatically send not only reminder emails but also follow-up emails is also needed.

[0829] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0830] In this invention, the server includes a data collection means for acquiring a user's behavioral history and task progress status, a machine learning model analysis means for identifying targets requiring reminders based on the acquired data, a template generation means for automatically generating reminder emails for targets, a sending means for sending the created reminder emails at an appropriate time, a follow-up means for automatically generating and sending a follow-up email if the task is not completed after sending, a batch processing means for periodically acquiring data, and a means for dynamically inserting information such as the user name, task name, and deadline into the content of the email to be sent. This encourages users to remember to complete tasks and improves work efficiency.

[0831] 1. "Data collection means" refers to a device or method for acquiring a user's behavioral history and task progress.

[0832] 2. "Machine learning model analysis means" means a device or method that uses a machine learning model to analyze acquired data and identify targets requiring reminders.

[0833] 3. "Template generation means" means a device or method that uses a template to automatically generate reminder emails to identified recipients.

[0834] 4. "Transmission means" means a device or method for sending the created reminder email at an appropriate time.

[0835] 5. "Follow-up means" means a device or method for automatically generating and sending a follow-up email if the task is not completed after sending.

[0836] 6. "Batch processing means" means a device or method that processes data in bulk to periodically obtain data.

[0837] 7. "Dynamic insertion means" means a device or method for automatically adding information such as user names, task names, and deadline dates to the content of emails being sent.

[0838] The present invention relates to a system for automating reminder emails, and specific embodiments thereof will be described below.

[0839] Data collection

[0840] The server obtains user activity history and task progress from a project management system (e.g., JIRA) or mail server (e.g., Exchange Server). This data collection is performed periodically by batch processing and stored in a database (e.g., MySQL) on the server. Specifically, the server sets up a Cron job every night to obtain task data from the project management system using an API request and store it in the database.

[0841] AI-powered analysis

[0842] The server analyzes the collected data using a machine learning model (e.g., Scikit-learn). The server uses a specific algorithm to analyze each user's task completion status and past behavioral history to identify users who need reminders. For example, the server uses the acquired task data to extract users who have tasks that are close to their submission deadline but have not yet been completed.

[0843] Creating a reminder email

[0844] The server automatically generates reminder emails for the identified recipients. Using a template engine (such as Jinja2), it dynamically inserts necessary information (such as user name, task name, deadline date, etc.) into the email content. Specifically, it generates an email with the content "Dear [user name], today is the deadline for submitting your report." This automatically creates a reminder email.

[0845] Sending emails

[0846] The server sends the generated reminder emails at the appropriate time. The sending timing is optimized based on the schedule settings, for example, sending them the day before the submission deadline and in the morning of the day itself. The server connects to an SMTP server (e.g., Postfix) to send the reminder email. The sending status is recorded in a log so that it can be checked later.

[0847] Follow-up

[0848] If the task is not completed even after sending the reminder email, the server automatically generates and sends another follow-up email. This ensures that the task is completed. For example, if the task is not completed even after the submission deadline, the server sends a follow-up email stating, "The submission is late. Please take immediate action."

[0849] Specific examples

[0850] 1. Data collection

[0851] The server obtains the task completion status of each user from the project management system and stores it in a database.

[0852] 2. AI-based analysis

[0853] The server analyzes the collected data using an AI model to identify users who have tasks that are due soon but have not yet been completed.

[0854] 3. Create a reminder email

[0855] The server creates a reminder email for the identified user with the following content: "Dear [user name], task [task name] for [project name] is incomplete. The deadline is [date]."

[0856] 4. Sending emails

[0857] The server sends the created reminder email at an appropriate time, for example, the day before the submission deadline and in the morning of the deadline.

[0858] 5. Follow-up

[0859] If the task is not completed after the deadline, the server will send another follow-up email.

[0860] Prompt Sentence Examples

[0861] Below are some example prompts to be input to the generative AI model:

[0862] Analyze user task data obtained from your project management system and identify users who have incomplete tasks with upcoming deadlines. Create templated reminder emails for those users and send them the day before and on the deadline. Also, send follow-up emails if the task is still incomplete after the deadline. Dynamically insert information such as the user name, task name, and due date into the reminder and follow-up emails.

[0863] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0864] Specific explanation of processing steps

[0865] Step 1: Collect data

[0866] The server periodically retrieves user action history and task progress from the project management system and mail server. The input data is task data retrieved from the project management system, and the output is updated task information stored in the database. Specifically, the server sets up a Cron job every night to execute batch processing. This process sends an API request to retrieve task data from the project management system and stores it in a MySQL database.

[0867] Step 2: AI analysis

[0868] The server analyzes all collected data using a machine learning model. The input data is task information stored in the database, and the output is a list of users who need reminders. Specifically, the server runs a Python script to read the necessary data from the database. It then inputs the data into a Scikit-learn model to generate a list of users who need reminders.

[0869] Step 3: Create a reminder email

[0870] The server uses a template engine to automatically generate reminder emails for the identified users. The input data is a list of users who need reminders and template information, and the output is the generated reminder email. Specifically, the server loads a Jinja2 template and dynamically embeds the user name and task information (task name, deadline date) into the template to generate the reminder email.

[0871] Step 4: Sending an email

[0872] The server sends the generated reminder email using an SMTP server. The input data is the generated reminder email and schedule information, and the output is the sent reminder email. Specifically, the server checks the sending timing based on the schedule settings, connects to the Postfix SMTP server, and sends the reminder email. The sending status is recorded in a log, making it possible to track it.

[0873] Step 5: Follow up

[0874] If the task is still incomplete after the reminder email is sent, the server automatically generates and sends another follow-up email. The input data is the task status data after submission, and the output is the follow-up email. Specifically, the server checks the database again after a certain period of time has passed and identifies users who have incomplete tasks. It then generates a follow-up email to that user stating, "Submission is late. Please take action as soon as possible," and sends it via the SMTP server.

[0875] Specific processing flow

[0876] Step 1:

[0877] The server runs a batch process every night by setting up a Cron job to retrieve task data from the project management system. The retrieved task data is obtained through an API request and stored in a MySQL database.

[0878] Step 2:

[0879] The server reads the task information stored in the database using a Python script and analyzes it using a machine learning model (Scikit-learn), which generates a list of users who need reminders.

[0880] Step 3:

[0881] The server uses the Jinja2 template engine to generate reminder emails for the identified users, dynamically populating the template with information such as the user name, task name, and due date to create the reminder email.

[0882] Step 4:

[0883] The server checks the schedule to send the generated reminder email, sends the reminder email using the Postfix SMTP server, and logs the delivery status.

[0884] Step 5:

[0885] After sending the reminder email, the server checks the database again to identify users with incomplete tasks. If necessary, it generates a follow-up email and sends it via the SMTP server with the message "Submission is late. Please take action as soon as possible."

[0886] (Application example 1)

[0887] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0888] In modern factories, worker task management is important, but it is difficult to grasp the progress of all workers in real time and provide appropriate reminders and follow-ups. To ensure that on-site workers complete their tasks at the appropriate time, an automated system that can provide immediate reminders is required. Furthermore, since reminders are sometimes not sent or notifications that are sent are ineffective, the importance of optimizing the timing of notifications and follow-ups is being questioned. Furthermore, conventional systems only notify workers via email, making it difficult to provide immediate notifications to workers who are working on-site.

[0889] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0890] In this invention, the server includes a data collection means for acquiring a user's behavioral history and task progress status, an AI analysis means for identifying individuals who need reminders based on the acquired data, a notification creation means for automatically generating reminder emails and real-time notifications for the individuals, and a transmission means for sending the created reminder emails and notifications at the appropriate time. This allows the progress of work in the factory to be grasped in real time, enabling reminders and follow-ups at the appropriate time. In addition, by using a wearable display device control means, on-site workers can be notified immediately, improving work efficiency.

[0891] The "data collection means" is a means for acquiring the behavioral history and task progress status of users and workers, and storing them in a database or the like.

[0892] "AI analysis methods" are methods that use machine learning models and artificial intelligence technology to analyze acquired data and identify targets that require reminders.

[0893] The "notification creation means" is a means for automatically generating reminder emails and real-time notifications for specified targets.

[0894] The "transmission means" refers to a means for sending the created reminder email or notification to the target person at an appropriate time.

[0895] A "scheduling means" is a means used to optimize the timing of sending reminder emails and notifications.

[0896] A "log recording means" is a means for recording the results of sent emails and notifications so that they can be referenced later.

[0897] The "follow-up method" is a method for automatically generating and sending a follow-up email or notification if the task is not completed after the reminder.

[0898] The "wearable display device control means" is a means for grasping the progress of work based on the acquired data and displaying reminders or follow-up notifications on the wearable display device (e.g., smart glasses).

[0899] The present invention is a system for automatically managing a user's behavior history and task progress, and sending reminder emails and real-time notifications. Specific embodiments of the system are described below.

[0900] First, the server plays an important role. This server has a means of collecting data to acquire the behavioral history and task progress of users and workers, and this data is stored in a database. This data collection is based on logs from sensors and robots installed in the factory, as well as input information from workers. Data is often collected in real time or periodically processed in batches.

[0901] Next, based on the collected data, the server's AI analysis method identifies those who need reminders. This AI analysis method uses machine learning models (e.g., RandomForestClassifier). Reminder emails and real-time notifications are automatically generated to provide appropriate reminders to the identified individuals. This notification creation method uses dynamic templates to automatically fill in important information such as user name, task name, and due date.

