System

Abstract

A system is provided.SOLUTION: A system comprising: means for analyzing a user's patterns and preferences using a generative model to generate an optimal schedule; terminal means for transmitting collected data to a server; and terminal means for receiving the generated schedule and displaying it to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In recent years, there has been a demand for more efficient time management among busy professionals. In particular, in urban areas of Japan, poor time management and a lack of work-life balance are common. This has led to serious problems such as burnout and reduced productivity. The present invention aims to solve these problems by generating optimal schedules that take into account individual patterns and preferences. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for analyzing a user's patterns and preferences using a generative model to generate an optimal schedule, a terminal means for transmitting collected data to a server, and a terminal means for receiving the generated schedule and displaying it to the user. This system allows users to obtain an optimal schedule that takes into account their work hours, break times, and preferred meeting times, enabling efficient time management and a balance between work and personal life. Furthermore, the effectiveness of the system can be enhanced by making an initial investment to optimize software development, model training, and user experience design.

[0006] A "generative model" is an artificial intelligence technology that analyzes input data such as user patterns and preferences and generates an optimal schedule from the results.

[0007] "User" refers to an individual or corporation that uses this system to manage their own schedule.

[0008] "Patterns and preferences" refers to information such as a user's daily behavior, specific time periods, and priorities for activities.

[0009] A "schedule" is a plan that shows the allocation of time for tasks and activities to be carried out over a specific period of time.

[0010] "Terminal" refers to the device that a user uses to input data and request schedule generation.

[0011] "Server" refers to a computer system that analyzes data received from terminals and generates a schedule using a generative model.

[0012] "Data" refers to information including user patterns, preferences, existing schedule information, and the like.

[0013] "Initial investment" refers to the funds required for system development, model training, and optimizing user experience design.

[0014] "Software development" refers to the design and implementation of programs and applications to realize the functions of this system.

[0015] "Model training" refers to the learning process that enables a generative model to generate accurate schedules.

[0016] "User experience design" refers to the process of designing a system so that users can use it comfortably and intuitively. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10]1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram illustrating a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] The present invention is a system that uses a generative model to analyze user patterns and preferences to generate an optimal schedule. In this system, data entered by the user is sent to a server, which then uses the generative model to generate a schedule and returns the results to the terminal for display to the user.

[0039] First, the user uses the device to input information related to their schedule. For example, the user inputs information such as "work hours," "lunch time," "preferred meeting times," etc. This input data is compiled in JSON format and sent to the server.

[0040] The data received from the device is analyzed by the server and converted into an appropriate format. The server then runs a generative model to generate an optimal schedule based on the user's patterns and preferences. The generative model takes into account the user's input data and creates a schedule by balancing task priorities, durations, break times, etc. The generated schedule is converted into JSON format and sent to the device as an HTTP response.

[0041] The device converts the schedule data received from the server into an internal format and displays it in an easy-to-read format for the user. The user can check this schedule and plan and execute daily tasks based on it. In addition, the generative model can learn more effectively based on user feedback and reflect this in the next schedule generation.

[0042] Next, the operation of the system will be explained using a concrete example.

[0043] As a concrete example, suppose a user starts a terminal application and inputs their "Work Hours" as "9:00-18:00", "Lunch Time" as "12:00-13:00", and "Preferred Meeting Times" as "10:00-11:00, 15:00-16:00". This information is compiled by the terminal in JSON format and sent to the server.

[0044] The server analyzes this data and uses a generative model to generate a schedule like this:

[0045] 09:00 - 09:30: Check email

[0046] 09:30 - 10:00: Preparation of materials

[0047] 10:00 - 11:00: Meeting 1

[0048] 11:00 - 12:00: Progress of Task A

[0049] 12:00 - 13:00: Lunch break

[0050] 13:00 - 15:00: Progress of Task B

[0051] 15:00 - 16:00: Meeting 2

[0052] 16:00 - 18:00: Progress of Task C

[0053] The generated schedule is sent from the server to the device, which receives it and displays it to the user. The user can then use this new schedule to efficiently complete their daily tasks. Initial investments in software development, generative model training, and user experience design can be used to optimize the system, further improving the user's quality of life.

[0054] In this way, the present invention generates an optimal schedule that takes into account the user's patterns and preferences, enabling efficient time management and improved quality of life.

[0055] The processing flow will be explained below.

[0056] Step 1:

[0057] A user launches a terminal application and enters schedule-related information such as work hours, lunch time, and preferred meeting times through the terminal UI.

[0058] Step 2:

[0059] The device collects the information entered by the user and converts it into JSON format. For example, if a user enters their work hours as 9:00-18:00, their lunch time as 12:00-13:00, and their preferred meeting times as 10:00-11:00 and 15:00-16:00, the information is compiled as follows:

[0060] json

[0061] {

[0062] "user_id": "12345",

[0063] "preferences": {

[0064] "work_hours": "9:00-18:00",

[0065] "lunch_break": "12:00-13:00",

[0066] "preferred_meeting_times": ["10:00-11:00", "15:00-16:00"]

[0067] },

[0068] "existing_schedule": {}

[0069] }

[0070] Step 3:

[0071] The device sends this JSON data to the server as an HTTP POST request. The endpoint is specified as / schedule, for example.

[0072] Step 4:

[0073] The server receives the HTTP POST request sent from the device. The server obtains the JSON format data from the request body, parses it, and converts it to the internal data format.

[0074] Step 5:

[0075] The server passes the analyzed data to the generative model, which analyzes the user's patterns and preferences based on the user ID, schedule preference information, and existing schedule information.

[0076] Step 6:

[0077] The generative model takes into account user input data and generates an optimal schedule by balancing task priorities, required times, and break times. For example, the following schedule may be generated:

[0078] 09:00 - 09:30: Check email

[0079] 09:30 - 10:00: Preparation of materials

[0080] 10:00 - 11:00: Meeting 1

[0081] 11:00 - 12:00: Progress of Task A

[0082] 12:00 - 13:00: Lunch break

[0083] 13:00 - 15:00: Progress of Task B

[0084] 15:00 - 16:00: Meeting 2

[0085] 16:00 - 18:00: Progress of Task C

[0086] Step 7:

[0087] The schedule generated by the generative model is converted into JSON format by the server and sent to the terminal as an HTTP response.

[0088] Step 8:

[0089] The terminal parses the HTTP response received from the server and converts the JSON data into an internal data format. After obtaining the new schedule information, the terminal displays the schedule in an easy-to-read format for the user.

[0090] Step 9:

[0091] The user checks the new schedule displayed on the terminal, and can efficiently carry out daily tasks based on the generated schedule.

[0092] Step 10:

[0093] Based on user feedback and actual schedule history, the generative model further learns and reflects this in the next schedule generation, resulting in a more personalized schedule.

[0094] Example 1

[0095] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0096] Conventional scheduling systems struggle to efficiently manage time because they fail to fully reflect users' patterns and preferences. Furthermore, continuous optimization is difficult because there is no mechanism for automatically improving the model based on user feedback. As a result, there are limitations to improving users' quality of life and the accuracy of task management.

[0097] 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.

[0098] In this invention, the server includes: means for analyzing a user's patterns and preferences using a generative model and generating an optimal schedule; terminal means for the user to input information related to the schedule and send it to the server in JSON format; means for the server to analyze the received data, execute the generative model to generate a schedule, and return the result in JSON format to the terminal; terminal means for receiving the generated schedule and visually displaying it to the user; and means for further training the generative model based on feedback from the user. This enables efficient schedule generation that reflects the user's individual patterns and preferences, and by continuously improving the model, more accurate task management and improved quality of life are possible.

[0099] A "generative model" is a machine learning algorithm used to analyze user patterns and preferences and generate optimal schedules.

[0100] "User" refers to a person or organization that inputs schedule-related information and transmits it to the server via a terminal.

[0101] "Terminal" refers to a device such as a computer, tablet, or smartphone that a user uses to input schedule-related information.

[0102] "Server" refers to a networked computer system that receives and analyzes data sent by users, executes generative models to generate optimal schedules, and returns them to the terminals.

[0103] "JSON format" is an abbreviation for JavaScript Object Notation, and is a format for structuring data and expressing it in text format.

[0104] An "HTTP request" refers to a request based on a protocol for a terminal to send and receive data to a server.

[0105] An "HTTP response" refers to data sent by a server in response to an HTTP request received from a terminal.

[0106] "Feedback" refers to opinions and evaluations provided by users regarding the generated schedule, and is used to improve the generative model.

[0107] The present invention is a system that uses a generative model to analyze user patterns and preferences to generate an optimal schedule. In this system, data entered by the user is sent to a server, which then uses the generative model to generate a schedule and returns the results to the terminal for display to the user.

[0108] Specifically, a user uses a terminal to input information related to their schedule. For example, the user inputs information such as "work hours," "lunch time," "preferred meeting times," etc. This input data is compiled in JSON format and sent to the server.

[0109] The server analyzes the data received from the device and converts it into an appropriate format. Python's json module can be used for analysis. The server then runs a generative model built using libraries such as TensorFlow and PyTorch to generate an optimal schedule based on the user's patterns and preferences. The generative model takes into account the user's input data and creates a schedule by balancing task priorities, required times, break times, and other factors.

[0110] The generated schedule is converted back to JSON format and sent to the device as an HTTP response. The device converts the schedule data received from the server into an internal format and displays it in an easy-to-read format for the user. The user can check this schedule and plan and execute daily tasks based on it.

[0111] Users can also provide feedback based on their experience using the schedule. The server uses this feedback to further train the generative model and reflect it in the next schedule generation. This cycle allows the system to be continuously optimized, enabling it to continue providing the best schedule for the user.

[0112] For example, if a user launches a terminal application and enters their "work hours" as "9:00-18:00," "lunchtime" as "12:00-13:00," and "preferred meeting times" as "10:00-11:00, 15:00-16:00," this information is compiled by the terminal in JSON format and sent to the server. The server analyzes this data and uses a generative model to generate the following schedule:

[0113] 09:00 - 09:30: Check email

[0114] 09:30 - 10:00: Preparation of materials

[0115] 10:00 - 11:00: Meeting 1

[0116] 11:00 - 12:00: Progress of Task A

[0117] 12:00 - 13:00: Lunch break

[0118] 13:00 - 15:00: Progress of Task B

[0119] 15:00 - 16:00: Meeting 2

[0120] 16:00 - 18:00: Progress of Task C

[0121] The generated schedule is sent from the server to the device, which receives it and displays it to the user, allowing the user to efficiently complete daily tasks based on this new schedule.

[0122] Below is an example of a prompt sentence to input to the generative AI model.

[0123] "User's schedule data:

[0124] Working hours: 9:00-18:00

[0125] Lunchtime: 12:00-13:00

[0126] Preferred meeting times: 10:00-11:00, 15:00-16:00

[0127] Generate an optimal daily schedule based on the information above.

[0128] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0129] Step 1:

[0130] Users launch the application on their device and enter information related to their schedule, such as "work hours," "lunch time," and "preferred meeting times." This information is formatted in JSON format.

[0131] Input: Schedule information entered by the user (e.g., work hours, lunch times, meeting times, etc.)

[0132] Output: Schedule information formatted in JSON format

[0133] Step 2:

[0134] The device sends the entered JSON format data to the server using an HTTP request. Specifically, the entered schedule information is formatted appropriately and sent to the specified URL.

[0135] Input: Schedule information in JSON format

[0136] Output: HTTP request to the server

[0137] Step 3:

[0138] The server receives the HTTP request sent from the terminal. This process uses server software such as Apache or Nginx. It extracts and analyzes the JSON data contained in the body of the HTTP request.

[0139] Input: HTTP request sent from the terminal

[0140] Output: Parsed schedule information

[0141] Step 4:

[0142] The server decodes the received JSON data using Python's json module and converts it into an internal format, extracts the appropriate fields, and converts them into a data structure for input to the generative model.

[0143] Input: Parsed schedule information (JSON format)

[0144] Output: A data structure to feed into the generative model.

[0145] Step 5:

[0146] The server runs a generative AI model to generate an optimal schedule. The generative model uses TensorFlow and PyTorch. Based on user input data, the model considers the priority, duration, and break times of each task to generate a balanced and appropriate schedule.

[0147] Input: The data structure to input to the model.

[0148] Output: The generated schedule

[0149] Step 6:

[0150] The server converts the generated schedule back into JSON format and sends it back to the terminal as an HTTP response. This conversion is performed using the Python json module. The generated schedule is included in the body of the HTTP response.

