System

Abstract

To provide a system.SOLUTION: A system includes: means for reading service information; means for determining what tasks should be done and by when with respect to a customer's desired delivery date obtained from the service information; means for reminding a user of the determination result; means for using a generative AI model to suggest optimal actions based on a prompt sentence regarding sales activities input by the user; and means for periodically acquiring the service information using a database management system and updating it as necessary.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] There is an issue where services cannot be launched as desired by customers due to a lack of overall management of delivery (such as failure to consider delivery dates). [Means for solving the problem]

[0005] To solve this problem, we provide a system that includes a means for reading service information (delivery dates, etc.) and internal application deadlines, a means for determining what tasks should be completed by when in relation to the customer's desired delivery date, and a means for reminding sales staff of the results of the determination. In particular, the reminding means uses email, and the determination means uses a machine learning algorithm to determine the tasks. [Brief explanation of the drawings]

[0006] [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. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13] FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment Example 2. [Figure 15] FIG. 10 is a sequence diagram showing the flow of processing in a data processing system according to a third embodiment of the third embodiment. [Figure 16]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0007] 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.

[0008] First, the terms used in the following description will be explained.

[0009] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] 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.

[0011] 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.

[0012] 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.

[0013] 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."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 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.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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.

[0022] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] 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.

[0024] 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.

[0025] 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.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] One embodiment of the present invention includes a means for reading service information (such as delivery dates) and in-house application deadlines from a database. This means can be realized, for example, by using a database management system. The database management system periodically obtains the service information and in-house application deadlines and updates them as necessary.

[0029] "Example 2"

[0030] There are also ways to determine what tasks should be completed by when in relation to the customer's desired delivery date. This can be achieved, for example, using machine learning algorithms. Machine learning algorithms learn from past data and estimate the optimal tasks and their deadlines for new service information and internal application deadlines.

[0031] "Example 3"

[0032] Furthermore, there is also a means for reminding the salesperson of the decision result. This means can be realized, for example, by using an email system. The email system automatically sends a reminder email to the salesperson based on the decision result.

[0033] The processing flow of each embodiment will be described below.

[0034] "Example 1"

[0035] Step 1: The database management system is operational and service information (delivery dates, etc.) and internal application deadlines are read from the database.

[0036] Step 2: Based on the information loaded, calculate the required tasks and their deadlines. For example, calculate the start and end dates for each task by working backwards from the delivery date requested by the customer.

[0037] Step 3: Based on the calculation results, a reminder email is sent to the sales team, clearly stating what tasks need to be completed and by when.

[0038] "Example 2"

[0039] Step 1: Machine learning algorithms are put to work, learning from past data.

[0040] Step 2: When new service information and internal application deadlines are entered, the trained model is used to estimate the optimal task and its deadline.

[0041] Step 3: Based on the estimation results, a reminder email is sent to the sales team, clearly stating what tasks need to be completed and by when.

[0042] "Example 3"

[0043] Step 1: The email system is operational and automatically sends reminder emails to sales staff based on the results of the decision.

[0044] Step 2: The email specifies what task needs to be completed by when, and which client and project it relates to.

[0045] Step 3: Sales receives the email and follows the instructions to complete the task.

[0046] Example 1

[0047] Next, a description will be given of Example 1 of Form 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."

[0048] In the previous system, management of service information and internal application deadlines was often done manually, resulting in the problem of time-consuming updates and confirmations of information. Furthermore, there was a lack of a way to determine the appropriate tasks for customer desired delivery dates and to send reminders to sales staff, which could lead to a decline in work efficiency. Furthermore, there was no way for users to quickly check the latest information, which could lead to work delays and mistakes.

[0049] 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.

[0050] In this invention, the server includes a means for reading service information and internal application deadlines, a means for determining what tasks should be completed by when in relation to the customer's desired delivery date, a means for reminding the sales department of the determination result, a means for periodically obtaining service information and internal application deadlines using a database management system and updating them as necessary, a means for a terminal to access the server to obtain data and display it to the user, and a means for the user to check the information through the terminal. This automates the management of service information and internal application deadlines, allowing for quick information updates and confirmations, improving work efficiency. Furthermore, by determining the appropriate tasks in relation to the customer's desired delivery date and reminding the sales department, it is possible to prevent work delays and errors.

[0051] "Service Information" refers to important information about the service, such as delivery dates and details of the services provided.

[0052] "Internal application deadline" refers to the deadline by which various internal applications must be completed.

[0053] "Database management system" means a software system for creating, managing, and manipulating databases.

[0054] A "server" refers to a computer system that provides data and services over a network.

[0055] "Terminal" refers to a device that allows a user to access a server and obtain data.

[0056] "User" refers to a person who uses the system to check service information and internal application deadlines.

[0057] "Reading means" refers to a method or device for obtaining the required information from the database.

[0058] "Means for determining" refers to a method or device for determining an appropriate task or action based on certain conditions.

[0059] "Means for reminding" refers to a method or device for notifying a user of specific information or tasks.

[0060] "Means for periodically acquiring and updating as necessary" refers to a method or device for acquiring data at regular intervals and updating the data if there are any changes.

[0061] "Means for accessing and obtaining data" refers to a method or device for connecting to a server and obtaining the required information.

[0062] The "display means" refers to a method or device for visually presenting the acquired information to the user.

[0063] "Means for checking" refers to a method or device for a user to view the acquired information and check its contents.

[0064] MODE FOR CARRYING OUT THE INVENTION

[0065] The present invention is a system for efficiently managing service information and in-house application deadlines and providing the information promptly to users. A specific embodiment of this system will be described below.

[0066] Server Processing

[0067] The server uses a database management system (DBMS) to read service information and internal application deadlines from a database. Specifically, a DBMS such as MySQL (registered trademark) or PostgreSQL is used. The server periodically executes queries to obtain the latest service information and internal application deadlines, and updates the database as necessary. For example, the server executes the following SQL query:

[0068] sql

[0069] SELECT FROM service_info;

[0070] SELECT FROM internal_deadlines;

[0071] This will capture all data on service information and internal application deadlines.

[0072] Terminal handling

[0073] The terminal uses a web browser (e.g., GOOGLE CHROME (registered trademark)) to access the server and obtain the latest service information and in-house application deadlines. Specifically, it accesses the following URL:

[0074] http: / / example.com / api / service_info

[0075] http: / / example.com / api / internal_deadlines

[0076] This allows the device to retrieve JSON formatted data from the server. The device then parses the retrieved JSON data and displays it in a format that is easy for the user to view. For example, the device uses HTML and JavaScript (registered trademark) to display the data as follows:

[0077] html

[0078]

[0079] <h2> Service Information< / h2>

[0080]

[0081] Service Name: New Service, Delivery Date: 2023-12-31

[0082]

[0083]

[0084]

[0085] <h2> Internal application deadline< / h2>

[0086]

[0087] Application Name: New Project, Deadline: 2023-11-30

[0088]

[0089]

[0090] This HTML code displays service information and internal application deadlines to the user.

[0091] User operations

[0092] The user checks the displayed service information and internal application deadlines through the device's web browser. For example, the user can use Google (registered trademark) Chrome to check the displayed information and find out the latest delivery dates and application deadlines. The user accesses the following URL:

[0093] http: / / example.com / dashboard

[0094] By accessing this URL, users can check the latest service information and internal application deadlines.

[0095] Example prompts for generative AI models

[0096] Below are some example prompts to input to a generative AI model:

[0097] "Please let me know the latest service information and internal application deadlines."

[0098] Using this prompt, the generative AI model provides up-to-date service information and internal application deadlines.

[0099] In this way, the management of service information and internal application deadlines is automated, allowing information to be updated and confirmed quickly, improving work efficiency and preventing work delays and errors.

[0100] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0101] Step 1:

[0102] The server retrieves the service information and the internal application deadline from the database.

[0103] Input: Database connection information

[0104] What happens: The server connects to the MySQL database and executes the following SQL query:

[0105] sql

[0106] SELECT FROM service_info;

[0107] SELECT FROM internal_deadlines;

[0108] Data processing: Convert the query results into JSON format.

[0109] Output: JSON data of service information and internal application deadline

[0110] Step 2:

[0111] The server updates the retrieved data as needed.

[0112] Input: New service information and internal application deadlines

[0113] What happens: The server checks the retrieved data and, if there is new information, updates the database by executing the following SQL query:

[0114] sql

[0115] INSERT INTO service_info (service_name, due_date) VALUES ('New Service', '2023-12-31');

[0116] Data manipulation: Adding new data to existing data.

[0117] Output: Updated database

[0118] Step 3:

[0119] The terminal accesses the server to obtain the data.

[0120] Input: Server API endpoint URL

[0121] Specific operation: The device accesses the following URL using a web browser (e.g., Google Chrome):

[0122] http: / / example.com / api / service_info

[0123] http: / / example.com / api / internal_deadlines

[0124] Data processing: Analyze the JSON data obtained from the server.

[0125] Output: Parsed service information and internal application deadline data

[0126] Step 4:

[0127] The terminal displays the acquired data to the user.

[0128] Input: Parsed service information and internal application deadline data

[0129] What happens: The device uses HTML and JavaScript to display the data as follows:

[0130] html

[0131]

[0132] <h2> Service Information< / h2>

[0133]

[0134] Service Name: New Service, Delivery Date: 2023-12-31

[0135]

[0136]

[0137]

[0138] <h2> Internal application deadline< / h2>

[0139]

[0140] Application Name: New Project, Deadline: 2023-11-30

[0141]

[0142]

[0143] Data processing: Convert the acquired data into HTML format.

[0144] Output: Service information and internal application deadlines displayed to users

[0145] Step 5:

[0146] The user checks the information through the terminal.

[0147] Input: Device web browser

[0148] What happens: The user opens a web browser on their device and accesses the following URL:

[0149] http: / / example.com / dashboard

[0150] Data processing: Check the displayed information.

[0151] Output: Service information confirmed by the user and internal application deadline

[0152] In this way, the management of service information and internal application deadlines is automated, allowing information to be updated and confirmed quickly, improving work efficiency and preventing work delays and errors.

[0153] (Application example 1)

[0154] Next, a description will be given of Application Example 1 of Embodiment 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."

[0155] In logistics centers, managing delivery dates and internal application deadlines is extremely important, but there is a lack of systems that can efficiently collect this information and suggest actions at the appropriate time. There is also a need for a function that suggests the optimal action based on prompts entered by the user.

[0156] 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.

[0157] In this invention, the server includes a means for reading service information (delivery dates, etc.) and in-house application deadlines, a means for determining what tasks should be completed by when in relation to the customer's desired delivery date, a means for reminding sales of the determination results, a means for using a generative AI model to propose optimal actions based on prompts entered by the user, and a means for periodically acquiring service information and application deadlines using a database management system and updating them as necessary. This enables efficient management of delivery dates and application deadlines at the logistics center and the proposal of optimal actions to users.

[0158] "Service information" is information relating to delivery dates and details of the services provided.

[0159] The "internal application deadline" is the deadline for carrying out necessary procedures and applications within the company.

[0160] "Customer desired delivery date" is the delivery date desired by the customer.

[0161] A "task" is an operation or activity that must be performed to achieve a specific purpose.

[0162] A "remind" is an act of drawing attention so that you do not forget.

[0163] A "generative AI model" is an algorithm that uses artificial intelligence to generate optimal actions based on user input.

[0164] A "prompt sentence" is a question or instruction sentence that a user enters into a system.

[0165] A "database management system" is software for creating, managing, and operating databases.

[0166] "Periodic acquisition" means collecting information at regular time intervals.

[0167] "Updating" means replacing existing information with new information.

[0168] The system for implementing this invention is designed to efficiently manage delivery dates and in-house application deadlines at a logistics center. The system includes the following main components:

[0169] server

[0170] The server has a means of reading service information (delivery dates, etc.) and internal application deadlines. Specifically, it uses a database management system (for example, SQLite or MySQL) to periodically retrieve service information and application deadlines and update them as necessary. This ensures that the latest information is always maintained.

[0171] The server also has a means of determining what tasks should be completed by when in relation to the customer's desired delivery date. This determination is made using machine learning algorithms (e.g., random forests and support vector machines), which automatically assigns appropriate tasks.

[0172] Furthermore, the server has a means for suggesting optimal actions based on the prompt sentence entered by the user using a generative AI model, such as a natural language processing model such as GPT-3 (registered trademark).

[0173] Terminal

[0174] The terminals are smartphones or tablets used by managers and staff at the distribution center. The terminals display information obtained from the server and provide an interface for users to input prompt sentences.

[0175] User

[0176] The user is a manager or staff member of the distribution center. The user can input the following prompt sentences using a terminal:

[0177] "When is the next deadline?"

[0178] "When is the next application deadline?"

[0179] The server uses a generative AI model to suggest optimal actions based on these prompts, such as, "The next delivery date is October 15, 2023. Please make the necessary preparations."

[0180] Specific examples

[0181] For example, if a logistics center manager inputs the prompt "When is the next delivery date?", the server retrieves the latest delivery date information from the database and uses the generative AI model to suggest the following action: "The next delivery date is October 15, 2023. Please make the necessary preparations." This information is displayed on the terminal, allowing the manager to make the appropriate preparations.

[0182] In this way, the present invention realizes efficient management of delivery dates and application deadlines at the logistics center and proposes optimal actions to the user.

[0183] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0184] Step 1:

[0185] The server uses a database management system to periodically retrieve service information (delivery dates, etc.) and internal application deadlines, updating them as needed. The input is the latest information from the database, and the output is the updated service information and application deadlines. Specifically, the server executes SQL queries to retrieve data and updates it as needed.

[0186] Step 2:

[0187] The user inputs a prompt sentence using a terminal. The input is the prompt sentence entered by the user, and the output is the prompt sentence displayed on the terminal. In concrete terms, the user inputs text through the interface of the terminal.

[0188] Step 3:

[0189] The terminal sends the input prompt to the server. The input is the prompt entered by the user, and the output is the prompt sent to the server. In concrete terms, the terminal sends the prompt to the server via the network.

[0190] Step 4:

[0191] The server uses a generative AI model to suggest the optimal action based on the received prompt. The input is the prompt, and the output is the action suggestion generated by the generative AI model. Specifically, the server inputs the prompt into the generative AI model and obtains the output from the model.

[0192] Step 5:

[0193] The server sends the generated action proposals to the terminal. The input is the action proposal generated by the generative AI model, and the output is the action proposal sent to the terminal. Specifically, the server sends the action proposals to the terminal via the network.

[0194] Step 6:

[0195] The terminal displays the received action proposal to the user. The input is the action proposal sent from the server, and the output is the action proposal displayed on the terminal. Specifically, the terminal displays the action proposal on the screen.

[0196] Step 7:

[0197] The user makes the necessary preparations and takes action based on the action suggestions displayed. The input is the action suggestions displayed on the terminal, and the output is the specific action the user takes. As a specific action, the user proceeds with the work according to the suggestions.

[0198] Example 2

[0199] Next, a description will be given of Example 2 of Form 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."

[0200] Conventional project management systems have difficulty efficiently estimating optimal tasks and their deadlines based on the customer's desired delivery date. Furthermore, they lack the functionality to automatically generate task schedules based on new project information using past data. This has led to issues such as reduced project management efficiency and increased risk of delivery delays.

[0201] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0202] In this invention, the server includes means for reading service information and internal application deadlines, means for determining what tasks should be completed by when in relation to a customer's desired delivery date, means for reminding sales of the determination result, means for acquiring past data, means for preprocessing the acquired data, means for training a machine learning model, means for estimating tasks and deadlines based on new project information, and means for returning the estimation result to the user. This makes it possible to automatically generate an optimal task schedule based on new project information using past data, thereby improving the efficiency of project management.

[0203] "Service information" refers to information such as deadlines and requirements related to projects and work.

[0204] The "internal application deadline" is the deadline for various internal applications and procedures.

[0205] "Customer Desired Delivery Date" is the date the customer desires for the project or service to be completed.

[0206] A "task" is a specific task or activity required to complete a project or job.

[0207] A "remind" is a notification or alert that alerts you to make sure you don't forget.

[0208] "Historical data" refers to records and information relating to previously carried out projects or operations.

[0209] "Preprocessing" is the process of converting data into a form suitable for analysis or model training.

[0210] A "machine learning model" is an algorithm that learns patterns and rules from data and makes predictions and classifications for new data.

[0211] "Estimation" means predicting unknown values ​​or results based on existing information and data.

[0212] "User" refers to an individual or organization that uses the system.

[0213] The present invention is a system for estimating optimal tasks and their deadlines in relation to a customer's desired delivery date in a project management system. Specific embodiments of this system will be described below.

[0214] System program generation

[0215] The user generates a program for the project management system. This program includes means for reading service information and internal application deadlines, means for determining what tasks should be completed by when in relation to the customer's desired delivery date, means for reminding sales of the determination results, means for acquiring past data, means for preprocessing the acquired data, means for training a machine learning model, means for estimating tasks and deadlines based on new project information, and means for returning the estimation results to the user.

[0216] Explanation of program processing

[0217] The server processes and calculates data using the following hardware and software.

[0218] Hardware: The servers are a database server and an application server. The database server uses MySQL, and the application server has Python installed.

[0219] Software: The server uses the Python programming language and the Scikit-learn library to train and estimate machine learning models, and the Pandas library for data preprocessing.

[0220] Specifically, the data is processed and calculated in the following manner.

[0221] 1. Data retrieval: The server retrieves historical project data from a MySQL database, including project start and end dates, and details of each task.

[0222] 2. Data preprocessing: The server preprocesses the acquired data, including missing value imputation, data normalization, and categorical data encoding.

[0223] 3. Training the machine learning model: The server trains the machine learning model using the preprocessed data. The algorithm used is the random forest regression model.

[0224] 4. Task and deadline estimation: The server uses the trained model to estimate the start and end dates of each task based on new project information.

[0225] 5. Returning the results: The server returns the estimation results to the user in JSON format. The user can then check the estimated task schedule on their device screen.

[0226] Examples of specific examples and prompts

[0227] As a concrete example, consider the following scenario.

[0228] Examples:

[0229] The user enters the start date and customer desired delivery date of a new project. The server estimates the start and end dates of each task based on data from similar past projects. For example, if the project start date is October 1, 2023, and the customer desired delivery date is December 31, 2023, the server generates the following task schedule:

[0230] Task 1: October 1, 2023 - October 15, 2023

[0231] Task 2: October 16, 2023 - November 15, 2023

[0232] Task 3: November 16, 2023 - December 15, 2023

[0233] Example prompt sentence:

[0234] "The start date of a new project is October 1, 2023, and the customer's desired delivery date is December 31, 2023. Based on this, estimate the start and end dates for each task."

[0235] In this way, users can use the system to efficiently manage project schedules.

[0236] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0237] Step 1:

[0238] The user enters the project information.

[0239] Enter: Project start date and customer desired delivery date.

[0240] Specific operation: The user enters the project start date (e.g., October 1, 2023) and the customer's desired delivery date (e.g., December 31, 2023) into the input form on the terminal and clicks the "Submit" button.

[0241] Output: The entered project information is sent to the server.

[0242] Step 2:

[0243] The server retrieves past project data.

[0244] Input: Project information sent to the server.

[0245] Specific operation: The server connects to a MySQL database and retrieves past project data using SQL queries.

[0246] Output: Retrieved historical project data.

[0247] Step 3:

[0248] The server preprocesses the data.

[0249] Input: Captured historical project data.

[0250] Specific operation: The server converts the data into a data frame using the Pandas library and performs preprocessing such as filling in missing values, normalizing the data, and encoding categorical data.

[0251] Output: Preprocessed data.

[0252] Step 4:

[0253] The server trains the machine learning model.

[0254] Input: Preprocessed data.

[0255] What it does: The server trains a random forest regression model using the Scikit-learn library.

[0256] Output: A trained machine learning model.

[0257] Step 5:

[0258] The server estimates tasks and deadlines based on new project information.

[0259] Input: A trained machine learning model and new project information.

[0260] What it does: The server uses the trained model to estimate the start and end dates for each task based on new project information.

[0261] Output: The estimated task schedule.

[0262] Step 6:

[0263] The server returns the estimated results to the user.

[0264] Input: Estimated task schedule.

[0265] Specific operation: The server returns the estimation results to the user in JSON format.

[0266] Output: The estimated task schedule displayed on the user's terminal.

[0267] In this way, users can use the system to efficiently manage project schedules.

[0268] (Application example 2)

[0269] Next, a description will be given of Application Example 2 of Form 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."

[0270] In logistics centers, it is important to efficiently manage the optimal tasks and deadlines for customer orders. However, with conventional methods, it is difficult to estimate the optimal tasks and deadlines using past data, and work efficiency is not sufficiently improved. There is also a lack of means to grasp the progress of tasks in real time and to send appropriate reminders. For this reason, a new system is needed to improve the work efficiency of logistics centers.

[0271] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0272] In this invention, the server includes a means for reading service information (delivery dates, etc.) and in-house application deadlines, a means for determining what tasks should be completed by when in relation to the customer's desired delivery date, a means for reminding the worker of the determination result, a means for estimating the optimal tasks and their deadlines using a machine learning algorithm based on past data, and a means for displaying the estimated tasks and deadlines. This makes task management in the logistics center more efficient, enabling the progress of work to be grasped in real time and appropriate reminders to be sent.

[0273] "Service information" refers to information such as delivery dates and detailed requirements regarding orders from customers.

[0274] The "internal application deadline" is the deadline for various applications set in the internal business process.

[0275] "Customer desired delivery date" is the date and time of delivery of the product desired by the customer.

[0276] A "task" refers to a specific job or operation, such as order processing or shipping preparation at a logistics center.

[0277] A "remind" is the act of notifying a worker of a specific task or deadline and drawing their attention to it.

[0278] A "machine learning algorithm" is a computational method that learns patterns based on past data and makes predictions and classifications for new data.

[0279] "Estimation" is the act of predicting future events or outcomes based on existing data and information.

[0280] "Display" refers to the act of visually indicating estimated tasks and deadlines, and refers to outputting information on a screen or display.

[0281] A system for carrying out the present invention is intended to improve the efficiency of task management in a logistics center. A specific embodiment of the system will be described below.

[0282] System Configuration

[0283] The system consists of the following main components:

[0284] 1. Server: Responsible for data processing and running machine learning algorithms.

[0285] 2. Terminal: A device such as a smartphone or tablet used by a business employee.

[0286] 3. User: Logistics center operations staff.

[0287] Hardware and software used

[0288] Hardware: Smartphone (iOS or ANDROID (registered trademark)), server (with a high-performance CPU and sufficient memory)

[0289] Software: Python, scikit-learn (machine learning library), pandas (data manipulation library)

[0290] Data processing and calculation

[0291] The server processes the data as follows:

[0292] 1. Data loading: Load past order data from a CSV file.

[0293] 2. Setting features and targets: Set features such as order size, order type, and season, and completion time as targets.

[0294] 3. Model Training: Train the machine learning model using RandomForestRegressor.

[0295] 4. Enter new order information: Enter new order information from the terminal.

[0296] 5. Task and Deadline Estimation: Using the trained model, we estimate the optimal tasks and their deadlines.