[0902] Reminder emails and notifications are sent at appropriate times. This sending method includes sending emails via a regular SMTP server or real-time notification functions using wearable display devices such as smart glasses. The sending timing is optimized by a scheduling method. For example, it can be set to match the user's work schedule, such as the day before the submission deadline or the morning of the deadline.

[0903] Furthermore, the results of the sent emails and notifications are recorded using a logging mechanism. This allows for future reference and serves as data for evaluating the effectiveness of the system. If the task is not completed after the reminder, the server's follow-up mechanism automatically generates and sends another follow-up email or notification. This improves the task completion rate.

[0904] Finally, it is important to have a wearable display control means to grasp the progress of work in the factory and notify workers immediately, which will allow real-time reminders and follow-ups at the workplace, greatly improving work efficiency.

[0905] Specific examples

[0906] For example, an example of use in a factory will be described.

[0907] 1. Data collection: The server collects real-time operational data from robots and sensors in the factory and stores it in a database.

[0908] 2. AI analysis: The server analyzes the collected data using an AI model (e.g., RandomForestClassifier) ​​to identify workers and tasks that require reminders.

[0909] 3. Creating and sending notifications: The server automatically generates reminder notifications for the identified workers and displays them on the smart glasses. The notification might say something like, "Worker B, the deadline for Task C is approaching. Please complete it as soon as possible."

[0910] 4. Follow-up: If the task is not completed after the reminder, a follow-up notification will be sent automatically.

[0911] Prompt Sentence Examples

[0912] Prompt Type: Industrial Task Management

[0913] Predictive Tasks: Forecast task progress and generate automatic reminders

[0914] Input data: {'worker_id': int, 'task_id': int, 'status': str, 'deadline': str}

[0915] Desired output: A list of tasks that need reminders

[0916] Example: Worker ID: 123 - Task ID: 789 is nearing its deadline.

[0917] In this way, the system can manage work progress within the factory in real time, send reminder notifications at appropriate times, and improve work efficiency.

[0918] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0919] Step 1:

[0920] The server collects work progress data from robots and sensors in the factory. This data collection is done in regular batch processing or in real time and stored in a database. For example, the location information of workers obtained from sensors and the operating hours of machines are stored in the database.

[0921] Input: Work progress data obtained from robots and sensors

[0922] Output: Working data stored in a database

[0923] Step 2:

[0924] The server inputs the stored data into an AI analysis method, which uses a machine learning model (e.g., RandomForestClassifier) ​​to identify workers and tasks that need reminding. The AI ​​model compares this data with past data and predicts who should be reminded based on certain criteria (e.g., tasks that are due soon but not completed).

[0925] Input: Working data stored in the database

[0926] Output: A list of workers and tasks that need reminding

[0927] Step 3:

[0928] The server automatically generates reminder notifications based on the workers and tasks identified by the AI ​​analysis method. The notification creation method uses templates to dynamically embed information such as the user name, task name, and deadline. For example, a notification might be created that reads, "Worker B, the deadline for Task C is approaching. Please complete it promptly."

[0929] Input: A list of workers and tasks that need reminding

[0930] Output: Reminder notification message

[0931] Step 4:

[0932] The server sends the created reminder notification at the appropriate time. The sending method includes email sending via an SMTP server and real-time notification using wearable display devices such as smart glasses. The notification timing is optimized by the schedule setting method. For example, notifications can be sent the day before the submission deadline or in the morning of the deadline.

[0933] Input: Reminder message

[0934] Output: Reminder sent

[0935] Step 5:

[0936] The server records the results of the sent reminders and notifications as a log. Using the log recording method, information such as the sending date and time, recipient, and notification content is saved in a database. This allows for future reference and can be used as data to evaluate the effectiveness of the system.

[0937] Input: Reminder notification information sent

[0938] Output: Log information recorded in the database

[0939] Step 6:

[0940] If the task is not completed after the reminder, the server automatically generates and sends another follow-up notification using the follow-up means. For example, a follow-up notification such as "Task C is not yet completed. Please take action immediately" can be generated and displayed on the worker's wearable display device at an appropriate time.

[0941] Input: Incomplete task information

[0942] Output: Follow-up notification message

[0943] Step 7:

[0944] The server notifies the on-site worker of the work progress in real time using the wearable display control means, which allows the worker wearing the smart glasses to receive immediate reminders and follow-up notifications, thereby improving work efficiency and increasing the task completion rate.

[0945] Input: Reminder notification message, Follow-up notification message

[0946] Output: Notifications displayed on wearable displays such as smart glasses

[0947] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0948] The present invention optimizes the content and sending timing of reminder emails according to the user's emotions by combining a system that automates reminder emails with an emotion engine that recognizes the user's emotions. Specific embodiments of this invention are described below.

[0949] Data collection

[0950] The server periodically retrieves user activity history and task progress status from the project management system and mail server. This allows daily updated information to be stored in the database. For example, the latest task status is saved in the database by a batch process scheduled every night.

[0951] AI-powered analysis

[0952] The server uses AI analysis tools based on the collected data to identify users who need reminders. It also uses machine learning models to make predictions based on each user's task completion status and past behavioral history. For example, it identifies users who have not yet completed a specific task even though the deadline for its submission is approaching.

[0953] emotion recognition

[0954] The server uses an emotion engine to recognize the user's emotions. This emotion recognition is performed, for example, by analyzing the user's email text and voice data. The emotion engine evaluates the user's emotional state, taking into account factors such as the user's stress level and motivation.

[0955] Creating a reminder email

[0956] The server automatically generates reminder emails for identified recipients, with content customized according to the emotions recognized by the emotion engine. The template file is dynamically modified, so that if the user is feeling stressed, for example, an email is created with a gentle tone. An email is generated with the following content: "Dear [user name], I'm concerned about the progress of your task. Please let me know if you need any help."

[0957] Sending emails

[0958] The server adds the generated reminder email to a sending queue and sends it at an optimized timing based on the emotional state recognized by the emotion engine. For example, it sends the email when the user is relaxed, avoiding busy times.

[0959] Follow-up

[0960] If the task is not completed after the reminder email is sent, the server automatically generates a follow-up email and sends it again. The content and timing of the follow-up email are also customized based on information from the emotion engine. For example, if the task is not completed even after the deadline for submission, an appropriate follow-up will be performed depending on the user's status. An email may be sent stating, "Your submission is late, but please let us know if there are no particular problems."

[0961] Specific examples

[0962] As a specific example of use, consider the use in a company's project management system.

[0963] 1. Data collection

[0964] The server obtains the task completion status of each employee from the project management system and stores it in a database.

[0965] 2. AI-based analysis

[0966] The server analyzes the collected data using an AI model to identify employees who have tasks that are due soon but have not yet been completed.

[0967] 3. Emotion recognition

[0968] The server uses an emotion engine to recognize employees' emotional states from email text and voice data, and evaluates their stress and motivation.

[0969] 4. Create a reminder email

[0970] The server automatically generates reminder emails for identified employees based on their emotional state. For example, for an employee feeling stressed, the server creates a gentle email saying, "Please proceed without overdoing it."

[0971] 5. Sending emails

[0972] The server sends reminder emails at appropriate times, often during relaxing hours, taking into account the user's emotional state.

[0973] 6. Follow-up

[0974] The server sends follow-up emails if the task is still incomplete after the deadline, and the content is also adjusted to take into account the user's emotional state.

[0975] This system not only automates reminder emails, but also enables more personalized communication that takes users' emotions into consideration, which is expected to improve work efficiency and user satisfaction.

[0976] The processing flow will be explained below.

[0977] Step 1:

[0978] The server acquires user activity history and task progress from the project management system and mail server. This acquisition process is performed periodically, with daily scheduled batch processing. For example, data such as each user's task ID, progress, and deadline is acquired and stored in a database.

[0979] Step 2:

[0980] The server stores the collected data in a database, which records detailed task information for each user. The acquired data is organized according to a storage format for later analysis.

[0981] Step 3:

[0982] The server uses a query to extract data on users who need reminders from the database. For example, it executes an SQL query to extract users who have tasks due the next day.

[0983] Step 4:

[0984] The server inputs the extracted data into an AI analysis model to identify those who need reminders, and uses a machine learning model to predict candidates who need reminders based on each user's task completion status and past behavioral history.

[0985] Step 5:

[0986] The server saves the reminder recipients in the database based on the analysis results, and updates the list for creating reminder emails.

[0987] Step 6:

[0988] The server uses an emotion engine to recognize the user's emotions. For example, it analyzes past emails and voice data to assess the user's stress level and motivation. It may also use NLP (natural language processing) technology to analyze the text of emails.

[0989] Step 7:

[0990] The server automatically generates emotion-based reminder emails for the reminder recipients. It reads a template file and dynamically fills in parameters such as the user name, task name, and due date. It also customizes the email content based on the results of the emotion engine. For example, it generates a message like, "Dear [user name], I'm concerned about the progress of your task. Please let me know if you need any help."

[0991] Step 8:

[0992] The server adds the generated reminder email to a sending queue and schedules the sending based on the emotional state recognized by the emotion engine. For example, it schedules the email to be sent during a time when the user is relaxed.

[0993] Step 9:

[0994] The server connects to the SMTP server according to the sending schedule and sends the reminder email. The sending result is recorded in a log, and the success / failure information is saved in a database.

[0995] Step 10:

[0996] The server monitors the submission results and automatically generates a follow-up email and adds it to the submission queue if the task is not completed by the deadline. The content of the follow-up email is customized based on the evaluation results of the emotion engine. For example, it could say, "Your submission is late, but please let us know if there are no particular problems."