[0151] Input: Generated schedule

[0152] Output: JSON formatted schedule, HTTP response

[0153] Step 7:

[0154] The device processes the HTTP response received from the server and parses the JSON-formatted schedule data using JavaScript's fetch API or XMLHttpRequest.

[0155] Input: HTTP response received from the server

[0156] Output: Parsed schedule data

[0157] Step 8:

[0158] The terminal converts the analyzed schedule data into an internal format and processes it for display on the user interface. Specifically, it visually displays the schedule using HTML and CSS.

[0159] Input: Parsed schedule data

[0160] Output: A schedule that is visually displayed to the user

[0161] Step 9:

[0162] The user can then view the displayed schedule, plan and execute their daily tasks based on it, and provide feedback if necessary, which is then formatted into JSON and sent from the device to the server.

[0163] Input: User feedback

[0164] Output: Feedback data formatted in JSON format

[0165] Step 10:

[0166] The server analyzes the received feedback and adds it to the training dataset of the generative model, which then reflects the feedback in the next schedule generation, allowing the system to continuously optimize.

[0167] Input: Feedback data in JSON format

[0168] Output: Updated training dataset, optimized generative model

[0169] (Application example 1)

[0170] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0171] Conventional schedule management systems tend to generate schedules that do not match actual usage conditions because they do not fully consider individual user patterns and preferences. Furthermore, task schedules for factory robots often require manual adjustments, limiting their efficient operation. This leads to problems such as reduced labor productivity and wasted time and effort. Furthermore, efficient task management for users and robots is difficult, and this situation needed to be improved.

[0172] 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.

[0173] In this invention, the server includes means for analyzing user patterns and preferences using a generative model and generating an optimal schedule, terminal means for transmitting collected data to the server, terminal means for receiving the generated schedule and displaying it to the user, and means for generating and optimizing task schedules for factory robots, thereby enabling schedule generation according to individual user needs and efficient task management for factory robots.

[0174] A "generative model" is a type of artificial intelligence used to analyze user patterns and preferences and generate optimal schedules.

[0175] The term "terminal means" refers to a device that allows a user to input information and a device that receives and displays a schedule generated from a server.

[0176] A "factory robot" is a mechanical device that automatically performs tasks within a factory and requires a schedule for efficient operation.

[0177] A "task schedule" is a plan that determines the allocation, order, and time slots of tasks within a specific period of time.

[0178] A "server" is a central processing unit that receives information from multiple terminals, generates a schedule using a generative model, and returns the results to the terminals.

[0179] "Collected data" refers to all information necessary for generating a schedule, such as information entered by users into terminals and operating information of factory robots.

[0180] "Priority" is a criterion that indicates which task is more important than others, and is taken into consideration when generating a schedule.

[0181] "Rest time" refers to a time period set for users or factory robots to take a rest while they are operating.

[0182] "Initial investment" refers to the funds and resources required to deploy the system, including software development, generative model training, and user experience design.

[0183] "User experience design" is a design process that aims to improve the experience users have when using a system.

[0184] The present invention is a system that uses a generative model to analyze user patterns and preferences to generate an optimal schedule. In this system, data entered by the user is sent to a server, which then uses the generative model to generate a schedule and returns the results to the terminal for display to the user.

[0185] First, a user uses a device (e.g., a tablet or PC) to input information related to their schedule. For example, a user might input information such as "work hours," "break times," and "preferred meeting times," or, in the case of a factory robot, "tasks in charge," "priority," and "break times." This input data is compiled in JSON format and sent to the server.

[0186] The server receives the input data, parses it, and converts it into the appropriate format. This data analysis is performed using Python-based scripts. The server then runs a generative AI model (such as GPT-4) to generate an optimal schedule based on the user's patterns and preferences. This generative model takes into account the user's input data and balances task priorities, durations, break times, and other factors to create a schedule.

[0187] The generated schedule is converted back to JSON format and sent to the device as an HTTP response. The device then converts the schedule data received from the server into an internal format and displays it in an easy-to-read format for the user.

[0188] As a concrete example, let's say the user is a factory manager and enters the following information:

[0189] {

[0190] "Operating hours": "08:00-17:00",

[0191] "Task": [

[0192] {"Name": "Welding work", "Priority": "High", "Duration": 60},

[0193] {"Name": "Quality Inspection", "Priority": "Medium", "Time Required": 30},

[0194] {"Name": "Transport", "Priority": "Low", "Duration": 45}

[0195] ],

[0196] "Break Time": "12:00-13:00"

[0197] }

[0198] This information is sent from the device to a server, and a generative AI model generates an optimal schedule that looks like this:

[0199] Generate an optimal schedule for the factory robots based on the following data:

[0200] Operating hours: 08:00-17:00

[0201] task:

[0202] Welding (High Priority, 60 minutes)

[0203] Quality Inspection (Priority: Medium, Time: 30 minutes)

[0204] Transport (Priority: Low, Time: 45 minutes)

[0205] Break time: 12:00-13:00

[0206] The generated schedule looks like this:

[0207] 08:00 - 09:00: Welding work

[0208] 09:00 - 09:30: Quality inspection

[0209] 09:30 - 10:15: Transport

[0210] 10:15 - 11:15: Welding work

[0211] 11:15 - 12:00: Quality inspection

[0212] 12:00 - 13:00: Break

[0213] 13:00 - 14:00: Transport

[0214] 14:00 - 15:00: Welding work

[0215] 15:00 - 15:30: Quality inspection

[0216] 15:30 - 16:15: Transport

[0217] 16:15 - 17:00: Quality inspection

[0218] This schedule is received from the server and displayed on the terminal, allowing users to check it and efficiently manage the operation of factory robots. This is expected to improve factory productivity and work efficiency. In addition, by investing initial funds in software development, generative model training, and user experience design, the system can be optimized to more effectively meet user demands.

[0219] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0220] Step 1:

[0221] Users use devices (e.g., tablets or PCs) to input schedule information, including work hours, break times, preferred meeting times, factory robot tasks, priorities, and required times. The input data is compiled in JSON format and sent to the server.

[0222] Input: Schedule-related information entered by the user into the device

[0223] Output: Data organized in JSON format

[0224] Step 2:

[0225] The server receives JSON-formatted data sent from the device. To receive this data, an HTTP request handler must be set up. The server analyzes the received data and converts it into a format suitable for the generative model. For this purpose, a Python json library or similar is used.

[0226] Input: JSON format data sent from the terminal

[0227] Output: Parsed and transformed schedule-related data

[0228] Step 3:

[0229] The server uses a generative AI model (e.g., GPT-4) to generate an optimal schedule. To do this, a prompt is first generated and sent to the generative model. The generative AI model then takes the input data into account and creates a schedule that balances task priorities, required time, break times, etc.

[0230] Input: Parsed and transformed schedule-related data, and generated prompt statements

[0231] Output: Schedule data generated by the generative AI model

[0232] Step 4:

[0233] The generated schedule is converted back to JSON format and sent to the terminal as an HTTP response. The server uses an HTTP communication library such as Python to generate the HTTP response.

[0234] Input: Generated schedule data

[0235] Output: Generated schedule data converted to JSON format

[0236] Step 5:

[0237] The terminal converts the schedule data received from the server into an internal format and displays it in an easy-to-read format for the user. The GUI application used for display is usually implemented using HTML, CSS, JavaScript, etc. This allows the user to check their schedule and manage tasks efficiently.

[0238] Input: Generated schedule data in JSON format received from the server

[0239] Output: Schedule information displayed on the device screen in a user-friendly format

[0240] 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.

[0241] This invention is a system that uses a generative model and an emotion engine to analyze a user's patterns, preferences, and emotional state to generate an optimal schedule. This system comprehensively analyzes data entered by the user and emotional information collected by the emotion engine, generates an optimal schedule for the user on the server, and displays it on the terminal.

[0242] First, the user inputs information related to their schedule via their device. Specifically, the user enters information such as "work hours," "lunch time," and "priority meeting times" into an input form on the device. The emotion engine then recognizes the user's emotions in real time and collects that information. For example, it can analyze facial expressions using the user's camera or extract emotions from their voice.

[0243] The device converts this information into JSON format and sends it to the server. The server analyzes the data and integrates the output of the generative model and emotion engine. The generative model generates a schedule based on the user's patterns and preferences, and the emotion engine adjusts the schedule according to the user's emotional state.

[0244] For example, if a user is feeling stressed, the emotion engine's output is fed back to the generative model, which adjusts the schedule to increase relaxation and rest time. In this way, a schedule is generated that optimizes the user's emotional state.

[0245] The server converts the generated schedule into JSON format and sends it to the device as an HTTP response. The device analyzes the received data and displays the new schedule in an easy-to-read format for the user. The user can plan and execute daily tasks based on this schedule. In addition, the generative model and emotion engine further learn based on user feedback and actual schedule history, and the learning is reflected in the next schedule generation.

[0246] As a concrete example, consider the case where a user launches a terminal application and inputs their "work hours" as "9:00-18:00," "lunchtime" as "12:00-13:00," and "priority meeting times" as "10:00-11:00, 15:00-16:00." Furthermore, suppose the emotion engine recognizes the user's face and determines their current emotion as "stressed." The server's generative model integrates the input information and the emotion engine's results to generate the following schedule:

[0247] 09:00 - 09:30: Check email

[0248] 09:30 - 10:00: Preparation of materials

[0249] 10:00 - 11:00: Meeting 1

[0250] 11:00 - 12:00: Progress of Task A

[0251] 12:00 - 13:00: Lunch break

[0252] 13:00 - 14:00: Relaxation time

[0253] 14:00 - 15:00: Progress of Task B

[0254] 15:00 - 16:00: Meeting 2

[0255] 16:00 - 17:00: Progress of Task C

[0256] 17:00 - 18:00: Easy stress relief activities

[0257] This schedule takes into account the user's work and meeting times, and is adjusted to reflect the user's stress level using the emotion engine. Based on this schedule, users can carry out their daily tasks efficiently and in a balanced manner.

[0258] As described above, the present invention provides an optimal schedule that takes into account a user's emotional state as well as their patterns and preferences, thereby improving the user's productivity and quality of life.

[0259] The processing flow will be explained below.

[0260] Step 1:

[0261] The user launches a terminal application and enters schedule-related information such as work hours (e.g., 9:00-18:00), lunch time (e.g., 12:00-13:00), and preferred meeting times (e.g., 10:00-11:00, 15:00-16:00) through the terminal UI.

[0262] Step 2:

[0263] The emotion engine recognizes the user's emotions. The device analyzes the user's facial expressions and voice in real time to collect emotional information. For example, it can detect "stress" from the user's facial expressions using camera footage.

[0264] Step 3:

[0265] The device converts the schedule information entered by the user and the emotional information recognized by the emotion engine into JSON format. Specifically, the data is summarized as follows:

[0266] json

[0267] {

[0268] "user_id": "12345",

[0269] "preferences": {

[0270] "work_hours": "9:00-18:00",

[0271] "lunch_break": "12:00-13:00",

[0272] "preferred_meeting_times": ["10:00-11:00", "15:00-16:00"]

[0273] },

[0274] "emotion": "stress",

[0275] "existing_schedule": {}

[0276] }

[0277] Step 4:

[0278] The device sends this compiled JSON data to the server as an HTTP POST request. The endpoint is, for example, / schedule.

[0279] Step 5:

[0280] The server receives the HTTP POST request sent from the device. The server obtains the JSON format data from the request body, parses it, and converts it to the internal data format.

[0281] Step 6:

[0282] The server passes the analyzed data to the generative model and emotion engine. The generative model generates a schedule based on the user's patterns and preferences, and the emotion engine further adjusts the generated schedule using the user's emotion information.