[0297] 6. Display results: Display estimated tasks and deadlines on your device.

[0298] Specific examples

[0299] Past data includes order size, order type, season, and completion time. For new order information, enter an order size of 10, order type as standard, and season as winter. From this, the server estimates the optimal task and its deadline and reminds the worker.

[0300] Prompt Sentence Examples

[0301] "Based on past logistics data, estimate the optimal tasks and their deadlines for an order size of 10, an order type of standard, and a season of winter."

[0302] This system will streamline task management at logistics centers, allowing for real-time understanding of work progress and appropriate reminders.

[0303] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0304] Step 1:

[0305] The server reads past order data from a CSV file.

[0306] Input: A CSV file containing historical order data.

[0307] Data processing: Convert the CSV file into a data frame using the pandas library.

[0308] Output: Historical order data in dataframe format.

[0309] Step 2:

[0310] The server sets the features and targets.

[0311] Input: Historical order data in dataframe format.

[0312] Data processing: Order size, order type, and season are extracted as features, and completion time is set as the target.

[0313] Output: A dataset of features and targets.

[0314] Step 3:

[0315] The server trains the machine learning model.

[0316] Input: Feature and target datasets.

[0317] Data computation: Train the model using scikit-learn's RandomForestRegressor.

[0318] Output: A trained machine learning model.

[0319] Step 4:

[0320] The terminal inputs new order information.

[0321] Input: New order information entered by the user (e.g., order size is 10, order type is standard, season is winter).

[0322] Data processing: Convert the input order information into a data frame.

[0323] Output: The new order information in a data frame format.

[0324] Step 5:

[0325] The server uses the trained model to estimate the optimal tasks and their deadlines.

[0326] Input: New order information in dataframe format, trained machine learning model.

[0327] Data calculation: New order information is input into the model and an estimated completion time is calculated.

[0328] Output: Estimated completion time and deadline.

[0329] Step 6:

[0330] The terminal displays estimated tasks and deadlines.

[0331] Inputs: Estimated completion time and deadline.

[0332] Specific behavior: Estimated tasks and deadlines are displayed on the device screen.

[0333] Output: Estimated tasks and deadlines are displayed visually for the worker.

[0334] Example 3

[0335] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0336] In the conventional system, there were limited means to determine tasks based on service information and internal application deadlines and to remind sales staff, making it difficult to operate efficiently.In addition, the process of generating judgment results based on prompts entered by users and reminding sales staff about them was not automated, so manual response was required, which was time-consuming and labor-intensive.

[0337] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0338] In this invention, the server includes means for the user to input a prompt sentence, means for the terminal to send the prompt sentence to the server, means for the server to pass the prompt sentence to the generative AI model, means for the generative AI model to generate a judgment result, means for the server to analyze the judgment result and create a reminder email as necessary, and means for the server to send the reminder email to the sales department. This makes it possible to automatically generate a judgment result based on the prompt sentence entered by the user and to efficiently remind the sales department.

[0339] "Service information" refers to information necessary for business operations, such as delivery dates and internal application deadlines.

[0340] "Customer desired delivery date" refers to the delivery date of the product desired by the customer.

[0341] A "task" refers to the work or activity that must be performed to achieve a specific goal.

[0342] "Judgment result" refers to the conclusion or recommended action generated based on the input information.

[0343] A "remind" refers to a re-notification of specific information or tasks.

[0344] A "prompt sentence" refers to a sentence containing a question or instruction that a user inputs to a system.

[0345] "Terminal" refers to a device such as a computer or smartphone operated by a user.

[0346] "Server" refers to a computer system that provides services over a network.

[0347] A "generative AI model" refers to an algorithm or system that uses artificial intelligence to generate judgment results from input data.

[0348] "Email" refers to digital messages sent and received over the Internet.

[0349] "SMTP Protocol" refers to the communications protocol used to send email.

[0350] This invention is a system that uses a generative AI model to generate a judgment result based on a prompt sentence entered by a user, and sends a reminder email to sales as necessary. A specific embodiment of this system is described below.

[0351] Hardware and software used

[0352] server

[0353] The server runs the program using Python and uses a general artificial intelligence model, specifically OpenAI's GPT-4 (registered trademark), as the generative AI model. The server also uses Python's smtplib library to send emails using the SMTP protocol.

[0354] Terminal

[0355] The terminal provides an interface for the user to input a prompt sentence. The terminal uses a web browser to display a form for the user to input a prompt sentence. Specific web browsers used are Google Chrome and Mozilla Firefox.

[0356] User

[0357] The user inputs a prompt through the web browser on the terminal, for example, "Please tell me your sales forecast for the next quarter," and presses the send button.

[0358] Data processing and calculation

[0359] Entering and sending a prompt

[0360] When a user enters a prompt in the device's web browser and presses the submit button, the device sends the prompt as an HTTP POST request to the server, converting the form data into JSON format and sending it to the specified endpoint on the server.

[0361] Parsing prompts and generating results

[0362] The server analyzes the received prompt and passes it to the generative AI model. Specifically, the server uses Python's requests library to send a request including the prompt to the generative AI model's API. The generative AI model generates a judgment result based on the received prompt. For example, it generates a response such as, "Sales forecast for the next quarter are expected to increase by 10% compared to the same period last year."

[0363] Analysis of decision results and creation of reminder emails

[0364] The server analyzes the judgment results returned by the generative AI model. If the analysis results determine that a reminder to the salesperson is necessary, a reminder email is created. Specifically, the server includes the judgment results in the email body and sets the email address of the salesperson as the recipient.

[0365] Sending reminder emails

[0366] The server sends the created reminder email using the SMTP protocol. For example, it uses the Python smtplib library to send the email through a common SMTP server. The subject of the email should read "Important: Sales Forecast Reminder" and the body should contain the generated decision result.

[0367] Specific examples

[0368] Prompt Sentence Examples

[0369] An example of a prompt that a user can enter is, "Please tell me your sales forecast for the next quarter." When the user enters this prompt and presses the send button, the server uses the generative AI model to generate a sales forecast and sends the results as a reminder email to the sales department.

[0370] In this way, a system is constructed in which the server generates a judgment result based on the prompt sentence entered by the user and sends a reminder email to the sales department as necessary. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0371] Step 1:

[0372] The user enters a prompt statement.

[0373] The user opens a web browser on their device and accesses the specified URL. They enter a prompt in the form that appears and press the submit button. For example, they might enter, "Please tell me your sales forecast for the next quarter." The input data is the prompt.

[0374] Step 2:

[0375] The terminal sends the prompt to the server.

[0376] The terminal sends the prompt text entered by the user to the server as an HTTP POST request. At this time, the terminal converts the form data into JSON format and sends it to the specified endpoint of the server. The input data is the prompt text, and the output data is the JSON-formatted data sent to the server.

[0377] Step 3:

[0378] The server passes the prompt to the generative AI model.

[0379] The server parses the received prompt sentence and passes it to the generative AI model. Specifically, the server uses the Python requests library to send a request including the prompt sentence to the generative AI model's API. The input data is the prompt sentence in JSON format, and the output data is the request sent to the generative AI model.

[0380] Step 4:

[0381] The generative AI model generates the judgment result.

[0382] A generative AI model generates a judgment result based on the received prompt. For example, it generates a response such as, "Sales forecast for the next quarter are expected to increase by 10% compared to the same period last year." The input data is the prompt, and the output data is the generated judgment result.

[0383] Step 5:

[0384] The server analyzes the results of the decision and creates a reminder email if necessary.

[0385] The server analyzes the judgment results returned by the generative AI model. If it determines that a reminder is necessary for the salesperson based on the analysis results, it creates a reminder email. Specifically, the server includes the judgment results in the email body and sets the email address of the salesperson as the recipient. The input data is the generated judgment results, and the output data is the created reminder email.

[0386] Step 6:

[0387] The server sends a reminder email to sales.

[0388] The server sends the created reminder email using the SMTP protocol. For example, it uses Python's smtplib library to send the email through a common SMTP server. The email subject should read "Important: Sales Forecast Reminder" and the body should include the generated judgment result. The input data is the created reminder email, and the output data is the email sent to sales.

[0389] (Application example 3)

[0390] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0391] In conventional sales activities, it was difficult to determine the next sales activity to be carried out based on the customer's purchase history and inquiry details, and to remind sales representatives at the appropriate time. Furthermore, reminders were often done manually, which hindered efficient sales activities. This resulted in problems such as delays in customer responses and lost opportunities.

[0392] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0393] In this invention, the server includes a means for reading service information (delivery dates, etc.) and in-house application deadlines, a means for determining what tasks should be completed by when in relation to the customer's desired delivery date, a means for reminding sales of the determination results, a means for determining the next sales activity to be carried out based on the customer's purchase history and inquiry details, and a means for automatically sending reminder emails based on the determination results. This makes it possible to determine appropriate sales activities based on the customer's purchase history and inquiry details, and to automatically send reminder emails in a timely manner.

[0394] "Service information" refers to information necessary for carrying out business, such as delivery dates and internal application deadlines.

[0395] "Internal application deadline" refers to the deadline by which internal procedures and applications must be completed.

[0396] "Customer desired delivery date" refers to the delivery date of the product desired by the customer.

[0397] A "task" refers to the work or task that must be performed to achieve a specific goal.

[0398] "Decision-making means" refers to a method or device for determining the next action to be taken based on specific conditions or data.

[0399] "Reminder means" refers to a method or device that provides notifications or alerts to encourage necessary action based on specific information.

[0400] "Customer purchase history" refers to a record of products that a customer has previously purchased.

[0401] "Inquiry content" refers to the details of questions or requests from customers.

[0402] "Sales activities" refers to a series of tasks and actions taken to sell products or services.

[0403] "Reminder email" refers to an email sent with specific information or to encourage specific action.

[0404] "Automatic sending means" refers to a method or device that sends email without manual operation when specific conditions are met.

[0405] A system for implementing this invention includes means for reading service information (delivery dates, etc.) and internal application deadlines, means for determining what tasks should be completed by when in relation to the customer's desired delivery date, means for reminding sales of the results of the determination, means for determining the next sales activity to be carried out based on the customer's purchase history and inquiry details, and means for automatically sending reminder emails based on the results of the determination.

[0406] Hardware and software used

[0407] Hardware: Servers, smartphones

[0408] Software: Python, smtplib library, email.mime library

[0409] Data processing and calculation

[0410] The server first reads service information (delivery dates, etc.) and internal application deadlines from a database. Next, it uses a machine learning algorithm to determine what tasks should be completed by when in relation to the customer's desired delivery date. This algorithm generates an optimal task schedule based on past data.

[0411] Then, based on the results of the decision, a reminder email is generated to remind the sales representative, and this reminder email is sent automatically using the smtplib and email.mime libraries.

[0412] Specific examples

[0413] For example, if a customer inquires about a specific product, the server determines the next sales activity based on the content of the inquiry. The server analyzes the customer's purchase history and the content of the inquiry, and decides which sales activity to take next. For example, if the server determines that "please make a follow-up call to this customer," a reminder email containing that content is automatically sent to the sales representative.

[0414] Prompt Sentence Examples

[0415] "Create a Python program that determines the next sales activity to take based on the customer's purchase history and inquiry details, and sends a reminder email to the sales representative."

[0416] In this way, it becomes possible to determine appropriate sales activities based on the customer's purchase history and inquiry details, and to automatically send timely reminder emails.

[0417] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0418] Step 1:

[0419] The server reads service information (delivery date, etc.) and internal application deadlines from the database.

[0420] Input: Service information stored in the database and internal application deadlines.

[0421] Data processing: Execute database queries to obtain the required information.

[0422] Output: Service information and internal application deadline data.

[0423] Step 2:

[0424] The server uses machine learning algorithms to determine what tasks need to be completed by when in relation to the customer's desired delivery date.

[0425] Input: Customer desired delivery date, service information, internal application deadline.

[0426] Data calculation: Using machine learning algorithms, optimal task schedules are generated based on past data.

[0427] Output: Task schedule.

[0428] Step 3:

[0429] The server determines the next sales activity to be carried out based on the customer's purchase history and inquiry details.

[0430] Input: Customer purchase history, inquiry details.

[0431] Data calculation: Analyze customer data and determine the next sales activity.

[0432] Output: Sales activity decision results.

[0433] Step 4:

[0434] The server generates a reminder email based on the result of the determination.

[0435] Input: Sales activity decision results.

[0436] Data processing: Generate the content of the reminder email.

[0437] Output: Reminder email content.

[0438] Step 5:

[0439] The server automatically sends reminder emails using the smtplib and email.mime libraries.

[0440] Input: Reminder email content, sales representative's email address.

[0441] Data calculation: Executes the email sending process.

[0442] Output: A reminder email is sent to the sales rep.

[0443] In this way, appropriate sales activities can be determined based on the customer's purchase history and inquiries, and timely reminder emails can be automatically sent.

[0444] 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.

[0445] "Example 1"

[0446] One embodiment of the present invention is a system that combines an emotion engine. This system recognizes the user's emotions and adjusts the timing and content of reminders according to that emotional state. Specifically, if it determines that the user is feeling stressed, it can take operations that take the user's emotional state into consideration, such as reducing the frequency of reminders.

[0447] "Example 2"

[0448] The emotion engine also uses machine learning algorithms to learn and predict a user's emotional state. Specifically, it predicts the user's emotional state based on their past reactions and behavioral patterns, and then sends reminders accordingly. For example, if it determines that a user always feels stressed before performing a specific task, it will send reminders for that task in a way that reduces stress.

[0449] "Example 3"

[0450] Furthermore, this system can also adjust the content of reminders depending on the user's emotional state. For example, if it determines that the user is feeling joy, it can include a message in the reminder that reinforces that joy. This allows for more effective reminders that take the user's emotional state into account.

[0451] The processing flow of each embodiment will be described below.

[0452] "Example 1"

[0453] Step 1: The system recognizes emotions from the user's actions and reactions.

[0454] Step 2: The emotion engine determines the user's emotional state based on the recognized emotions.

[0455] Step 3: Adjust the timing and content of your reminders depending on your emotional state.

[0456] "Example 2"

[0457] Step 1: The emotion engine learns the user's emotional state from their past reactions and behavioral patterns.

[0458] Step 2: Predict the user's current emotional state based on the learned emotional state.

[0459] Step 3: Adjust the timing and content of your reminders based on your predicted emotional state.

[0460] "Example 3"

[0461] Step 1: The system recognizes emotions from the user's actions and reactions.

[0462] Step 2: The emotion engine determines the user's emotional state based on the recognized emotions.

[0463] Step 3: Tailor your reminders to your emotional state.

[0464] Example 1

[0465] Next, a description will be given of Example 1 of Form 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."

[0466] In the previous system, it was possible to read service information and internal application deadlines, but it was not possible to adjust the timing or content of reminders according to the user's emotional state. As a result, even if the user was feeling stressed, reminders were sent at a fixed frequency, which increased the burden on the user. Furthermore, because the content of reminders was uniform, it was not possible to respond flexibly according to the user's situation.

[0467] 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.

[0468] In this invention, the server includes a means for reading service information and in-house application deadlines, a means for determining what tasks should be completed by when in relation to the customer's desired delivery date, a means for reminding the sales department of the determination result, and a means for recognizing the user's emotions and adjusting the timing and content of the reminder according to the user's emotional state. This allows for reminders that take the user's emotional state into consideration, reduces the user's burden, and enables more effective task management.

[0469] "Service information" is information relating to delivery dates and details of the services provided.

[0470] "Internal application deadline" refers to the deadline by which the internal application procedure must be completed.

[0471] "Customer desired delivery date" refers to the delivery date desired by the customer.

[0472] A "task" refers to the work or activity that must be performed to achieve a specific goal.

[0473] A "remind" refers to a re-notification of specific information or tasks.

[0474] "User emotions" refers to the psychological state, such as stress or satisfaction, that the user feels.

[0475] "Emotional state" refers to the user's current psychological state, including states such as stress or relaxation.

[0476] A "machine learning algorithm" refers to a computational method for learning patterns based on data and making predictions and judgments.

[0477] MODE FOR CARRYING OUT THE INVENTION

[0478] This invention is a system that includes means for reading service information and internal application deadlines, means for determining what tasks should be completed by when in relation to the customer's desired delivery date, means for reminding sales of the results of the determination, and means for recognizing the user's emotions and adjusting the timing and content of the reminders according to the user's emotional state.

[0479] Server Processing

[0480] The server periodically reads service information and internal application deadlines from a database using a database management system (DBMS). Specifically, it uses a DBMS such as MySQL or PostgreSQL to obtain this information and update it as needed. For example, the server accesses the database at 2:00 AM every day to obtain the latest service information and application deadlines.

[0481] User Action

[0482] The user uses a system that combines an emotion engine. This system recognizes the user's emotions and adjusts the timing and content of reminders according to their emotional state. Specifically, if the system determines that the user is feeling stressed, it will take measures such as reducing the frequency of reminders. For example, if the user inputs "I'm busy today," the system will use that information to reduce the frequency of reminders.

[0483] Terminal handling

[0484] The device will then display a reminder to the user based on the adjusted reminder timing. For example, the user might see a notification like this on their device:

[0485] "The next application deadline is tomorrow. Don't forget."

[0486] Specific examples

[0487] Server processing example

[0488] The server accesses the MySQL database every day at 2 AM and executes the following query:

[0489] sql

[0490] SELECT FROM service_info WHERE update_time >= CURDATE();

[0491] This query retrieves the service information updated for that day.

[0492] User processing example

[0493] If a user types "I'm busy today," the emotion engine will determine that the user is stressed and reduce the frequency of reminders, specifically changing the usual hourly reminders to every three hours.

[0494] Prompt Sentence Examples

[0495] Examples of prompts to input to a generative AI model might include:

[0496] If the user types "I'm busy today," how would the emotion engine adjust the frequency of reminders?

[0497] This prompt tells the generative AI model how to adjust reminders based on the user's emotional state.

[0498] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0499] Step 1:

[0500] The server retrieves the service information and the internal application deadline from the database.

[0501] Input: Database connection information, SQL query

[0502] What happens: The server connects to the MySQL database and executes the following SQL query:

[0503] sql

[0504] SELECT FROM service_info;

[0505] SELECT FROM application_deadlines;

[0506] Output: Data set of acquired service information and internal application deadlines

[0507] Step 2:

[0508] The server periodically updates the information it has obtained.

[0509] Input: Recurring job schedule, database connection information

[0510] What happens: The server runs a cron job every day at 2 AM to retrieve the latest information from the database. For example, it runs the following script:

[0511] bash

[0512] ! / bin / bash

[0513] mysql -u username -p password -e "SELECT FROM service_info;" > / path / to / service_info.json

[0514] mysql -u username -p password -e "SELECT FROM application_deadlines;" > / path / to / application_deadlines.json

[0515] Output: JSON file containing the latest service information and internal application deadlines

[0516] Step 3:

[0517] A user accesses the system and the emotion engine recognizes the user's emotions.

[0518] Input: User input data (e.g., "I'm busy today")

[0519] How it works: When a user logs into the system and types "I'm busy today," the emotion engine analyzes the text and determines that the user is stressed.

[0520] Output: User's emotional state (e.g., stress)

[0521] Step 4:

[0522] The emotional engine adjusts the timing and content of reminders according to the user's emotional state.

[0523] Input: User's emotional state, reminder settings information

[0524] How it works: The emotion engine adjusts the timing and content of reminders based on the user's emotional state. For example, if it determines that the user is feeling stressed, it will change reminders from every hour to every three hours.

[0525] Output: Adjusted reminder timing and content

[0526] Step 5:

[0527] The device displays a reminder to the user.

[0528] Input: Adjusted reminder timing and content

[0529] Specific behavior: The device will display a notification to the user based on the adjusted reminder timing. For example, the following notification will be displayed:

[0530] "The next application deadline is tomorrow. Don't forget."

[0531] Output: Reminder notification displayed to the user

[0532] (Application example 1)

[0533] Next, a description will be given of Application Example 1 of Embodiment 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."

[0534] In conventional production management systems, reminders are sent without taking into account the emotional state of the workers, which often causes stress for the workers and reduces production efficiency. In addition, the timing and content of reminders are fixed, which means that flexible responses based on the situation of each worker are not possible.

[0535] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means for reading service information (delivery dates, etc.) and in-house application deadlines, means for determining what tasks should be completed by when in relation to the customer's desired delivery date, means for reminding sales of the determination result, means for recognizing the user's emotional state using an emotion engine and adjusting the timing and content of reminders, and means for periodically acquiring and updating information using a database management system. This makes it possible to provide reminders according to the emotional state of workers, thereby improving production efficiency and reducing worker stress.

[0536] "Service information" refers to important information related to business operations, such as delivery dates and internal application deadlines.

[0537] "Internal application deadline" refers to the deadline by which various internal applications must be completed.

[0538] "Customer desired delivery date" refers to the delivery date of the product desired by the customer.

[0539] A "task" refers to an operation or activity performed to achieve a specific purpose.

[0540] A "reminder" is a notification that helps you avoid forgetting a specific task or deadline.

[0541] An "emotion engine" refers to technology that recognizes the user's emotional state and adjusts the system's behavior based on that information.

[0542] "User's emotional state" refers to the psychological state, such as stress or relaxation, that the user feels.

[0543] A "database management system" refers to software for creating, managing, and operating a database.

[0544] "Regularly acquiring and updating information" means collecting necessary information at regular intervals and keeping it up to date.

[0545] A "machine learning algorithm" refers to a computational method that automatically learns from data and makes predictions and judgments.

[0546] The system for carrying out this invention is configured as follows: The server includes means for reading service information (delivery dates, etc.) and in-house application deadlines, means for determining what tasks should be completed by when in relation to the customer's desired delivery date, means for reminding sales of the determination results, means for recognizing the user's emotional state using an emotion engine and adjusting the timing and content of reminders, and means for periodically acquiring and updating information using a database management system.

[0547] Program processing explanation

[0548] The server first uses a database management system (such as SQLite) to periodically retrieve and update service information and internal application deadlines. This ensures that the latest information is always available. Next, it uses an emotion engine (such as EmotionEngine) to recognize the user's emotional state. The emotion engine analyzes the user's facial expressions and voice through cameras and sensors to determine their emotional state, such as stress or relaxation.

[0549] After recognizing the user's emotional state, the server can adjust the timing and content of reminders based on that information. For example, if the user is stressed, the server will reduce the frequency of reminders and only remind them about important tasks. On the other hand, if the user is relaxed, the server will continue to remind them about all tasks as usual.

[0550] Specific examples

[0551] For example, if a factory worker is feeling stressed, the server will remind him / her only about important tasks and postpone other tasks. This reduces the worker's stress and improves production efficiency. On the other hand, if the worker is relaxed, the server will remind him / her about all tasks as usual, promoting efficient work.

[0552] Prompt Sentence Examples

[0553] By entering the following prompt statements into the generative AI model, you can generate system design and program code.

[0554] Design a system that adjusts the timing and content of reminders based on the user's emotional state. Retrieve the production schedule from a database and use an emotion engine to recognize the worker's emotions. If the worker is stressed, reduce the frequency of reminders and only remind them about important tasks. Please provide the specific program code.