[0997] Step 11:

[0998] The server sends follow-up emails on a scheduled basis and again logs the results, allowing the effectiveness of the follow-up emails to be monitored and further follow-ups to be performed if necessary.

[0999] This specific processing flow automates the sending and receiving of reminder emails that take the user's emotions into consideration, thereby improving work efficiency and user satisfaction.

[1000] Example 2

[1001] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1002] Conventional reminder systems can create and send reminder emails based on the user's behavioral history and task progress, but it is difficult to set the optimal content and timing of the emails while taking the user's emotional state into account. As a result, problems arise, such as increased user stress and inappropriate follow-up. In particular, reminder emails can be counterproductive because they are insensitive to the user's emotions.

[1003] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a data collection means for acquiring a user's behavioral history and work progress status, an AI analysis means for identifying targets requiring reminders based on the acquired data, an email creation means for automatically generating reminder emails for the targets, a sending means for adding the generated reminder emails to a sending queue and sending them at an appropriate time, an emotion recognition means for recognizing the user's emotions, an email adjustment means for customizing the content of the reminder email according to the emotion recognized by the emotion recognition means, and a follow-up means for automatically generating and sending a follow-up email if the task is not completed even after sending. This makes it possible to optimize the content and sending timing of the reminder email taking the user's emotions into consideration.

[1004] A "user" is a person or organization that uses the system.

[1005] "Behavioral history" is a record of the operations and activities performed by a user.

[1006] "Work progress" is data on the progress of tasks and projects that a user is responsible for.

[1007] "Data collection means" refers to a mechanism or device for acquiring a user's behavior history and work progress.

[1008] "AI analysis methods" are methods that use artificial intelligence to analyze collected data and identify targets that require reminders.

[1009] A "reminder email" is an email sent to a user to encourage them to progress on a task or project.

[1010] "Email creation means" refers to a system or program for automatically generating reminder emails.

[1011] A "sending queue" is a temporary storage location or list of emails waiting to be sent.

[1012] "Transmission means" refers to the method or technology used to send reminder emails to users.

[1013] "Emotion recognition means" refers to a technology or system for determining a user's emotions or mental state.

[1014] The "email adjustment means" is a function for customizing the contents of the reminder email according to the user's emotions.

[1015] A "follow-up method" is a mechanism for sending another email if the task is not completed after the reminder email has been sent.

[1016] The system of the present invention acquires a user's behavior history and work progress, and takes the user's emotions into consideration when automatically generating and sending reminder emails. This system includes data collection means, AI analysis means, email creation means, email sending means, emotion recognition means, email adjustment means, and follow-up means.

[1017] An embodiment of this system will now be described in detail.

[1018] Data collection methods

[1019] The server periodically collects user activity history and work progress from the project management system and mail server. This is done by using automatic data acquisition via API or batch processing. For example, the latest task progress is stored in a database by batch processing scheduled overnight.

[1020] AI analysis means

[1021] The server analyzes the collected data using an AI model. It uses a machine learning algorithm to identify users who have incomplete tasks that are due soon. The AI ​​model makes predictions based on each user's task completion status and past behavioral history.

[1022] emotion recognition means

[1023] The server uses an emotion recognition engine to recognize the user's emotions, including natural language processing (NLP) and voice recognition technologies, to assess the user's stress level and motivation from the text of their emails and their voice data.

[1024] Email creation method

[1025] The server automatically generates reminder emails based on the emotions recognized by the emotion engine. This includes the ability to use template files to customize the content of emails depending on the user's emotional state. For example, a friendly email could be created that reads, "Dear [user name], I'm concerned about your task progress. Please let me know if you need any help."

[1026] Transmission method

[1027] The server adds the generated reminder email to a sending queue and sends it at the optimal time, which is set to a time when the user is relaxed.

[1028] Follow-up measures

[1029] If the task is not completed after the reminder email is sent, the server automatically generates and sends a follow-up email. This includes the ability to customize the content and timing of the email based on information obtained from the emotion engine. For example, an email could be sent with the following content: "Your submission is late, but please let us know if there are no particular problems."

[1030] Specific examples

[1031] As a specific example of use, consider using it in a company's project management system.

[1032] 1. Data collection: The server obtains the task completion status of each employee from the project management system API, and stores the progress status of each employee in a database.

[1033] 2. AI analysis: The server analyzes the collected data using an AI model to identify employees who have incomplete tasks that are due soon.

[1034] 3. Emotion recognition: The server uses an emotion engine to recognize employees' emotional states from email text and voice data, and evaluates their stress and motivation.

[1035] 4. Creating reminder emails: The server automatically generates reminder emails for identified employees according to their emotional state. For example, for an employee who is feeling stressed, the server creates a gentle email saying, "Please proceed without overdoing it."

[1036] 5. Sending emails: The server sends reminder emails at appropriate times, taking into account the user's emotional state and sending them during times when the user is relaxed.

[1037] 6. Follow-up: If the task is still incomplete after the deadline, the server will send a follow-up email. The content of the email will also be adjusted based on the user's emotional state.

[1038] Example prompt sentence:

[1039] "A system that retrieves the latest task data from a project management system, identifies users with incomplete tasks using an AI model, and generates and sends reminder emails based on their emotional state using an emotion engine."

[1040] This system goes beyond simply automating reminder emails, enabling more personalized communication that takes user emotions into account.

[1041] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1042] Step 1:

[1043] The server collects user activity history and work progress from the project management system and mail server. Inputs include data from the project management system's API and mail server. This data is periodically retrieved and stored in a database. For example, the latest task data and user activity logs are saved to the database by batch processing scheduled overnight.

[1044] Specific behavior:

[1045] Retrieving task data from a project management system's API

[1046] Collecting email logs from the email server

[1047] Store the collected data in a database

[1048] Step 2:

[1049] The server uses an AI model to analyze the collected data. The inputs include the task data and behavioral history collected in step 1. The AI ​​model analyzes users' task completion status and past behavioral history to identify users who need reminders. The output is a list of users who need reminders.

[1050] Specific behavior:

[1051] Input data collected from the database into the AI ​​model

[1052] Use machine learning algorithms to analyze incomplete tasks and behavioral history

[1053] Make a list of users who need reminders

[1054] Step 3:

[1055] The server uses an emotion recognition engine to recognize the user's emotions. Inputs include the user's email text and voice data. The emotion engine uses natural language processing (NLP) and voice analysis technologies to analyze the user's emotional state (e.g., stress level and motivation), and outputs the user's emotional state data.

[1056] Specific behavior:

[1057] Analyzing email text using natural language processing technology

[1058] Analyzing voice data using voice recognition technology

[1059] The emotion engine evaluates and outputs the user's emotional state.

[1060] Step 4:

[1061] The server automatically generates reminder emails based on the output of the emotion recognition engine. The input is a list of users who need reminding and their emotional state data. A template file is used to customize the email content according to the emotional state. The output is a customized reminder email.

[1062] Specific behavior:

[1063] Get the target users from the list of users who need to be reminded

[1064] Select and customize template files based on your emotional state

[1065] Generate customized reminder emails

[1066] Step 5:

[1067] The server adds the generated reminder email to the sending queue and sends it at the optimal time. The input is the customized reminder email and the user's appropriate sending timing data. The output is that the reminder email is sent.

[1068] Specific behavior:

[1069] Add the generated reminder email to the sending queue

[1070] Optimizing transmission timing based on the user's emotional state

[1071] Send reminders at the perfect time

[1072] Step 6:

[1073] If the task is not completed after the reminder email is sent, the server automatically generates and sends a follow-up email. The input is the task completion status data and emotional state data after the reminder email is sent. The output is the generation and sending of a follow-up email.

[1074] Specific behavior:

[1075] Check task completion status after sending a reminder email

[1076] Generate follow-up emails based on sentiment engine data when there are open tasks

[1077] Send a follow-up email

[1078] Through these steps, the system automatically generates and sends reminder emails that take the user's emotions into consideration, thereby improving work efficiency and user satisfaction.

[1079] (Application example 2)

[1080] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1081] Conventional reminder email systems send reminder emails based only on the user's behavioral history and task progress, and therefore are unable to take the user's emotional state into consideration. This has resulted in problems such as inappropriate reminders being sent based on the user's emotional state, and the effectiveness of reminders being insufficient. To solve this problem, the present invention aims to provide a system that recognizes the user's emotional state, automatically generates reminder emails based on the user's emotions, and sends them at the optimal time.

[1082] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a data collection means for acquiring the user's behavioral history and task progress status, an AI analysis means for identifying targets requiring reminders based on the acquired data, an emotion recognition means for recognizing the user's emotional state, an email creation means for automatically generating a reminder email according to the emotional state, and a sending means for sending the created reminder email at an appropriate time. This makes it possible to automatically generate a personalized reminder email that takes the user's emotional state into consideration and send it at the optimal time.

[1083] "User behavior history" refers to data such as the operations a user performs on the system, access history, and task progress.

[1084] "Task progress status" indicates information such as the current completion status, progress, and deadline of the task for which the user is responsible.

[1085] "Data collection means" refers to the technical means for acquiring data such as user behavior history and task progress on the system.

[1086] "AI analysis method" refers to an analysis technology that uses artificial intelligence to identify users who need reminders based on collected data.

[1087] "Emotion recognition means" refers to technology that analyzes a user's emotional state and evaluates their stress level, motivation, etc.

[1088] A "reminder email" refers to an email sent to a user to encourage them to progress with a task.

[1089] "Email creation means" refers to technology that automatically generates the content of reminder emails based on the user's emotional state.