[0283] Step 7:

[0284] The generative model first generates a standard schedule based on user input data. This schedule balances task priority, duration, and break times. For example, the following schedule might be generated:

[0285] 09:00 - 09:30: Check email

[0286] 09:30 - 10:00: Preparation of materials

[0287] 10:00 - 11:00: Meeting 1

[0288] 11:00 - 12:00: Progress of Task A

[0289] 12:00 - 13:00: Lunch break

[0290] 13:00 - 15:00: Progress of Task B

[0291] 15:00 - 16:00: Meeting 2

[0292] 16:00 - 18:00: Progress of Task C

[0293] Step 8:

[0294] The emotion engine adjusts the schedule based on the standard schedule according to the user's emotion information. For example, if the emotion engine determines that the user's emotion is "stress," it adjusts the schedule to increase break time and relaxation time. The adjusted schedule will look like this:

[0295] 09:00 - 09:30: Check email

[0296] 09:30 - 10:00: Preparation of materials

[0297] 10:00 - 11:00: Meeting 1

[0298] 11:00 - 12:00: Progress of Task A

[0299] 12:00 - 13:00: Lunch break

[0300] 13:00 - 14:00: Relaxation time

[0301] 14:00 - 15:00: Progress of Task B

[0302] 15:00 - 16:00: Meeting 2

[0303] 16:00 - 17:00: Progress of Task C

[0304] 17:00 - 18:00: Easy stress relief activities

[0305] Step 9:

[0306] The server converts the schedule generated and adjusted by the generative model and emotion engine into JSON format and sends it to the terminal as an HTTP response.

[0307] Step 10:

[0308] The terminal parses the HTTP response received from the server and converts the JSON data into an internal data format. After obtaining the new schedule information, the terminal displays the schedule in an easy-to-read format for the user.

[0309] Step 11:

[0310] The user can check the new schedule displayed on the terminal and efficiently carry out daily tasks based on the generated schedule.

[0311] Step 12:

[0312] Based on user feedback and actual schedule history, the generative model and emotion engine further learn and reflect this in the next schedule generation, resulting in a more personalized schedule that optimally reflects the user's emotional state.

[0313] Example 2

[0314] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0315] Conventional schedule generation systems only analyze user patterns and preferences, but are unable to consider the user's emotional state. As a result, they may generate schedules that ignore the user's stress and fatigue, making it difficult for the user to complete tasks efficiently. Furthermore, they lacked a learning function that utilizes user feedback and schedule history, making it difficult to generate schedules that are optimized for individual users' needs.

[0316] 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.

[0317] In this invention, the server includes means for analyzing a user's patterns and emotional state using a generative model and an emotion recognition engine to generate an optimal schedule, means for acquiring data entered by the user and emotional information collected by the emotion recognition engine at a terminal and transmitting the data to the server, and means for receiving a schedule generated based on the analyzed data by the server and displaying it to the user. This makes it possible to generate an optimal schedule that reflects the user's emotional state, and furthermore, a learning function based on user feedback and schedule history makes it possible to provide a more personalized schedule for the user.

[0318] A "generative model" is an algorithm that generates an optimal schedule based on a user's patterns and preferences.

[0319] An "emotion recognition engine" is a software component that recognizes and analyzes a user's emotional state in real time.

[0320] A "pattern" is a consistent tendency or habit based on a user's behavior or preferences.

[0321] "Preferences" refer to tasks and time allocations that the user particularly prefers.

[0322] A "schedule" is a plan that arranges a user's daily tasks and events in time.

[0323] A "terminal" is an electronic device that allows a user to input and display information.

[0324] "Server" refers to the central computer system that analyzes data sent from the terminals and generates and adjusts schedules.

[0325] "Data transmission" refers to the process of sending information from a terminal to a server.

[0326] "Data analysis" refers to the process by which the server processes the data it receives to extract useful information.

[0327] "Feedback" refers to opinions and ratings that users provide to a system, which the system uses to learn and improve based on that information.

[0328] "Learning function" refers to the system's ability to improve future performance based on past data and feedback.

[0329] MODE FOR CARRYING OUT THE INVENTION

[0330] This invention is a system that uses a generative model and an emotion recognition engine to analyze a user's patterns, preferences, and emotional state to generate an optimal schedule. This system comprehensively analyzes data entered by the user and emotional information collected by the emotion recognition engine, generates an optimal schedule on the server, and displays it on the terminal.

[0331] First, the user inputs information related to their schedule via their device. Specifically, the user enters information such as "work hours," "lunch time," and "priority meeting times" into an input form on the device. The emotion recognition engine then recognizes the user's emotions in real time and collects that information. For example, the device's camera can be used to analyze facial expressions and extract emotional information from voice data.

[0332] The device converts the information entered by the user and the emotion data collected by the emotion recognition engine into JSON format and sends it to the server using an HTTP request, for example, as a POST request to "https: / / server.url / schedule."

[0333] The server analyzes the received data and integrates the outputs of the generative model and the emotion recognition engine. The generative model generates an initial schedule based on the user's patterns and preferences. The emotion recognition engine then adjusts the generated schedule based on the user's emotional state. For example, if the user is feeling stressed, the engine may add relaxation time or breaks to the generated schedule.

[0334] The server converts the final adjusted schedule into JSON format and sends it to the device as an HTTP response. The device then analyzes the received data and displays the schedule in a user-friendly format, enabling users to plan and complete their daily tasks based on an efficient and balanced schedule.

[0335] Furthermore, user feedback and actual schedule history are sent to the server, and the generative model and emotion recognition engine use this data for training, which is reflected in the next schedule generation, providing a more personalized schedule for the user.

[0336] As a concrete example, suppose a user enters the following information into a terminal:

[0337] Working hours: 9:00-18:00

[0338] Lunchtime: 12:00-13:00

[0339] Preferred meeting times: 10:00-11:00, 15:00-16:00

[0340] If the emotion recognition engine recognizes the user's face and determines that the current emotion is "stress," the generative model on the server will generate the following schedule:

[0341] 09:00 - 09:30: Check email

[0342] 09:30 - 10:00: Preparation of materials

[0343] 10:00 - 11:00: Meeting 1

[0344] 11:00 - 12:00: Progress of Task A

[0345] 12:00 - 13:00: Lunch break

[0346] 13:00 - 14:00: Relaxation time

[0347] 14:00 - 15:00: Progress of Task B

[0348] 15:00 - 16:00: Meeting 2

[0349] 16:00 - 17:00: Progress of Task C

[0350] 17:00 - 18:00: Easy stress relief activities

[0351] An example prompt is:

[0352] "Generate the best schedule for your users based on their current situation. Create a schedule based on the following information:

[0353] Working hours: 9:00-18:00

[0354] Lunchtime: 12:00-13:00

[0355] Preferred meeting times: 10:00-11:00, 15:00-16:00

[0356] Furthermore, the emotion recognition engine determined that the user's emotion was 'stress'.

[0357] In this way, the system provides an optimal schedule that takes into account the user's patterns and preferences as well as their emotional state, improving their productivity and quality of life.

[0358] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0359] Step 1:

[0360] User Data Input

[0361] The user enters schedule-related information such as "work hours," "lunchtime," and "preferred meeting times" into an input form on the terminal. Specifically, the user enters "work hours" as "9:00-18:00," "lunchtime" as "12:00-13:00," and "preferred meeting times" as "10:00-11:00, 15:00-16:00." After entering the information, the user presses the send button. The input in this step is schedule information manually entered by the user, and the output is temporary data stored in the terminal.

[0362] Step 2:

[0363] Emotional Data Collection

[0364] The device collects the user's emotional data using an emotion recognition engine. The device's camera is used to analyze the user's facial expressions in real time, and the emotion recognition engine recognizes "stress" from the facial expressions. If there is voice input, the device extracts emotions from the voice data. The input for this step is the user's facial and voice data, and the output is emotional data analyzed by the emotion recognition engine.

[0365] Step 3:

[0366] Data transmission

[0367] The device combines the schedule information entered by the user with the emotion data collected by the emotion recognition engine and converts it into JSON format. It then sends the data to the server using an HTTP request. For example, the destination is a POST request to "https: / / server.url / schedule." The input of this step is the schedule information and emotion data, and the output is the data converted into JSON format.

[0368] Step 4:

[0369] Data analysis

[0370] The server parses the received JSON data and extracts the user's schedule information and emotional state. This analysis is typically performed using programming languages ​​such as Python or Java. The input for this step is JSON-formatted data, and the output is the parsed schedule information and emotional data.

[0371] Step 5:

[0372] Schedule Generation

[0373] The server's generative model generates an initial schedule based on the analyzed schedule information and user patterns. For example, it arranges tasks such as "09:00-09:30: Check email" and "09:30-10:00: Prepare documents." The input of this step is the analyzed schedule information, and the output is an initial schedule proposal.

[0374] Step 6:

[0375] Schedule adjustment

[0376] The generated initial schedule is adjusted based on the output of the emotion recognition engine. For example, if the user is recognized as "stressed," relaxation time or rest time is added to the schedule. The input of this step is the initial schedule and emotion data, and the output is the adjusted final schedule.

[0377] Step 7:

[0378] Scheduled Sending

[0379] The server converts the adjusted final schedule into JSON format and sends it to the terminal as an HTTP response. The input of this step is the adjusted final schedule, and the output is the transmission of JSON format data.

[0380] Step 8:

[0381] Schedule Display

[0382] The device parses the received JSON data and displays the schedule in a visually easy-to-understand format. For example, it may use the in-app calendar function to display the schedule in a color-coded format. The input of this step is the JSON data received from the server, and the output is a visual schedule display that the user can view.

[0383] Step 9:

[0384] Feedback gathering and learning

[0385] The user enters feedback on the task they performed into a feedback form within the device app. For example, they answer questions such as, "Was today's schedule appropriate?" The device sends this feedback to the server, and the server's generative model and emotion recognition engine use the data for training. The input of this step is the user's feedback data, and the output is the trained generative model and emotion recognition engine.

[0386] As a result, the system improves users' productivity and quality of life by providing an optimal schedule that takes into account their emotional state as well as their patterns and preferences.

[0387] (Application example 2)

[0388] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0389] In modern society, stress and busyness make it difficult for users to efficiently manage their schedules. Furthermore, there is a lack of systems that can recommend optimal content and tasks according to a user's emotional state, which means that users are unable to find appropriate ways to relax or progress with their work according to their emotions.

[0390] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing a user's patterns and preferences using a generative model and generating an optimal schedule, terminal means for transmitting collected data to the server, terminal means for receiving the generated schedule and displaying it to the user, means for analyzing the user's emotional state using an emotion engine, and means for adjusting the schedule based on the emotional state. This allows the user to obtain an optimal schedule based on not only their own patterns and preferences but also their emotional state recognized in real time. Furthermore, appropriate content and relaxation methods are simultaneously suggested based on the user's emotional state, allowing them to perform daily tasks efficiently and comfortably.

[0391] A "generative model" is an algorithm that takes data as input, analyzes user patterns and preferences, and generates output tailored to a specific purpose.

[0392] A "pattern" is a recurring feature that indicates a user's tendencies in behavior or choices.

[0393] "Preferences" are specific activities, content, or options that a user prefers.

[0394] An "optimal schedule" is a timetable or plan that maximizes a user's efficiency and comfort, based on the user's patterns, preferences, and emotional state.

[0395] "Means" refers to a device, system, algorithm, or other technical means used to achieve a specific purpose.

[0396] A "server" is a computer system that provides a set of computing resources for storing, analyzing, and processing data.

[0397] A "terminal" is a device or apparatus that a user directly operates to input, display, and transmit information.

[0398] An "emotion engine" is an algorithm or system that analyzes a user's facial expressions, voice, and behavioral data to identify their emotional state in real time.

[0399] "Collecting" refers to the act or process of gathering necessary data, which in the present invention refers to data relating to the user's emotional state, behavioral patterns, and preferences.

[0400] "Analysis" is the process of examining collected data in detail and deriving meaning and trends from it.

[0401] "Tuning" is the act or process of changing components to optimize them based on specific conditions.

[0402] "Relaxation methods" refer to specific means or activities for reducing the user's stress and resting the mind and body.

[0403] "Content" refers to the information media consumed by users, including, for example, movies, music, videos, etc.

[0404] This invention is a system that uses a generative model and an emotion engine to analyze a user's patterns, preferences, and emotional state to generate an optimal schedule. This system comprehensively analyzes data entered by the user and emotional information collected by the emotion engine, generates an optimal schedule for the user on the server, and displays it on the terminal.

[0405] First, the user inputs information related to their schedule via their device. Specifically, the user enters information such as "work hours," "lunch time," and "priority meeting times" into an input form on the device. The emotion engine then recognizes the user's emotions in real time and collects that information. For example, it can analyze facial expressions using the user's camera or extract emotions from their voice.

[0406] The device converts this information into JSON format and sends it to the server. The server analyzes the data and integrates the output of the generative model and emotion engine. The generative model generates a schedule based on the user's patterns and preferences, and the emotion engine adjusts the schedule according to the user's emotional state.