[0555] In this way, the server can provide reminders according to the user's emotional state, thereby improving production efficiency and reducing worker stress.

[0556] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0557] Step 1:

[0558] The server uses a database management system (such as SQLite) to periodically retrieve and update service information and internal application deadlines. The input is a query from the database, and the output is the latest service information and internal application deadlines. In this step, an SQL query is executed against the database to retrieve the required information.

[0559] Step 2:

[0560] The server uses an emotion engine (such as EmotionEngine) to recognize the user's emotional state. The input is the user's facial expression and voice data acquired from a camera or sensor, and the output is the user's emotional state (stress, relaxation, etc.). In this step, the emotion engine analyzes the facial expression and voice data and determines the user's emotional state.

[0561] Step 3:

[0562] The server adjusts the timing and content of reminders based on the user's emotional state. The inputs are the service information and internal application deadlines obtained in step 1, and the user's emotional state obtained in step 2, and the output is an adjusted reminder schedule. In this step, if the user is feeling stressed, the server adjusts the schedule to reduce the frequency of reminders and only remind them of important tasks.

[0563] Step 4:

[0564] The server sends reminders based on the adjusted reminder schedule. The input is the reminder schedule adjusted in step 3, and the output is a reminder notification for the user. This step involves sending reminders to the user using email or a notification system.

[0565] Step 5:

[0566] The server records the result of the reminder transmission in the database. The input is the result of the reminder transmission, and the output is the updated database record. This step checks whether the reminder was sent successfully and stores the result in the database.

[0567] Through the above steps, the server can provide reminders according to the user's emotional state, thereby improving production efficiency and reducing worker stress.

[0568] Example 2

[0569] Next, a description will be given of Example 2 of Form 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."

[0570] With conventional systems, it was difficult to determine the appropriate tasks and their deadlines based on the customer's desired delivery date, and they were unable to provide reminders that took into account the user's emotional state. As a result, there were problems such as project progress being delayed and users' stress increasing.

[0571] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for reading service information and internal application deadlines, a means for determining what tasks should be completed by when in relation to the customer's desired delivery date, a means for notifying the determination result, a means for collecting user behavior data, a means for predicting the user's emotional state, a means for determining the content of reminders based on the prediction result, and a means for notifying the content of reminders. This makes it possible to determine appropriate tasks and their deadlines in relation to the customer's desired delivery date, and to provide reminders that take the user's emotional state into consideration.

[0572] "Service information" is information related to the services provided by the customer, including delivery dates and requirements.

[0573] "Internal application deadline" refers to the deadline required for procedures and approvals within a company.

[0574] "Customer Desired Delivery Date" refers to the date the customer desires for the project or service to be completed.

[0575] A "task" refers to a specific task or activity required to progress a project or business.

[0576] "Means of determination" refers to methods and techniques for determining the optimal tasks and their deadlines based on specific conditions and data.

[0577] "Means of notification" refers to the methods and techniques for communicating the results of judgments and reminders to users and related parties.

[0578] "Behavioral data" refers to information about a user's behavior and reactions, including task completion times and survey results.

[0579] "Emotional state" refers to the user's psychological state and emotions, including stress and satisfaction.

[0580] "Reminder content" refers to the content of the notification or message sent to the user.

[0581] This invention is a system that determines appropriate tasks and their deadlines based on a customer's desired delivery date, and also provides reminders that take into account the user's emotional state. Specific embodiments of this system are described below.

[0582] System configuration

[0583] server

[0584] The server has the following functions:

[0585] 1. Function to read service information and internal application deadlines: Obtain service information and internal application deadlines from the database. Specifically, extract data using SQL queries.

[0586] 2. Function to determine tasks based on the customer's desired delivery date: Using a machine learning algorithm, we predict the tasks required and their deadlines based on the customer's desired delivery date. Specifically, we use Scikit-learn's RandomForestRegressor.

[0587] 3. Function to notify the judgment result: The judgment result is notified to the user via email or in-app notification.

[0588] 4. Ability to collect user behavior data: Collect user behavior data (task completion time, survey results, etc.).

[0589] 5. Function to predict the user's emotional state: Based on the collected behavioral data, the system uses a machine learning algorithm to predict the user's emotional state. Specifically, it uses an LSTM model built using Keras.

[0590] 6. Function to determine the content of reminders: Based on the prediction results, the content of reminders for the user is determined.

[0591] 7. Function to notify reminder content: The determined reminder content is notified to the user via email or in-app notification.

[0592] Terminal

[0593] The terminal has the following features:

[0594] 1. Ability to collect user behavioral data: Collects behavioral data such as task completion time and survey results.

[0595] 2. Function to notify the user of reminder content: Notify the user of the reminder content received from the server, specifically using in-app notifications or pop-up messages.

[0596] User

[0597] The user does the following:

[0598] 1. Entering the customer's desired delivery date: Enter the customer's desired delivery date in the system's input form.

[0599] 2. Answer the questionnaire: Answer the questionnaire that appears before starting the task.

[0600] Specific examples

[0601] Examples of task decisions based on customer desired delivery dates:

[0602] A user enters into the system's input form, "I want to complete the project by December 25, 2023."

[0603] The server runs an SQL query such as "SELECT FROM projects WHERE type='similar'" against the database to retrieve data on similar past projects.

[0604] The server uses Scikit-learn's RandomForestRegressor to generate prediction results such as "Requirements definition will be completed by November 1, 2023, and design will be completed by November 15, 2023."

[0605] The server displays the prediction results to the user, who can then view the specific tasks and their deadlines on the screen.

[0606] Examples of predicting and reminding users' emotional state:

[0607] Before the user starts the task, the terminal displays a questionnaire and asks questions such as, "How are you feeling right now?" The user answers, "I feel stressed."

[0608] The server inputs this data into an LSTM model built using Keras and predicts that "users feel stressed every Monday morning."

[0609] The server generates a reminder message such as "Take a deep breath and relax."

[0610] On Monday morning, the device will notify the user with a message such as "Take a deep breath and relax."

[0611] Example prompt for a generative AI model:

[0612] The client wants the project completed by December 25, 2023. Based on past project data, what tasks are required and when?

[0613]

[0614] I predict that my users will feel stressed every Monday morning preparing for a meeting. What reminder messages can I use to reduce this stress?

[0615] The above is a specific embodiment for carrying out the present invention.

[0616] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0617] Step 1: Enter customer desired delivery date

[0618] The user enters the customer's desired delivery date into the system's input form. For example, they might enter, "I want the project completed by December 25, 2023." This input data is sent to the server.

[0619] Step 2: Obtaining historical data

[0620] The server retrieves past project data from the database. Specifically, it uses an SQL query to extract data about similar projects. The input is the customer's desired delivery date, and the output is data about similar past projects.

[0621] Step 3: Applying the machine learning model

[0622] The server uses the acquired data to input a machine learning model. It uses Scikit-learn's RandomForestRegressor to predict the duration and deadline of each task. The input is past project data, and the output is the predicted tasks and their deadlines.

[0623] Step 4: Present tasks and deadlines

[0624] The server presents the prediction results to the user. For example, it displays specific tasks and deadlines, such as "Requirements definition will be completed by November 1, 2023, and design will be completed by November 15, 2023." The input is the prediction results, and the output is the tasks and deadlines displayed to the user.

[0625] Step 5: Collect user behavior data

[0626] The terminal collects user behavior data. For example, it records the time it takes to complete a task or the results of a questionnaire given before starting the task. The input is the user behavior data, and the output is the collected data.

[0627] Step 6: Applying the emotion prediction model

[0628] The server uses the collected data to input into an emotion prediction model. It predicts the user's emotional state using an LSTM model built using Keras. The input is the user's behavioral data, and the output is the predicted emotional state.

[0629] Step 7: Decide what to remind

[0630] The server determines the content of the reminder based on the prediction result. For example, if the server predicts that the user will feel stressed, it generates a message to help them relax. The input is the predicted emotional state, and the output is the reminder content.

[0631] Step 8: Execute the reminder

[0632] The device notifies the user of the determined reminder content. For example, it displays a message such as "Take a deep breath and relax." The input is the reminder content, and the output is the message to be notified to the user.

[0633] (Application example 2)

[0634] Next, a description will be given of Application Example 2 of Form 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."

[0635] While conventional task management systems can estimate optimal tasks and their deadlines based on a customer's desired delivery date, they have the problem of being unable to provide reminders that take the user's emotional state into account, making it difficult to reduce user stress. Furthermore, they are unable to provide appropriate support for tasks that cause users stress, which can lead to a decline in work efficiency.

[0636] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0637] In this invention, the server includes a means for reading service information (delivery dates, etc.) and in-house application deadlines, a means for determining what tasks should be completed by when in relation to the customer's desired delivery date, a means for reminding the sales department of the determination result, a means for learning and predicting the user's emotional state, and a means for reminding according to the emotional state. This makes it possible to provide reminders that take the user's emotional state into consideration, reducing user stress and improving work efficiency.

[0638] "Service information" refers to important information related to business operations, such as delivery dates and internal application deadlines.

[0639] "Customer desired delivery date" refers to the delivery deadline desired by the customer.

[0640] A "task" refers to the work or activity that must be performed to achieve a specific goal.

[0641] "Decision-making means" refers to a means for estimating optimal tasks and their deadlines using machine learning algorithms, etc.

[0642] "Reminding means" refers to a means for notifying the user of the judgment result.

[0643] "Emotional state" refers to the user's current psychological state.

[0644] "Learning means" refers to a means for learning patterns from past data.

[0645] "Prediction means" refers to a means for predicting future states based on learned data.

[0646] "Stress reduction reminders" refer to reminders that are given to users in a way that reduces stress when performing tasks that cause stress to the user.

[0647] A system for implementing the present invention is configured as follows.

[0648] System Configuration

[0649] The server includes a means for reading service information (delivery dates, etc.) and internal application deadlines, a means for determining what tasks should be completed by when in relation to the customer's desired delivery date, a means for reminding sales of the results of the determination, a means for learning and predicting the user's emotional state, and a means for providing reminders according to the user's emotional state.

[0650] Hardware and software used

[0651] Hardware: Factory robots, sensors (collecting user behavior data)

[0652] Software: Python, scikit-learn (machine learning library)

[0653] Data processing and calculation

[0654] The server first collects past task data and user behavior data. Then, using machine learning algorithms, it trains a model to estimate optimal task deadlines and a model to predict emotional states. Using new tasks and user behavior data as input, it estimates task deadlines and emotional states, and generates reminder messages according to the emotional states.

[0655] Specific examples

[0656] For example, when a factory robot assembles parts, the server estimates the optimal deadline for the task based on past data. If the user feels stressed before performing this task, the server generates a reminder message saying, "Take a deep breath and start assembling the parts. You can do it!"

[0657] Prompt Sentence Examples

[0658] For the new task "Assemble parts," estimate the optimal deadline based on past data. Also, if the user feels stressed before performing this task, generate a reminder message to reduce stress.

[0659] In this way, the system can take the user's emotional state into account and provide reminders in a way that reduces stress, thereby improving the user's work efficiency.

[0660] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0661] Step 1:

[0662] The server reads service information (delivery date, etc.) and internal application deadlines.

[0663] Input: Service information, internal application deadline

[0664] Output: Loaded service information, internal application deadline

[0665] Specific operation: The server retrieves service information and internal application deadlines from the database and loads them into memory.

[0666] Step 2:

[0667] The server collects past task data and user behavior data.

[0668] Input: Past task data, user behavior data

[0669] Output: Collected task data, behavioral data

[0670] Specific operation: The server collects past task data and user behavior data from sensors and log files and stores them in a database.

[0671] Step 3:

[0672] The server uses machine learning algorithms to train a model that estimates optimal deadlines for tasks.

[0673] Input: Collected task data

[0674] Output: A trained task deadline estimation model

[0675] What it does: The server uses the scikit-learn library to train a random forest regression model on the collected task data.

[0676] Step 4:

[0677] The server uses machine learning algorithms to train a model that predicts emotional states.

[0678] Input: Collected user behavior data

[0679] Output: A trained emotional state prediction model

[0680] What it does: The server uses the scikit-learn library to train a random forest regression model based on collected user behavior data.

[0681] Step 5:

[0682] The server takes the new task and the user's behavioral data as input and estimates the task's deadline.

[0683] Input: New task data, a trained task deadline estimation model

[0684] Output: Estimated task deadline

[0685] What it does: The server inputs new task data into the trained model and estimates the optimal task deadline.

[0686] Step 6:

[0687] The server takes the behavioral data of a new user as input and predicts the emotional state.

[0688] Input: New user behavior data, trained emotional state prediction model

[0689] Output: Predicted emotional state

[0690] What it does: The server inputs new user behavior data into the trained model to predict the emotional state.

[0691] Step 7:

[0692] The server generates a reminder message according to the emotional state.

[0693] Input: predicted emotional state, task information

[0694] Output: Reminder message

[0695] Specific operation: The server generates a reminder message to reduce stress based on the predicted emotional state and task information.

[0696] Step 8:

[0697] The server notifies the user of the generated remind message.

[0698] Input: Reminder message

[0699] Output: User notification

[0700] What happens: The server uses email or a notification system to send the generated reminder message to the user.

[0701] Example 3

[0702] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0703] In the conventional system, it was possible to determine tasks based on service information and internal application deadlines and send reminders to salespeople, but it was not possible to send reminders that took into account the user's emotional state. As a result, it was not possible to send effective reminders that reflected the user's emotions, which led to a problem of reduced efficiency in sales activities.

[0704] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0705] In this invention, the server includes means for reading service information (delivery dates, etc.) and in-house application deadlines, means for determining what tasks should be completed by when in relation to the customer's desired delivery date, means for reminding the sales department of the determination results, means for collecting user input data, means for analyzing the user's emotional state, means for generating the contents of the reminder email based on the results of the emotion analysis, and means for sending the generated reminder email. This enables effective reminders that take the user's emotional state into consideration.

[0706] "Service information" refers to important information regarding the provision of services, such as delivery dates and internal application deadlines.

[0707] "Internal application deadline" refers to the deadline for completing the necessary procedures within the company.

[0708] "Customer desired delivery date" refers to the delivery date of a service or product desired by the customer.

[0709] A "task" refers to the work or activity that must be performed to achieve a specific goal.

[0710] A "remind" refers to a re-notification of specific information or tasks.

[0711] "User input data" refers to data such as text or voice that a user provides to the system.

[0712] "Emotional state" refers to the emotions such as joy, sadness, anger, etc. that a user is feeling.

[0713] "Emotion analysis" refers to the process of analyzing a user's input data to determine their emotional state.

[0714] "Reminder email" refers to an email sent to notify you of specific information or tasks.

[0715] A "natural language processing algorithm" refers to an algorithm that analyzes text data to understand meaning and emotion.

[0716] MODE FOR CARRYING OUT THE INVENTION

[0717] The present invention relates to a reminder system that takes into account the emotional state of a user. A specific embodiment of this system will be described below.

[0718] System configuration

[0719] This system consists of three main components: a server, a terminal, and a user. The server reads service information and internal application deadlines, determines the tasks required to meet the customer's desired delivery date, and sends reminders of the results to the sales department. It also collects user input data, analyzes their emotional state, and generates and sends reminder emails based on the results.

[0720] Hardware and software used

[0721] The server is a computer equipped with a high-performance processor and large memory capacity. Sentiment analysis requires software to run natural language processing algorithms, specifically "IBM Watson (registered trademark)" and "Google Cloud Natural Language API." Reminder emails are sent using email systems such as "Microsoft (registered trademark) Outlook" and "Gmail."

[0722] Data processing and calculation

[0723] The server first collects user input data. Users enter product reviews and feedback in text format and send it to the server via their devices. The server then passes this text data to a natural language processing algorithm to analyze the user's emotional state. The analysis results in a determination of whether the user is feeling emotions such as joy, sadness, or anger.

[0724] Next, the server generates the content of the reminder email based on the results of the sentiment analysis. For example, if it is determined that the user is feeling happy, the server generates a reminder email with the content, "The user is very satisfied with the product. Please consider offering a special discount coupon to further enhance the user's happiness."

[0725] Finally, the server automatically sends the generated reminder email to the sales department via the email system, who then receives the email and considers what action to take to further improve user satisfaction.

[0726] Specific examples

[0727] As a concrete example, consider the case where a user posts a review of a product. If the user's review contains the content "This product is truly amazing!", the sentiment analysis algorithm will determine that the user is feeling happy. Based on this determination, the server will send a reminder email to the sales department stating, "The user is very satisfied with the product. Please consider offering a special discount coupon to further enhance their happiness."

[0728] Prompt Sentence Examples

[0729] "Analyze user reviews to determine their emotional state. Then generate a reminder email to send to sales based on that emotional state."

[0730] In this way, the system can send effective reminders to salespeople that take into account the emotional state of the user. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0731] Step 1:

[0732] Users input product reviews and feedback in text format. The terminal sends this input data to the server. The input data is the text information entered by the user, and the output is the text data sent to the server.

[0733] Step 2:

[0734] The server passes the received user input data to an emotion analysis algorithm. Specifically, the server analyzes the text data using a "natural language processing algorithm." The input is the user's text data, and the output is an analysis result that indicates the user's emotional state (happiness, sadness, anger, etc.).

[0735] Step 3:

[0736] The server generates the content of the reminder email based on the results of the sentiment analysis. For example, if it is determined that the user is feeling happy, the server generates a reminder email with the content, "The user is very satisfied with the product. To further enhance their happiness, please consider offering a special discount coupon." The input is the result of the sentiment analysis, and the output is the content of the generated reminder email.

[0737] Step 4:

[0738] The server automatically sends the generated reminder email to the sales department using an email system. Specifically, the server sends the reminder email using the "email system." The input is the content of the generated reminder email, and the output is the reminder email sent to the sales department.

[0739] Step 5:

[0740] The sales department reviews the reminder emails they receive and considers actions to further increase user satisfaction. The input is the reminder email received by the sales department, and the output is the specific actions that the sales department will take.

[0741] In this way, the system can send effective reminders to salespeople that take into account the user's emotional state.

[0742] (Application example 3)

[0743] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0744] Conventional reminder systems send uniform messages without considering the user's emotional state, which limits the effectiveness of reminders. Furthermore, there was no way to provide appropriate reminders based on the user's emotions, making it difficult to maximize the user's motivation to purchase. This has led to a need to improve the effectiveness of reminders and encourage users to make purchases.

[0745] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0746] In this invention, the server includes means for reading service information (delivery dates, etc.) and in-house application deadlines, means for determining what tasks should be completed by when in relation to the customer's desired delivery date, means for reminding the sales department of the determination result, means for detecting the user's emotional state, means for adjusting the content of the reminder according to the emotional state, and means for automatically sending reminder emails. This enables effective reminders that take the user's emotional state into consideration, maximizing the user's desire to purchase.

[0747] "Service information" refers to important information related to business operations, such as delivery dates and internal application deadlines.

[0748] "Internal application deadline" refers to the final deadline for completing the necessary procedures within the company.

[0749] "Customer desired delivery date" refers to the delivery date of the product desired by the customer.

[0750] A "task" refers to the work or activity required to achieve a specific purpose.

[0751] "Decision result" refers to the result of the system deciding the timing and content of task execution.

[0752] "Sales" refers to a job that involves selling products and services.

[0753] A "remind" refers to sending a notification or message to encourage a specific action.

[0754] "User's emotional state" refers to the type and intensity of the emotion the user is currently feeling.

[0755] "Reminder Email" refers to a notification sent via email to encourage a specific action.

[0756] A "machine learning algorithm" refers to a computational method that automatically learns from data and makes predictions and judgments.

[0757] A system for carrying out this invention has the following configuration: The server includes means for reading service information (delivery date, etc.) and in-house application deadlines, means for determining what tasks should be completed by when in relation to the customer's desired delivery date, means for reminding sales of the determination result, means for detecting the user's emotional state, means for adjusting the content of the reminder depending on the user's emotional state, and means for automatically sending reminder emails.

[0758] Program processing explanation

[0759] Loading service information

[0760] The server reads service information (delivery dates and internal application deadlines) from a database, which can be, for example, an SQL database.

[0761] Task Judgment

[0762] The server uses a machine learning algorithm to determine what tasks should be completed by when in accordance with the customer's desired delivery date. This algorithm learns from past data and generates an optimal task schedule.

[0763] Implementing reminders

[0764] The server sends reminders to the salesperson based on the results of the judgment. The reminders are sent via email.

[0765] Emotional state detection

[0766] The server analyzes the user's behavioral data and past purchase history and uses a generative AI model to detect the user's emotional state. For example, if a user is very satisfied with a recent purchase, the server detects the emotion as "joy."

[0767] Adjustment of reminder content

[0768] The server tailors the reminder content depending on the detected emotional state: for example, if the user is feeling "joy," the reminder email will include a message that reinforces that emotion.

[0769] Sending reminder emails

[0770] The server automatically sends a reminder email containing the adjusted reminder content, for example, using the SMTP protocol.

[0771] Specific examples

[0772] For example, if a user is very happy with a recent purchase, we can detect that emotion and send them a message saying, "You have a great product in your cart! Buy now and enjoy even more!"

[0773] Prompt Sentence Examples

[0774] Create a program that detects the user's emotional state and sends them a reminder email based on that emotion. If the user is feeling happy, include a message that reinforces that emotion. Use the following information:

[0775] User ID: user123

[0776] Cart information: get_user_cart(user_id)

[0777] Emotion detection: detect_emotion(user_id)

[0778] Get email address: get_user_email(user_id)

[0779] Sending email: smtplib

[0780] In this way, effective reminders that take into account the user's emotional state are possible, thereby maximizing the user's motivation to purchase.

[0781] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0782] Step 1:

[0783] The server reads service information (delivery dates and internal application deadlines) from the database. Database connection information and a query are required as input, and the service information is obtained as output. Specifically, the server executes the SQL query and obtains the results.

[0784] Step 2:

[0785] The server uses a machine learning algorithm to determine what tasks should be completed by when in relation to the customer's desired delivery date. Service information and the customer's desired delivery date are required as input, and a task schedule is obtained as output. Specifically, the server uses a model learned from past data to generate an optimal task schedule.

[0786] Step 3:

[0787] The server sends a reminder to the salesperson based on the judgment result. The task schedule is required as input, and the content of the reminder email is obtained as output. Specifically, the server embeds the task schedule in the reminder email template and generates the email content.

[0788] Step 4:

[0789] The server analyzes the user's behavioral data and past purchase history and uses a generative AI model to detect the user's emotional state. The input is the user's behavioral data and purchase history, and the output is the emotional state. Specifically, the server inputs the data into the generative AI model and estimates the emotional state.

[0790] Step 5:

[0791] The server adjusts the content of the reminder email according to the detected emotional state. The inputs are the emotional state and the content of the reminder email, and the output is the adjusted content of the reminder email. Specifically, the server selects a message based on the emotional state and updates the content of the reminder email.

[0792] Step 6:

[0793] The server automatically sends a reminder email containing the adjusted reminder content. As input, the adjusted reminder content and the user's email address are required, and as output, the reminder email is sent. Specifically, the server sends the email using the SMTP protocol.

[0794] 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.

[0795] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ) 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.