[1090] "Transmission means" refers to a technology for sending the generated reminder email to the user at an appropriate time.

[1091] "Schedule setting means" refers to a technology that sets the optimal timing for sending reminder emails.

[1092] "Logging means" refers to technology for recording sent emails and their results.

[1093] "Follow-up measures" refer to technology that automatically generates and sends another email if the task is not completed after the reminder.

[1094] "Personalization" refers to optimizing content and services according to the individual characteristics and circumstances of the user.

[1095] The present invention is a system that recognizes a user's emotions and automatically generates and sends reminder emails according to the user's emotions. This system includes multifunctional technology that acquires the user's behavioral history and task progress, and optimizes the appropriate timing and content of reminders.

[1096] Collecting data on user behavior history and task progress

[1097] The server has a means of collecting data to acquire the user's behavioral history and task progress. For example, if a user adds a product to their cart on an online shopping site but leaves it unpurchased, that information is sent to the server. The server also collects information about the products the user has viewed and how frequently they have viewed them.

[1098] AI analysis to identify necessary reminders

[1099] The server uses AI analysis methods based on the collected data to identify users who need reminders. This process predicts whether a reminder to make a purchase is necessary based on, for example, the products the user has pending purchases or the pages they frequently visit. The artificial intelligence techniques used here include generative AI models.

[1100] Emotion evaluation of users using emotion recognition methods

[1101] The server uses emotion recognition techniques to recognize the user's emotional state. For example, it analyzes the context of the words used by the user in emails and chats to assess their stress level and motivation. Natural language processing technology and machine learning models are used for this emotion recognition.

[1102] Automatically generate reminder emails

[1103] The server automatically generates reminder emails according to the user's emotional state. The email creator adjusts the content based on the user's emotions. For example, for a user with low purchasing motivation, it generates a reminder email with the content "We will give you a limited-time discount coupon!"

[1104] Sending reminders and following up

[1105] The reminder email is sent to the user at an appropriate time by the server's sending means. For example, it is sent during a time period when the user is relaxing, taking into account the user's activity history. If the task is not completed after the reminder, another reminder email is automatically generated and sent using the follow-up means.

[1106] Examples and prompts

[1107] As a concrete example, consider the use of an online shopping site. If a user adds an item to their cart but holds off on purchasing, the emotion engine determines that the user is not highly motivated to purchase. In this situation, the reminder bot sends a reminder notification with a limited coupon during a relaxing time.

[1108] Here are some examples of prompts for generative AI models:

[1109] Customize the content of reminder emails based on the user's emotional state. A user has product A and product B in their cart. Their emotional state is low. What kind of reminder email should you create to encourage them to make a purchase?

[1110] In this way, by taking into account the user's emotional state and sending a personalized reminder email, it is possible to maximize the effectiveness of the reminder.

[1111] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1112] Step 1:

[1113] The server acquires the user's behavioral history and task progress. Specifically, it collects data such as the products the user viewed on the online shopping site, the products they added to their cart, and their purchase history. This data is stored in a database and used for later analysis.

[1114] Input: User behavior history, task progress data

[1115] Output: User behavior history and task progress stored in a database

[1116] Step 2:

[1117] The server uses AI analytics to identify users who need reminders based on the collected data, and uses a generative AI model to determine whether a particular user has left an item in their cart unpurchased.

[1118] Input: User behavior history and task progress stored in a database

[1119] Output: A list of users who need to be reminded

[1120] Step 3:

[1121] The server uses emotion recognition to recognize the user's emotional state, analyzing data such as email and chat messages and browsing history to assess the user's stress level and motivation.

[1122] Input: Email and chat text, browsing history

[1123] Output: User's emotional state (high motivation / low motivation, stress level, etc.)

[1124] Step 4:

[1125] The server automatically generates reminder emails based on the user's emotional state, using a generative AI model to create prompts tailored to the user's emotions and then constructing the email content accordingly.

[1126] Input: User's emotional state, prompt

[1127] Output: Reminder email content

[1128] Step 5:

[1129] The server then sends the created reminder email at the appropriate time, taking into account the user's behavioral history and emotional state, and sends the email at the optimal time, such as during a relaxed time.

[1130] Input: Reminder email content, user activity history

[1131] Output: Reminder email sent to user

[1132] Step 6:

[1133] If the user does not take action based on the reminder email, the server will automatically generate and send a follow-up email again, again using AI analysis methods to analyze the user's emotional state and customize the content of the follow-up email accordingly.

[1134] Input: Reminder email sending results, user behavior history

[1135] Output: Content and sending of follow-up email

[1136] This allows reminder emails and follow-up emails to be automatically generated and sent at the appropriate time, taking into account the user's emotional state.

[1137] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1138] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1139] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1140] [Fourth embodiment]

[1141] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1142] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1143] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1144] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1145] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1146] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1147] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1148] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1149] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1150] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[1151] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1152] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1153] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1154] The present invention is a system for automating reminder emails, and a specific embodiment thereof will be described below.

[1155] Data collection

[1156] The server acquires user activity history and task progress status from a project management system, mail server, etc. This data collection is performed periodically, and the updated information is stored in a database. For example, the latest task status is saved in the database by a batch process scheduled every night.

[1157] AI-powered analysis

[1158] The server uses AI analytics to identify users who need reminders based on the collected data. This is done using machine learning models to make predictions based on each user's task completion status and past behavior. For example, it identifies users who have not yet completed a specific task that is due to be submitted.

[1159] Creating a reminder email

[1160] The server automatically generates reminder emails for the identified recipients. The email content is constructed using a template file, and important information such as the user name, task name, and deadline is dynamically embedded. For example, an email might be generated with the following content: "Dear [user name], today is the deadline for submitting your report."

[1161] Sending emails

[1162] The server sends the generated reminder email at an appropriate time. The sending timing is optimized using a schedule setting means, and is set to send, for example, one day before the submission deadline and in the morning of the day of the deadline. The server connects to the SMTP server and sends the email.

[1163] Follow-up

[1164] If the task is not completed after the reminder email is sent, the server automatically generates and sends a follow-up email. This increases the certainty of task completion. For example, if the task remains incomplete after the deadline, a follow-up email stating, "Submission is late. Please take immediate action." is sent.

[1165] Specific examples

[1166] As a specific example of use, consider the use in a company's project management system.

[1167] 1. Data collection

[1168] The server obtains the task completion status of each employee from the project management system and stores it in a database.

[1169] 2. AI-based analysis

[1170] The server analyzes the collected data using an AI model to identify employees who have tasks that are due soon but have not yet been completed.

[1171] 3. Create a reminder email

[1172] The server creates a reminder email for the identified employee, stating, "Dear [Employee Name], task [Task Name] for [Project Name] is incomplete. The deadline is [Date]."

[1173] 4. Sending emails

[1174] The server sends the created reminder email at an appropriate time, for example, the day before the submission deadline and in the morning of the deadline.

[1175] 5. Follow-up

[1176] If the task is not completed after the deadline, the server will send another follow-up email.

[1177] This system reduces the workload for both users and administrators and improves work efficiency.

[1178] The processing flow will be explained below.

[1179] Step 1:

[1180] The server acquires user activity history and task progress status from the project management system and mail server. This acquisition process is performed periodically, and a scheduled batch process is executed daily to acquire the latest data.

[1181] Step 2:

[1182] The server stores the acquired data in a database. The stored data shows the progress of each user's task in detail and is used for later analysis. For example, the user ID, task ID, deadline, progress status, etc. are saved in the database.

[1183] Step 3:

[1184] The server uses a query to extract data on people who need reminders from the database. For example, it executes an SQL query to extract "users who have tasks due the next day."

[1185] Step 4:

[1186] The server inputs the extracted data into an AI analysis model to identify those who need reminders. The AI ​​model uses machine learning models that have learned from past data to predict which users need reminders.

[1187] Step 5:

[1188] The server saves the analysis results in a database and updates the list of reminder recipients, ensuring the information is available for creating reminder emails in the next step.

[1189] Step 6:

[1190] The server loads the reminder email template and automatically generates emails by embedding individual information for each reminder recipient. For example, the template embeds parameters such as the user name, task name, and deadline date.

[1191] Step 7:

[1192] The server adds the generated reminder email to a sending queue and schedules it for sending. The schedule is set so that the email is sent at the optimal time, for example, the day before the deadline and in the morning of the deadline.

[1193] Step 8:

[1194] The server connects to the SMTP server and sends reminder emails according to the sending schedule. The sending result of each email is recorded in a log, and the success / failure is saved in a database.

[1195] Step 9:

[1196] The server monitors the sending results, and if the task is not completed by the deadline, it automatically generates a follow-up email and adds it to the sending queue. The follow-up email contains a message urging the user to complete the task again.

[1197] Step 10:

[1198] The server will send follow-up emails according to the schedule and again log the results, allowing for continuous follow-up until the task is completed.

[1199] This processing flow automates the sending and receiving of reminder emails, improving work efficiency.

[1200] Example 1

[1201] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1202] Conventional task management systems have problems such as users forgetting tasks or not receiving reminders to meet deadlines, resulting in reduced work efficiency. Manual reminders are time-consuming and difficult to send at the right time, so an automated reminder mechanism is needed. Furthermore, a system that can automatically send not only reminder emails but also follow-up emails is also needed.

[1203] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1204] In this invention, the server includes a data collection means for acquiring a user's behavioral history and task progress status, a machine learning model analysis means for identifying targets requiring reminders based on the acquired data, a template generation means for automatically generating reminder emails for targets, a sending means for sending the created reminder emails at an appropriate time, a follow-up means for automatically generating and sending a follow-up email if the task is not completed after sending, a batch processing means for periodically acquiring data, and a means for dynamically inserting information such as the user name, task name, and deadline into the content of the email to be sent. This encourages users to remember to complete tasks and improves work efficiency.