[0407] The server uses a machine learning algorithm as a generative model to learn the user's past behavioral data and patterns. Specifically, a deep learning model (e.g., TensorFlow) can be used. Furthermore, a library for analyzing the user's emotional state in real time (e.g., OpenCV, Microsoft Azure's Emotion API) can be used as an emotion engine.

[0408] For example, if a user is feeling stressed, the output of the emotion engine is fed back to the generative model, which adjusts the schedule to increase relaxation and rest periods. In this way, a schedule is generated to optimize the user's emotional state. The server converts the generated schedule into JSON format and sends it to the device as an HTTP response. The device analyzes the received data and displays the new schedule in an easy-to-read format for the user. The user can plan and execute daily tasks based on this schedule.

[0409] As a concrete example, consider the case where a user launches a terminal application and inputs their "work hours" as "9:00-18:00," "lunchtime" as "12:00-13:00," and "priority meeting times" as "10:00-11:00, 15:00-16:00." Furthermore, suppose the emotion engine recognizes the user's face and determines their current emotion as "stressed." The server's generative model integrates the input information and the emotion engine's results to generate the following schedule:

[0410] ---

[0411] Example prompt sentence:

[0412] If the user is "stressed", generate a schedule like this:

[0413] 09:00 - 10:00: Relaxation music

[0414] 10:00 - 11:00: Comedy movie

[0415] 11:00 - 12:00: Light fitness videos

[0416] 12:00 - 13:00: Lunch break

[0417] 13:00 - 14:00: Reflection and journaling

[0418] 14:00 - 15:00: Music appreciation (selected songs)

[0419] 15:00 - 16:00: Meditation video

[0420] Based on this schedule, users can take effective actions that are tailored to their own emotions and patterns.

[0421] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0422] Step 1:

[0423] A user inputs information related to his or her schedule (such as "work hours," "lunch time," and "priority meeting times") via a terminal. This information is entered into the terminal using an input form. The input data is used as the initial data required to generate a schedule.

[0424] Input: Schedule-related information (work time, lunch time, meeting time, etc.)

[0425] Output: Structured input data

[0426] Step 2:

[0427] The device uses the user's camera and microphone to analyze the user's facial expressions and voice in real time, and the emotion engine recognizes the user's emotional state. This emotion information is fed back to the generative model.

[0428] Input: Real-time data from camera and microphone

[0429] Output: Parsed emotional state information

[0430] Step 3:

[0431] The device converts the collected schedule information and emotional state information into JSON format and sends it to the server. This data becomes the initial dataset for schedule generation.

[0432] Input: Structured input data and parsed emotional state information

[0433] Output: JSON format data

[0434] Step 4:

[0435] The server analyzes the received data and uses a generative model to analyze the user's patterns and preferences. The generative model uses a deep learning-based model (e.g., TensorFlow). The generative model learns the user's behavioral patterns from past data and generates an optimal schedule.

[0436] Input: JSON format data

[0437] Output: An initial schedule that reflects user patterns and preferences

[0438] Step 5:

[0439] The server then feeds back the analysis results of the emotion engine to the generative model and adjusts the schedule based on the user's emotional state. For example, if the user is feeling stressed, the schedule may be adjusted to increase relaxation time.

[0440] Input: Initial schedule, emotional state information

[0441] Output: An optimized schedule that reflects emotional state

[0442] Step 6:

[0443] The server converts the generated optimized schedule into JSON format and sends it to the terminal as an HTTP response. The optimized schedule is structured in a format that is visually easy for users to understand.

[0444] Input: Optimized schedule reflecting emotional state

[0445] Output: Response data in JSON format

[0446] Step 7:

[0447] The device analyzes the received data and displays the schedule in an easy-to-read format for the user, who can then plan and execute their daily tasks.

[0448] Input: Response data in JSON format

[0449] Output: A visual representation of the schedule

[0450] 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.

[0451] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0452] 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.

[0453] [Second embodiment]

[0454] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0455] 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.

[0456] 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).

[0457] 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.

[0458] 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.

[0459] 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).

[0460] 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.

[0461] 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.

[0462] 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.

[0463] 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.

[0464] 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.

[0465] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0466] The present invention is a system that uses a generative model to analyze user patterns and preferences to generate an optimal schedule. In this system, data entered by the user is sent to a server, which then uses the generative model to generate a schedule and returns the results to the terminal for display to the user.

[0467] First, the user uses the device to input information related to their schedule. For example, the user inputs information such as "work hours," "lunch time," "preferred meeting times," etc. This input data is compiled in JSON format and sent to the server.

[0468] The data received from the device is analyzed by the server and converted into an appropriate format. The server then runs a generative model to generate an optimal schedule based on the user's patterns and preferences. The generative model takes into account the user's input data and creates a schedule by balancing task priorities, durations, break times, etc. The generated schedule is converted into JSON format and sent to the device as an HTTP response.

[0469] The device converts the schedule data received from the server into an internal format and displays it in an easy-to-read format for the user. The user can check this schedule and plan and execute daily tasks based on it. In addition, the generative model can learn more effectively based on user feedback and reflect this in the next schedule generation.

[0470] Next, the operation of the system will be explained using a concrete example.

[0471] As a concrete example, suppose a user starts a terminal application and inputs their "Work Hours" as "9:00-18:00", "Lunch Time" as "12:00-13:00", and "Preferred Meeting Times" as "10:00-11:00, 15:00-16:00". This information is compiled by the terminal in JSON format and sent to the server.

[0472] The server analyzes this data and uses a generative model to generate a schedule like this:

[0473] 09:00 - 09:30: Check email

[0474] 09:30 - 10:00: Preparation of materials

[0475] 10:00 - 11:00: Meeting 1

[0476] 11:00 - 12:00: Progress of Task A

[0477] 12:00 - 13:00: Lunch break

[0478] 13:00 - 15:00: Progress of Task B

[0479] 15:00 - 16:00: Meeting 2

[0480] 16:00 - 18:00: Progress of Task C

[0481] The generated schedule is sent from the server to the device, which receives it and displays it to the user. The user can then use this new schedule to efficiently complete their daily tasks. Initial investments in software development, generative model training, and user experience design can be used to optimize the system, further improving the user's quality of life.

[0482] In this way, the present invention generates an optimal schedule that takes into account the user's patterns and preferences, enabling efficient time management and improved quality of life.

[0483] The processing flow will be explained below.

[0484] Step 1:

[0485] A user launches a terminal application and enters schedule-related information such as work hours, lunch time, and preferred meeting times through the terminal UI.

[0486] Step 2:

[0487] The device collects the information entered by the user and converts it into JSON format. For example, if a user enters their work hours as 9:00-18:00, their lunch time as 12:00-13:00, and their preferred meeting times as 10:00-11:00 and 15:00-16:00, the information is compiled as follows:

[0488] json

[0489] {

[0490] "user_id": "12345",

[0491] "preferences": {

[0492] "work_hours": "9:00-18:00",

[0493] "lunch_break": "12:00-13:00",

[0494] "preferred_meeting_times": ["10:00-11:00", "15:00-16:00"]

[0495] },

[0496] "existing_schedule": {}

[0497] }

[0498] Step 3:

[0499] The device sends this JSON data to the server as an HTTP POST request. The endpoint is specified as / schedule, for example.

[0500] Step 4:

[0501] The server receives the HTTP POST request sent from the device. The server obtains the JSON format data from the request body, parses it, and converts it to the internal data format.

[0502] Step 5:

[0503] The server passes the analyzed data to the generative model, which analyzes the user's patterns and preferences based on the user ID, schedule preference information, and existing schedule information.

[0504] Step 6:

[0505] The generative model takes into account user input data and generates an optimal schedule by balancing task priorities, required times, and break times. For example, the following schedule may be generated:

[0506] 09:00 - 09:30: Check email

[0507] 09:30 - 10:00: Preparation of materials

[0508] 10:00 - 11:00: Meeting 1

[0509] 11:00 - 12:00: Progress of Task A

[0510] 12:00 - 13:00: Lunch break

[0511] 13:00 - 15:00: Progress of Task B

[0512] 15:00 - 16:00: Meeting 2

[0513] 16:00 - 18:00: Progress of Task C

[0514] Step 7:

[0515] The schedule generated by the generative model is converted into JSON format by the server and sent to the terminal as an HTTP response.

[0516] Step 8:

[0517] The terminal parses the HTTP response received from the server and converts the JSON data into an internal data format. After obtaining the new schedule information, the terminal displays the schedule in an easy-to-read format for the user.

[0518] Step 9:

[0519] The user checks the new schedule displayed on the terminal, and can efficiently carry out daily tasks based on the generated schedule.

[0520] Step 10:

[0521] Based on user feedback and actual schedule history, the generative model further learns and reflects this in the next schedule generation, resulting in a more personalized schedule.

[0522] Example 1

[0523] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0524] Conventional scheduling systems struggle to efficiently manage time because they fail to fully reflect users' patterns and preferences. Furthermore, continuous optimization is difficult because there is no mechanism for automatically improving the model based on user feedback. As a result, there are limitations to improving users' quality of life and the accuracy of task management.

[0525] 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.

[0526] In this invention, the server includes: means for analyzing a user's patterns and preferences using a generative model and generating an optimal schedule; terminal means for the user to input information related to the schedule and send it to the server in JSON format; means for the server to analyze the received data, execute the generative model to generate a schedule, and return the result in JSON format to the terminal; terminal means for receiving the generated schedule and visually displaying it to the user; and means for further training the generative model based on feedback from the user. This enables efficient schedule generation that reflects the user's individual patterns and preferences, and by continuously improving the model, more accurate task management and improved quality of life are possible.

[0527] A "generative model" is a machine learning algorithm used to analyze user patterns and preferences and generate optimal schedules.

[0528] "User" refers to a person or organization that inputs schedule-related information and transmits it to the server via a terminal.

[0529] "Terminal" refers to a device such as a computer, tablet, or smartphone that a user uses to input schedule-related information.

[0530] "Server" refers to a networked computer system that receives and analyzes data sent by users, executes generative models to generate optimal schedules, and returns them to the terminals.

[0531] "JSON format" is an abbreviation for JavaScript Object Notation, and is a format for structuring data and expressing it in text format.

[0532] An "HTTP request" refers to a request based on a protocol for a terminal to send and receive data to a server.

[0533] An "HTTP response" refers to data sent by a server in response to an HTTP request received from a terminal.

[0534] "Feedback" refers to opinions and evaluations provided by users regarding the generated schedule, and is used to improve the generative model.

[0535] The present invention is a system that uses a generative model to analyze user patterns and preferences to generate an optimal schedule. In this system, data entered by the user is sent to a server, which then uses the generative model to generate a schedule and returns the results to the terminal for display to the user.

[0536] Specifically, a user uses a terminal to input information related to their schedule. For example, the user inputs information such as "work hours," "lunch time," "preferred meeting times," etc. This input data is compiled in JSON format and sent to the server.

[0537] The server analyzes the data received from the device and converts it into an appropriate format. Python's json module can be used for analysis. The server then runs a generative model built using libraries such as TensorFlow and PyTorch to generate an optimal schedule based on the user's patterns and preferences. The generative model takes into account the user's input data and creates a schedule by balancing task priorities, required times, break times, and other factors.

[0538] The generated schedule is converted back to JSON format and sent to the device as an HTTP response. The device converts the schedule data received from the server into an internal format and displays it in an easy-to-read format for the user. The user can check this schedule and plan and execute daily tasks based on it.

[0539] Users can also provide feedback based on their experience using the schedule. The server uses this feedback to further train the generative model and reflect it in the next schedule generation. This cycle allows the system to be continuously optimized, enabling it to continue providing the best schedule for the user.

[0540] For example, if a user launches a terminal application and enters their "work hours" as "9:00-18:00," "lunchtime" as "12:00-13:00," and "preferred meeting times" as "10:00-11:00, 15:00-16:00," this information is compiled by the terminal in JSON format and sent to the server. The server analyzes this data and uses a generative model to generate the following schedule:

[0541] 09:00 - 09:30: Check email

[0542] 09:30 - 10:00: Preparation of materials

[0543] 10:00 - 11:00: Meeting 1

[0544] 11:00 - 12:00: Progress of Task A

[0545] 12:00 - 13:00: Lunch break

[0546] 13:00 - 15:00: Progress of Task B

[0547] 15:00 - 16:00: Meeting 2

[0548] 16:00 - 18:00: Progress of Task C

[0549] The generated schedule is sent from the server to the device, which receives it and displays it to the user, allowing the user to efficiently complete daily tasks based on this new schedule.