[0796] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[0797] 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.

[0798] [Second embodiment]

[0799] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0800] 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.

[0801] 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.

[0802] 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).

[0803] 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.

[0804] 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.

[0805] 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).

[0806] 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.

[0807] 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.

[0808] 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.

[0809] 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.

[0810] 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.

[0811] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0812] "Example 1"

[0813] One embodiment of the present invention includes a means for reading service information (such as delivery dates) and in-house application deadlines from a database. This means can be realized, for example, by using a database management system. The database management system periodically obtains the service information and in-house application deadlines and updates them as necessary.

[0814] "Example 2"

[0815] There are also ways to determine what tasks should be completed by when in relation to the customer's desired delivery date. This can be achieved, for example, using machine learning algorithms. Machine learning algorithms learn from past data and estimate the optimal tasks and their deadlines for new service information and internal application deadlines.

[0816] "Example 3"

[0817] Furthermore, there is also a means for reminding the salesperson of the decision result. This means can be realized, for example, by using an email system. The email system automatically sends a reminder email to the salesperson based on the decision result.

[0818] The processing flow of each embodiment will be described below.

[0819] "Example 1"

[0820] Step 1: The database management system is operational and service information (delivery dates, etc.) and internal application deadlines are read from the database.

[0821] Step 2: Based on the information loaded, calculate the required tasks and their deadlines. For example, calculate the start and end dates for each task by working backwards from the delivery date requested by the customer.

[0822] Step 3: Based on the calculation results, a reminder email is sent to the sales team, clearly stating what tasks need to be completed and by when.

[0823] "Example 2"

[0824] Step 1: Machine learning algorithms are put to work, learning from past data.

[0825] Step 2: When new service information and internal application deadlines are entered, the trained model is used to estimate the optimal task and its deadline.

[0826] Step 3: Based on the estimation results, a reminder email is sent to the sales team, clearly stating what tasks need to be completed and by when.

[0827] "Example 3"

[0828] Step 1: The email system is operational and automatically sends reminder emails to sales staff based on the results of the decision.

[0829] Step 2: The email specifies what task needs to be completed by when, and which client and project it relates to.

[0830] Step 3: Sales receives the email and follows the instructions to complete the task.

[0831] Example 1

[0832] Next, a description will be given of Example 1 of Form 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."

[0833] In the previous system, management of service information and internal application deadlines was often done manually, resulting in the problem of time-consuming updates and confirmations of information. Furthermore, there was a lack of a way to determine the appropriate tasks for customer desired delivery dates and to send reminders to sales staff, which could lead to a decline in work efficiency. Furthermore, there was no way for users to quickly check the latest information, which could lead to work delays and mistakes.

[0834] 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.

[0835] In this invention, the server includes a means for reading service information and internal application deadlines, a means for determining what tasks should be completed by when in relation to the customer's desired delivery date, a means for reminding the sales department of the determination result, a means for periodically obtaining service information and internal application deadlines using a database management system and updating them as necessary, a means for a terminal to access the server to obtain data and display it to the user, and a means for the user to check the information through the terminal. This automates the management of service information and internal application deadlines, allowing for quick information updates and confirmations, improving work efficiency. Furthermore, by determining the appropriate tasks in relation to the customer's desired delivery date and reminding the sales department, it is possible to prevent work delays and errors.

[0836] "Service Information" refers to important information about the service, such as delivery dates and details of the services provided.

[0837] "Internal application deadline" refers to the deadline by which various internal applications must be completed.

[0838] "Database management system" means a software system for creating, managing, and manipulating databases.

[0839] A "server" refers to a computer system that provides data and services over a network.

[0840] "Terminal" refers to a device that allows a user to access a server and obtain data.

[0841] "User" refers to a person who uses the system to check service information and internal application deadlines.

[0842] "Reading means" refers to a method or device for obtaining the required information from the database.

[0843] "Means for determining" refers to a method or device for determining an appropriate task or action based on certain conditions.

[0844] "Means for reminding" refers to a method or device for notifying a user of specific information or tasks.

[0845] "Means for periodically acquiring and updating as necessary" refers to a method or device for acquiring data at regular intervals and updating the data if there are any changes.

[0846] "Means for accessing and obtaining data" refers to a method or device for connecting to a server and obtaining the required information.

[0847] The "display means" refers to a method or device for visually presenting the acquired information to the user.

[0848] "Means for checking" refers to a method or device for a user to view the acquired information and check its contents.

[0849] MODE FOR CARRYING OUT THE INVENTION

[0850] The present invention is a system for efficiently managing service information and in-house application deadlines and providing the information promptly to users. A specific embodiment of this system will be described below.

[0851] Server Processing

[0852] The server uses a database management system (DBMS) to read service information and internal application deadlines from a database. Specifically, a DBMS such as MySQL or PostgreSQL is used. The server periodically executes queries to obtain the latest service information and internal application deadlines, and updates the database as necessary. For example, the server executes the following SQL query:

[0853] sql

[0854] SELECT FROM service_info;

[0855] SELECT FROM internal_deadlines;

[0856] This will capture all data on service information and internal application deadlines.

[0857] Terminal handling

[0858] The device accesses the server using a web browser (e.g., Google Chrome) to obtain the latest service information and internal application deadlines. Specifically, it accesses the following URL:

[0859] http: / / example.com / api / service_info

[0860] http: / / example.com / api / internal_deadlines

[0861] This allows the device to retrieve JSON formatted data from the server. The device then parses the retrieved JSON data and displays it in a format that is easy for the user to view. For example, the device uses HTML and JavaScript to display the data as follows:

[0862] html

[0863]

[0864] <h2> Service Information< / h2>

[0865]

[0866] Service Name: New Service, Delivery Date: 2023-12-31

[0867]

[0868]

[0869]

[0870] <h2> Internal application deadline< / h2>

[0871]

[0872] Application Name: New Project, Deadline: 2023-11-30

[0873]

[0874]

[0875] This HTML code displays service information and internal application deadlines to the user.

[0876] User operations

[0877] The user checks the displayed service information and internal application deadlines through the device's web browser. For example, the user can use Google Chrome to check the displayed information and find out the latest delivery dates and application deadlines. The user accesses the following URL:

[0878] http: / / example.com / dashboard

[0879] By accessing this URL, users can check the latest service information and internal application deadlines.

[0880] Example prompts for generative AI models

[0881] Below are some example prompts to input to a generative AI model:

[0882] "Please let me know the latest service information and internal application deadlines."

[0883] Using this prompt, the generative AI model provides up-to-date service information and internal application deadlines.

[0884] In this way, the management of service information and internal application deadlines is automated, allowing information to be updated and confirmed quickly, improving work efficiency and preventing work delays and errors.

[0885] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0886] Step 1:

[0887] The server retrieves the service information and the internal application deadline from the database.

[0888] Input: Database connection information

[0889] What happens: The server connects to the MySQL database and executes the following SQL query:

[0890] sql

[0891] SELECT FROM service_info;

[0892] SELECT FROM internal_deadlines;

[0893] Data processing: Convert the query results into JSON format.

[0894] Output: JSON data of service information and internal application deadline

[0895] Step 2:

[0896] The server updates the retrieved data as needed.

[0897] Input: New service information and internal application deadlines

[0898] What happens: The server checks the retrieved data and, if there is new information, updates the database by executing the following SQL query:

[0899] sql

[0900] INSERT INTO service_info (service_name, due_date) VALUES ('New Service', '2023-12-31');

[0901] Data manipulation: Adding new data to existing data.

[0902] Output: Updated database

[0903] Step 3:

[0904] The terminal accesses the server to obtain the data.

[0905] Input: Server API endpoint URL

[0906] Specific operation: The device accesses the following URL using a web browser (e.g., Google Chrome):

[0907] http: / / example.com / api / service_info

[0908] http: / / example.com / api / internal_deadlines

[0909] Data processing: Analyze the JSON data obtained from the server.

[0910] Output: Parsed service information and internal application deadline data

[0911] Step 4:

[0912] The terminal displays the acquired data to the user.

[0913] Input: Parsed service information and internal application deadline data

[0914] What happens: The device uses HTML and JavaScript to display the data as follows:

[0915] html

[0916]

[0917] <h2> Service Information< / h2>

[0918]

[0919] Service Name: New Service, Delivery Date: 2023-12-31

[0920]

[0921]

[0922]

[0923] <h2> Internal application deadline< / h2>

[0924]

[0925] Application Name: New Project, Deadline: 2023-11-30

[0926]

[0927]

[0928] Data processing: Convert the acquired data into HTML format.

[0929] Output: Service information and internal application deadlines displayed to users

[0930] Step 5:

[0931] The user checks the information through the terminal.

[0932] Input: Device web browser

[0933] What happens: The user opens a web browser on their device and accesses the following URL:

[0934] http: / / example.com / dashboard

[0935] Data processing: Check the displayed information.

[0936] Output: Service information confirmed by the user and internal application deadline

[0937] In this way, the management of service information and internal application deadlines is automated, allowing information to be updated and confirmed quickly, improving work efficiency and preventing work delays and errors.

[0938] (Application example 1)

[0939] Next, a description will be given of Application Example 1 of Form 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."

[0940] In logistics centers, managing delivery dates and internal application deadlines is extremely important, but there is a lack of systems that can efficiently collect this information and suggest actions at the appropriate time. There is also a need for a function that suggests the optimal action based on prompts entered by the user.

[0941] 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.

[0942] In this invention, the server includes a means for reading service information (delivery dates, etc.) and in-house application deadlines, a means for determining what tasks should be completed by when in relation to the customer's desired delivery date, a means for reminding sales of the determination results, a means for using a generative AI model to propose optimal actions based on prompts entered by the user, and a means for periodically acquiring service information and application deadlines using a database management system and updating them as necessary. This enables efficient management of delivery dates and application deadlines at the logistics center and the proposal of optimal actions to users.

[0943] "Service information" is information relating to delivery dates and details of the services provided.

[0944] The "internal application deadline" is the deadline for carrying out necessary procedures and applications within the company.

[0945] "Customer desired delivery date" is the delivery date desired by the customer.

[0946] A "task" is an operation or activity that must be performed to achieve a specific purpose.

[0947] A "remind" is an act of drawing attention so that you do not forget.

[0948] A "generative AI model" is an algorithm that uses artificial intelligence to generate optimal actions based on user input.

[0949] A "prompt sentence" is a question or instruction sentence that a user enters into a system.

[0950] A "database management system" is software for creating, managing, and operating databases.

[0951] "Periodic acquisition" means collecting information at regular time intervals.

[0952] "Updating" means replacing existing information with new information.

[0953] The system for implementing this invention is designed to efficiently manage delivery dates and in-house application deadlines at a logistics center. The system includes the following main components:

[0954] server

[0955] The server has a means of reading service information (delivery dates, etc.) and internal application deadlines. Specifically, it uses a database management system (for example, SQLite or MySQL) to periodically retrieve service information and application deadlines and update them as necessary. This ensures that the latest information is always maintained.

[0956] The server also has a means of determining what tasks should be completed by when in relation to the customer's desired delivery date. This determination is made using machine learning algorithms (e.g., random forests and support vector machines), which automatically assigns appropriate tasks.

[0957] Furthermore, the server has a means to suggest the optimal action based on the prompt sentence entered by the user using a generative AI model, such as a natural language processing model like GPT-3.

[0958] Terminal

[0959] The terminals are smartphones or tablets used by managers and staff at the distribution center. The terminals display information obtained from the server and provide an interface for users to input prompt sentences.

[0960] User

[0961] The user is a manager or staff member of the distribution center. The user can input the following prompt sentences using a terminal:

[0962] "When is the next deadline?"

[0963] "When is the next application deadline?"

[0964] The server uses a generative AI model to suggest optimal actions based on these prompts, such as, "The next delivery date is October 15, 2023. Please make the necessary preparations."

[0965] Specific examples

[0966] For example, if a logistics center manager inputs the prompt "When is the next delivery date?", the server retrieves the latest delivery date information from the database and uses the generative AI model to suggest the following action: "The next delivery date is October 15, 2023. Please make the necessary preparations." This information is displayed on the terminal, allowing the manager to make the appropriate preparations.

[0967] In this way, the present invention realizes efficient management of delivery dates and application deadlines at the logistics center and proposes optimal actions to the user.

[0968] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0969] Step 1:

[0970] The server uses a database management system to periodically retrieve service information (delivery dates, etc.) and internal application deadlines, updating them as needed. The input is the latest information from the database, and the output is the updated service information and application deadlines. Specifically, the server executes SQL queries to retrieve data and updates it as needed.

[0971] Step 2:

[0972] The user inputs a prompt sentence using a terminal. The input is the prompt sentence entered by the user, and the output is the prompt sentence displayed on the terminal. In concrete terms, the user inputs text through the interface of the terminal.

[0973] Step 3:

[0974] The terminal sends the input prompt to the server. The input is the prompt entered by the user, and the output is the prompt sent to the server. In concrete terms, the terminal sends the prompt to the server via the network.

[0975] Step 4:

[0976] The server uses a generative AI model to suggest the optimal action based on the received prompt. The input is the prompt, and the output is the action suggestion generated by the generative AI model. Specifically, the server inputs the prompt into the generative AI model and obtains the output from the model.

[0977] Step 5:

[0978] The server sends the generated action proposals to the terminal. The input is the action proposal generated by the generative AI model, and the output is the action proposal sent to the terminal. Specifically, the server sends the action proposals to the terminal via the network.

[0979] Step 6:

[0980] The terminal displays the received action proposal to the user. The input is the action proposal sent from the server, and the output is the action proposal displayed on the terminal. Specifically, the terminal displays the action proposal on the screen.

[0981] Step 7:

[0982] The user makes the necessary preparations and takes action based on the action suggestions displayed. The input is the action suggestions displayed on the terminal, and the output is the specific action the user takes. As a specific action, the user proceeds with the work according to the suggestions.

[0983] Example 2

[0984] Next, a description will be given of Example 2 of Form 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."

[0985] Conventional project management systems have difficulty efficiently estimating optimal tasks and their deadlines based on the customer's desired delivery date. Furthermore, they lack the functionality to automatically generate task schedules based on new project information using past data. This has led to issues such as reduced project management efficiency and increased risk of delivery delays.

[0986] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0987] In this invention, the server includes means for reading service information and internal application deadlines, means for determining what tasks should be completed by when in relation to a customer's desired delivery date, means for reminding sales of the determination result, means for acquiring past data, means for preprocessing the acquired data, means for training a machine learning model, means for estimating tasks and deadlines based on new project information, and means for returning the estimation result to the user. This makes it possible to automatically generate an optimal task schedule based on new project information using past data, thereby improving the efficiency of project management.

[0988] "Service information" refers to information such as deadlines and requirements related to projects and work.

[0989] The "internal application deadline" is the deadline for various internal applications and procedures.

[0990] "Customer Desired Delivery Date" is the date the customer desires for the project or service to be completed.

[0991] A "task" is a specific task or activity required to complete a project or job.

[0992] A "remind" is a notification or alert that alerts you to make sure you don't forget.

[0993] "Historical data" refers to records and information relating to previously carried out projects or operations.

[0994] "Preprocessing" is the process of converting data into a form suitable for analysis or model training.

[0995] A "machine learning model" is an algorithm that learns patterns and rules from data and makes predictions and classifications for new data.

[0996] "Estimation" means predicting unknown values ​​or results based on existing information and data.

[0997] "User" refers to an individual or organization that uses the system.

[0998] The present invention is a system for estimating optimal tasks and their deadlines in relation to a customer's desired delivery date in a project management system. Specific embodiments of this system will be described below.

[0999] System program generation

[1000] The user generates a program for the project management system. This program includes means for reading service information and internal application deadlines, means for determining what tasks should be completed by when in relation to the customer's desired delivery date, means for reminding sales of the determination results, means for acquiring past data, means for preprocessing the acquired data, means for training a machine learning model, means for estimating tasks and deadlines based on new project information, and means for returning the estimation results to the user.

[1001] Explanation of program processing

[1002] The server processes and calculates data using the following hardware and software.

[1003] Hardware: The servers are a database server and an application server. The database server uses MySQL, and the application server has Python installed.

[1004] Software: The server uses the Python programming language and the Scikit-learn library to train and estimate machine learning models, and the Pandas library for data preprocessing.

[1005] Specifically, the data is processed and calculated in the following manner.

[1006] 1. Data retrieval: The server retrieves historical project data from a MySQL database, including project start and end dates, and details of each task.

[1007] 2. Data preprocessing: The server preprocesses the acquired data, including missing value imputation, data normalization, and categorical data encoding.

[1008] 3. Training the machine learning model: The server trains the machine learning model using the preprocessed data. The algorithm used is the random forest regression model.

[1009] 4. Task and deadline estimation: The server uses the trained model to estimate the start and end dates of each task based on new project information.

[1010] 5. Returning the results: The server returns the estimation results to the user in JSON format. The user can then check the estimated task schedule on their device screen.

[1011] Examples of specific examples and prompts

[1012] As a concrete example, consider the following scenario.

[1013] Examples:

[1014] The user enters the start date and customer desired delivery date of a new project. The server estimates the start and end dates of each task based on data from similar past projects. For example, if the project start date is October 1, 2023, and the customer desired delivery date is December 31, 2023, the server generates the following task schedule:

[1015] Task 1: October 1, 2023 - October 15, 2023

[1016] Task 2: October 16, 2023 - November 15, 2023

[1017] Task 3: November 16, 2023 - December 15, 2023

[1018] Example prompt sentence:

[1019] "The start date of a new project is October 1, 2023, and the customer's desired delivery date is December 31, 2023. Based on this, estimate the start and end dates for each task."

[1020] In this way, users can use the system to efficiently manage project schedules.

[1021] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1022] Step 1:

[1023] The user enters the project information.

[1024] Enter: Project start date and customer desired delivery date.

[1025] Specific operation: The user enters the project start date (e.g., October 1, 2023) and the customer's desired delivery date (e.g., December 31, 2023) into the input form on the terminal and clicks the "Submit" button.

[1026] Output: The entered project information is sent to the server.

[1027] Step 2:

[1028] The server retrieves past project data.

[1029] Input: Project information sent to the server.

[1030] Specific operation: The server connects to a MySQL database and retrieves past project data using SQL queries.

[1031] Output: Retrieved historical project data.

[1032] Step 3:

[1033] The server preprocesses the data.

[1034] Input: Captured historical project data.

[1035] Specific operation: The server converts the data into a data frame using the Pandas library and performs preprocessing such as filling in missing values, normalizing the data, and encoding categorical data.

[1036] Output: Preprocessed data.

[1037] Step 4:

[1038] The server trains the machine learning model.

[1039] Input: Preprocessed data.

[1040] What it does: The server trains a random forest regression model using the Scikit-learn library.

[1041] Output: A trained machine learning model.

[1042] Step 5:

[1043] The server estimates tasks and deadlines based on new project information.

[1044] Input: A trained machine learning model and new project information.

[1045] What it does: The server uses the trained model to estimate the start and end dates for each task based on new project information.

[1046] Output: The estimated task schedule.

[1047] Step 6:

[1048] The server returns the estimated results to the user.

[1049] Input: Estimated task schedule.

[1050] Specific operation: The server returns the estimation results to the user in JSON format.

[1051] Output: The estimated task schedule displayed on the user's terminal.

[1052] In this way, users can use the system to efficiently manage project schedules.

[1053] (Application example 2)

[1054] Next, a description will be given of Application Example 2 of Form 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."

[1055] In logistics centers, it is important to efficiently manage the optimal tasks and deadlines for customer orders. However, with conventional methods, it is difficult to estimate the optimal tasks and deadlines using past data, and work efficiency is not sufficiently improved. There is also a lack of means to grasp the progress of tasks in real time and to send appropriate reminders. For this reason, a new system is needed to improve the work efficiency of logistics centers.

[1056] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1057] In this invention, the server includes a means for reading service information (delivery dates, etc.) and in-house application deadlines, a means for determining what tasks should be completed by when in relation to the customer's desired delivery date, a means for reminding the worker of the determination result, a means for estimating the optimal tasks and their deadlines using a machine learning algorithm based on past data, and a means for displaying the estimated tasks and deadlines. This makes task management in the logistics center more efficient, enabling the progress of work to be grasped in real time and appropriate reminders to be sent.

[1058] "Service information" refers to information such as delivery dates and detailed requirements regarding orders from customers.

[1059] The "internal application deadline" is the deadline for various applications set in the internal business process.

[1060] "Customer desired delivery date" is the date and time of delivery of the product desired by the customer.

[1061] A "task" refers to a specific job or operation, such as order processing or shipping preparation at a logistics center.

[1062] A "remind" is the act of notifying a worker of a specific task or deadline and drawing their attention to it.

[1063] A "machine learning algorithm" is a computational method that learns patterns based on past data and makes predictions and classifications for new data.

[1064] "Estimation" is the act of predicting future events or outcomes based on existing data and information.

[1065] "Display" refers to the act of visually indicating estimated tasks and deadlines, and refers to outputting information on a screen or display.

[1066] A system for carrying out the present invention is intended to improve the efficiency of task management in a logistics center. A specific embodiment of the system will be described below.

[1067] System Configuration

[1068] The system consists of the following main components:

[1069] 1. Server: Responsible for data processing and running machine learning algorithms.

[1070] 2. Terminal: A device such as a smartphone or tablet used by a business employee.

[1071] 3. User: Logistics center operations staff.

[1072] Hardware and software used

[1073] Hardware: Smartphone (iOS or Android), server (with a powerful CPU and sufficient memory)

[1074] Software: Python, scikit-learn (machine learning library), pandas (data manipulation library)

[1075] Data processing and calculation

[1076] The server processes the data as follows:

[1077] 1. Data loading: Load past order data from a CSV file.

[1078] 2. Setting features and targets: Set features such as order size, order type, and season, and completion time as targets.

[1079] 3. Model Training: Train the machine learning model using RandomForestRegressor.

[1080] 4. Enter new order information: Enter new order information from the terminal.

[1081] 5. Task and Deadline Estimation: Using the trained model, we estimate the optimal tasks and their deadlines.

[1082] 6. Display results: Display estimated tasks and deadlines on your device.

[1083] Specific examples

[1084] Past data includes order size, order type, season, and completion time. For new order information, enter an order size of 10, order type as standard, and season as winter. From this, the server estimates the optimal task and its deadline and reminds the worker.

[1085] Prompt Sentence Examples

[1086] "Based on past logistics data, estimate the optimal tasks and their deadlines for an order size of 10, an order type of standard, and a season of winter."

[1087] This system will streamline task management at logistics centers, allowing for real-time understanding of work progress and appropriate reminders.

[1088] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1089] Step 1:

[1090] The server reads past order data from a CSV file.

[1091] Input: A CSV file containing historical order data.

[1092] Data processing: Convert the CSV file into a data frame using the pandas library.

[1093] Output: Historical order data in dataframe format.

[1094] Step 2:

[1095] The server sets the features and targets.

[1096] Input: Historical order data in dataframe format.

[1097] Data processing: Order size, order type, and season are extracted as features, and completion time is set as the target.

[1098] Output: A dataset of features and targets.

[1099] Step 3:

[1100] The server trains the machine learning model.