[1205] 1. "Data collection means" refers to a device or method for acquiring a user's behavioral history and task progress.

[1206] 2. "Machine learning model analysis means" means a device or method that uses a machine learning model to analyze acquired data and identify targets requiring reminders.

[1207] 3. "Template generation means" means a device or method that uses a template to automatically generate reminder emails to identified recipients.

[1208] 4. "Transmission means" means a device or method for sending the created reminder email at an appropriate time.

[1209] 5. "Follow-up means" means a device or method for automatically generating and sending a follow-up email if the task is not completed after sending.

[1210] 6. "Batch processing means" means a device or method that processes data in bulk to periodically obtain data.

[1211] 7. "Dynamic insertion means" means a device or method for automatically adding information such as user names, task names, and deadline dates to the content of emails being sent.

[1212] The present invention relates to a system for automating reminder emails, and specific embodiments thereof will be described below.

[1213] Data collection

[1214] The server obtains user activity history and task progress from a project management system (e.g., JIRA) or mail server (e.g., Exchange Server). This data collection is performed periodically by batch processing and stored in a database (e.g., MySQL) on the server. Specifically, the server sets up a Cron job every night to obtain task data from the project management system using an API request and store it in the database.

[1215] AI-powered analysis

[1216] The server analyzes the collected data using a machine learning model (e.g., Scikit-learn). The server uses a specific algorithm to analyze each user's task completion status and past behavioral history to identify users who need reminders. For example, the server uses the acquired task data to extract users who have tasks that are close to their submission deadline but have not yet been completed.

[1217] Creating a reminder email

[1218] The server automatically generates reminder emails for the identified recipients. Using a template engine (such as Jinja2), it dynamically inserts necessary information (such as user name, task name, deadline date, etc.) into the email content. Specifically, it generates an email with the content "Dear [user name], today is the deadline for submitting your report." This automatically creates a reminder email.

[1219] Sending emails

[1220] The server sends the generated reminder emails at the appropriate time. The sending timing is optimized based on the schedule settings, for example, sending them the day before the submission deadline and in the morning of the day itself. The server connects to an SMTP server (e.g., Postfix) to send the reminder email. The sending status is recorded in a log so that it can be checked later.

[1221] Follow-up

[1222] If the task is not completed even after sending the reminder email, the server automatically generates and sends another follow-up email. This ensures that the task is completed. For example, if the task is not completed even after the submission deadline, the server sends a follow-up email stating, "The submission is late. Please take immediate action."

[1223] Specific examples

[1224] 1. Data collection

[1225] The server obtains the task completion status of each user from the project management system and stores it in a database.

[1226] 2. AI-based analysis

[1227] The server analyzes the collected data using an AI model to identify users who have tasks that are due soon but have not yet been completed.

[1228] 3. Create a reminder email

[1229] The server creates a reminder email for the identified user with the following content: "Dear [user name], task [task name] for [project name] is incomplete. The deadline is [date]."

[1230] 4. Sending emails

[1231] The server sends the created reminder email at an appropriate time, for example, the day before the submission deadline and in the morning of the deadline.

[1232] 5. Follow-up

[1233] If the task is not completed after the deadline, the server will send another follow-up email.

[1234] Prompt Sentence Examples

[1235] Below are some example prompts to be input to the generative AI model:

[1236] Analyze user task data obtained from your project management system and identify users who have incomplete tasks with upcoming deadlines. Create templated reminder emails for those users and send them the day before and on the deadline. Also, send follow-up emails if the task is still incomplete after the deadline. Dynamically insert information such as the user name, task name, and due date into the reminder and follow-up emails.

[1237] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1238] Specific explanation of processing steps

[1239] Step 1: Collect data

[1240] The server periodically retrieves user action history and task progress from the project management system and mail server. The input data is task data retrieved from the project management system, and the output is updated task information stored in the database. Specifically, the server sets up a Cron job every night to execute batch processing. This process sends an API request to retrieve task data from the project management system and stores it in a MySQL database.

[1241] Step 2: AI analysis

[1242] The server analyzes all collected data using a machine learning model. The input data is task information stored in the database, and the output is a list of users who need reminders. Specifically, the server runs a Python script to read the necessary data from the database. It then inputs the data into a Scikit-learn model to generate a list of users who need reminders.

[1243] Step 3: Create a reminder email

[1244] The server uses a template engine to automatically generate reminder emails for the identified users. The input data is a list of users who need reminders and template information, and the output is the generated reminder email. Specifically, the server loads a Jinja2 template and dynamically embeds the user name and task information (task name, deadline date) into the template to generate the reminder email.

[1245] Step 4: Sending an email

[1246] The server sends the generated reminder email using an SMTP server. The input data is the generated reminder email and schedule information, and the output is the sent reminder email. Specifically, the server checks the sending timing based on the schedule settings, connects to the Postfix SMTP server, and sends the reminder email. The sending status is recorded in a log, making it possible to track it.

[1247] Step 5: Follow up

[1248] If the task is still incomplete after the reminder email is sent, the server automatically generates and sends another follow-up email. The input data is the task status data after submission, and the output is the follow-up email. Specifically, the server checks the database again after a certain period of time has passed and identifies users who have incomplete tasks. It then generates a follow-up email to that user stating, "Submission is late. Please take action as soon as possible," and sends it via the SMTP server.

[1249] Specific processing flow

[1250] Step 1:

[1251] The server runs a batch process every night by setting up a Cron job to retrieve task data from the project management system. The retrieved task data is obtained through an API request and stored in a MySQL database.

[1252] Step 2:

[1253] The server reads the task information stored in the database using a Python script and analyzes it using a machine learning model (Scikit-learn), which generates a list of users who need reminders.

[1254] Step 3:

[1255] The server uses the Jinja2 template engine to generate reminder emails for the identified users, dynamically populating the template with information such as the user name, task name, and due date to create the reminder email.

[1256] Step 4:

[1257] The server checks the schedule to send the generated reminder email, sends the reminder email using the Postfix SMTP server, and logs the delivery status.

[1258] Step 5:

[1259] After sending the reminder email, the server checks the database again to identify users with incomplete tasks. If necessary, it generates a follow-up email and sends it via the SMTP server with the message "Submission is late. Please take action as soon as possible."

[1260] (Application example 1)

[1261] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1262] In modern factories, worker task management is important, but it is difficult to grasp the progress of all workers in real time and provide appropriate reminders and follow-ups. To ensure that on-site workers complete their tasks at the appropriate time, an automated system that can provide immediate reminders is required. Furthermore, since reminders are sometimes not sent or notifications that are sent are ineffective, the importance of optimizing the timing of notifications and follow-ups is being questioned. Furthermore, conventional systems only notify workers via email, making it difficult to provide immediate notifications to workers who are working on-site.

[1263] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1264] In this invention, the server includes a data collection means for acquiring a user's behavioral history and task progress status, an AI analysis means for identifying individuals who need reminders based on the acquired data, a notification creation means for automatically generating reminder emails and real-time notifications for the individuals, and a transmission means for sending the created reminder emails and notifications at the appropriate time. This allows the progress of work in the factory to be grasped in real time, enabling reminders and follow-ups at the appropriate time. In addition, by using a wearable display device control means, on-site workers can be notified immediately, improving work efficiency.

[1265] The "data collection means" is a means for acquiring the behavioral history and task progress status of users and workers, and storing them in a database or the like.

[1266] "AI analysis methods" are methods that use machine learning models and artificial intelligence technology to analyze acquired data and identify targets that require reminders.

[1267] The "notification creation means" is a means for automatically generating reminder emails and real-time notifications for specified targets.

[1268] The "transmission means" refers to a means for sending the created reminder email or notification to the target person at an appropriate time.

[1269] A "scheduling means" is a means used to optimize the timing of sending reminder emails and notifications.

[1270] A "log recording means" is a means for recording the results of sent emails and notifications so that they can be referenced later.

[1271] The "follow-up method" is a method for automatically generating and sending a follow-up email or notification if the task is not completed after the reminder.

[1272] The "wearable display device control means" is a means for grasping the progress of work based on the acquired data and displaying reminders or follow-up notifications on the wearable display device (e.g., smart glasses).

[1273] The present invention is a system for automatically managing a user's behavior history and task progress, and sending reminder emails and real-time notifications. Specific embodiments of the system are described below.

[1274] First, the server plays an important role. This server has a means of collecting data to acquire the behavioral history and task progress of users and workers, and this data is stored in a database. This data collection is based on logs from sensors and robots installed in the factory, as well as input information from workers. Data is often collected in real time or periodically processed in batches.

[1275] Next, based on the collected data, the server's AI analysis method identifies those who need reminders. This AI analysis method uses machine learning models (e.g., RandomForestClassifier). Reminder emails and real-time notifications are automatically generated to provide appropriate reminders to the identified individuals. This notification creation method uses dynamic templates to automatically fill in important information such as user name, task name, and due date.

[1276] Reminder emails and notifications are sent at appropriate times. This sending method includes sending emails via a regular SMTP server or real-time notification functions using wearable display devices such as smart glasses. The sending timing is optimized by a scheduling method. For example, it can be set to match the user's work schedule, such as the day before the submission deadline or the morning of the deadline.