[0550] Below is an example of a prompt sentence to input to the generative AI model.

[0551] "User's schedule data:

[0552] Working hours: 9:00-18:00

[0553] Lunchtime: 12:00-13:00

[0554] Preferred meeting times: 10:00-11:00, 15:00-16:00

[0555] Generate an optimal daily schedule based on the information above.

[0556] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0557] Step 1:

[0558] Users launch the application on their device and enter information related to their schedule, such as "work hours," "lunch time," and "preferred meeting times." This information is formatted in JSON format.

[0559] Input: Schedule information entered by the user (e.g., work hours, lunch times, meeting times, etc.)

[0560] Output: Schedule information formatted in JSON format

[0561] Step 2:

[0562] The device sends the entered JSON format data to the server using an HTTP request. Specifically, the entered schedule information is formatted appropriately and sent to the specified URL.

[0563] Input: Schedule information in JSON format

[0564] Output: HTTP request to the server

[0565] Step 3:

[0566] The server receives the HTTP request sent from the terminal. This process uses server software such as Apache or Nginx. It extracts and analyzes the JSON data contained in the body of the HTTP request.

[0567] Input: HTTP request sent from the terminal

[0568] Output: Parsed schedule information

[0569] Step 4:

[0570] The server decodes the received JSON data using Python's json module and converts it into an internal format, extracts the appropriate fields, and converts them into a data structure for input to the generative model.

[0571] Input: Parsed schedule information (JSON format)

[0572] Output: A data structure to feed into the generative model.

[0573] Step 5:

[0574] The server runs a generative AI model to generate an optimal schedule. The generative model uses TensorFlow and PyTorch. Based on user input data, the model considers the priority, duration, and break times of each task to generate a balanced and appropriate schedule.

[0575] Input: The data structure to input to the model.

[0576] Output: The generated schedule

[0577] Step 6:

[0578] The server converts the generated schedule back into JSON format and sends it back to the terminal as an HTTP response. This conversion is performed using the Python json module. The generated schedule is included in the body of the HTTP response.

[0579] Input: Generated schedule

[0580] Output: JSON formatted schedule, HTTP response

[0581] Step 7:

[0582] The device processes the HTTP response received from the server and parses the JSON-formatted schedule data using JavaScript's fetch API or XMLHttpRequest.

[0583] Input: HTTP response received from the server

[0584] Output: Parsed schedule data

[0585] Step 8:

[0586] The terminal converts the analyzed schedule data into an internal format and processes it for display on the user interface. Specifically, it visually displays the schedule using HTML and CSS.

[0587] Input: Parsed schedule data

[0588] Output: A schedule that is visually displayed to the user

[0589] Step 9:

[0590] The user can then view the displayed schedule, plan and execute their daily tasks based on it, and provide feedback if necessary, which is then formatted into JSON and sent from the device to the server.

[0591] Input: User feedback

[0592] Output: Feedback data formatted in JSON format

[0593] Step 10:

[0594] The server analyzes the received feedback and adds it to the training dataset of the generative model, which then reflects the feedback in the next schedule generation, allowing the system to continuously optimize.

[0595] Input: Feedback data in JSON format

[0596] Output: Updated training dataset, optimized generative model

[0597] (Application example 1)

[0598] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0599] Conventional schedule management systems tend to generate schedules that do not match actual usage conditions because they do not fully consider individual user patterns and preferences. Furthermore, task schedules for factory robots often require manual adjustments, limiting their efficient operation. This leads to problems such as reduced labor productivity and wasted time and effort. Furthermore, efficient task management for users and robots is difficult, and this situation needed to be improved.

[0600] 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.

[0601] In this invention, the server includes means for analyzing user patterns and preferences using a generative model and generating an optimal schedule, terminal means for transmitting collected data to the server, terminal means for receiving the generated schedule and displaying it to the user, and means for generating and optimizing task schedules for factory robots, thereby enabling schedule generation according to individual user needs and efficient task management for factory robots.

[0602] A "generative model" is a type of artificial intelligence used to analyze user patterns and preferences and generate optimal schedules.

[0603] The term "terminal means" refers to a device that allows a user to input information and a device that receives and displays a schedule generated from a server.

[0604] A "factory robot" is a mechanical device that automatically performs tasks within a factory and requires a schedule for efficient operation.

[0605] A "task schedule" is a plan that determines the allocation, order, and time slots of tasks within a specific period of time.

[0606] A "server" is a central processing unit that receives information from multiple terminals, generates a schedule using a generative model, and returns the results to the terminals.

[0607] "Collected data" refers to all information necessary for generating a schedule, such as information entered by users into terminals and operating information of factory robots.

[0608] "Priority" is a criterion that indicates which task is more important than others, and is taken into consideration when generating a schedule.

[0609] "Rest time" refers to a time period set for users or factory robots to take a rest while they are operating.

[0610] "Initial investment" refers to the funds and resources required to deploy the system, including software development, generative model training, and user experience design.

[0611] "User experience design" is a design process that aims to improve the experience users have when using a system.

[0612] The present invention is a system that uses a generative model to analyze user patterns and preferences to generate an optimal schedule. In this system, data entered by the user is sent to a server, which then uses the generative model to generate a schedule and returns the results to the terminal for display to the user.

[0613] First, a user uses a device (e.g., a tablet or PC) to input information related to their schedule. For example, a user might input information such as "work hours," "break times," and "preferred meeting times," or, in the case of a factory robot, "tasks in charge," "priority," and "break times." This input data is compiled in JSON format and sent to the server.

[0614] The server receives the input data, parses it, and converts it into the appropriate format. This data analysis is performed using Python-based scripts. The server then runs a generative AI model (such as GPT-4) to generate an optimal schedule based on the user's patterns and preferences. This generative model takes into account the user's input data and balances task priorities, durations, break times, and other factors to create a schedule.

[0615] The generated schedule is converted back to JSON format and sent to the device as an HTTP response. The device then converts the schedule data received from the server into an internal format and displays it in an easy-to-read format for the user.

[0616] As a concrete example, let's say the user is a factory manager and enters the following information:

[0617] {

[0618] "Operating hours": "08:00-17:00",

[0619] "Task": [

[0620] {"Name": "Welding work", "Priority": "High", "Duration": 60},

[0621] {"Name": "Quality Inspection", "Priority": "Medium", "Time Required": 30},

[0622] {"Name": "Transport", "Priority": "Low", "Duration": 45}

[0623] ],

[0624] "Break Time": "12:00-13:00"

[0625] }

[0626] This information is sent from the device to a server, and a generative AI model generates an optimal schedule that looks like this:

[0627] Generate an optimal schedule for the factory robots based on the following data:

[0628] Operating hours: 08:00-17:00

[0629] task:

[0630] Welding (High Priority, 60 minutes)

[0631] Quality Inspection (Priority: Medium, Time: 30 minutes)

[0632] Transport (Priority: Low, Time: 45 minutes)

[0633] Break time: 12:00-13:00

[0634] The generated schedule looks like this:

[0635] 08:00 - 09:00: Welding work

[0636] 09:00 - 09:30: Quality inspection

[0637] 09:30 - 10:15: Transport

[0638] 10:15 - 11:15: Welding work

[0639] 11:15 - 12:00: Quality inspection

[0640] 12:00 - 13:00: Break

[0641] 13:00 - 14:00: Transport

[0642] 14:00 - 15:00: Welding work

[0643] 15:00 - 15:30: Quality inspection

[0644] 15:30 - 16:15: Transport

[0645] 16:15 - 17:00: Quality inspection

[0646] This schedule is received from the server and displayed on the terminal, allowing users to check it and efficiently manage the operation of factory robots. This is expected to improve factory productivity and work efficiency. In addition, by investing initial funds in software development, generative model training, and user experience design, the system can be optimized to more effectively meet user demands.

[0647] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0648] Step 1:

[0649] Users use devices (e.g., tablets or PCs) to input schedule information, including work hours, break times, preferred meeting times, factory robot tasks, priorities, and required times. The input data is compiled in JSON format and sent to the server.

[0650] Input: Schedule-related information entered by the user into the device

[0651] Output: Data organized in JSON format

[0652] Step 2:

[0653] The server receives JSON-formatted data sent from the device. To receive this data, an HTTP request handler must be set up. The server analyzes the received data and converts it into a format suitable for the generative model. For this purpose, a Python json library or similar is used.

[0654] Input: JSON format data sent from the terminal

[0655] Output: Parsed and transformed schedule-related data

[0656] Step 3:

[0657] The server uses a generative AI model (e.g., GPT-4) to generate an optimal schedule. To do this, a prompt is first generated and sent to the generative model. The generative AI model then takes the input data into account and creates a schedule that balances task priorities, required time, break times, etc.

[0658] Input: Parsed and transformed schedule-related data, and generated prompt statements

[0659] Output: Schedule data generated by the generative AI model

[0660] Step 4:

[0661] The generated schedule is converted back to JSON format and sent to the terminal as an HTTP response. The server uses an HTTP communication library such as Python to generate the HTTP response.

[0662] Input: Generated schedule data

[0663] Output: Generated schedule data converted to JSON format

[0664] Step 5:

[0665] The terminal converts the schedule data received from the server into an internal format and displays it in an easy-to-read format for the user. The GUI application used for display is usually implemented using HTML, CSS, JavaScript, etc. This allows the user to check their schedule and manage tasks efficiently.

[0666] Input: Generated schedule data in JSON format received from the server

[0667] Output: Schedule information displayed on the device screen in a user-friendly format

[0668] 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.

[0669] This invention is a system that uses a generative model and an emotion engine to analyze a user's patterns, preferences, and emotional state to generate an optimal schedule. This system comprehensively analyzes data entered by the user and emotional information collected by the emotion engine, generates an optimal schedule for the user on the server, and displays it on the terminal.

[0670] First, the user inputs information related to their schedule via their device. Specifically, the user enters information such as "work hours," "lunch time," and "priority meeting times" into an input form on the device. The emotion engine then recognizes the user's emotions in real time and collects that information. For example, it can analyze facial expressions using the user's camera or extract emotions from their voice.

[0671] The device converts this information into JSON format and sends it to the server. The server analyzes the data and integrates the output of the generative model and emotion engine. The generative model generates a schedule based on the user's patterns and preferences, and the emotion engine adjusts the schedule according to the user's emotional state.

[0672] For example, if a user is feeling stressed, the emotion engine's output is fed back to the generative model, which adjusts the schedule to increase relaxation and rest time. In this way, a schedule is generated that optimizes the user's emotional state.

[0673] The server converts the generated schedule into JSON format and sends it to the device as an HTTP response. The device analyzes the received data and displays the new schedule in an easy-to-read format for the user. The user can plan and execute daily tasks based on this schedule. In addition, the generative model and emotion engine further learn based on user feedback and actual schedule history, and the learning is reflected in the next schedule generation.

[0674] As a concrete example, consider the case where a user launches a terminal application and inputs their "work hours" as "9:00-18:00," "lunchtime" as "12:00-13:00," and "priority meeting times" as "10:00-11:00, 15:00-16:00." Furthermore, suppose the emotion engine recognizes the user's face and determines their current emotion as "stressed." The server's generative model integrates the input information and the emotion engine's results to generate the following schedule:

[0675] 09:00 - 09:30: Check email

[0676] 09:30 - 10:00: Preparation of materials

[0677] 10:00 - 11:00: Meeting 1

[0678] 11:00 - 12:00: Progress of Task A

[0679] 12:00 - 13:00: Lunch break

[0680] 13:00 - 14:00: Relaxation time

[0681] 14:00 - 15:00: Progress of Task B

[0682] 15:00 - 16:00: Meeting 2

[0683] 16:00 - 17:00: Progress of Task C

[0684] 17:00 - 18:00: Easy stress relief activities

[0685] This schedule takes into account the user's work and meeting times, and is adjusted to reflect the user's stress level using the emotion engine. Based on this schedule, users can carry out their daily tasks efficiently and in a balanced manner.

[0686] As described above, the present invention provides an optimal schedule that takes into account a user's emotional state as well as their patterns and preferences, thereby improving the user's productivity and quality of life.

[0687] The processing flow will be explained below.

[0688] Step 1:

[0689] The user launches a terminal application and enters schedule-related information such as work hours (e.g., 9:00-18:00), lunch time (e.g., 12:00-13:00), and preferred meeting times (e.g., 10:00-11:00, 15:00-16:00) through the terminal UI.