[1101] Input: Feature and target datasets.

[1102] Data computation: Train the model using scikit-learn's RandomForestRegressor.

[1103] Output: A trained machine learning model.

[1104] Step 4:

[1105] The terminal inputs new order information.

[1106] Input: New order information entered by the user (e.g., order size is 10, order type is standard, season is winter).

[1107] Data processing: Convert the input order information into a data frame.

[1108] Output: The new order information in a data frame format.

[1109] Step 5:

[1110] The server uses the trained model to estimate the optimal tasks and their deadlines.

[1111] Input: New order information in dataframe format, trained machine learning model.

[1112] Data calculation: New order information is input into the model and an estimated completion time is calculated.

[1113] Output: Estimated completion time and deadline.

[1114] Step 6:

[1115] The terminal displays estimated tasks and deadlines.

[1116] Inputs: Estimated completion time and deadline.

[1117] Specific behavior: Estimated tasks and deadlines are displayed on the device screen.

[1118] Output: Estimated tasks and deadlines are displayed visually for the worker.

[1119] Example 3

[1120] Next, a description will be given of Example 3 of Form Example 3. 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."

[1121] In the conventional system, there were limited means to determine tasks based on service information and internal application deadlines and to remind sales staff, making it difficult to operate efficiently.In addition, the process of generating judgment results based on prompts entered by users and reminding sales staff about them was not automated, so manual response was required, which was time-consuming and labor-intensive.

[1122] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1123] In this invention, the server includes means for the user to input a prompt sentence, means for the terminal to send the prompt sentence to the server, means for the server to pass the prompt sentence to the generative AI model, means for the generative AI model to generate a judgment result, means for the server to analyze the judgment result and create a reminder email as necessary, and means for the server to send the reminder email to the sales department. This makes it possible to automatically generate a judgment result based on the prompt sentence entered by the user and to efficiently remind the sales department.

[1124] "Service information" refers to information necessary for business operations, such as delivery dates and internal application deadlines.

[1125] "Customer desired delivery date" refers to the delivery date of the product desired by the customer.

[1126] A "task" refers to the work or activity that must be performed to achieve a specific goal.

[1127] "Judgment result" refers to the conclusion or recommended action generated based on the input information.

[1128] A "remind" refers to a re-notification of specific information or tasks.

[1129] A "prompt sentence" refers to a sentence containing a question or instruction that a user inputs to a system.

[1130] "Terminal" refers to a device such as a computer or smartphone operated by a user.

[1131] "Server" refers to a computer system that provides services over a network.

[1132] A "generative AI model" refers to an algorithm or system that uses artificial intelligence to generate judgment results from input data.

[1133] "Email" refers to digital messages sent and received over the Internet.

[1134] "SMTP Protocol" refers to the communications protocol used to send email.

[1135] This invention is a system that uses a generative AI model to generate a judgment result based on a prompt sentence entered by a user, and sends a reminder email to sales as necessary. A specific embodiment of this system is described below.

[1136] Hardware and software used

[1137] server

[1138] The server runs the program using Python and uses a general artificial intelligence model, specifically OpenAI's GPT-4, as the generative AI model. The server also uses Python's smtplib library to send emails using the SMTP protocol.

[1139] Terminal

[1140] The terminal provides an interface for the user to input a prompt sentence. The terminal uses a web browser to display a form for the user to input a prompt sentence. Specific web browsers used are Google Chrome and Mozilla Firefox.

[1141] User

[1142] The user inputs a prompt through the web browser on the terminal, for example, "Please tell me your sales forecast for the next quarter," and presses the send button.

[1143] Data processing and calculation

[1144] Entering and sending a prompt

[1145] When a user enters a prompt in the device's web browser and presses the submit button, the device sends the prompt as an HTTP POST request to the server, converting the form data into JSON format and sending it to the specified endpoint on the server.

[1146] Parsing prompts and generating results

[1147] The server analyzes the received prompt and passes it to the generative AI model. Specifically, the server uses Python's requests library to send a request including the prompt to the generative AI model's API. The generative AI model generates a judgment result based on the received prompt. For example, it generates a response such as, "Sales forecast for the next quarter are expected to increase by 10% compared to the same period last year."

[1148] Analysis of decision results and creation of reminder emails

[1149] The server analyzes the judgment results returned by the generative AI model. If the analysis results determine that a reminder to the salesperson is necessary, a reminder email is created. Specifically, the server includes the judgment results in the email body and sets the email address of the salesperson as the recipient.

[1150] Sending reminder emails

[1151] The server sends the created reminder email using the SMTP protocol. For example, it uses the Python smtplib library to send the email through a common SMTP server. The subject of the email should read "Important: Sales Forecast Reminder" and the body should contain the generated decision result.

[1152] Specific examples

[1153] Prompt Sentence Examples

[1154] An example of a prompt that a user can enter is, "Please tell me your sales forecast for the next quarter." When the user enters this prompt and presses the send button, the server uses the generative AI model to generate a sales forecast and sends the results as a reminder email to the sales department.

[1155] In this way, a system is constructed in which the server generates a judgment result based on the prompt sentence entered by the user and sends a reminder email to the sales department as necessary. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1156] Step 1:

[1157] The user enters a prompt statement.

[1158] The user opens a web browser on their device and accesses the specified URL. They enter a prompt in the form that appears and press the submit button. For example, they might enter, "Please tell me your sales forecast for the next quarter." The input data is the prompt.

[1159] Step 2:

[1160] The terminal sends the prompt to the server.

[1161] The terminal sends the prompt text entered by the user to the server as an HTTP POST request. At this time, the terminal converts the form data into JSON format and sends it to the specified endpoint of the server. The input data is the prompt text, and the output data is the JSON-formatted data sent to the server.

[1162] Step 3:

[1163] The server passes the prompt to the generative AI model.

[1164] The server parses the received prompt sentence and passes it to the generative AI model. Specifically, the server uses the Python requests library to send a request including the prompt sentence to the generative AI model's API. The input data is the prompt sentence in JSON format, and the output data is the request sent to the generative AI model.

[1165] Step 4:

[1166] The generative AI model generates the judgment result.

[1167] A generative AI model generates a judgment result based on the received prompt. For example, it generates a response such as, "Sales forecast for the next quarter are expected to increase by 10% compared to the same period last year." The input data is the prompt, and the output data is the generated judgment result.

[1168] Step 5:

[1169] The server analyzes the results of the decision and creates a reminder email if necessary.

[1170] The server analyzes the judgment results returned by the generative AI model. If it determines that a reminder is necessary for the salesperson based on the analysis results, it creates a reminder email. Specifically, the server includes the judgment results in the email body and sets the email address of the salesperson as the recipient. The input data is the generated judgment results, and the output data is the created reminder email.

[1171] Step 6:

[1172] The server sends a reminder email to sales.

[1173] The server sends the created reminder email using the SMTP protocol. For example, it uses Python's smtplib library to send the email through a common SMTP server. The email subject should read "Important: Sales Forecast Reminder" and the body should include the generated judgment result. The input data is the created reminder email, and the output data is the email sent to sales.

[1174] (Application example 3)

[1175] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1176] In conventional sales activities, it was difficult to determine the next sales activity to be carried out based on the customer's purchase history and inquiry details, and to remind sales representatives at the appropriate time. Furthermore, reminders were often done manually, which hindered efficient sales activities. This resulted in problems such as delays in customer responses and lost opportunities.

[1177] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1178] In this invention, the server includes a means for reading service information (delivery dates, etc.) and in-house application deadlines, a means for determining what tasks should be completed by when in relation to the customer's desired delivery date, a means for reminding sales of the determination results, a means for determining the next sales activity to be carried out based on the customer's purchase history and inquiry details, and a means for automatically sending reminder emails based on the determination results. This makes it possible to determine appropriate sales activities based on the customer's purchase history and inquiry details, and to automatically send reminder emails in a timely manner.

[1179] "Service information" refers to information necessary for carrying out business, such as delivery dates and internal application deadlines.

[1180] "Internal application deadline" refers to the deadline by which internal procedures and applications must be completed.

[1181] "Customer desired delivery date" refers to the delivery date of the product desired by the customer.

[1182] A "task" refers to the work or task that must be performed to achieve a specific goal.

[1183] "Decision-making means" refers to a method or device for determining the next action to be taken based on specific conditions or data.

[1184] "Reminder means" refers to a method or device that provides notifications or alerts to encourage necessary action based on specific information.

[1185] "Customer purchase history" refers to a record of products that a customer has previously purchased.

[1186] "Inquiry content" refers to the details of questions or requests from customers.

[1187] "Sales activities" refers to a series of tasks and actions taken to sell products or services.

[1188] "Reminder email" refers to an email sent with specific information or to encourage specific action.

[1189] "Automatic sending means" refers to a method or device that sends email without manual operation when specific conditions are met.

[1190] A system for implementing this invention includes means for reading service information (delivery dates, etc.) and internal application deadlines, means for determining what tasks should be completed by when in relation to the customer's desired delivery date, means for reminding sales of the results of the determination, means for determining the next sales activity to be carried out based on the customer's purchase history and inquiry details, and means for automatically sending reminder emails based on the results of the determination.

[1191] Hardware and software used

[1192] Hardware: Servers, smartphones

[1193] Software: Python, smtplib library, email.mime library

[1194] Data processing and calculation

[1195] The server first reads service information (delivery dates, etc.) and internal application deadlines from a database. Next, it uses a machine learning algorithm to determine what tasks should be completed by when in relation to the customer's desired delivery date. This algorithm generates an optimal task schedule based on past data.

[1196] Then, based on the results of the decision, a reminder email is generated to remind the sales representative, and this reminder email is sent automatically using the smtplib and email.mime libraries.

[1197] Specific examples

[1198] For example, if a customer inquires about a specific product, the server determines the next sales activity based on the content of the inquiry. The server analyzes the customer's purchase history and the content of the inquiry, and decides which sales activity to take next. For example, if the server determines that "please make a follow-up call to this customer," a reminder email containing that content is automatically sent to the sales representative.

[1199] Prompt Sentence Examples

[1200] "Create a Python program that determines the next sales activity to take based on the customer's purchase history and inquiry details, and sends a reminder email to the sales representative."

[1201] In this way, it becomes possible to determine appropriate sales activities based on the customer's purchase history and inquiry details, and to automatically send timely reminder emails.

[1202] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1203] Step 1:

[1204] The server reads service information (delivery date, etc.) and internal application deadlines from the database.

[1205] Input: Service information stored in the database and internal application deadlines.

[1206] Data processing: Execute database queries to obtain the required information.

[1207] Output: Service information and internal application deadline data.

[1208] Step 2:

[1209] The server uses machine learning algorithms to determine what tasks need to be completed by when in relation to the customer's desired delivery date.

[1210] Input: Customer desired delivery date, service information, internal application deadline.

[1211] Data calculation: Using machine learning algorithms, optimal task schedules are generated based on past data.

[1212] Output: Task schedule.

[1213] Step 3:

[1214] The server determines the next sales activity to be carried out based on the customer's purchase history and inquiry details.

[1215] Input: Customer purchase history, inquiry details.

[1216] Data calculation: Analyze customer data and determine the next sales activity.

[1217] Output: Sales activity decision results.

[1218] Step 4:

[1219] The server generates a reminder email based on the result of the determination.

[1220] Input: Sales activity decision results.

[1221] Data processing: Generate the content of the reminder email.

[1222] Output: Reminder email content.

[1223] Step 5:

[1224] The server automatically sends reminder emails using the smtplib and email.mime libraries.

[1225] Input: Reminder email content, sales representative's email address.

[1226] Data calculation: Executes the email sending process.

[1227] Output: A reminder email is sent to the sales rep.

[1228] In this way, appropriate sales activities can be determined based on the customer's purchase history and inquiries, and timely reminder emails can be automatically sent.

[1229] 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.

[1230] "Example 1"

[1231] One embodiment of the present invention is a system that combines an emotion engine. This system recognizes the user's emotions and adjusts the timing and content of reminders according to that emotional state. Specifically, if it determines that the user is feeling stressed, it can take operations that take the user's emotional state into consideration, such as reducing the frequency of reminders.

[1232] "Example 2"

[1233] The emotion engine also uses machine learning algorithms to learn and predict a user's emotional state. Specifically, it predicts the user's emotional state based on their past reactions and behavioral patterns, and then sends reminders accordingly. For example, if it determines that a user always feels stressed before performing a specific task, it will send reminders for that task in a way that reduces stress.

[1234] "Example 3"

[1235] Furthermore, this system can also adjust the content of reminders depending on the user's emotional state. For example, if it determines that the user is feeling joy, it can include a message in the reminder that reinforces that joy. This allows for more effective reminders that take the user's emotional state into account.

[1236] The processing flow of each embodiment will be described below.

[1237] "Example 1"

[1238] Step 1: The system recognizes emotions from the user's actions and reactions.

[1239] Step 2: The emotion engine determines the user's emotional state based on the recognized emotions.

[1240] Step 3: Adjust the timing and content of your reminders depending on your emotional state.

[1241] "Example 2"

[1242] Step 1: The emotion engine learns the user's emotional state from their past reactions and behavioral patterns.

[1243] Step 2: Predict the user's current emotional state based on the learned emotional state.

[1244] Step 3: Adjust the timing and content of your reminders based on your predicted emotional state.

[1245] "Example 3"

[1246] Step 1: The system recognizes emotions from the user's actions and reactions.

[1247] Step 2: The emotion engine determines the user's emotional state based on the recognized emotions.

[1248] Step 3: Tailor your reminders to your emotional state.

[1249] Example 1

[1250] Next, a description will be given of Example 1 of Form 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."

[1251] In the previous system, it was possible to read service information and internal application deadlines, but it was not possible to adjust the timing or content of reminders according to the user's emotional state. As a result, even if the user was feeling stressed, reminders were sent at a fixed frequency, which increased the burden on the user. Furthermore, because the content of reminders was uniform, it was not possible to respond flexibly according to the user's situation.

[1252] 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.

[1253] In this invention, the server includes a means for reading service information and in-house application deadlines, a means for determining what tasks should be completed by when in relation to the customer's desired delivery date, a means for reminding the sales department of the determination result, and a means for recognizing the user's emotions and adjusting the timing and content of the reminder according to the user's emotional state. This allows for reminders that take the user's emotional state into consideration, reduces the user's burden, and enables more effective task management.

[1254] "Service information" is information relating to delivery dates and details of the services provided.

[1255] "Internal application deadline" refers to the deadline by which the internal application procedure must be completed.

[1256] "Customer desired delivery date" refers to the delivery date desired by the customer.

[1257] A "task" refers to the work or activity that must be performed to achieve a specific goal.

[1258] A "remind" refers to a re-notification of specific information or tasks.

[1259] "User emotions" refers to the psychological state, such as stress or satisfaction, that the user feels.

[1260] "Emotional state" refers to the user's current psychological state, including states such as stress or relaxation.

[1261] A "machine learning algorithm" refers to a computational method for learning patterns based on data and making predictions and judgments.

[1262] MODE FOR CARRYING OUT THE INVENTION

[1263] This invention is a system that includes means for reading service information and internal application deadlines, means for determining what tasks should be completed by when in relation to the customer's desired delivery date, means for reminding sales of the results of the determination, and means for recognizing the user's emotions and adjusting the timing and content of the reminders according to the user's emotional state.

[1264] Server Processing

[1265] The server periodically reads service information and internal application deadlines from a database using a database management system (DBMS). Specifically, it uses a DBMS such as MySQL or PostgreSQL to obtain this information and update it as needed. For example, the server accesses the database at 2:00 AM every day to obtain the latest service information and application deadlines.

[1266] User Action

[1267] The user uses a system that combines an emotion engine. This system recognizes the user's emotions and adjusts the timing and content of reminders according to their emotional state. Specifically, if the system determines that the user is feeling stressed, it will take measures such as reducing the frequency of reminders. For example, if the user inputs "I'm busy today," the system will use that information to reduce the frequency of reminders.

[1268] Terminal handling

[1269] The device will then display a reminder to the user based on the adjusted reminder timing. For example, the user might see a notification like this on their device:

[1270] "The next application deadline is tomorrow. Don't forget."

[1271] Specific examples

[1272] Server processing example

[1273] The server accesses the MySQL database every day at 2 AM and executes the following query:

[1274] sql

[1275] SELECT FROM service_info WHERE update_time >= CURDATE();

[1276] This query retrieves the service information updated for that day.

[1277] User processing example

[1278] If a user types "I'm busy today," the emotion engine will determine that the user is stressed and reduce the frequency of reminders, specifically changing the usual hourly reminders to every three hours.

[1279] Prompt Sentence Examples

[1280] Examples of prompts to input to a generative AI model might include:

[1281] If the user types "I'm busy today," how would the emotion engine adjust the frequency of reminders?

[1282] This prompt tells the generative AI model how to adjust reminders based on the user's emotional state.

[1283] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1284] Step 1:

[1285] The server retrieves the service information and the internal application deadline from the database.

[1286] Input: Database connection information, SQL query

[1287] What happens: The server connects to the MySQL database and executes the following SQL query:

[1288] sql

[1289] SELECT FROM service_info;

[1290] SELECT FROM application_deadlines;

[1291] Output: Data set of acquired service information and internal application deadlines

[1292] Step 2:

[1293] The server periodically updates the information it has obtained.

[1294] Input: Recurring job schedule, database connection information

[1295] What happens: The server runs a cron job every day at 2 AM to retrieve the latest information from the database. For example, it runs the following script:

[1296] bash

[1297] ! / bin / bash

[1298] mysql -u username -p password -e "SELECT FROM service_info;" > / path / to / service_info.json

[1299] mysql -u username -p password -e "SELECT FROM application_deadlines;" > / path / to / application_deadlines.json

[1300] Output: JSON file containing the latest service information and internal application deadlines

[1301] Step 3:

[1302] A user accesses the system and the emotion engine recognizes the user's emotions.

[1303] Input: User input data (e.g., "I'm busy today")

[1304] How it works: When a user logs into the system and types "I'm busy today," the emotion engine analyzes the text and determines that the user is stressed.

[1305] Output: User's emotional state (e.g., stress)

[1306] Step 4:

[1307] The emotional engine adjusts the timing and content of reminders according to the user's emotional state.

[1308] Input: User's emotional state, reminder settings information

[1309] How it works: The emotion engine adjusts the timing and content of reminders based on the user's emotional state. For example, if it determines that the user is feeling stressed, it will change reminders from every hour to every three hours.

[1310] Output: Adjusted reminder timing and content

[1311] Step 5:

[1312] The device displays a reminder to the user.

[1313] Input: Adjusted reminder timing and content

[1314] Specific behavior: The device will display a notification to the user based on the adjusted reminder timing. For example, the following notification will be displayed:

[1315] "The next application deadline is tomorrow. Don't forget."

[1316] Output: Reminder notification displayed to the user

[1317] (Application example 1)

[1318] Next, a description will be given of Application Example 1 of Form 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."

[1319] In conventional production management systems, reminders are sent without taking into account the emotional state of the workers, which often causes stress for the workers and reduces production efficiency. In addition, the timing and content of reminders are fixed, which means that flexible responses based on the situation of each worker are not possible.

[1320] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means for reading service information (delivery dates, etc.) and in-house application deadlines, means for determining what tasks should be completed by when in relation to the customer's desired delivery date, means for reminding sales of the determination result, means for recognizing the user's emotional state using an emotion engine and adjusting the timing and content of reminders, and means for periodically acquiring and updating information using a database management system. This makes it possible to provide reminders according to the emotional state of workers, thereby improving production efficiency and reducing worker stress.

[1321] "Service information" refers to important information related to business operations, such as delivery dates and internal application deadlines.

[1322] "Internal application deadline" refers to the deadline by which various internal applications must be completed.

[1323] "Customer desired delivery date" refers to the delivery date of the product desired by the customer.

[1324] A "task" refers to an operation or activity performed to achieve a specific purpose.

[1325] A "reminder" is a notification that helps you avoid forgetting a specific task or deadline.

[1326] An "emotion engine" refers to technology that recognizes the user's emotional state and adjusts the system's behavior based on that information.

[1327] "User's emotional state" refers to the psychological state, such as stress or relaxation, that the user feels.

[1328] A "database management system" refers to software for creating, managing, and operating a database.

[1329] "Regularly acquiring and updating information" means collecting necessary information at regular intervals and keeping it up to date.

[1330] A "machine learning algorithm" refers to a computational method that automatically learns from data and makes predictions and judgments.

[1331] The system for carrying out this invention is configured as follows: The server includes means for reading service information (delivery dates, etc.) and in-house application deadlines, means for determining what tasks should be completed by when in relation to the customer's desired delivery date, means for reminding sales of the determination results, means for recognizing the user's emotional state using an emotion engine and adjusting the timing and content of reminders, and means for periodically acquiring and updating information using a database management system.

[1332] Program processing explanation

[1333] The server first uses a database management system (such as SQLite) to periodically retrieve and update service information and internal application deadlines. This ensures that the latest information is always available. Next, it uses an emotion engine (such as EmotionEngine) to recognize the user's emotional state. The emotion engine analyzes the user's facial expressions and voice through cameras and sensors to determine their emotional state, such as stress or relaxation.

[1334] After recognizing the user's emotional state, the server can adjust the timing and content of reminders based on that information. For example, if the user is stressed, the server will reduce the frequency of reminders and only remind them about important tasks. On the other hand, if the user is relaxed, the server will continue to remind them about all tasks as usual.

[1335] Specific examples

[1336] For example, if a factory worker is feeling stressed, the server will remind him / her only about important tasks and postpone other tasks. This reduces the worker's stress and improves production efficiency. On the other hand, if the worker is relaxed, the server will remind him / her about all tasks as usual, promoting efficient work.

[1337] Prompt Sentence Examples

[1338] By entering the following prompt statements into the generative AI model, you can generate system design and program code.

[1339] Design a system that adjusts the timing and content of reminders based on the user's emotional state. Retrieve the production schedule from a database and use an emotion engine to recognize the worker's emotions. If the worker is stressed, reduce the frequency of reminders and only remind them about important tasks. Please provide the specific program code.

[1340] In this way, the server can provide reminders according to the user's emotional state, thereby improving production efficiency and reducing worker stress.

[1341] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1342] Step 1:

[1343] The server uses a database management system (such as SQLite) to periodically retrieve and update service information and internal application deadlines. The input is a query from the database, and the output is the latest service information and internal application deadlines. In this step, an SQL query is executed against the database to retrieve the required information.

[1344] Step 2:

[1345] The server uses an emotion engine (such as EmotionEngine) to recognize the user's emotional state. The input is the user's facial expression and voice data acquired from a camera or sensor, and the output is the user's emotional state (stress, relaxation, etc.). In this step, the emotion engine analyzes the facial expression and voice data and determines the user's emotional state.

[1346] Step 3:

[1347] The server adjusts the timing and content of reminders based on the user's emotional state. The inputs are the service information and internal application deadlines obtained in step 1, and the user's emotional state obtained in step 2, and the output is an adjusted reminder schedule. In this step, if the user is feeling stressed, the server adjusts the schedule to reduce the frequency of reminders and only remind them of important tasks.