[1277] Furthermore, the results of the sent emails and notifications are recorded using a logging mechanism. This allows for future reference and serves as data for evaluating the effectiveness of the system. If the task is not completed after the reminder, the server's follow-up mechanism automatically generates and sends another follow-up email or notification. This improves the task completion rate.

[1278] Finally, it is important to have a wearable display control means to grasp the progress of work in the factory and notify workers immediately, which will allow real-time reminders and follow-ups at the workplace, greatly improving work efficiency.

[1279] Specific examples

[1280] For example, an example of use in a factory will be described.

[1281] 1. Data collection: The server collects real-time operational data from robots and sensors in the factory and stores it in a database.

[1282] 2. AI analysis: The server analyzes the collected data using an AI model (e.g., RandomForestClassifier) ​​to identify workers and tasks that require reminders.

[1283] 3. Creating and sending notifications: The server automatically generates reminder notifications for the identified workers and displays them on the smart glasses. The notification might say something like, "Worker B, the deadline for Task C is approaching. Please complete it as soon as possible."

[1284] 4. Follow-up: If the task is not completed after the reminder, a follow-up notification will be sent automatically.

[1285] Prompt Sentence Examples

[1286] Prompt Type: Industrial Task Management

[1287] Predictive Tasks: Forecast task progress and generate automatic reminders

[1288] Input data: {'worker_id': int, 'task_id': int, 'status': str, 'deadline': str}

[1289] Desired output: A list of tasks that need reminders

[1290] Example: Worker ID: 123 - Task ID: 789 is nearing its deadline.

[1291] In this way, the system can manage work progress within the factory in real time, send reminder notifications at appropriate times, and improve work efficiency.

[1292] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1293] Step 1:

[1294] The server collects work progress data from robots and sensors in the factory. This data collection is done in regular batch processing or in real time and stored in a database. For example, the location information of workers obtained from sensors and the operating hours of machines are stored in the database.

[1295] Input: Work progress data obtained from robots and sensors

[1296] Output: Working data stored in a database

[1297] Step 2:

[1298] The server inputs the stored data into an AI analysis method, which uses a machine learning model (e.g., RandomForestClassifier) ​​to identify workers and tasks that need reminding. The AI ​​model compares this data with past data and predicts who should be reminded based on certain criteria (e.g., tasks that are due soon but not completed).

[1299] Input: Working data stored in the database

[1300] Output: A list of workers and tasks that need reminding

[1301] Step 3:

[1302] The server automatically generates reminder notifications based on the workers and tasks identified by the AI ​​analysis method. The notification creation method uses templates to dynamically embed information such as the user name, task name, and deadline. For example, a notification might be created that reads, "Worker B, the deadline for Task C is approaching. Please complete it promptly."

[1303] Input: A list of workers and tasks that need reminding

[1304] Output: Reminder notification message

[1305] Step 4:

[1306] The server sends the created reminder notification at the appropriate time. The sending method includes email sending via an SMTP server and real-time notification using wearable display devices such as smart glasses. The notification timing is optimized by the schedule setting method. For example, notifications can be sent the day before the submission deadline or in the morning of the deadline.

[1307] Input: Reminder message

[1308] Output: Reminder sent

[1309] Step 5:

[1310] The server records the results of the sent reminders and notifications as a log. Using the log recording method, information such as the sending date and time, recipient, and notification content is saved in a database. This allows for future reference and can be used as data to evaluate the effectiveness of the system.

[1311] Input: Reminder notification information sent

[1312] Output: Log information recorded in the database

[1313] Step 6:

[1314] If the task is not completed after the reminder, the server automatically generates and sends another follow-up notification using the follow-up means. For example, a follow-up notification such as "Task C is not yet completed. Please take action immediately" can be generated and displayed on the worker's wearable display device at an appropriate time.

[1315] Input: Incomplete task information

[1316] Output: Follow-up notification message

[1317] Step 7:

[1318] The server notifies the on-site worker of the work progress in real time using the wearable display control means, which allows the worker wearing the smart glasses to receive immediate reminders and follow-up notifications, thereby improving work efficiency and increasing the task completion rate.

[1319] Input: Reminder notification message, Follow-up notification message

[1320] Output: Notifications displayed on wearable displays such as smart glasses

[1321] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1322] The present invention optimizes the content and sending timing of reminder emails according to the user's emotions by combining a system that automates reminder emails with an emotion engine that recognizes the user's emotions. Specific embodiments of this invention are described below.

[1323] Data collection

[1324] The server periodically retrieves user activity history and task progress status from the project management system and mail server. This allows daily updated information to be stored in the database. For example, the latest task status is saved in the database by a batch process scheduled every night.

[1325] AI-powered analysis

[1326] The server uses AI analysis tools based on the collected data to identify users who need reminders. It also uses machine learning models to make predictions based on each user's task completion status and past behavioral history. For example, it identifies users who have not yet completed a specific task even though the deadline for its submission is approaching.

[1327] emotion recognition

[1328] The server uses an emotion engine to recognize the user's emotions. This emotion recognition is performed, for example, by analyzing the user's email text and voice data. The emotion engine evaluates the user's emotional state, taking into account factors such as the user's stress level and motivation.

[1329] Creating a reminder email

[1330] The server automatically generates reminder emails for identified recipients, with content customized according to the emotions recognized by the emotion engine. The template file is dynamically modified, so that if the user is feeling stressed, for example, an email is created with a gentle tone. An email is generated with the following content: "Dear [user name], I'm concerned about the progress of your task. Please let me know if you need any help."

[1331] Sending emails

[1332] The server adds the generated reminder email to a sending queue and sends it at an optimized timing based on the emotional state recognized by the emotion engine. For example, it sends the email when the user is relaxed, avoiding busy times.

[1333] Follow-up

[1334] If the task is not completed after the reminder email is sent, the server automatically generates a follow-up email and sends it again. The content and timing of the follow-up email are also customized based on information from the emotion engine. For example, if the task is not completed even after the deadline for submission, an appropriate follow-up will be performed depending on the user's status. An email may be sent stating, "Your submission is late, but please let us know if there are no particular problems."

[1335] Specific examples

[1336] As a specific example of use, consider the use in a company's project management system.

[1337] 1. Data collection

[1338] The server obtains the task completion status of each employee from the project management system and stores it in a database.

[1339] 2. AI-based analysis

[1340] The server analyzes the collected data using an AI model to identify employees who have tasks that are due soon but have not yet been completed.

[1341] 3. Emotion recognition

[1342] The server uses an emotion engine to recognize employees' emotional states from email text and voice data, and evaluates their stress and motivation.

[1343] 4. Create a reminder email

[1344] The server automatically generates reminder emails for identified employees based on their emotional state. For example, for an employee feeling stressed, the server creates a gentle email saying, "Please proceed without overdoing it."

[1345] 5. Sending emails

[1346] The server sends reminder emails at appropriate times, often during relaxing hours, taking into account the user's emotional state.

[1347] 6. Follow-up

[1348] The server sends follow-up emails if the task is still incomplete after the deadline, and the content is also adjusted to take into account the user's emotional state.

[1349] This system not only automates reminder emails, but also enables more personalized communication that takes users' emotions into consideration, which is expected to improve work efficiency and user satisfaction.

[1350] The processing flow will be explained below.

[1351] Step 1:

[1352] The server acquires user activity history and task progress from the project management system and mail server. This acquisition process is performed periodically, with daily scheduled batch processing. For example, data such as each user's task ID, progress, and deadline is acquired and stored in a database.

[1353] Step 2:

[1354] The server stores the collected data in a database, which records detailed task information for each user. The acquired data is organized according to a storage format for later analysis.

[1355] Step 3:

[1356] The server uses a query to extract data on users who need reminders from the database. For example, it executes an SQL query to extract users who have tasks due the next day.

[1357] Step 4:

[1358] The server inputs the extracted data into an AI analysis model to identify those who need reminders, and uses a machine learning model to predict candidates who need reminders based on each user's task completion status and past behavioral history.

[1359] Step 5:

[1360] The server saves the reminder recipients in the database based on the analysis results, and updates the list for creating reminder emails.

[1361] Step 6:

[1362] The server uses an emotion engine to recognize the user's emotions. For example, it analyzes past emails and voice data to assess the user's stress level and motivation. It may also use NLP (natural language processing) technology to analyze the text of emails.

[1363] Step 7:

[1364] The server automatically generates emotion-based reminder emails for the reminder recipients. It reads a template file and dynamically fills in parameters such as the user name, task name, and due date. It also customizes the email content based on the results of the emotion engine. For example, it generates a message like, "Dear [user name], I'm concerned about the progress of your task. Please let me know if you need any help."

[1365] Step 8:

[1366] The server adds the generated reminder email to a sending queue and schedules the sending based on the emotional state recognized by the emotion engine. For example, it schedules the email to be sent during a time when the user is relaxed.

[1367] Step 9:

[1368] The server connects to the SMTP server according to the sending schedule and sends the reminder email. The sending result is recorded in a log, and the success / failure information is saved in a database.

[1369] Step 10:

[1370] The server monitors the submission results and automatically generates a follow-up email and adds it to the submission queue if the task is not completed by the deadline. The content of the follow-up email is customized based on the evaluation results of the emotion engine. For example, it could say, "Your submission is late, but please let us know if there are no particular problems."

[1371] Step 11:

[1372] The server sends follow-up emails on a scheduled basis and again logs the results, allowing the effectiveness of the follow-up emails to be monitored and further follow-ups to be performed if necessary.

[1373] This specific processing flow automates the sending and receiving of reminder emails that take the user's emotions into consideration, thereby improving work efficiency and user satisfaction.