[0690] Step 2:

[0691] The emotion engine recognizes the user's emotions. The device analyzes the user's facial expressions and voice in real time to collect emotional information. For example, it can detect "stress" from the user's facial expressions using camera footage.

[0692] Step 3:

[0693] The device converts the schedule information entered by the user and the emotional information recognized by the emotion engine into JSON format. Specifically, the data is summarized as follows:

[0694] json

[0695] {

[0696] "user_id": "12345",

[0697] "preferences": {

[0698] "work_hours": "9:00-18:00",

[0699] "lunch_break": "12:00-13:00",

[0700] "preferred_meeting_times": ["10:00-11:00", "15:00-16:00"]

[0701] },

[0702] "emotion": "stress",

[0703] "existing_schedule": {}

[0704] }

[0705] Step 4:

[0706] The device sends this compiled JSON data to the server as an HTTP POST request. The endpoint is, for example, / schedule.

[0707] Step 5:

[0708] The server receives the HTTP POST request sent from the device. The server obtains the JSON format data from the request body, parses it, and converts it to the internal data format.

[0709] Step 6:

[0710] The server passes the analyzed data to the generative model and emotion engine. The generative model generates a schedule based on the user's patterns and preferences, and the emotion engine further adjusts the generated schedule using the user's emotion information.

[0711] Step 7:

[0712] The generative model first generates a standard schedule based on user input data. This schedule balances task priority, duration, and break times. For example, the following schedule might be generated:

[0713] 09:00 - 09:30: Check email

[0714] 09:30 - 10:00: Preparation of materials

[0715] 10:00 - 11:00: Meeting 1

[0716] 11:00 - 12:00: Progress of Task A

[0717] 12:00 - 13:00: Lunch break

[0718] 13:00 - 15:00: Progress of Task B

[0719] 15:00 - 16:00: Meeting 2

[0720] 16:00 - 18:00: Progress of Task C

[0721] Step 8:

[0722] The emotion engine adjusts the schedule based on the standard schedule according to the user's emotion information. For example, if the emotion engine determines that the user's emotion is "stress," it adjusts the schedule to increase break time and relaxation time. The adjusted schedule will look like this:

[0723] 09:00 - 09:30: Check email

[0724] 09:30 - 10:00: Preparation of materials

[0725] 10:00 - 11:00: Meeting 1

[0726] 11:00 - 12:00: Progress of Task A

[0727] 12:00 - 13:00: Lunch break

[0728] 13:00 - 14:00: Relaxation time

[0729] 14:00 - 15:00: Progress of Task B

[0730] 15:00 - 16:00: Meeting 2

[0731] 16:00 - 17:00: Progress of Task C

[0732] 17:00 - 18:00: Easy stress relief activities

[0733] Step 9:

[0734] The server converts the schedule generated and adjusted by the generative model and emotion engine into JSON format and sends it to the terminal as an HTTP response.

[0735] Step 10:

[0736] The terminal parses the HTTP response received from the server and converts the JSON data into an internal data format. After obtaining the new schedule information, the terminal displays the schedule in an easy-to-read format for the user.

[0737] Step 11:

[0738] The user can check the new schedule displayed on the terminal and efficiently carry out daily tasks based on the generated schedule.

[0739] Step 12:

[0740] Based on user feedback and actual schedule history, the generative model and emotion engine further learn and reflect this in the next schedule generation, resulting in a more personalized schedule that optimally reflects the user's emotional state.

[0741] Example 2

[0742] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0743] Conventional schedule generation systems only analyze user patterns and preferences, but are unable to consider the user's emotional state. As a result, they may generate schedules that ignore the user's stress and fatigue, making it difficult for the user to complete tasks efficiently. Furthermore, they lacked a learning function that utilizes user feedback and schedule history, making it difficult to generate schedules that are optimized for individual users' needs.

[0744] 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.

[0745] In this invention, the server includes means for analyzing a user's patterns and emotional state using a generative model and an emotion recognition engine to generate an optimal schedule, means for acquiring data entered by the user and emotional information collected by the emotion recognition engine at a terminal and transmitting the data to the server, and means for receiving a schedule generated based on the analyzed data by the server and displaying it to the user. This makes it possible to generate an optimal schedule that reflects the user's emotional state, and furthermore, a learning function based on user feedback and schedule history makes it possible to provide a more personalized schedule for the user.

[0746] A "generative model" is an algorithm that generates an optimal schedule based on a user's patterns and preferences.

[0747] An "emotion recognition engine" is a software component that recognizes and analyzes a user's emotional state in real time.

[0748] A "pattern" is a consistent tendency or habit based on a user's behavior or preferences.

[0749] "Preferences" refer to tasks and time allocations that the user particularly prefers.

[0750] A "schedule" is a plan that arranges a user's daily tasks and events in time.

[0751] A "terminal" is an electronic device that allows a user to input and display information.

[0752] "Server" refers to the central computer system that analyzes data sent from the terminals and generates and adjusts schedules.

[0753] "Data transmission" refers to the process of sending information from a terminal to a server.

[0754] "Data analysis" refers to the process by which the server processes the data it receives to extract useful information.

[0755] "Feedback" refers to opinions and ratings that users provide to a system, which the system uses to learn and improve based on that information.

[0756] "Learning function" refers to the system's ability to improve future performance based on past data and feedback.

[0757] MODE FOR CARRYING OUT THE INVENTION

[0758] This invention is a system that uses a generative model and an emotion recognition engine to analyze a user's patterns, preferences, and emotional state to generate an optimal schedule. This system comprehensively analyzes data entered by the user and emotional information collected by the emotion recognition engine, generates an optimal schedule on the server, and displays it on the terminal.

[0759] First, the user inputs information related to their schedule via their device. Specifically, the user enters information such as "work hours," "lunch time," and "priority meeting times" into an input form on the device. The emotion recognition engine then recognizes the user's emotions in real time and collects that information. For example, the device's camera can be used to analyze facial expressions and extract emotional information from voice data.

[0760] The device converts the information entered by the user and the emotion data collected by the emotion recognition engine into JSON format and sends it to the server using an HTTP request, for example, as a POST request to "https: / / server.url / schedule."

[0761] The server analyzes the received data and integrates the outputs of the generative model and the emotion recognition engine. The generative model generates an initial schedule based on the user's patterns and preferences. The emotion recognition engine then adjusts the generated schedule based on the user's emotional state. For example, if the user is feeling stressed, the engine may add relaxation time or breaks to the generated schedule.

[0762] The server converts the final adjusted schedule into JSON format and sends it to the device as an HTTP response. The device then analyzes the received data and displays the schedule in a user-friendly format, enabling users to plan and complete their daily tasks based on an efficient and balanced schedule.

[0763] Furthermore, user feedback and actual schedule history are sent to the server, and the generative model and emotion recognition engine use this data for training, which is reflected in the next schedule generation, providing a more personalized schedule for the user.

[0764] As a concrete example, suppose a user enters the following information into a terminal:

[0765] Working hours: 9:00-18:00

[0766] Lunchtime: 12:00-13:00

[0767] Preferred meeting times: 10:00-11:00, 15:00-16:00

[0768] If the emotion recognition engine recognizes the user's face and determines that the current emotion is "stress," the generative model on the server will generate the following schedule:

[0769] 09:00 - 09:30: Check email

[0770] 09:30 - 10:00: Preparation of materials

[0771] 10:00 - 11:00: Meeting 1

[0772] 11:00 - 12:00: Progress of Task A

[0773] 12:00 - 13:00: Lunch break

[0774] 13:00 - 14:00: Relaxation time

[0775] 14:00 - 15:00: Progress of Task B

[0776] 15:00 - 16:00: Meeting 2

[0777] 16:00 - 17:00: Progress of Task C

[0778] 17:00 - 18:00: Easy stress relief activities

[0779] An example prompt is:

[0780] "Generate the best schedule for your users based on their current situation. Create a schedule based on the following information:

[0781] Working hours: 9:00-18:00

[0782] Lunchtime: 12:00-13:00

[0783] Preferred meeting times: 10:00-11:00, 15:00-16:00

[0784] Furthermore, the emotion recognition engine determined that the user's emotion was 'stress'.

[0785] In this way, the system provides an optimal schedule that takes into account the user's patterns and preferences as well as their emotional state, improving their productivity and quality of life.

[0786] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0787] Step 1:

[0788] User Data Input

[0789] The user enters schedule-related information such as "work hours," "lunchtime," and "preferred meeting times" into an input form on the terminal. Specifically, the user enters "work hours" as "9:00-18:00," "lunchtime" as "12:00-13:00," and "preferred meeting times" as "10:00-11:00, 15:00-16:00." After entering the information, the user presses the send button. The input in this step is schedule information manually entered by the user, and the output is temporary data stored in the terminal.

[0790] Step 2:

[0791] Emotional Data Collection

[0792] The device collects the user's emotional data using an emotion recognition engine. The device's camera is used to analyze the user's facial expressions in real time, and the emotion recognition engine recognizes "stress" from the facial expressions. If there is voice input, the device extracts emotions from the voice data. The input for this step is the user's facial and voice data, and the output is emotional data analyzed by the emotion recognition engine.

[0793] Step 3:

[0794] Data transmission

[0795] The device combines the schedule information entered by the user with the emotion data collected by the emotion recognition engine and converts it into JSON format. It then sends the data to the server using an HTTP request. For example, the destination is a POST request to "https: / / server.url / schedule." The input of this step is the schedule information and emotion data, and the output is the data converted into JSON format.

[0796] Step 4:

[0797] Data analysis

[0798] The server parses the received JSON data and extracts the user's schedule information and emotional state. This analysis is typically performed using programming languages ​​such as Python or Java. The input for this step is JSON-formatted data, and the output is the parsed schedule information and emotional data.

[0799] Step 5:

[0800] Schedule Generation

[0801] The server's generative model generates an initial schedule based on the analyzed schedule information and user patterns. For example, it arranges tasks such as "09:00-09:30: Check email" and "09:30-10:00: Prepare documents." The input of this step is the analyzed schedule information, and the output is an initial schedule proposal.

[0802] Step 6:

[0803] Schedule adjustment

[0804] The generated initial schedule is adjusted based on the output of the emotion recognition engine. For example, if the user is recognized as "stressed," relaxation time or rest time is added to the schedule. The input of this step is the initial schedule and emotion data, and the output is the adjusted final schedule.

[0805] Step 7:

[0806] Scheduled Sending

[0807] The server converts the adjusted final schedule into JSON format and sends it to the terminal as an HTTP response. The input of this step is the adjusted final schedule, and the output is the transmission of JSON format data.

[0808] Step 8:

[0809] Schedule Display

[0810] The device parses the received JSON data and displays the schedule in a visually easy-to-understand format. For example, it may use the in-app calendar function to display the schedule in a color-coded format. The input of this step is the JSON data received from the server, and the output is a visual schedule display that the user can view.

[0811] Step 9:

[0812] Feedback gathering and learning

[0813] The user enters feedback on the task they performed into a feedback form within the device app. For example, they answer questions such as, "Was today's schedule appropriate?" The device sends this feedback to the server, and the server's generative model and emotion recognition engine use the data for training. The input of this step is the user's feedback data, and the output is the trained generative model and emotion recognition engine.

[0814] As a result, the system improves users' productivity and quality of life by providing an optimal schedule that takes into account their emotional state as well as their patterns and preferences.

[0815] (Application example 2)

[0816] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0817] In modern society, stress and busyness make it difficult for users to efficiently manage their schedules. Furthermore, there is a lack of systems that can recommend optimal content and tasks according to a user's emotional state, which means that users are unable to find appropriate ways to relax or progress with their work according to their emotions.

[0818] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing a user's patterns and preferences using a generative model and generating an optimal schedule, terminal means for transmitting collected data to the server, terminal means for receiving the generated schedule and displaying it to the user, means for analyzing the user's emotional state using an emotion engine, and means for adjusting the schedule based on the emotional state. This allows the user to obtain an optimal schedule based on not only their own patterns and preferences but also their emotional state recognized in real time. Furthermore, appropriate content and relaxation methods are simultaneously suggested based on the user's emotional state, allowing them to perform daily tasks efficiently and comfortably.

[0819] A "generative model" is an algorithm that takes data as input, analyzes user patterns and preferences, and generates output tailored to a specific purpose.

[0820] A "pattern" is a recurring feature that indicates a user's tendencies in behavior or choices.

[0821] "Preferences" are specific activities, content, or options that a user prefers.