[1348] Step 4:

[1349] The server sends reminders based on the adjusted reminder schedule. The input is the reminder schedule adjusted in step 3, and the output is a reminder notification for the user. This step involves sending reminders to the user using email or a notification system.

[1350] Step 5:

[1351] The server records the result of the reminder transmission in the database. The input is the result of the reminder transmission, and the output is the updated database record. This step checks whether the reminder was sent successfully and stores the result in the database.

[1352] Through the above steps, the server can provide reminders according to the user's emotional state, thereby improving production efficiency and reducing worker stress.

[1353] Example 2

[1354] Next, a description will be given of Example 2 of Form 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."

[1355] With conventional systems, it was difficult to determine the appropriate tasks and their deadlines based on the customer's desired delivery date, and they were unable to provide reminders that took into account the user's emotional state. As a result, there were problems such as project progress being delayed and users' stress increasing.

[1356] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for reading service information and internal application deadlines, a means for determining what tasks should be completed by when in relation to the customer's desired delivery date, a means for notifying the determination result, a means for collecting user behavior data, a means for predicting the user's emotional state, a means for determining the content of reminders based on the prediction result, and a means for notifying the content of reminders. This makes it possible to determine appropriate tasks and their deadlines in relation to the customer's desired delivery date, and to provide reminders that take the user's emotional state into consideration.

[1357] "Service information" is information related to the services provided by the customer, including delivery dates and requirements.

[1358] "Internal application deadline" refers to the deadline required for procedures and approvals within a company.

[1359] "Customer Desired Delivery Date" refers to the date the customer desires for the project or service to be completed.

[1360] A "task" refers to a specific task or activity required to progress a project or business.

[1361] "Means of determination" refers to methods and techniques for determining the optimal tasks and their deadlines based on specific conditions and data.

[1362] "Means of notification" refers to the methods and techniques for communicating the results of judgments and reminders to users and related parties.

[1363] "Behavioral data" refers to information about a user's behavior and reactions, including task completion times and survey results.

[1364] "Emotional state" refers to the user's psychological state and emotions, including stress and satisfaction.

[1365] "Reminder content" refers to the content of the notification or message sent to the user.

[1366] This invention is a system that determines appropriate tasks and their deadlines based on a customer's desired delivery date, and also provides reminders that take into account the user's emotional state. Specific embodiments of this system are described below.

[1367] System configuration

[1368] server

[1369] The server has the following functions:

[1370] 1. Function to read service information and internal application deadlines: Obtain service information and internal application deadlines from the database. Specifically, extract data using SQL queries.

[1371] 2. Function to determine tasks based on the customer's desired delivery date: Using a machine learning algorithm, we predict the tasks required and their deadlines based on the customer's desired delivery date. Specifically, we use Scikit-learn's RandomForestRegressor.

[1372] 3. Function to notify the judgment result: The judgment result is notified to the user via email or in-app notification.

[1373] 4. Ability to collect user behavior data: Collect user behavior data (task completion time, survey results, etc.).

[1374] 5. Function to predict the user's emotional state: Based on the collected behavioral data, the system uses a machine learning algorithm to predict the user's emotional state. Specifically, it uses an LSTM model built using Keras.

[1375] 6. Function to determine the content of reminders: Based on the prediction results, the content of reminders for the user is determined.

[1376] 7. Function to notify reminder content: The determined reminder content is notified to the user via email or in-app notification.

[1377] Terminal

[1378] The terminal has the following features:

[1379] 1. Ability to collect user behavioral data: Collects behavioral data such as task completion time and survey results.

[1380] 2. Function to notify the user of reminder content: Notify the user of the reminder content received from the server, specifically using in-app notifications or pop-up messages.

[1381] User

[1382] The user does the following:

[1383] 1. Entering the customer's desired delivery date: Enter the customer's desired delivery date in the system's input form.

[1384] 2. Answer the questionnaire: Answer the questionnaire that appears before starting the task.

[1385] Specific examples

[1386] Examples of task decisions based on customer desired delivery dates:

[1387] A user enters into the system's input form, "I want to complete the project by December 25, 2023."

[1388] The server runs an SQL query such as "SELECT FROM projects WHERE type='similar'" against the database to retrieve data on similar past projects.

[1389] The server uses Scikit-learn's RandomForestRegressor to generate prediction results such as "Requirements definition will be completed by November 1, 2023, and design will be completed by November 15, 2023."

[1390] The server displays the prediction results to the user, who can then view the specific tasks and their deadlines on the screen.

[1391] Examples of predicting and reminding users' emotional state:

[1392] Before the user starts the task, the terminal displays a questionnaire and asks questions such as, "How are you feeling right now?" The user answers, "I feel stressed."

[1393] The server inputs this data into an LSTM model built using Keras and predicts that "users feel stressed every Monday morning."

[1394] The server generates a reminder message such as "Take a deep breath and relax."

[1395] On Monday morning, the device will notify the user with a message such as "Take a deep breath and relax."

[1396] Example prompt for a generative AI model:

[1397] The client wants the project completed by December 25, 2023. Based on past project data, what tasks are required and when?

[1398]

[1399] I predict that my users will feel stressed every Monday morning preparing for a meeting. What reminder messages can I use to reduce this stress?

[1400] The above is a specific embodiment for carrying out the present invention.

[1401] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1402] Step 1: Enter customer desired delivery date

[1403] The user enters the customer's desired delivery date into the system's input form. For example, they might enter, "I want the project completed by December 25, 2023." This input data is sent to the server.

[1404] Step 2: Obtaining historical data

[1405] The server retrieves past project data from the database. Specifically, it uses an SQL query to extract data about similar projects. The input is the customer's desired delivery date, and the output is data about similar past projects.

[1406] Step 3: Applying the machine learning model

[1407] The server uses the acquired data to input a machine learning model. It uses Scikit-learn's RandomForestRegressor to predict the duration and deadline of each task. The input is past project data, and the output is the predicted tasks and their deadlines.

[1408] Step 4: Present tasks and deadlines

[1409] The server presents the prediction results to the user. For example, it displays specific tasks and deadlines, such as "Requirements definition will be completed by November 1, 2023, and design will be completed by November 15, 2023." The input is the prediction results, and the output is the tasks and deadlines displayed to the user.

[1410] Step 5: Collect user behavior data

[1411] The terminal collects user behavior data. For example, it records the time it takes to complete a task or the results of a questionnaire given before starting the task. The input is the user behavior data, and the output is the collected data.

[1412] Step 6: Applying the emotion prediction model

[1413] The server uses the collected data to input into an emotion prediction model. It predicts the user's emotional state using an LSTM model built using Keras. The input is the user's behavioral data, and the output is the predicted emotional state.

[1414] Step 7: Decide what to remind

[1415] The server determines the content of the reminder based on the prediction result. For example, if the server predicts that the user will feel stressed, it generates a message to help them relax. The input is the predicted emotional state, and the output is the reminder content.

[1416] Step 8: Execute the reminder

[1417] The device notifies the user of the determined reminder content. For example, it displays a message such as "Take a deep breath and relax." The input is the reminder content, and the output is the message to be notified to the user.

[1418] (Application example 2)

[1419] Next, a description will be given of Application Example 2 of Form 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."

[1420] While conventional task management systems can estimate optimal tasks and their deadlines based on a customer's desired delivery date, they have the problem of being unable to provide reminders that take the user's emotional state into account, making it difficult to reduce user stress. Furthermore, they are unable to provide appropriate support for tasks that cause users stress, which can lead to a decline in work efficiency.

[1421] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1422] In this invention, the server includes a means for reading service information (delivery dates, etc.) and in-house application deadlines, a means for determining what tasks should be completed by when in relation to the customer's desired delivery date, a means for reminding the sales department of the determination result, a means for learning and predicting the user's emotional state, and a means for reminding according to the emotional state. This makes it possible to provide reminders that take the user's emotional state into consideration, reducing user stress and improving work efficiency.

[1423] "Service information" refers to important information related to business operations, such as delivery dates and internal application deadlines.

[1424] "Customer desired delivery date" refers to the delivery deadline desired by the customer.

[1425] A "task" refers to the work or activity that must be performed to achieve a specific goal.

[1426] "Decision-making means" refers to a means for estimating optimal tasks and their deadlines using machine learning algorithms, etc.

[1427] "Reminding means" refers to a means for notifying the user of the judgment result.

[1428] "Emotional state" refers to the user's current psychological state.

[1429] "Learning means" refers to a means for learning patterns from past data.

[1430] "Prediction means" refers to a means for predicting future states based on learned data.

[1431] "Stress reduction reminders" refer to reminders that are given to users in a way that reduces stress when performing tasks that cause stress to the user.

[1432] A system for implementing the present invention is configured as follows.

[1433] System Configuration

[1434] The server includes a means for reading service information (delivery dates, etc.) and internal application deadlines, a means for determining what tasks should be completed by when in relation to the customer's desired delivery date, a means for reminding sales of the results of the determination, a means for learning and predicting the user's emotional state, and a means for providing reminders according to the user's emotional state.

[1435] Hardware and software used

[1436] Hardware: Factory robots, sensors (collecting user behavior data)

[1437] Software: Python, scikit-learn (machine learning library)

[1438] Data processing and calculation

[1439] The server first collects past task data and user behavior data. Then, using machine learning algorithms, it trains a model to estimate optimal task deadlines and a model to predict emotional states. Using new tasks and user behavior data as input, it estimates task deadlines and emotional states, and generates reminder messages according to the emotional states.

[1440] Specific examples

[1441] For example, when a factory robot assembles parts, the server estimates the optimal deadline for the task based on past data. If the user feels stressed before performing this task, the server generates a reminder message saying, "Take a deep breath and start assembling the parts. You can do it!"

[1442] Prompt Sentence Examples

[1443] For the new task "Assemble parts," estimate the optimal deadline based on past data. Also, if the user feels stressed before performing this task, generate a reminder message to reduce stress.

[1444] In this way, the system can take the user's emotional state into account and provide reminders in a way that reduces stress, thereby improving the user's work efficiency.

[1445] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1446] Step 1:

[1447] The server reads service information (delivery date, etc.) and internal application deadlines.

[1448] Input: Service information, internal application deadline

[1449] Output: Loaded service information, internal application deadline

[1450] Specific operation: The server retrieves service information and internal application deadlines from the database and loads them into memory.

[1451] Step 2:

[1452] The server collects past task data and user behavior data.

[1453] Input: Past task data, user behavior data

[1454] Output: Collected task data, behavioral data

[1455] Specific operation: The server collects past task data and user behavior data from sensors and log files and stores them in a database.

[1456] Step 3:

[1457] The server uses machine learning algorithms to train a model that estimates optimal deadlines for tasks.

[1458] Input: Collected task data

[1459] Output: A trained task deadline estimation model

[1460] What it does: The server uses the scikit-learn library to train a random forest regression model on the collected task data.

[1461] Step 4:

[1462] The server uses machine learning algorithms to train a model that predicts emotional states.

[1463] Input: Collected user behavior data

[1464] Output: A trained emotional state prediction model

[1465] What it does: The server uses the scikit-learn library to train a random forest regression model based on collected user behavior data.

[1466] Step 5:

[1467] The server takes the new task and the user's behavioral data as input and estimates the task's deadline.

[1468] Input: New task data, a trained task deadline estimation model

[1469] Output: Estimated task deadline

[1470] What it does: The server inputs new task data into the trained model and estimates the optimal task deadline.

[1471] Step 6:

[1472] The server takes the behavioral data of a new user as input and predicts the emotional state.

[1473] Input: New user behavior data, trained emotional state prediction model

[1474] Output: Predicted emotional state

[1475] What it does: The server inputs new user behavior data into the trained model to predict the emotional state.

[1476] Step 7:

[1477] The server generates a reminder message according to the emotional state.

[1478] Input: predicted emotional state, task information

[1479] Output: Reminder message

[1480] Specific operation: The server generates a reminder message to reduce stress based on the predicted emotional state and task information.

[1481] Step 8:

[1482] The server notifies the user of the generated remind message.

[1483] Input: Reminder message

[1484] Output: User notification

[1485] What happens: The server uses email or a notification system to send the generated reminder message to the user.

[1486] Example 3

[1487] Next, a description will be given of Example 3 of Form Example 3. 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."

[1488] In the conventional system, it was possible to determine tasks based on service information and internal application deadlines and send reminders to salespeople, but it was not possible to send reminders that took into account the user's emotional state. As a result, it was not possible to send effective reminders that reflected the user's emotions, which led to a problem of reduced efficiency in sales activities.

[1489] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1490] In this invention, the server includes means for reading service information (delivery dates, etc.) and in-house application deadlines, means for determining what tasks should be completed by when in relation to the customer's desired delivery date, means for reminding the sales department of the determination results, means for collecting user input data, means for analyzing the user's emotional state, means for generating the contents of the reminder email based on the results of the emotion analysis, and means for sending the generated reminder email. This enables effective reminders that take the user's emotional state into consideration.

[1491] "Service information" refers to important information regarding the provision of services, such as delivery dates and internal application deadlines.

[1492] "Internal application deadline" refers to the deadline for completing the necessary procedures within the company.

[1493] "Customer desired delivery date" refers to the delivery date of a service or product desired by the customer.

[1494] A "task" refers to the work or activity that must be performed to achieve a specific goal.

[1495] A "remind" refers to a re-notification of specific information or tasks.

[1496] "User input data" refers to data such as text or voice that a user provides to the system.

[1497] "Emotional state" refers to the emotions such as joy, sadness, anger, etc. that a user is feeling.

[1498] "Emotion analysis" refers to the process of analyzing a user's input data to determine their emotional state.

[1499] "Reminder email" refers to an email sent to notify you of specific information or tasks.

[1500] A "natural language processing algorithm" refers to an algorithm that analyzes text data to understand meaning and emotion.

[1501] MODE FOR CARRYING OUT THE INVENTION

[1502] The present invention relates to a reminder system that takes into account the emotional state of a user. A specific embodiment of this system will be described below.

[1503] System configuration

[1504] This system consists of three main components: a server, a terminal, and a user. The server reads service information and internal application deadlines, determines the tasks required to meet the customer's desired delivery date, and sends reminders of the results to the sales department. It also collects user input data, analyzes their emotional state, and generates and sends reminder emails based on the results.

[1505] Hardware and software used

[1506] The server is a computer equipped with a high-performance processor and large memory capacity. Sentiment analysis requires software to run natural language processing algorithms, specifically IBM Watson and Google Cloud Natural Language API. Reminder emails are sent using Microsoft Outlook and Gmail email systems.

[1507] Data processing and calculation

[1508] The server first collects user input data. Users enter product reviews and feedback in text format and send it to the server via their devices. The server then passes this text data to a natural language processing algorithm to analyze the user's emotional state. The analysis results in a determination of whether the user is feeling emotions such as joy, sadness, or anger.

[1509] Next, the server generates the content of the reminder email based on the results of the sentiment analysis. For example, if it is determined that the user is feeling happy, the server generates a reminder email with the content, "The user is very satisfied with the product. Please consider offering a special discount coupon to further enhance the user's happiness."

[1510] Finally, the server automatically sends the generated reminder email to the sales department via the email system, who then receives the email and considers what action to take to further improve user satisfaction.

[1511] Specific examples

[1512] As a concrete example, consider the case where a user posts a review of a product. If the user's review contains the content "This product is truly amazing!", the sentiment analysis algorithm will determine that the user is feeling happy. Based on this determination, the server will send a reminder email to the sales department stating, "The user is very satisfied with the product. Please consider offering a special discount coupon to further enhance their happiness."

[1513] Prompt Sentence Examples

[1514] "Analyze user reviews to determine their emotional state. Then generate a reminder email to send to sales based on that emotional state."

[1515] In this way, the system can send effective reminders to salespeople that take into account the emotional state of the user. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1516] Step 1:

[1517] Users input product reviews and feedback in text format. The terminal sends this input data to the server. The input data is the text information entered by the user, and the output is the text data sent to the server.

[1518] Step 2:

[1519] The server passes the received user input data to an emotion analysis algorithm. Specifically, the server analyzes the text data using a "natural language processing algorithm." The input is the user's text data, and the output is an analysis result that indicates the user's emotional state (happiness, sadness, anger, etc.).

[1520] Step 3:

[1521] The server generates the content of the reminder email based on the results of the sentiment analysis. For example, if it is determined that the user is feeling happy, the server generates a reminder email with the content, "The user is very satisfied with the product. To further enhance their happiness, please consider offering a special discount coupon." The input is the result of the sentiment analysis, and the output is the content of the generated reminder email.

[1522] Step 4:

[1523] The server automatically sends the generated reminder email to the sales department using an email system. Specifically, the server sends the reminder email using the "email system." The input is the content of the generated reminder email, and the output is the reminder email sent to the sales department.

[1524] Step 5:

[1525] The sales department reviews the reminder emails they receive and considers actions to further increase user satisfaction. The input is the reminder email received by the sales department, and the output is the specific actions that the sales department will take.

[1526] In this way, the system can send effective reminders to salespeople that take into account the user's emotional state.

[1527] (Application example 3)

[1528] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1529] Conventional reminder systems send uniform messages without considering the user's emotional state, which limits the effectiveness of reminders. Furthermore, there was no way to provide appropriate reminders based on the user's emotions, making it difficult to maximize the user's motivation to purchase. This has led to a need to improve the effectiveness of reminders and encourage users to make purchases.

[1530] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1531] In this invention, the server includes means for reading service information (delivery dates, etc.) and in-house application deadlines, means for determining what tasks should be completed by when in relation to the customer's desired delivery date, means for reminding the sales department of the determination result, means for detecting the user's emotional state, means for adjusting the content of the reminder according to the emotional state, and means for automatically sending reminder emails. This enables effective reminders that take the user's emotional state into consideration, maximizing the user's desire to purchase.

[1532] "Service information" refers to important information related to business operations, such as delivery dates and internal application deadlines.

[1533] "Internal application deadline" refers to the final deadline for completing the necessary procedures within the company.

[1534] "Customer desired delivery date" refers to the delivery date of the product desired by the customer.

[1535] A "task" refers to the work or activity required to achieve a specific purpose.

[1536] "Decision result" refers to the result of the system deciding the timing and content of task execution.

[1537] "Sales" refers to a job that involves selling products and services.

[1538] A "remind" refers to sending a notification or message to encourage a specific action.

[1539] "User's emotional state" refers to the type and intensity of the emotion the user is currently feeling.

[1540] "Reminder Email" refers to a notification sent via email to encourage a specific action.

[1541] A "machine learning algorithm" refers to a computational method that automatically learns from data and makes predictions and judgments.

[1542] A system for carrying out this invention has the following configuration: The server includes means for reading service information (delivery date, etc.) and in-house application deadlines, means for determining what tasks should be completed by when in relation to the customer's desired delivery date, means for reminding sales of the determination result, means for detecting the user's emotional state, means for adjusting the content of the reminder depending on the user's emotional state, and means for automatically sending reminder emails.

[1543] Program processing explanation

[1544] Loading service information

[1545] The server reads service information (delivery dates and internal application deadlines) from a database, which can be, for example, an SQL database.

[1546] Task Judgment

[1547] The server uses a machine learning algorithm to determine what tasks should be completed by when in accordance with the customer's desired delivery date. This algorithm learns from past data and generates an optimal task schedule.

[1548] Implementing reminders

[1549] The server sends reminders to the salesperson based on the results of the judgment. The reminders are sent via email.

[1550] Emotional state detection

[1551] The server analyzes the user's behavioral data and past purchase history and uses a generative AI model to detect the user's emotional state. For example, if a user is very satisfied with a recent purchase, the server detects the emotion as "joy."

[1552] Adjustment of reminder content

[1553] The server tailors the reminder content depending on the detected emotional state: for example, if the user is feeling "joy," the reminder email will include a message that reinforces that emotion.

[1554] Sending reminder emails

[1555] The server automatically sends a reminder email containing the adjusted reminder content, for example, using the SMTP protocol.

[1556] Specific examples

[1557] For example, if a user is very happy with a recent purchase, we can detect that emotion and send them a message saying, "You have a great product in your cart! Buy now and enjoy even more!"

[1558] Prompt Sentence Examples

[1559] Create a program that detects the user's emotional state and sends them a reminder email based on that emotion. If the user is feeling happy, include a message that reinforces that emotion. Use the following information:

[1560] User ID: user123

[1561] Cart information: get_user_cart(user_id)

[1562] Emotion detection: detect_emotion(user_id)

[1563] Get email address: get_user_email(user_id)

[1564] Sending email: smtplib

[1565] In this way, effective reminders that take into account the user's emotional state are possible, thereby maximizing the user's motivation to purchase.

[1566] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1567] Step 1:

[1568] The server reads service information (delivery dates and internal application deadlines) from the database. Database connection information and a query are required as input, and the service information is obtained as output. Specifically, the server executes the SQL query and obtains the results.

[1569] Step 2:

[1570] The server uses a machine learning algorithm to determine what tasks should be completed by when in relation to the customer's desired delivery date. Service information and the customer's desired delivery date are required as input, and a task schedule is obtained as output. Specifically, the server uses a model learned from past data to generate an optimal task schedule.

[1571] Step 3:

[1572] The server sends a reminder to the salesperson based on the judgment result. The task schedule is required as input, and the content of the reminder email is obtained as output. Specifically, the server embeds the task schedule in the reminder email template and generates the email content.

[1573] Step 4:

[1574] The server analyzes the user's behavioral data and past purchase history and uses a generative AI model to detect the user's emotional state. The input is the user's behavioral data and purchase history, and the output is the emotional state. Specifically, the server inputs the data into the generative AI model and estimates the emotional state.

[1575] Step 5:

[1576] The server adjusts the content of the reminder email according to the detected emotional state. The inputs are the emotional state and the content of the reminder email, and the output is the adjusted content of the reminder email. Specifically, the server selects a message based on the emotional state and updates the content of the reminder email.

[1577] Step 6:

[1578] The server automatically sends a reminder email containing the adjusted reminder content. As input, the adjusted reminder content and the user's email address are required, and as output, the reminder email is sent. Specifically, the server sends the email using the SMTP protocol.

[1579] 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.

[1580] 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> ) 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.

[1581] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[1582] 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.

[1583] [Third embodiment]

[1584] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1585] 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.

[1586] 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).

[1587] 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.

[1588] 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.

[1589] 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).

[1590] 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.

[1591] 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.

[1592] 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.

[1593] 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.

[1594] 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.

[1595] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1596] "Example 1"

[1597] One embodiment of the present invention includes a means for reading service information (such as delivery dates) and in-house application deadlines from a database. This means can be realized, for example, by using a database management system. The database management system periodically obtains the service information and in-house application deadlines and updates them as necessary.

[1598] "Example 2"

[1599] There are also ways to determine what tasks should be completed by when in relation to the customer's desired delivery date. This can be achieved, for example, using machine learning algorithms. Machine learning algorithms learn from past data and estimate the optimal tasks and their deadlines for new service information and internal application deadlines.

[1600] "Example 3"

[1601] Furthermore, there is also a means for reminding the salesperson of the decision result. This means can be realized, for example, by using an email system. The email system automatically sends a reminder email to the salesperson based on the decision result.