[1374] Example 2

[1375] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1376] Conventional reminder systems can create and send reminder emails based on the user's behavioral history and task progress, but it is difficult to set the optimal content and timing of the emails while taking the user's emotional state into account. As a result, problems arise, such as increased user stress and inappropriate follow-up. In particular, reminder emails can be counterproductive because they are insensitive to the user's emotions.

[1377] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a data collection means for acquiring a user's behavioral history and work progress status, an AI analysis means for identifying targets requiring reminders based on the acquired data, an email creation means for automatically generating reminder emails for the targets, a sending means for adding the generated reminder emails to a sending queue and sending them at an appropriate time, an emotion recognition means for recognizing the user's emotions, an email adjustment means for customizing the content of the reminder email according to the emotion recognized by the emotion recognition means, and a follow-up means for automatically generating and sending a follow-up email if the task is not completed even after sending. This makes it possible to optimize the content and sending timing of the reminder email taking the user's emotions into consideration.

[1378] A "user" is a person or organization that uses the system.

[1379] "Behavioral history" is a record of the operations and activities performed by a user.

[1380] "Work progress" is data on the progress of tasks and projects that a user is responsible for.

[1381] "Data collection means" refers to a mechanism or device for acquiring a user's behavior history and work progress.

[1382] "AI analysis methods" are methods that use artificial intelligence to analyze collected data and identify targets that require reminders.

[1383] A "reminder email" is an email sent to a user to encourage them to progress on a task or project.

[1384] "Email creation means" refers to a system or program for automatically generating reminder emails.

[1385] A "sending queue" is a temporary storage location or list of emails waiting to be sent.

[1386] "Transmission means" refers to the method or technology used to send reminder emails to users.

[1387] "Emotion recognition means" refers to a technology or system for determining a user's emotions or mental state.

[1388] The "email adjustment means" is a function for customizing the contents of the reminder email according to the user's emotions.

[1389] A "follow-up method" is a mechanism for sending another email if the task is not completed after the reminder email has been sent.

[1390] The system of the present invention acquires a user's behavior history and work progress, and takes the user's emotions into consideration when automatically generating and sending reminder emails. This system includes data collection means, AI analysis means, email creation means, email sending means, emotion recognition means, email adjustment means, and follow-up means.

[1391] An embodiment of this system will now be described in detail.

[1392] Data collection methods

[1393] The server periodically collects user activity history and work progress from the project management system and mail server. This is done by using automatic data acquisition via API or batch processing. For example, the latest task progress is stored in a database by batch processing scheduled overnight.

[1394] AI analysis means

[1395] The server analyzes the collected data using an AI model. It uses a machine learning algorithm to identify users who have incomplete tasks that are due soon. The AI ​​model makes predictions based on each user's task completion status and past behavioral history.

[1396] emotion recognition means

[1397] The server uses an emotion recognition engine to recognize the user's emotions, including natural language processing (NLP) and voice recognition technologies, to assess the user's stress level and motivation from the text of their emails and their voice data.

[1398] Email creation method

[1399] The server automatically generates reminder emails based on the emotions recognized by the emotion engine. This includes the ability to use template files to customize the content of emails depending on the user's emotional state. For example, a friendly email could be created that reads, "Dear [user name], I'm concerned about your task progress. Please let me know if you need any help."

[1400] Transmission method

[1401] The server adds the generated reminder email to a sending queue and sends it at the optimal time, which is set to a time when the user is relaxed.

[1402] Follow-up measures

[1403] If the task is not completed after the reminder email is sent, the server automatically generates and sends a follow-up email. This includes the ability to customize the content and timing of the email based on information obtained from the emotion engine. For example, an email could be sent with the following content: "Your submission is late, but please let us know if there are no particular problems."

[1404] Specific examples

[1405] As a specific example of use, consider using it in a company's project management system.

[1406] 1. Data collection: The server obtains the task completion status of each employee from the project management system API, and stores the progress status of each employee in a database.

[1407] 2. AI analysis: The server analyzes the collected data using an AI model to identify employees who have incomplete tasks that are due soon.

[1408] 3. Emotion recognition: The server uses an emotion engine to recognize employees' emotional states from email text and voice data, and evaluates their stress and motivation.

[1409] 4. Creating reminder emails: The server automatically generates reminder emails for identified employees according to their emotional state. For example, for an employee who is feeling stressed, the server creates a gentle email saying, "Please proceed without overdoing it."

[1410] 5. Sending emails: The server sends reminder emails at appropriate times, taking into account the user's emotional state and sending them during times when the user is relaxed.

[1411] 6. Follow-up: If the task is still incomplete after the deadline, the server will send a follow-up email. The content of the email will also be adjusted based on the user's emotional state.

[1412] Example prompt sentence:

[1413] "A system that retrieves the latest task data from a project management system, identifies users with incomplete tasks using an AI model, and generates and sends reminder emails based on their emotional state using an emotion engine."

[1414] This system goes beyond simply automating reminder emails, enabling more personalized communication that takes user emotions into account.

[1415] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1416] Step 1:

[1417] The server collects user activity history and work progress from the project management system and mail server. Inputs include data from the project management system's API and mail server. This data is periodically retrieved and stored in a database. For example, the latest task data and user activity logs are saved to the database by batch processing scheduled overnight.

[1418] Specific behavior:

[1419] Retrieving task data from a project management system's API

[1420] Collecting email logs from the email server

[1421] Store the collected data in a database

[1422] Step 2:

[1423] The server uses an AI model to analyze the collected data. The inputs include the task data and behavioral history collected in step 1. The AI ​​model analyzes users' task completion status and past behavioral history to identify users who need reminders. The output is a list of users who need reminders.

[1424] Specific behavior:

[1425] Input data collected from the database into the AI ​​model

[1426] Use machine learning algorithms to analyze incomplete tasks and behavioral history

[1427] Make a list of users who need reminders

[1428] Step 3:

[1429] The server uses an emotion recognition engine to recognize the user's emotions. Inputs include the user's email text and voice data. The emotion engine uses natural language processing (NLP) and voice analysis technologies to analyze the user's emotional state (e.g., stress level and motivation), and outputs the user's emotional state data.

[1430] Specific behavior:

[1431] Analyzing email text using natural language processing technology

[1432] Analyzing voice data using voice recognition technology

[1433] The emotion engine evaluates and outputs the user's emotional state.

[1434] Step 4:

[1435] The server automatically generates reminder emails based on the output of the emotion recognition engine. The input is a list of users who need reminding and their emotional state data. A template file is used to customize the email content according to the emotional state. The output is a customized reminder email.

[1436] Specific behavior:

[1437] Get the target users from the list of users who need to be reminded

[1438] Select and customize template files based on your emotional state

[1439] Generate customized reminder emails

[1440] Step 5:

[1441] The server adds the generated reminder email to the sending queue and sends it at the optimal time. The input is the customized reminder email and the user's appropriate sending timing data. The output is that the reminder email is sent.

[1442] Specific behavior:

[1443] Add the generated reminder email to the sending queue

[1444] Optimizing transmission timing based on the user's emotional state

[1445] Send reminders at the perfect time

[1446] Step 6:

[1447] If the task is not completed after the reminder email is sent, the server automatically generates and sends a follow-up email. The input is the task completion status data and emotional state data after the reminder email is sent. The output is the generation and sending of a follow-up email.

[1448] Specific behavior:

[1449] Check task completion status after sending a reminder email

[1450] Generate follow-up emails based on sentiment engine data when there are open tasks

[1451] Send a follow-up email

[1452] Through these steps, the system automatically generates and sends reminder emails that take the user's emotions into consideration, thereby improving work efficiency and user satisfaction.

[1453] (Application example 2)

[1454] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1455] Conventional reminder email systems send reminder emails based only on the user's behavioral history and task progress, and therefore are unable to take the user's emotional state into consideration. This has resulted in problems such as inappropriate reminders being sent based on the user's emotional state, and the effectiveness of reminders being insufficient. To solve this problem, the present invention aims to provide a system that recognizes the user's emotional state, automatically generates reminder emails based on the user's emotions, and sends them at the optimal time.

[1456] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a data collection means for acquiring the user's behavioral history and task progress status, an AI analysis means for identifying targets requiring reminders based on the acquired data, an emotion recognition means for recognizing the user's emotional state, an email creation means for automatically generating a reminder email according to the emotional state, and a sending means for sending the created reminder email at an appropriate time. This makes it possible to automatically generate a personalized reminder email that takes the user's emotional state into consideration and send it at the optimal time.

[1457] "User behavior history" refers to data such as the operations a user performs on the system, access history, and task progress.

[1458] "Task progress status" indicates information such as the current completion status, progress, and deadline of the task for which the user is responsible.

[1459] "Data collection means" refers to the technical means for acquiring data such as user behavior history and task progress on the system.

[1460] "AI analysis method" refers to an analysis technology that uses artificial intelligence to identify users who need reminders based on collected data.

[1461] "Emotion recognition means" refers to technology that analyzes a user's emotional state and evaluates their stress level, motivation, etc.

[1462] A "reminder email" refers to an email sent to a user to encourage them to progress with a task.

[1463] "Email creation means" refers to technology that automatically generates the content of reminder emails based on the user's emotional state.

[1464] "Transmission means" refers to a technology for sending the generated reminder email to the user at an appropriate time.

[1465] "Schedule setting means" refers to a technology that sets the optimal timing for sending reminder emails.

[1466] "Logging means" refers to technology for recording sent emails and their results.

[1467] "Follow-up measures" refer to technology that automatically generates and sends another email if the task is not completed after the reminder.