[0822] An "optimal schedule" is a timetable or plan that maximizes a user's efficiency and comfort, based on the user's patterns, preferences, and emotional state.

[0823] "Means" refers to a device, system, algorithm, or other technical means used to achieve a specific purpose.

[0824] A "server" is a computer system that provides a set of computing resources for storing, analyzing, and processing data.

[0825] A "terminal" is a device or apparatus that a user directly operates to input, display, and transmit information.

[0826] An "emotion engine" is an algorithm or system that analyzes a user's facial expressions, voice, and behavioral data to identify their emotional state in real time.

[0827] "Collecting" refers to the act or process of gathering necessary data, which in the present invention refers to data relating to the user's emotional state, behavioral patterns, and preferences.

[0828] "Analysis" is the process of examining collected data in detail and deriving meaning and trends from it.

[0829] "Tuning" is the act or process of changing components to optimize them based on specific conditions.

[0830] "Relaxation methods" refer to specific means or activities for reducing the user's stress and resting the mind and body.

[0831] "Content" refers to the information media consumed by users, including, for example, movies, music, videos, etc.

[0832] This invention is a system that uses a generative model and an emotion engine to analyze a user's patterns, preferences, and emotional state to generate an optimal schedule. This system comprehensively analyzes data entered by the user and emotional information collected by the emotion engine, generates an optimal schedule for the user on the server, and displays it on the terminal.

[0833] First, the user inputs information related to their schedule via their device. Specifically, the user enters information such as "work hours," "lunch time," and "priority meeting times" into an input form on the device. The emotion engine then recognizes the user's emotions in real time and collects that information. For example, it can analyze facial expressions using the user's camera or extract emotions from their voice.

[0834] The device converts this information into JSON format and sends it to the server. The server analyzes the data and integrates the output of the generative model and emotion engine. The generative model generates a schedule based on the user's patterns and preferences, and the emotion engine adjusts the schedule according to the user's emotional state.

[0835] The server uses a machine learning algorithm as a generative model to learn the user's past behavioral data and patterns. Specifically, a deep learning model (e.g., TensorFlow) can be used. Furthermore, a library for analyzing the user's emotional state in real time (e.g., OpenCV, Microsoft Azure's Emotion API) can be used as an emotion engine.

[0836] For example, if a user is feeling stressed, the output of the emotion engine is fed back to the generative model, which adjusts the schedule to increase relaxation and rest periods. In this way, a schedule is generated to optimize the user's emotional state. The server converts the generated schedule into JSON format and sends it to the device as an HTTP response. The device analyzes the received data and displays the new schedule in an easy-to-read format for the user. The user can plan and execute daily tasks based on this schedule.

[0837] As a concrete example, consider the case where a user launches a terminal application and inputs their "work hours" as "9:00-18:00," "lunchtime" as "12:00-13:00," and "priority meeting times" as "10:00-11:00, 15:00-16:00." Furthermore, suppose the emotion engine recognizes the user's face and determines their current emotion as "stressed." The server's generative model integrates the input information and the emotion engine's results to generate the following schedule:

[0838] ---

[0839] Example prompt sentence:

[0840] If the user is "stressed", generate a schedule like this:

[0841] 09:00 - 10:00: Relaxation music

[0842] 10:00 - 11:00: Comedy movie

[0843] 11:00 - 12:00: Light fitness videos

[0844] 12:00 - 13:00: Lunch break

[0845] 13:00 - 14:00: Reflection and journaling

[0846] 14:00 - 15:00: Music appreciation (selected songs)

[0847] 15:00 - 16:00: Meditation video

[0848] Based on this schedule, users can take effective actions that are tailored to their own emotions and patterns.

[0849] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0850] Step 1:

[0851] A user inputs information related to his or her schedule (such as "work hours," "lunch time," and "priority meeting times") via a terminal. This information is entered into the terminal using an input form. The input data is used as the initial data required to generate a schedule.

[0852] Input: Schedule-related information (work time, lunch time, meeting time, etc.)

[0853] Output: Structured input data

[0854] Step 2:

[0855] The device uses the user's camera and microphone to analyze the user's facial expressions and voice in real time, and the emotion engine recognizes the user's emotional state. This emotion information is fed back to the generative model.

[0856] Input: Real-time data from camera and microphone

[0857] Output: Parsed emotional state information

[0858] Step 3:

[0859] The device converts the collected schedule information and emotional state information into JSON format and sends it to the server. This data becomes the initial dataset for schedule generation.

[0860] Input: Structured input data and parsed emotional state information

[0861] Output: JSON format data

[0862] Step 4:

[0863] The server analyzes the received data and uses a generative model to analyze the user's patterns and preferences. The generative model uses a deep learning-based model (e.g., TensorFlow). The generative model learns the user's behavioral patterns from past data and generates an optimal schedule.

[0864] Input: JSON format data

[0865] Output: An initial schedule that reflects user patterns and preferences

[0866] Step 5:

[0867] The server then feeds back the analysis results of the emotion engine to the generative model and adjusts the schedule based on the user's emotional state. For example, if the user is feeling stressed, the schedule may be adjusted to increase relaxation time.

[0868] Input: Initial schedule, emotional state information

[0869] Output: An optimized schedule that reflects emotional state

[0870] Step 6:

[0871] The server converts the generated optimized schedule into JSON format and sends it to the terminal as an HTTP response. The optimized schedule is structured in a format that is visually easy for users to understand.

[0872] Input: Optimized schedule reflecting emotional state

[0873] Output: Response data in JSON format

[0874] Step 7:

[0875] The device analyzes the received data and displays the schedule in an easy-to-read format for the user, who can then plan and execute their daily tasks.

[0876] Input: Response data in JSON format

[0877] Output: A visual representation of the schedule

[0878] 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.

[0879] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0880] 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.

[0881] [Third embodiment]

[0882] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0883] 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.

[0884] 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).

[0885] 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.

[0886] 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.

[0887] 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).

[0888] 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.

[0889] 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.

[0890] 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.

[0891] 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.

[0892] 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.

[0893] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0894] The present invention is a system that uses a generative model to analyze user patterns and preferences to generate an optimal schedule. In this system, data entered by the user is sent to a server, which then uses the generative model to generate a schedule and returns the results to the terminal for display to the user.

[0895] First, the user uses the device to input information related to their schedule. For example, the user inputs information such as "work hours," "lunch time," "preferred meeting times," etc. This input data is compiled in JSON format and sent to the server.

[0896] The data received from the device is analyzed by the server and converted into an appropriate format. The server then runs a generative model to generate an optimal schedule based on the user's patterns and preferences. The generative model takes into account the user's input data and creates a schedule by balancing task priorities, durations, break times, etc. The generated schedule is converted into JSON format and sent to the device as an HTTP response.

[0897] The device converts the schedule data received from the server into an internal format and displays it in an easy-to-read format for the user. The user can check this schedule and plan and execute daily tasks based on it. In addition, the generative model can learn more effectively based on user feedback and reflect this in the next schedule generation.

[0898] Next, the operation of the system will be explained using a concrete example.

[0899] As a concrete example, suppose a user starts a terminal application and inputs their "Work Hours" as "9:00-18:00", "Lunch Time" as "12:00-13:00", and "Preferred Meeting Times" as "10:00-11:00, 15:00-16:00". This information is compiled by the terminal in JSON format and sent to the server.

[0900] The server analyzes this data and uses a generative model to generate a schedule like this:

[0901] 09:00 - 09:30: Check email

[0902] 09:30 - 10:00: Preparation of materials

[0903] 10:00 - 11:00: Meeting 1

[0904] 11:00 - 12:00: Progress of Task A

[0905] 12:00 - 13:00: Lunch break

[0906] 13:00 - 15:00: Progress of Task B

[0907] 15:00 - 16:00: Meeting 2

[0908] 16:00 - 18:00: Progress of Task C

[0909] The generated schedule is sent from the server to the device, which receives it and displays it to the user. The user can then use this new schedule to efficiently complete their daily tasks. Initial investments in software development, generative model training, and user experience design can be used to optimize the system, further improving the user's quality of life.

[0910] In this way, the present invention generates an optimal schedule that takes into account the user's patterns and preferences, enabling efficient time management and improved quality of life.

[0911] The processing flow will be explained below.

[0912] Step 1:

[0913] A user launches a terminal application and enters schedule-related information such as work hours, lunch time, and preferred meeting times through the terminal UI.

[0914] Step 2:

[0915] The device collects the information entered by the user and converts it into JSON format. For example, if a user enters their work hours as 9:00-18:00, their lunch time as 12:00-13:00, and their preferred meeting times as 10:00-11:00 and 15:00-16:00, the information is compiled as follows:

[0916] json

[0917] {

[0918] "user_id": "12345",

[0919] "preferences": {

[0920] "work_hours": "9:00-18:00",

[0921] "lunch_break": "12:00-13:00",

[0922] "preferred_meeting_times": ["10:00-11:00", "15:00-16:00"]

[0923] },

[0924] "existing_schedule": {}

[0925] }

[0926] Step 3:

[0927] The device sends this JSON data to the server as an HTTP POST request. The endpoint is specified as / schedule, for example.

[0928] Step 4:

[0929] The server receives the HTTP POST request sent from the device. The server obtains the JSON format data from the request body, parses it, and converts it to the internal data format.

[0930] Step 5:

[0931] The server passes the analyzed data to the generative model, which analyzes the user's patterns and preferences based on the user ID, schedule preference information, and existing schedule information.

[0932] Step 6:

[0933] The generative model takes into account user input data and generates an optimal schedule by balancing task priorities, required times, and break times. For example, the following schedule may be generated:

[0934] 09:00 - 09:30: Check email

[0935] 09:30 - 10:00: Preparation of materials

[0936] 10:00 - 11:00: Meeting 1

[0937] 11:00 - 12:00: Progress of Task A

[0938] 12:00 - 13:00: Lunch break

[0939] 13:00 - 15:00: Progress of Task B

[0940] 15:00 - 16:00: Meeting 2

[0941] 16:00 - 18:00: Progress of Task C

[0942] Step 7:

[0943] The schedule generated by the generative model is converted into JSON format by the server and sent to the terminal as an HTTP response.

[0944] Step 8:

[0945] The terminal parses the HTTP response received from the server and converts the JSON data into an internal data format. After obtaining the new schedule information, the terminal displays the schedule in an easy-to-read format for the user.

[0946] Step 9:

[0947] The user checks the new schedule displayed on the terminal, and can efficiently carry out daily tasks based on the generated schedule.

[0948] Step 10:

[0949] Based on user feedback and actual schedule history, the generative model further learns and reflects this in the next schedule generation, resulting in a more personalized schedule.

[0950] Example 1

[0951] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0952] Conventional scheduling systems struggle to efficiently manage time because they fail to fully reflect users' patterns and preferences. Furthermore, continuous optimization is difficult because there is no mechanism for automatically improving the model based on user feedback. As a result, there are limitations to improving users' quality of life and the accuracy of task management.

[0953] 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.

[0954] In this invention, the server includes: means for analyzing a user's patterns and preferences using a generative model and generating an optimal schedule; terminal means for the user to input information related to the schedule and send it to the server in JSON format; means for the server to analyze the received data, execute the generative model to generate a schedule, and return the result in JSON format to the terminal; terminal means for receiving the generated schedule and visually displaying it to the user; and means for further training the generative model based on feedback from the user. This enables efficient schedule generation that reflects the user's individual patterns and preferences, and by continuously improving the model, more accurate task management and improved quality of life are possible.

[0955] A "generative model" is a machine learning algorithm used to analyze user patterns and preferences and generate optimal schedules.

[0956] "User" refers to a person or organization that inputs schedule-related information and transmits it to the server via a terminal.

[0957] "Terminal" refers to a device such as a computer, tablet, or smartphone that a user uses to input schedule-related information.

[0958] "Server" refers to a networked computer system that receives and analyzes data sent by users, executes generative models to generate optimal schedules, and returns them to the terminals.

[0959] "JSON format" is an abbreviation for JavaScript Object Notation, and is a format for structuring data and expressing it in text format.

[0960] An "HTTP request" refers to a request based on a protocol for a terminal to send and receive data to a server.

[0961] An "HTTP response" refers to data sent by a server in response to an HTTP request received from a terminal.

[0962] "Feedback" refers to opinions and evaluations provided by users regarding the generated schedule, and is used to improve the generative model.

[0963] The present invention is a system that uses a generative model to analyze user patterns and preferences to generate an optimal schedule. In this system, data entered by the user is sent to a server, which then uses the generative model to generate a schedule and returns the results to the terminal for display to the user.