[1602] The processing flow of each embodiment will be described below.

[1603] "Example 1"

[1604] Step 1: The database management system is operational and service information (delivery dates, etc.) and internal application deadlines are read from the database.

[1605] Step 2: Based on the information loaded, calculate the required tasks and their deadlines. For example, calculate the start and end dates for each task by working backwards from the delivery date requested by the customer.

[1606] Step 3: Based on the calculation results, a reminder email is sent to the sales team, clearly stating what tasks need to be completed and by when.

[1607] "Example 2"

[1608] Step 1: Machine learning algorithms are put to work, learning from past data.

[1609] Step 2: When new service information and internal application deadlines are entered, the trained model is used to estimate the optimal task and its deadline.

[1610] Step 3: Based on the estimation results, a reminder email is sent to the sales team, clearly stating what tasks need to be completed and by when.

[1611] "Example 3"

[1612] Step 1: The email system is operational and automatically sends reminder emails to sales staff based on the results of the decision.

[1613] Step 2: The email specifies what task needs to be completed by when, and which client and project it relates to.

[1614] Step 3: Sales receives the email and follows the instructions to complete the task.

[1615] Example 1

[1616] Next, a description will be given of Example 1 of Form 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."

[1617] In the previous system, management of service information and internal application deadlines was often done manually, resulting in the problem of time-consuming updates and confirmations of information. Furthermore, there was a lack of a way to determine the appropriate tasks for customer desired delivery dates and to send reminders to sales staff, which could lead to a decline in work efficiency. Furthermore, there was no way for users to quickly check the latest information, which could lead to work delays and mistakes.

[1618] 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.

[1619] In this invention, the server includes a means for reading service information and internal application deadlines, a means for determining what tasks should be completed by when in relation to the customer's desired delivery date, a means for reminding the sales department of the determination result, a means for periodically obtaining service information and internal application deadlines using a database management system and updating them as necessary, a means for a terminal to access the server to obtain data and display it to the user, and a means for the user to check the information through the terminal. This automates the management of service information and internal application deadlines, allowing for quick information updates and confirmations, improving work efficiency. Furthermore, by determining the appropriate tasks in relation to the customer's desired delivery date and reminding the sales department, it is possible to prevent work delays and errors.

[1620] "Service Information" refers to important information about the service, such as delivery dates and details of the services provided.

[1621] "Internal application deadline" refers to the deadline by which various internal applications must be completed.

[1622] "Database management system" means a software system for creating, managing, and manipulating databases.

[1623] A "server" refers to a computer system that provides data and services over a network.

[1624] "Terminal" refers to a device that allows a user to access a server and obtain data.

[1625] "User" refers to a person who uses the system to check service information and internal application deadlines.

[1626] "Reading means" refers to a method or device for obtaining the required information from the database.

[1627] "Means for determining" refers to a method or device for determining an appropriate task or action based on certain conditions.

[1628] "Means for reminding" refers to a method or device for notifying a user of specific information or tasks.

[1629] "Means for periodically acquiring and updating as necessary" refers to a method or device for acquiring data at regular intervals and updating the data if there are any changes.

[1630] "Means for accessing and obtaining data" refers to a method or device for connecting to a server and obtaining the required information.

[1631] The "display means" refers to a method or device for visually presenting the acquired information to the user.

[1632] "Means for checking" refers to a method or device for a user to view the acquired information and check its contents.

[1633] MODE FOR CARRYING OUT THE INVENTION

[1634] The present invention is a system for efficiently managing service information and in-house application deadlines and providing the information promptly to users. A specific embodiment of this system will be described below.

[1635] Server Processing

[1636] The server uses a database management system (DBMS) to read service information and internal application deadlines from a database. Specifically, a DBMS such as MySQL or PostgreSQL is used. The server periodically executes queries to obtain the latest service information and internal application deadlines, and updates the database as necessary. For example, the server executes the following SQL query:

[1637] sql

[1638] SELECT FROM service_info;

[1639] SELECT FROM internal_deadlines;

[1640] This will capture all data on service information and internal application deadlines.

[1641] Terminal handling

[1642] The device accesses the server using a web browser (e.g., Google Chrome) to obtain the latest service information and internal application deadlines. Specifically, it accesses the following URL:

[1643] http: / / example.com / api / service_info

[1644] http: / / example.com / api / internal_deadlines

[1645] This allows the device to retrieve JSON formatted data from the server. The device then parses the retrieved JSON data and displays it in a format that is easy for the user to view. For example, the device uses HTML and JavaScript to display the data as follows:

[1646] html

[1647]

[1648] <h2> Service Information< / h2>

[1649]

[1650] Service Name: New Service, Delivery Date: 2023-12-31

[1651]

[1652]

[1653]

[1654] <h2> Internal application deadline< / h2>

[1655]

[1656] Application Name: New Project, Deadline: 2023-11-30

[1657]

[1658]

[1659] This HTML code displays service information and internal application deadlines to the user.

[1660] User operations

[1661] The user checks the displayed service information and internal application deadlines through the device's web browser. For example, the user can use Google Chrome to check the displayed information and find out the latest delivery dates and application deadlines. The user accesses the following URL:

[1662] http: / / example.com / dashboard

[1663] By accessing this URL, users can check the latest service information and internal application deadlines.

[1664] Example prompts for generative AI models

[1665] Below are some example prompts to input to a generative AI model:

[1666] "Please let me know the latest service information and internal application deadlines."

[1667] Using this prompt, the generative AI model provides up-to-date service information and internal application deadlines.

[1668] In this way, the management of service information and internal application deadlines is automated, allowing information to be updated and confirmed quickly, improving work efficiency and preventing work delays and errors.

[1669] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1670] Step 1:

[1671] The server retrieves the service information and the internal application deadline from the database.

[1672] Input: Database connection information

[1673] What happens: The server connects to the MySQL database and executes the following SQL query:

[1674] sql

[1675] SELECT FROM service_info;

[1676] SELECT FROM internal_deadlines;

[1677] Data processing: Convert the query results into JSON format.

[1678] Output: JSON data of service information and internal application deadline

[1679] Step 2:

[1680] The server updates the retrieved data as needed.

[1681] Input: New service information and internal application deadlines

[1682] What happens: The server checks the retrieved data and, if there is new information, updates the database by executing the following SQL query:

[1683] sql

[1684] INSERT INTO service_info (service_name, due_date) VALUES ('New Service', '2023-12-31');

[1685] Data manipulation: Adding new data to existing data.

[1686] Output: Updated database

[1687] Step 3:

[1688] The terminal accesses the server to obtain the data.

[1689] Input: Server API endpoint URL

[1690] Specific operation: The device accesses the following URL using a web browser (e.g., Google Chrome):

[1691] http: / / example.com / api / service_info

[1692] http: / / example.com / api / internal_deadlines

[1693] Data processing: Analyze the JSON data obtained from the server.

[1694] Output: Parsed service information and internal application deadline data

[1695] Step 4:

[1696] The terminal displays the acquired data to the user.

[1697] Input: Parsed service information and internal application deadline data

[1698] What happens: The device uses HTML and JavaScript to display the data as follows:

[1699] html

[1700]

[1701] <h2> Service Information< / h2>

[1702]

[1703] Service Name: New Service, Delivery Date: 2023-12-31

[1704]

[1705]

[1706]

[1707] <h2> Internal application deadline< / h2>

[1708]

[1709] Application Name: New Project, Deadline: 2023-11-30

[1710]

[1711]

[1712] Data processing: Convert the acquired data into HTML format.

[1713] Output: Service information and internal application deadlines displayed to users

[1714] Step 5:

[1715] The user checks the information through the terminal.

[1716] Input: Device web browser

[1717] What happens: The user opens a web browser on their device and accesses the following URL:

[1718] http: / / example.com / dashboard

[1719] Data processing: Check the displayed information.

[1720] Output: Service information confirmed by the user and internal application deadline

[1721] In this way, the management of service information and internal application deadlines is automated, allowing information to be updated and confirmed quickly, improving work efficiency and preventing work delays and errors.

[1722] (Application example 1)

[1723] Next, a description will be given of Application Example 1 of Form 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."

[1724] In logistics centers, managing delivery dates and internal application deadlines is extremely important, but there is a lack of systems that can efficiently collect this information and suggest actions at the appropriate time. There is also a need for a function that suggests the optimal action based on prompts entered by the user.

[1725] 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.

[1726] In this invention, the server includes a means for reading service information (delivery dates, etc.) and in-house application deadlines, a means for determining what tasks should be completed by when in relation to the customer's desired delivery date, a means for reminding sales of the determination results, a means for using a generative AI model to propose optimal actions based on prompts entered by the user, and a means for periodically acquiring service information and application deadlines using a database management system and updating them as necessary. This enables efficient management of delivery dates and application deadlines at the logistics center and the proposal of optimal actions to users.

[1727] "Service information" is information relating to delivery dates and details of the services provided.

[1728] The "internal application deadline" is the deadline for carrying out necessary procedures and applications within the company.

[1729] "Customer desired delivery date" is the delivery date desired by the customer.

[1730] A "task" is an operation or activity that must be performed to achieve a specific purpose.

[1731] A "remind" is an act of drawing attention so that you do not forget.

[1732] A "generative AI model" is an algorithm that uses artificial intelligence to generate optimal actions based on user input.

[1733] A "prompt sentence" is a question or instruction sentence that a user enters into a system.

[1734] A "database management system" is software for creating, managing, and operating databases.

[1735] "Periodic acquisition" means collecting information at regular time intervals.

[1736] "Updating" means replacing existing information with new information.

[1737] The system for implementing this invention is designed to efficiently manage delivery dates and in-house application deadlines at a logistics center. The system includes the following main components:

[1738] server

[1739] The server has a means of reading service information (delivery dates, etc.) and internal application deadlines. Specifically, it uses a database management system (for example, SQLite or MySQL) to periodically retrieve service information and application deadlines and update them as necessary. This ensures that the latest information is always maintained.

[1740] The server also has a means of determining what tasks should be completed by when in relation to the customer's desired delivery date. This determination is made using machine learning algorithms (e.g., random forests and support vector machines), which automatically assigns appropriate tasks.

[1741] Furthermore, the server has a means to suggest the optimal action based on the prompt sentence entered by the user using a generative AI model, such as a natural language processing model like GPT-3.

[1742] Terminal

[1743] The terminals are smartphones or tablets used by managers and staff at the distribution center. The terminals display information obtained from the server and provide an interface for users to input prompt sentences.

[1744] User

[1745] The user is a manager or staff member of the distribution center. The user can input the following prompt sentences using a terminal:

[1746] "When is the next deadline?"

[1747] "When is the next application deadline?"

[1748] The server uses a generative AI model to suggest optimal actions based on these prompts, such as, "The next delivery date is October 15, 2023. Please make the necessary preparations."

[1749] Specific examples

[1750] For example, if a logistics center manager inputs the prompt "When is the next delivery date?", the server retrieves the latest delivery date information from the database and uses the generative AI model to suggest the following action: "The next delivery date is October 15, 2023. Please make the necessary preparations." This information is displayed on the terminal, allowing the manager to make the appropriate preparations.

[1751] In this way, the present invention realizes efficient management of delivery dates and application deadlines at the logistics center and proposes optimal actions to the user.

[1752] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1753] Step 1:

[1754] The server uses a database management system to periodically retrieve service information (delivery dates, etc.) and internal application deadlines, updating them as needed. The input is the latest information from the database, and the output is the updated service information and application deadlines. Specifically, the server executes SQL queries to retrieve data and updates it as needed.

[1755] Step 2:

[1756] The user inputs a prompt sentence using a terminal. The input is the prompt sentence entered by the user, and the output is the prompt sentence displayed on the terminal. In concrete terms, the user inputs text through the interface of the terminal.

[1757] Step 3:

[1758] The terminal sends the input prompt to the server. The input is the prompt entered by the user, and the output is the prompt sent to the server. In concrete terms, the terminal sends the prompt to the server via the network.

[1759] Step 4:

[1760] The server uses a generative AI model to suggest the optimal action based on the received prompt. The input is the prompt, and the output is the action suggestion generated by the generative AI model. Specifically, the server inputs the prompt into the generative AI model and obtains the output from the model.

[1761] Step 5:

[1762] The server sends the generated action proposals to the terminal. The input is the action proposal generated by the generative AI model, and the output is the action proposal sent to the terminal. Specifically, the server sends the action proposals to the terminal via the network.

[1763] Step 6:

[1764] The terminal displays the received action proposal to the user. The input is the action proposal sent from the server, and the output is the action proposal displayed on the terminal. Specifically, the terminal displays the action proposal on the screen.

[1765] Step 7:

[1766] The user makes the necessary preparations and takes action based on the action suggestions displayed. The input is the action suggestions displayed on the terminal, and the output is the specific action the user takes. As a specific action, the user proceeds with the work according to the suggestions.

[1767] Example 2

[1768] Next, a description will be given of Example 2 of Form 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."

[1769] Conventional project management systems have difficulty efficiently estimating optimal tasks and their deadlines based on the customer's desired delivery date. Furthermore, they lack the functionality to automatically generate task schedules based on new project information using past data. This has led to issues such as reduced project management efficiency and increased risk of delivery delays.

[1770] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1771] In this invention, the server includes means for reading service information and internal application deadlines, means for determining what tasks should be completed by when in relation to a customer's desired delivery date, means for reminding sales of the determination result, means for acquiring past data, means for preprocessing the acquired data, means for training a machine learning model, means for estimating tasks and deadlines based on new project information, and means for returning the estimation result to the user. This makes it possible to automatically generate an optimal task schedule based on new project information using past data, thereby improving the efficiency of project management.

[1772] "Service information" refers to information such as deadlines and requirements related to projects and work.

[1773] The "internal application deadline" is the deadline for various internal applications and procedures.

[1774] "Customer Desired Delivery Date" is the date the customer desires for the project or service to be completed.

[1775] A "task" is a specific task or activity required to complete a project or job.

[1776] A "remind" is a notification or alert that alerts you to make sure you don't forget.

[1777] "Historical data" refers to records and information relating to previously carried out projects or operations.

[1778] "Preprocessing" is the process of converting data into a form suitable for analysis or model training.

[1779] A "machine learning model" is an algorithm that learns patterns and rules from data and makes predictions and classifications for new data.

[1780] "Estimation" means predicting unknown values ​​or results based on existing information and data.

[1781] "User" refers to an individual or organization that uses the system.

[1782] The present invention is a system for estimating optimal tasks and their deadlines in relation to a customer's desired delivery date in a project management system. Specific embodiments of this system will be described below.

[1783] System program generation

[1784] The user generates a program for the project management system. This program includes means for reading service information and internal application deadlines, means for determining what tasks should be completed by when in relation to the customer's desired delivery date, means for reminding sales of the determination results, means for acquiring past data, means for preprocessing the acquired data, means for training a machine learning model, means for estimating tasks and deadlines based on new project information, and means for returning the estimation results to the user.

[1785] Explanation of program processing

[1786] The server processes and calculates data using the following hardware and software.

[1787] Hardware: The servers are a database server and an application server. The database server uses MySQL, and the application server has Python installed.

[1788] Software: The server uses the Python programming language and the Scikit-learn library to train and estimate machine learning models, and the Pandas library for data preprocessing.

[1789] Specifically, the data is processed and calculated in the following manner.

[1790] 1. Data retrieval: The server retrieves historical project data from a MySQL database, including project start and end dates, and details of each task.

[1791] 2. Data preprocessing: The server preprocesses the acquired data, including missing value imputation, data normalization, and categorical data encoding.

[1792] 3. Training the machine learning model: The server trains the machine learning model using the preprocessed data. The algorithm used is the random forest regression model.

[1793] 4. Task and deadline estimation: The server uses the trained model to estimate the start and end dates of each task based on new project information.

[1794] 5. Returning the results: The server returns the estimation results to the user in JSON format. The user can then check the estimated task schedule on their device screen.

[1795] Examples of specific examples and prompts

[1796] As a concrete example, consider the following scenario.

[1797] Examples:

[1798] The user enters the start date and customer desired delivery date of a new project. The server estimates the start and end dates of each task based on data from similar past projects. For example, if the project start date is October 1, 2023, and the customer desired delivery date is December 31, 2023, the server generates the following task schedule:

[1799] Task 1: October 1, 2023 - October 15, 2023

[1800] Task 2: October 16, 2023 - November 15, 2023

[1801] Task 3: November 16, 2023 - December 15, 2023

[1802] Example prompt sentence:

[1803] "The start date of a new project is October 1, 2023, and the customer's desired delivery date is December 31, 2023. Based on this, estimate the start and end dates for each task."

[1804] In this way, users can use the system to efficiently manage project schedules.

[1805] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1806] Step 1:

[1807] The user enters the project information.

[1808] Enter: Project start date and customer desired delivery date.

[1809] Specific operation: The user enters the project start date (e.g., October 1, 2023) and the customer's desired delivery date (e.g., December 31, 2023) into the input form on the terminal and clicks the "Submit" button.

[1810] Output: The entered project information is sent to the server.

[1811] Step 2:

[1812] The server retrieves past project data.

[1813] Input: Project information sent to the server.

[1814] Specific operation: The server connects to a MySQL database and retrieves past project data using SQL queries.

[1815] Output: Retrieved historical project data.

[1816] Step 3:

[1817] The server preprocesses the data.

[1818] Input: Captured historical project data.

[1819] Specific operation: The server converts the data into a data frame using the Pandas library and performs preprocessing such as filling in missing values, normalizing the data, and encoding categorical data.

[1820] Output: Preprocessed data.

[1821] Step 4:

[1822] The server trains the machine learning model.

[1823] Input: Preprocessed data.

[1824] What it does: The server trains a random forest regression model using the Scikit-learn library.

[1825] Output: A trained machine learning model.

[1826] Step 5:

[1827] The server estimates tasks and deadlines based on new project information.

[1828] Input: A trained machine learning model and new project information.

[1829] What it does: The server uses the trained model to estimate the start and end dates for each task based on new project information.

[1830] Output: The estimated task schedule.

[1831] Step 6:

[1832] The server returns the estimated results to the user.

[1833] Input: Estimated task schedule.

[1834] Specific operation: The server returns the estimation results to the user in JSON format.

[1835] Output: The estimated task schedule displayed on the user's terminal.

[1836] In this way, users can use the system to efficiently manage project schedules.

[1837] (Application example 2)

[1838] Next, a description will be given of Application Example 2 of Form 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."

[1839] In logistics centers, it is important to efficiently manage the optimal tasks and deadlines for customer orders. However, with conventional methods, it is difficult to estimate the optimal tasks and deadlines using past data, and work efficiency is not sufficiently improved. There is also a lack of means to grasp the progress of tasks in real time and to send appropriate reminders. For this reason, a new system is needed to improve the work efficiency of logistics centers.

[1840] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1841] In this invention, the server includes a means for reading service information (delivery dates, etc.) and in-house application deadlines, a means for determining what tasks should be completed by when in relation to the customer's desired delivery date, a means for reminding the worker of the determination result, a means for estimating the optimal tasks and their deadlines using a machine learning algorithm based on past data, and a means for displaying the estimated tasks and deadlines. This makes task management in the logistics center more efficient, enabling the progress of work to be grasped in real time and appropriate reminders to be sent.

[1842] "Service information" refers to information such as delivery dates and detailed requirements regarding orders from customers.

[1843] The "internal application deadline" is the deadline for various applications set in the internal business process.

[1844] "Customer desired delivery date" is the date and time of delivery of the product desired by the customer.

[1845] A "task" refers to a specific job or operation, such as order processing or shipping preparation at a logistics center.

[1846] A "remind" is the act of notifying a worker of a specific task or deadline and drawing their attention to it.

[1847] A "machine learning algorithm" is a computational method that learns patterns based on past data and makes predictions and classifications for new data.

[1848] "Estimation" is the act of predicting future events or outcomes based on existing data and information.

[1849] "Display" refers to the act of visually indicating estimated tasks and deadlines, and refers to outputting information on a screen or display.

[1850] A system for carrying out the present invention is intended to improve the efficiency of task management in a logistics center. A specific embodiment of the system will be described below.

[1851] System Configuration

[1852] The system consists of the following main components:

[1853] 1. Server: Responsible for data processing and running machine learning algorithms.

[1854] 2. Terminal: A device such as a smartphone or tablet used by a business employee.

[1855] 3. User: Logistics center operations staff.

[1856] Hardware and software used

[1857] Hardware: Smartphone (iOS or Android), server (with a powerful CPU and sufficient memory)

[1858] Software: Python, scikit-learn (machine learning library), pandas (data manipulation library)

[1859] Data processing and calculation

[1860] The server processes the data as follows:

[1861] 1. Data loading: Load past order data from a CSV file.

[1862] 2. Setting features and targets: Set features such as order size, order type, and season, and completion time as targets.

[1863] 3. Model Training: Train the machine learning model using RandomForestRegressor.

[1864] 4. Enter new order information: Enter new order information from the terminal.

[1865] 5. Task and Deadline Estimation: Using the trained model, we estimate the optimal tasks and their deadlines.

[1866] 6. Display results: Display estimated tasks and deadlines on your device.

[1867] Specific examples

[1868] Past data includes order size, order type, season, and completion time. For new order information, enter an order size of 10, order type as standard, and season as winter. From this, the server estimates the optimal task and its deadline and reminds the worker.

[1869] Prompt Sentence Examples

[1870] "Based on past logistics data, estimate the optimal tasks and their deadlines for an order size of 10, an order type of standard, and a season of winter."

[1871] This system will streamline task management at logistics centers, allowing for real-time understanding of work progress and appropriate reminders.

[1872] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1873] Step 1:

[1874] The server reads past order data from a CSV file.

[1875] Input: A CSV file containing historical order data.

[1876] Data processing: Convert the CSV file into a data frame using the pandas library.

[1877] Output: Historical order data in dataframe format.

[1878] Step 2:

[1879] The server sets the features and targets.

[1880] Input: Historical order data in dataframe format.

[1881] Data processing: Order size, order type, and season are extracted as features, and completion time is set as the target.

[1882] Output: A dataset of features and targets.

[1883] Step 3:

[1884] The server trains the machine learning model.

[1885] Input: Feature and target datasets.

[1886] Data computation: Train the model using scikit-learn's RandomForestRegressor.

[1887] Output: A trained machine learning model.

[1888] Step 4:

[1889] The terminal inputs new order information.

[1890] Input: New order information entered by the user (e.g., order size is 10, order type is standard, season is winter).

[1891] Data processing: Convert the input order information into a data frame.

[1892] Output: The new order information in a data frame format.

[1893] Step 5:

[1894] The server uses the trained model to estimate the optimal tasks and their deadlines.

[1895] Input: New order information in dataframe format, trained machine learning model.

[1896] Data calculation: New order information is input into the model and an estimated completion time is calculated.

[1897] Output: Estimated completion time and deadline.

[1898] Step 6:

[1899] The terminal displays estimated tasks and deadlines.

[1900] Inputs: Estimated completion time and deadline.

[1901] Specific behavior: Estimated tasks and deadlines are displayed on the device screen.

[1902] Output: Estimated tasks and deadlines are displayed visually for the worker.