[1468] "Personalization" refers to optimizing content and services according to the individual characteristics and circumstances of the user.

[1469] The present invention is a system that recognizes a user's emotions and automatically generates and sends reminder emails according to the user's emotions. This system includes multifunctional technology that acquires the user's behavioral history and task progress, and optimizes the appropriate timing and content of reminders.

[1470] Collecting data on user behavior history and task progress

[1471] The server has a means of collecting data to acquire the user's behavioral history and task progress. For example, if a user adds a product to their cart on an online shopping site but leaves it unpurchased, that information is sent to the server. The server also collects information about the products the user has viewed and how frequently they have viewed them.

[1472] AI analysis to identify necessary reminders

[1473] The server uses AI analysis methods based on the collected data to identify users who need reminders. This process predicts whether a reminder to make a purchase is necessary based on, for example, the products the user has pending purchases or the pages they frequently visit. The artificial intelligence techniques used here include generative AI models.

[1474] Emotion evaluation of users using emotion recognition methods

[1475] The server uses emotion recognition techniques to recognize the user's emotional state. For example, it analyzes the context of the words used by the user in emails and chats to assess their stress level and motivation. Natural language processing technology and machine learning models are used for this emotion recognition.

[1476] Automatically generate reminder emails

[1477] The server automatically generates reminder emails according to the user's emotional state. The email creator adjusts the content based on the user's emotions. For example, for a user with low purchasing motivation, it generates a reminder email with the content "We will give you a limited-time discount coupon!"

[1478] Sending reminders and following up

[1479] The reminder email is sent to the user at an appropriate time by the server's sending means. For example, it is sent during a time period when the user is relaxing, taking into account the user's activity history. If the task is not completed after the reminder, another reminder email is automatically generated and sent using the follow-up means.

[1480] Examples and prompts

[1481] As a concrete example, consider the use of an online shopping site. If a user adds an item to their cart but holds off on purchasing, the emotion engine determines that the user is not highly motivated to purchase. In this situation, the reminder bot sends a reminder notification with a limited coupon during a relaxing time.

[1482] Here are some examples of prompts for generative AI models:

[1483] Customize the content of reminder emails based on the user's emotional state. A user has product A and product B in their cart. Their emotional state is low. What kind of reminder email should you create to encourage them to make a purchase?

[1484] In this way, by taking into account the user's emotional state and sending a personalized reminder email, it is possible to maximize the effectiveness of the reminder.

[1485] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1486] Step 1:

[1487] The server acquires the user's behavioral history and task progress. Specifically, it collects data such as the products the user viewed on the online shopping site, the products they added to their cart, and their purchase history. This data is stored in a database and used for later analysis.

[1488] Input: User behavior history, task progress data

[1489] Output: User behavior history and task progress stored in a database

[1490] Step 2:

[1491] The server uses AI analytics to identify users who need reminders based on the collected data, and uses a generative AI model to determine whether a particular user has left an item in their cart unpurchased.

[1492] Input: User behavior history and task progress stored in a database

[1493] Output: A list of users who need to be reminded

[1494] Step 3:

[1495] The server uses emotion recognition to recognize the user's emotional state, analyzing data such as email and chat messages and browsing history to assess the user's stress level and motivation.

[1496] Input: Email and chat text, browsing history

[1497] Output: User's emotional state (high motivation / low motivation, stress level, etc.)

[1498] Step 4:

[1499] The server automatically generates reminder emails based on the user's emotional state, using a generative AI model to create prompts tailored to the user's emotions and then constructing the email content accordingly.

[1500] Input: User's emotional state, prompt

[1501] Output: Reminder email content

[1502] Step 5:

[1503] The server then sends the created reminder email at the appropriate time, taking into account the user's behavioral history and emotional state, and sends the email at the optimal time, such as during a relaxed time.

[1504] Input: Reminder email content, user activity history

[1505] Output: Reminder email sent to user

[1506] Step 6:

[1507] If the user does not take action based on the reminder email, the server will automatically generate and send a follow-up email again, again using AI analysis methods to analyze the user's emotional state and customize the content of the follow-up email accordingly.

[1508] Input: Reminder email sending results, user behavior history

[1509] Output: Content and sending of follow-up email

[1510] This allows reminder emails and follow-up emails to be automatically generated and sent at the appropriate time, taking into account the user's emotional state.

[1511] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1512] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1513] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1514] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1515] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1516] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1517] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1518] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1519] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1520] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1521] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1522] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1523] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1524] 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.

[1525] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1526] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1527] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1528] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1529] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1530] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1531] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1532] The following is further disclosed regarding the above embodiment.

[1533] (Claim 1)

[1534] A data collection means for acquiring a user's behavior history and task progress;

[1535] AI analysis method to identify targets that need reminders based on the acquired data, and

[1536] An email creation means for automatically generating reminder emails to target individuals;

[1537] A sending means for sending the created reminder email at an appropriate time;

[1538] A system including:

[1539] (Claim 2)

[1540] A scheduling method to optimize the timing of sending reminder emails;

[1541] a logging means for recording the results of the sent emails;

[1542] 10. The system of claim 1, further comprising:

[1543] (Claim 3)

[1544] A follow-up method that automatically generates and sends follow-up emails if the task is not completed after the reminder.

[1545] 10. The system of claim 1, further comprising:

[1546] "Example 1"

[1547] (Claim 1)

[1548] A data collection means for acquiring a user's behavior history and task progress;

[1549] A machine learning model analysis method that identifies targets that require reminders based on the acquired data;

[1550] a template generation means for automatically generating a reminder email for a target person;

[1551] A sending means for sending the created reminder email at an appropriate time;

[1552] A follow-up method that automatically generates and sends a follow-up email if the task is not completed after sending.

[1553] A system including:

[1554] (Claim 2)

[1555] A scheduling method to optimize the timing of sending reminder emails;

[1556] a logging means for recording the results of the sent emails;

[1557] 10. The system of claim 1, further comprising:

[1558] (Claim 3)

[1559] a batch processing means for periodically acquiring data;

[1560] A method to dynamically insert information such as user name, task name, deadline date, etc. into the content of the email to be sent,

[1561] 10. The system of claim 1, further comprising:

[1562] "Application Example 1"

[1563] (Claim 1)

[1564] A data collection means for acquiring a user's behavior history and task progress;

[1565] AI analysis method to identify targets that need reminders based on the acquired data, and

[1566] A notification creation method that automatically generates reminder emails and real-time notifications for target users;

[1567] A means of sending the created reminder emails and notifications at the appropriate time,

[1568] A system including:

[1569] (Claim 2)

[1570] A scheduling method to optimize the timing of reminder emails and notifications, and

[1571] A logging mechanism to record the results of sent emails and notifications;

[1572] 10. The system of claim 1, further comprising:

[1573] (Claim 3)

[1574] A follow-up method that automatically generates and sends follow-up emails and notifications if a task is not completed after a reminder.

[1575] 10. The system of claim 1, further comprising:

[1576] (Claim 4)

[1577] a wearable display device control means for grasping the progress of work in the factory based on the acquired data and displaying reminders or follow-up notices to the workers;

[1578] 10. The system of claim 1, further comprising:

[1579] "Example 2: Combining Emotion Engines"

[1580] (Claim 1)

[1581] A data collection means for acquiring a user's behavior history and work progress status;

[1582] AI analysis method to identify targets that need reminders based on the acquired data, and

[1583] An email creation means for automatically generating reminder emails to target individuals;

[1584] A sending means for adding the generated reminder email to a sending queue and sending it at an appropriate time;

[1585] emotion recognition means for recognizing an emotion of a user;

[1586] an email adjustment means for customizing the content of the reminder email according to the emotion recognized by the emotion recognition means;

[1587] A follow-up method that automatically generates and sends a follow-up email if the task is not completed after sending.

[1588] A system including:

[1589] (Claim 2)

[1590] A scheduling method to optimize the timing of sending reminder emails;

[1591] a logging means for recording the results of the sent emails;

[1592] 10. The system of claim 1, further comprising:

[1593] (Claim 3)

[1594] emotion evaluation means for evaluating the user's emotional state and determining an appropriate reminder timing;

[1595] 10. The system of claim 1, further comprising:

[1596] "Application example 2 when combining emotion engines"

[1597] (Claim 1)

[1598] A data collection means for acquiring a user's behavior history and task progress;

[1599] AI analysis method to identify targets that need reminders based on the acquired data, and

[1600] emotion recognition means for recognizing an emotional state of a user;

[1601] An email creation method that automatically generates reminder emails according to the user's emotional state;

[1602] A sending means for sending the created reminder email at an appropriate time;

[1603] A system including:

[1604] (Claim 2)

[1605] A scheduling method to optimize the timing of sending reminder emails;

[1606] a logging means for recording the results of the sent emails;

[1607] 10. The system of claim 1, further comprising:

[1608] (Claim 3)

[1609] A follow-up method that automatically generates and sends follow-up emails if the task is not completed after the reminder.

[1610] 10. The system of claim 1, further comprising: [Explanation of symbols]

[1611] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A data collection means for acquiring a user's behavior history and task progress; AI analysis method to identify targets that need reminders based on the acquired data, and An email creation means for automatically generating reminder emails to target individuals; A sending means for sending the created reminder email at an appropriate time; A system including:

2. A scheduling method to optimize the timing of sending reminder emails; a logging means for recording the results of the sent emails; The system of claim 1 further comprising:

3. A follow-up method that automatically generates and sends follow-up emails if the task is not completed after the reminder. The system of claim 1 further comprising:

Images