[1903] Example 3

[1904] Next, a third embodiment of the third embodiment will be described. 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."

[1905] In the conventional system, there were limited means to determine tasks based on service information and internal application deadlines and to remind sales staff, making it difficult to operate efficiently.In addition, the process of generating judgment results based on prompts entered by users and reminding sales staff about them was not automated, so manual response was required, which was time-consuming and labor-intensive.

[1906] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1907] In this invention, the server includes means for the user to input a prompt sentence, means for the terminal to send the prompt sentence to the server, means for the server to pass the prompt sentence to the generative AI model, means for the generative AI model to generate a judgment result, means for the server to analyze the judgment result and create a reminder email as necessary, and means for the server to send the reminder email to the sales department. This makes it possible to automatically generate a judgment result based on the prompt sentence entered by the user and to efficiently remind the sales department.

[1908] "Service information" refers to information necessary for business operations, such as delivery dates and internal application deadlines.

[1909] "Customer desired delivery date" refers to the delivery date of the product desired by the customer.

[1910] A "task" refers to the work or activity that must be performed to achieve a specific goal.

[1911] "Judgment result" refers to the conclusion or recommended action generated based on the input information.

[1912] A "remind" refers to a re-notification of specific information or tasks.

[1913] A "prompt sentence" refers to a sentence containing a question or instruction that a user inputs to a system.

[1914] "Terminal" refers to a device such as a computer or smartphone operated by a user.

[1915] "Server" refers to a computer system that provides services over a network.

[1916] A "generative AI model" refers to an algorithm or system that uses artificial intelligence to generate judgment results from input data.

[1917] "Email" refers to digital messages sent and received over the Internet.

[1918] "SMTP Protocol" refers to the communications protocol used to send email.

[1919] This invention is a system that uses a generative AI model to generate a judgment result based on a prompt sentence entered by a user, and sends a reminder email to sales as necessary. A specific embodiment of this system is described below.

[1920] Hardware and software used

[1921] server

[1922] The server runs the program using Python and uses a general artificial intelligence model, specifically OpenAI's GPT-4, as the generative AI model. The server also uses Python's smtplib library to send emails using the SMTP protocol.

[1923] Terminal

[1924] The terminal provides an interface for the user to input a prompt sentence. The terminal uses a web browser to display a form for the user to input a prompt sentence. Specific web browsers used are Google Chrome and Mozilla Firefox.

[1925] User

[1926] The user inputs a prompt through the web browser on the terminal, for example, "Please tell me your sales forecast for the next quarter," and presses the send button.

[1927] Data processing and calculation

[1928] Entering and sending a prompt

[1929] When a user enters a prompt in the device's web browser and presses the submit button, the device sends the prompt as an HTTP POST request to the server, converting the form data into JSON format and sending it to the specified endpoint on the server.

[1930] Parsing prompts and generating results

[1931] The server analyzes the received prompt and passes it to the generative AI model. Specifically, the server uses Python's requests library to send a request including the prompt to the generative AI model's API. The generative AI model generates a judgment result based on the received prompt. For example, it generates a response such as, "Sales forecast for the next quarter are expected to increase by 10% compared to the same period last year."

[1932] Analysis of decision results and creation of reminder emails

[1933] The server analyzes the judgment results returned by the generative AI model. If the analysis results determine that a reminder to the salesperson is necessary, a reminder email is created. Specifically, the server includes the judgment results in the email body and sets the email address of the salesperson as the recipient.

[1934] Sending reminder emails

[1935] The server sends the created reminder email using the SMTP protocol. For example, it uses the Python smtplib library to send the email through a common SMTP server. The subject of the email should read "Important: Sales Forecast Reminder" and the body should contain the generated decision result.

[1936] Specific examples

[1937] Prompt Sentence Examples

[1938] An example of a prompt that a user can enter is, "Please tell me your sales forecast for the next quarter." When the user enters this prompt and presses the send button, the server uses the generative AI model to generate a sales forecast and sends the results as a reminder email to the sales department.

[1939] In this way, a system is constructed in which the server generates a judgment result based on the prompt sentence entered by the user and sends a reminder email to the sales department as necessary. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1940] Step 1:

[1941] The user enters a prompt statement.

[1942] The user opens a web browser on their device and accesses the specified URL. They enter a prompt in the form that appears and press the submit button. For example, they might enter, "Please tell me your sales forecast for the next quarter." The input data is the prompt.

[1943] Step 2:

[1944] The terminal sends the prompt to the server.

[1945] The terminal sends the prompt text entered by the user to the server as an HTTP POST request. At this time, the terminal converts the form data into JSON format and sends it to the specified endpoint of the server. The input data is the prompt text, and the output data is the JSON-formatted data sent to the server.

[1946] Step 3:

[1947] The server passes the prompt to the generative AI model.

[1948] The server parses the received prompt sentence and passes it to the generative AI model. Specifically, the server uses the Python requests library to send a request including the prompt sentence to the generative AI model's API. The input data is the prompt sentence in JSON format, and the output data is the request sent to the generative AI model.

[1949] Step 4:

[1950] The generative AI model generates the judgment result.

[1951] A generative AI model generates a judgment result based on the received prompt. For example, it generates a response such as, "Sales forecast for the next quarter are expected to increase by 10% compared to the same period last year." The input data is the prompt, and the output data is the generated judgment result.

[1952] Step 5:

[1953] The server analyzes the results of the decision and creates a reminder email if necessary.

[1954] The server analyzes the judgment results returned by the generative AI model. If it determines that a reminder is necessary for the salesperson based on the analysis results, it creates a reminder email. Specifically, the server includes the judgment results in the email body and sets the email address of the salesperson as the recipient. The input data is the generated judgment results, and the output data is the created reminder email.

[1955] Step 6:

[1956] The server sends a reminder email to sales.

[1957] The server sends the created reminder email using the SMTP protocol. For example, it uses Python's smtplib library to send the email through a common SMTP server. The email subject should read "Important: Sales Forecast Reminder" and the body should include the generated judgment result. The input data is the created reminder email, and the output data is the email sent to sales.

[1958] (Application example 3)

[1959] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1960] In conventional sales activities, it was difficult to determine the next sales activity to be carried out based on the customer's purchase history and inquiry details, and to remind sales representatives at the appropriate time. Furthermore, reminders were often done manually, which hindered efficient sales activities. This resulted in problems such as delays in customer responses and lost opportunities.

[1961] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1962] In this invention, the server includes a means for reading service information (delivery dates, etc.) and in-house application deadlines, a means for determining what tasks should be completed by when in relation to the customer's desired delivery date, a means for reminding sales of the determination results, a means for determining the next sales activity to be carried out based on the customer's purchase history and inquiry details, and a means for automatically sending reminder emails based on the determination results. This makes it possible to determine appropriate sales activities based on the customer's purchase history and inquiry details, and to automatically send reminder emails in a timely manner.

[1963] "Service information" refers to information necessary for carrying out business, such as delivery dates and internal application deadlines.

[1964] "Internal application deadline" refers to the deadline by which internal procedures and applications must be completed.

[1965] "Customer desired delivery date" refers to the delivery date of the product desired by the customer.

[1966] A "task" refers to the work or task that must be performed to achieve a specific goal.

[1967] "Decision-making means" refers to a method or device for determining the next action to be taken based on specific conditions or data.

[1968] "Reminder means" refers to a method or device that provides notifications or alerts to encourage necessary action based on specific information.

[1969] "Customer purchase history" refers to a record of products that a customer has previously purchased.

[1970] "Inquiry content" refers to the details of questions or requests from customers.

[1971] "Sales activities" refers to a series of tasks and actions taken to sell products or services.

[1972] "Reminder email" refers to an email sent with specific information or to encourage specific action.

[1973] "Automatic sending means" refers to a method or device that sends email without manual operation when specific conditions are met.

[1974] A system for implementing this invention includes means for reading service information (delivery dates, etc.) and internal application deadlines, means for determining what tasks should be completed by when in relation to the customer's desired delivery date, means for reminding sales of the results of the determination, means for determining the next sales activity to be carried out based on the customer's purchase history and inquiry details, and means for automatically sending reminder emails based on the results of the determination.

[1975] Hardware and software used

[1976] Hardware: Servers, smartphones

[1977] Software: Python, smtplib library, email.mime library

[1978] Data processing and calculation

[1979] The server first reads service information (delivery dates, etc.) and internal application deadlines from a database. Next, it uses a machine learning algorithm to determine what tasks should be completed by when in relation to the customer's desired delivery date. This algorithm generates an optimal task schedule based on past data.

[1980] Then, based on the results of the decision, a reminder email is generated to remind the sales representative, and this reminder email is sent automatically using the smtplib and email.mime libraries.

[1981] Specific examples

[1982] For example, if a customer inquires about a specific product, the server determines the next sales activity based on the content of the inquiry. The server analyzes the customer's purchase history and the content of the inquiry, and decides which sales activity to take next. For example, if the server determines that "please make a follow-up call to this customer," a reminder email containing that content is automatically sent to the sales representative.

[1983] Prompt Sentence Examples

[1984] "Create a Python program that determines the next sales activity to take based on the customer's purchase history and inquiry details, and sends a reminder email to the sales representative."

[1985] In this way, it becomes possible to determine appropriate sales activities based on the customer's purchase history and inquiry details, and to automatically send timely reminder emails.

[1986] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1987] Step 1:

[1988] The server reads service information (delivery date, etc.) and internal application deadlines from the database.

[1989] Input: Service information stored in the database and internal application deadlines.

[1990] Data processing: Execute database queries to obtain the required information.

[1991] Output: Service information and internal application deadline data.

[1992] Step 2:

[1993] The server uses machine learning algorithms to determine what tasks need to be completed by when in relation to the customer's desired delivery date.

[1994] Input: Customer desired delivery date, service information, internal application deadline.

[1995] Data calculation: Using machine learning algorithms, optimal task schedules are generated based on past data.

[1996] Output: Task schedule.

[1997] Step 3:

[1998] The server determines the next sales activity to be carried out based on the customer's purchase history and inquiry details.

[1999] Input: Customer purchase history, inquiry details.

[2000] Data calculation: Analyze customer data and determine the next sales activity.

[2001] Output: Sales activity decision results.

[2002] Step 4:

[2003] The server generates a reminder email based on the result of the determination.

[2004] Input: Sales activity decision results.

[2005] Data processing: Generate the content of the reminder email.

[2006] Output: Reminder email content.

[2007] Step 5:

[2008] The server automatically sends reminder emails using the smtplib and email.mime libraries.

[2009] Input: Reminder email content, sales representative's email address.

[2010] Data calculation: Executes the email sending process.

[2011] Output: A reminder email is sent to the sales rep.

[2012] In this way, appropriate sales activities can be determined based on the customer's purchase history and inquiries, and timely reminder emails can be automatically sent.

[2013] 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.

[2014] "Example 1"

[2015] One embodiment of the present invention is a system that combines an emotion engine. This system recognizes the user's emotions and adjusts the timing and content of reminders according to that emotional state. Specifically, if it determines that the user is feeling stressed, it can take operations that take the user's emotional state into consideration, such as reducing the frequency of reminders.

[2016] "Example 2"

[2017] The emotion engine also uses machine learning algorithms to learn and predict a user's emotional state. Specifically, it predicts the user's emotional state based on their past reactions and behavioral patterns, and then sends reminders accordingly. For example, if it determines that a user always feels stressed before performing a specific task, it will send reminders for that task in a way that reduces stress.

[2018] "Example 3"

[2019] Furthermore, this system can also adjust the content of reminders depending on the user's emotional state. For example, if it determines that the user is feeling joy, it can include a message in the reminder that reinforces that joy. This allows for more effective reminders that take the user's emotional state into account.

[2020] The processing flow of each embodiment will be described below.

[2021] "Example 1"

[2022] Step 1: The system recognizes emotions from the user's actions and reactions.

[2023] Step 2: The emotion engine determines the user's emotional state based on the recognized emotions.

[2024] Step 3: Adjust the timing and content of your reminders depending on your emotional state.

[2025] "Example 2"

[2026] Step 1: The emotion engine learns the user's emotional state from their past reactions and behavioral patterns.

[2027] Step 2: Predict the user's current emotional state based on the learned emotional state.

[2028] Step 3: Adjust the timing and content of your reminders based on your predicted emotional state.

[2029] "Example 3"

[2030] Step 1: The system recognizes emotions from the user's actions and reactions.

[2031] Step 2: The emotion engine determines the user's emotional state based on the recognized emotions.

[2032] Step 3: Tailor your reminders to your emotional state.

[2033] Example 1

[2034] Next, a description will be given of Example 1 of Form 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."

[2035] In the previous system, it was possible to read service information and internal application deadlines, but it was not possible to adjust the timing or content of reminders according to the user's emotional state. As a result, even if the user was feeling stressed, reminders were sent at a fixed frequency, which increased the burden on the user. Furthermore, because the content of reminders was uniform, it was not possible to respond flexibly according to the user's situation.

[2036] 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.

[2037] In this invention, the server includes a means for reading service information and in-house application deadlines, a means for determining what tasks should be completed by when in relation to the customer's desired delivery date, a means for reminding the sales department of the determination result, and a means for recognizing the user's emotions and adjusting the timing and content of the reminder according to the user's emotional state. This allows for reminders that take the user's emotional state into consideration, reduces the user's burden, and enables more effective task management.

[2038] "Service information" is information relating to delivery dates and details of the services provided.

[2039] "Internal application deadline" refers to the deadline by which the internal application procedure must be completed.

[2040] "Customer desired delivery date" refers to the delivery date desired by the customer.

[2041] A "task" refers to the work or activity that must be performed to achieve a specific goal.

[2042] A "remind" refers to a re-notification of specific information or tasks.

[2043] "User emotions" refers to the psychological state, such as stress or satisfaction, that the user feels.

[2044] "Emotional state" refers to the user's current psychological state, including states such as stress or relaxation.

[2045] A "machine learning algorithm" refers to a computational method for learning patterns based on data and making predictions and judgments.

[2046] MODE FOR CARRYING OUT THE INVENTION

[2047] This invention is a system that includes means for reading service information and internal application deadlines, means for determining what tasks should be completed by when in relation to the customer's desired delivery date, means for reminding sales of the results of the determination, and means for recognizing the user's emotions and adjusting the timing and content of the reminders according to the user's emotional state.

[2048] Server Processing

[2049] The server periodically reads service information and internal application deadlines from a database using a database management system (DBMS). Specifically, it uses a DBMS such as MySQL or PostgreSQL to obtain this information and update it as needed. For example, the server accesses the database at 2:00 AM every day to obtain the latest service information and application deadlines.

[2050] User Action

[2051] The user uses a system that combines an emotion engine. This system recognizes the user's emotions and adjusts the timing and content of reminders according to their emotional state. Specifically, if the system determines that the user is feeling stressed, it will take measures such as reducing the frequency of reminders. For example, if the user inputs "I'm busy today," the system will use that information to reduce the frequency of reminders.

[2052] Terminal handling

[2053] The device will then display a reminder to the user based on the adjusted reminder timing. For example, the user might see a notification like this on their device:

[2054] "The next application deadline is tomorrow. Don't forget."

[2055] Specific examples

[2056] Server processing example

[2057] The server accesses the MySQL database every day at 2 AM and executes the following query:

[2058] sql

[2059] SELECT FROM service_info WHERE update_time >= CURDATE();

[2060] This query retrieves the service information updated for that day.

[2061] User processing example

[2062] If a user types "I'm busy today," the emotion engine will determine that the user is stressed and reduce the frequency of reminders, specifically changing the usual hourly reminders to every three hours.

[2063] Prompt Sentence Examples

[2064] Examples of prompts to input to a generative AI model might include:

[2065] If the user types "I'm busy today," how would the emotion engine adjust the frequency of reminders?

[2066] This prompt tells the generative AI model how to adjust reminders based on the user's emotional state.

[2067] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2068] Step 1:

[2069] The server retrieves the service information and the internal application deadline from the database.

[2070] Input: Database connection information, SQL query

[2071] What happens: The server connects to the MySQL database and executes the following SQL query:

[2072] sql

[2073] SELECT FROM service_info;

[2074] SELECT FROM application_deadlines;

[2075] Output: Data set of acquired service information and internal application deadlines

[2076] Step 2:

[2077] The server periodically updates the information it has obtained.

[2078] Input: Recurring job schedule, database connection information

[2079] What happens: The server runs a cron job every day at 2 AM to retrieve the latest information from the database. For example, it runs the following script:

[2080] bash

[2081] ! / bin / bash

[2082] mysql -u username -p password -e "SELECT FROM service_info;" > / path / to / service_info.json

[2083] mysql -u username -p password -e "SELECT FROM application_deadlines;" > / path / to / application_deadlines.json

[2084] Output: JSON file containing the latest service information and internal application deadlines

[2085] Step 3:

[2086] A user accesses the system and the emotion engine recognizes the user's emotions.

[2087] Input: User input data (e.g., "I'm busy today")

[2088] How it works: When a user logs into the system and types "I'm busy today," the emotion engine analyzes the text and determines that the user is stressed.

[2089] Output: User's emotional state (e.g., stress)

[2090] Step 4:

[2091] The emotional engine adjusts the timing and content of reminders according to the user's emotional state.

[2092] Input: User's emotional state, reminder settings information

[2093] How it works: The emotion engine adjusts the timing and content of reminders based on the user's emotional state. For example, if it determines that the user is feeling stressed, it will change reminders from every hour to every three hours.

[2094] Output: Adjusted reminder timing and content

[2095] Step 5:

[2096] The device displays a reminder to the user.

[2097] Input: Adjusted reminder timing and content

[2098] Specific behavior: The device will display a notification to the user based on the adjusted reminder timing. For example, the following notification will be displayed:

[2099] "The next application deadline is tomorrow. Don't forget."

[2100] Output: Reminder notification displayed to the user

[2101] (Application example 1)

[2102] Next, a description will be given of Application Example 1 of Form 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."

[2103] In conventional production management systems, reminders are sent without taking into account the emotional state of the workers, which often causes stress for the workers and reduces production efficiency. In addition, the timing and content of reminders are fixed, which means that flexible responses based on the situation of each worker are not possible.

[2104] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means for reading service information (delivery dates, etc.) and in-house application deadlines, means for determining what tasks should be completed by when in relation to the customer's desired delivery date, means for reminding sales of the determination result, means for recognizing the user's emotional state using an emotion engine and adjusting the timing and content of reminders, and means for periodically acquiring and updating information using a database management system. This makes it possible to provide reminders according to the emotional state of workers, thereby improving production efficiency and reducing worker stress.

[2105] "Service information" refers to important information related to business operations, such as delivery dates and internal application deadlines.

[2106] "Internal application deadline" refers to the deadline by which various internal applications must be completed.

[2107] "Customer desired delivery date" refers to the delivery date of the product desired by the customer.

[2108] A "task" refers to an operation or activity performed to achieve a specific purpose.

[2109] A "reminder" is a notification that helps you avoid forgetting a specific task or deadline.

[2110] An "emotion engine" refers to technology that recognizes the user's emotional state and adjusts the system's behavior based on that information.

[2111] "User's emotional state" refers to the psychological state, such as stress or relaxation, that the user feels.

[2112] A "database management system" refers to software for creating, managing, and operating a database.

[2113] "Regularly acquiring and updating information" means collecting necessary information at regular intervals and keeping it up to date.

[2114] A "machine learning algorithm" refers to a computational method that automatically learns from data and makes predictions and judgments.

[2115] The system for carrying out this invention is configured as follows: The server includes means for reading service information (delivery dates, etc.) and in-house application deadlines, means for determining what tasks should be completed by when in relation to the customer's desired delivery date, means for reminding sales of the determination results, means for recognizing the user's emotional state using an emotion engine and adjusting the timing and content of reminders, and means for periodically acquiring and updating information using a database management system.

[2116] Program processing explanation

[2117] The server first uses a database management system (such as SQLite) to periodically retrieve and update service information and internal application deadlines. This ensures that the latest information is always available. Next, it uses an emotion engine (such as EmotionEngine) to recognize the user's emotional state. The emotion engine analyzes the user's facial expressions and voice through cameras and sensors to determine their emotional state, such as stress or relaxation.

[2118] After recognizing the user's emotional state, the server can adjust the timing and content of reminders based on that information. For example, if the user is stressed, the server will reduce the frequency of reminders and only remind them about important tasks. On the other hand, if the user is relaxed, the server will continue to remind them about all tasks as usual.

[2119] Specific examples

[2120] For example, if a factory worker is feeling stressed, the server will remind him / her only about important tasks and postpone other tasks. This reduces the worker's stress and improves production efficiency. On the other hand, if the worker is relaxed, the server will remind him / her about all tasks as usual, promoting efficient work.

[2121] Prompt Sentence Examples

[2122] By entering the following prompt statements into the generative AI model, you can generate system design and program code.

[2123] Design a system that adjusts the timing and content of reminders based on the user's emotional state. Retrieve the production schedule from a database and use an emotion engine to recognize the worker's emotions. If the worker is stressed, reduce the frequency of reminders and only remind them about important tasks. Please provide the specific program code.

[2124] In this way, the server can provide reminders according to the user's emotional state, thereby improving production efficiency and reducing worker stress.

[2125] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2126] Step 1:

[2127] The server uses a database management system (such as SQLite) to periodically retrieve and update service information and internal application deadlines. The input is a query from the database, and the output is the latest service information and internal application deadlines. In this step, an SQL query is executed against the database to retrieve the required information.

[2128] Step 2:

[2129] The server uses an emotion engine (such as EmotionEngine) to recognize the user's emotional state. The input is the user's facial expression and voice data acquired from a camera or sensor, and the output is the user's emotional state (stress, relaxation, etc.). In this step, the emotion engine analyzes the facial expression and voice data and determines the user's emotional state.

[2130] Step 3:

[2131] The server adjusts the timing and content of reminders based on the user's emotional state. The inputs are the service information and internal application deadlines obtained in step 1, and the user's emotional state obtained in step 2, and the output is an adjusted reminder schedule. In this step, if the user is feeling stressed, the server adjusts the schedule to reduce the frequency of reminders and only remind them of important tasks.

[2132] Step 4:

[2133] The server sends reminders based on the adjusted reminder schedule. The input is the reminder schedule adjusted in step 3, and the output is a reminder notification for the user. This step involves sending reminders to the user using email or a notification system.

[2134] Step 5:

[2135] The server records the result of the reminder transmission in the database. The input is the result of the reminder transmission, and the output is the updated database record. This step checks whether the reminder was sent successfully and stores the result in the database.

[2136] Through the above steps, the server can provide reminders according to the user's emotional state, thereby improving production efficiency and reducing worker stress.

[2137] Example 2 ...

Claims

1. A means for reading service information; A means for determining what tasks should be completed and by when in accordance with a customer desired delivery date obtained from the service information; A means for reminding the user of the result of the decision; A means for suggesting an optimal action based on a prompt sentence regarding sales activities input by the user using a generative AI model; A means for periodically acquiring the service information using a database management system and updating the information as necessary; A system including:

2. The system according to claim 1 , wherein the reminding means performs the reminding using email.

3. The system of claim 1 , wherein the means for determining performs task determination using a machine learning algorithm.

Images