[0964] Specifically, a user uses a terminal to input information related to their schedule. For example, the user inputs information such as "work hours," "lunch time," "preferred meeting times," etc. This input data is compiled in JSON format and sent to the server.

[0965] The server analyzes the data received from the device and converts it into an appropriate format. Python's json module can be used for analysis. The server then runs a generative model built using libraries such as TensorFlow and PyTorch to generate an optimal schedule based on the user's patterns and preferences. The generative model takes into account the user's input data and creates a schedule by balancing task priorities, required times, break times, and other factors.

[0966] The generated schedule is converted back to JSON format and sent to the device as an HTTP response. The device converts the schedule data received from the server into an internal format and displays it in an easy-to-read format for the user. The user can check this schedule and plan and execute daily tasks based on it.

[0967] Users can also provide feedback based on their experience using the schedule. The server uses this feedback to further train the generative model and reflect it in the next schedule generation. This cycle allows the system to be continuously optimized, enabling it to continue providing the best schedule for the user.

[0968] For example, if a user launches a terminal application and enters their "work hours" as "9:00-18:00," "lunchtime" as "12:00-13:00," and "preferred meeting times" as "10:00-11:00, 15:00-16:00," this information is compiled by the terminal in JSON format and sent to the server. The server analyzes this data and uses a generative model to generate the following schedule:

[0969] 09:00 - 09:30: Check email

[0970] 09:30 - 10:00: Preparation of materials

[0971] 10:00 - 11:00: Meeting 1

[0972] 11:00 - 12:00: Progress of Task A

[0973] 12:00 - 13:00: Lunch break

[0974] 13:00 - 15:00: Progress of Task B

[0975] 15:00 - 16:00: Meeting 2

[0976] 16:00 - 18:00: Progress of Task C

[0977] The generated schedule is sent from the server to the device, which receives it and displays it to the user, allowing the user to efficiently complete daily tasks based on this new schedule.

[0978] Below is an example of a prompt sentence to input to the generative AI model.

[0979] "User's schedule data:

[0980] Working hours: 9:00-18:00

[0981] Lunchtime: 12:00-13:00

[0982] Preferred meeting times: 10:00-11:00, 15:00-16:00

[0983] Generate an optimal daily schedule based on the information above.

[0984] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0985] Step 1:

[0986] Users launch the application on their device and enter information related to their schedule, such as "work hours," "lunch time," and "preferred meeting times." This information is formatted in JSON format.

[0987] Input: Schedule information entered by the user (e.g., work hours, lunch times, meeting times, etc.)

[0988] Output: Schedule information formatted in JSON format

[0989] Step 2:

[0990] The device sends the entered JSON format data to the server using an HTTP request. Specifically, the entered schedule information is formatted appropriately and sent to the specified URL.

[0991] Input: Schedule information in JSON format

[0992] Output: HTTP request to the server

[0993] Step 3:

[0994] The server receives the HTTP request sent from the terminal. This process uses server software such as Apache or Nginx. It extracts and analyzes the JSON data contained in the body of the HTTP request.

[0995] Input: HTTP request sent from the terminal

[0996] Output: Parsed schedule information

[0997] Step 4:

[0998] The server decodes the received JSON data using Python's json module and converts it into an internal format, extracts the appropriate fields, and converts them into a data structure for input to the generative model.

[0999] Input: Parsed schedule information (JSON format)

[1000] Output: A data structure to feed into the generative model.

[1001] Step 5:

[1002] The server runs a generative AI model to generate an optimal schedule. The generative model uses TensorFlow and PyTorch. Based on user input data, the model considers the priority, duration, and break times of each task to generate a balanced and appropriate schedule.

[1003] Input: The data structure to input to the model.

[1004] Output: The generated schedule

[1005] Step 6:

[1006] The server converts the generated schedule back into JSON format and sends it back to the terminal as an HTTP response. This conversion is performed using the Python json module. The generated schedule is included in the body of the HTTP response.

[1007] Input: Generated schedule

[1008] Output: JSON formatted schedule, HTTP response

[1009] Step 7:

[1010] The device processes the HTTP response received from the server and parses the JSON-formatted schedule data using JavaScript's fetch API or XMLHttpRequest.

[1011] Input: HTTP response received from the server

[1012] Output: Parsed schedule data

[1013] Step 8:

[1014] The terminal converts the analyzed schedule data into an internal format and processes it for display on the user interface. Specifically, it visually displays the schedule using HTML and CSS.

[1015] Input: Parsed schedule data

[1016] Output: A schedule that is visually displayed to the user

[1017] Step 9:

[1018] The user can then view the displayed schedule, plan and execute their daily tasks based on it, and provide feedback if necessary, which is then formatted into JSON and sent from the device to the server.

[1019] Input: User feedback

[1020] Output: Feedback data formatted in JSON format

[1021] Step 10:

[1022] The server analyzes the received feedback and adds it to the training dataset of the generative model, which then reflects the feedback in the next schedule generation, allowing the system to continuously optimize.

[1023] Input: Feedback data in JSON format

[1024] Output: Updated training dataset, optimized generative model

[1025] (Application example 1)

[1026] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1027] Conventional schedule management systems tend to generate schedules that do not match actual usage conditions because they do not fully consider individual user patterns and preferences. Furthermore, task schedules for factory robots often require manual adjustments, limiting their efficient operation. This leads to problems such as reduced labor productivity and wasted time and effort. Furthermore, efficient task management for users and robots is difficult, and this situation needed to be improved.

[1028] 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.

[1029] In this invention, the server includes means for analyzing user patterns and preferences using a generative model and generating an optimal schedule, terminal means for transmitting collected data to the server, terminal means for receiving the generated schedule and displaying it to the user, and means for generating and optimizing task schedules for factory robots, thereby enabling schedule generation according to individual user needs and efficient task management for factory robots.

[1030] A "generative model" is a type of artificial intelligence used to analyze user patterns and preferences and generate optimal schedules.

[1031] The term "terminal means" refers to a device that allows a user to input information and a device that receives and displays a schedule generated from a server.

[1032] A "factory robot" is a mechanical device that automatically performs tasks within a factory and requires a schedule for efficient operation.

[1033] A "task schedule" is a plan that determines the allocation, order, and time slots of tasks within a specific period of time.

[1034] A "server" is a central processing unit that receives information from multiple terminals, generates a schedule using a generative model, and returns the results to the terminals.

[1035] "Collected data" refers to all information necessary for generating a schedule, such as information entered by users into terminals and operating information of factory robots.

[1036] "Priority" is a criterion that indicates which task is more important than others, and is taken into consideration when generating a schedule.

[1037] "Rest time" refers to a time period set for users or factory robots to take a rest while they are operating.

[1038] "Initial investment" refers to the funds and resources required to deploy the system, including software development, generative model training, and user experience design.

[1039] "User experience design" is a design process that aims to improve the experience users have when using a system.

[1040] The present invention is a system that uses a generative model to analyze user patterns and preferences to generate an optimal schedule. In this system, data entered by the user is sent to a server, which then uses the generative model to generate a schedule and returns the results to the terminal for display to the user.

[1041] First, a user uses a device (e.g., a tablet or PC) to input information related to their schedule. For example, a user might input information such as "work hours," "break times," and "preferred meeting times," or, in the case of a factory robot, "tasks in charge," "priority," and "break times." This input data is compiled in JSON format and sent to the server.

[1042] The server receives the input data, parses it, and converts it into the appropriate format. This data analysis is performed using Python-based scripts. The server then runs a generative AI model (such as GPT-4) to generate an optimal schedule based on the user's patterns and preferences. This generative model takes into account the user's input data and balances task priorities, durations, break times, and other factors to create a schedule.

[1043] The generated schedule is converted back to JSON format and sent to the device as an HTTP response. The device then converts the schedule data received from the server into an internal format and displays it in an easy-to-read format for the user.

[1044] As a concrete example, let's say the user is a factory manager and enters the following information:

[1045] {

[1046] "Operating hours": "08:00-17:00",

[1047] "Task": [

[1048] {"Name": "Welding work", "Priority": "High", "Duration": 60},

[1049] {"Name": "Quality Inspection", "Priority": "Medium", "Time Required": 30},

[1050] {"Name": "Transport", "Priority": "Low", "Duration": 45}

[1051] ],

[1052] "Break Time": "12:00-13:00"

[1053] }

[1054] This information is sent from the device to a server, and a generative AI model generates an optimal schedule that looks like this:

[1055] Generate an optimal schedule for the factory robots based on the following data:

[1056] Operating hours: 08:00-17:00

[1057] task:

[1058] Welding (High Priority, 60 minutes)

[1059] Quality Inspection (Priority: Medium, Time: 30 minutes)

[1060] Transport (Priority: Low, Time: 45 minutes)

[1061] Break time: 12:00-13:00

[1062] The generated schedule looks like this:

[1063] 08:00 - 09:00: Welding work

[1064] 09:00 - 09:30: Quality inspection

[1065] 09:30 - 10:15: Transport

[1066] 10:15 - 11:15: Welding work

[1067] 11:15 - 12:00: Quality inspection

[1068] 12:00 - 13:00: Break

[1069] 13:00 - 14:00: Transport

[1070] 14:00 - 15:00: Welding work

[1071] 15:00 - 15:30: Quality inspection

[1072] 15:30 - 16:15: Transport

[1073] 16:15 - 17:00: Quality inspection

[1074] This schedule is received from the server and displayed on the terminal, allowing users to check it and efficiently manage the operation of factory robots. This is expected to improve factory productivity and work efficiency. In addition, by investing initial funds in software development, generative model training, and user experience design, the system can be optimized to more effectively meet user demands.

[1075] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1076] Step 1:

[1077] Users use devices (e.g., tablets or PCs) to input schedule information, including work hours, break times, preferred meeting times, factory robot tasks, priorities, and required times. The input data is compiled in JSON format and sent to the server.

[1078] Input: Schedule-related information entered by the user into the device

[1079] Output: Data organized in JSON format

[1080] Step 2:

[1081] The server receives JSON-formatted data sent from the device. To receive this data, an HTTP request handler must be set up. The server analyzes the received data and converts it into a format suitable for the generative model. For this purpose, a Python json library or similar is used.

[1082] Input: JSON format data sent from the terminal

[1083] Output: Parsed and transformed schedule-related data

[1084] Step 3:

[1085] The server uses a generative AI model (e.g., GPT-4) to generate an optimal schedule. To do this, a prompt is first generated and sent to the generative model. The generative AI model then takes the input data into account and creates a schedule that balances task priorities, required time, break times, etc.

[1086] Input: Parsed and transformed schedule-related data, and generated prompt statements

[1087] Output: Schedule data generated by the generative AI model

[1088] Step 4:

[1089] The generated schedule is converted back to JSON format and sent to the terminal as an HTTP response. The server uses an HTTP communication library such as Python to generate the HTTP response.

[1090] Input: Generated schedule data

[1091] Output: Generated schedule data converted to JSON format

[1092] Step 5:

[1093] The terminal converts the schedule data received from the server into an internal format and displays it in an easy-to-read format for the user. The GUI application used for display is usually implemented using HTML, CSS, JavaScript, etc. This allows the user to check their schedule and manage tasks efficiently.

[1094] Input: Generated schedule data in JSON format received from the server

[1095] Output: Schedule information displayed on the device screen in a user-friendly format

[1096] 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.

[1097] This invention is a system that uses a generative model and an emotion engine to analyze a user's patterns, preferences, and emotional state to generate an optimal schedule. This system comprehensively analyzes data entered by the user and emotional information collected by the emotion engine, generates an optimal schedule for the user on the server, and displays it on the terminal.

[1098] First, the user inputs information related to their schedule via their device. Specifically, the user enters information such as "work hours," "lunch time," and "priority meeting times" into an input form on the device. The emotion engine then recognizes the user's emotions in real time and collects that information. For example, it can analyze facial expressions using the user's camera or extract emotions from their voice.

[1099] The device converts this information into JSON format and sends it to the server. The server analyzes the data and integrates the output of the generative model and emotion engine. The generative model generates a schedule based on the user's patterns and preferences, and the emotion engine adjusts the schedule according to the user's emotional state.

[1100] For example, if a user is feeling stressed, the emotion engine's output is fed back to the generative model, which adjusts the schedule to increase relaxation and rest time. In this way, a schedule is generated that optimizes the user's emotional state.

[1101] The server converts the generated schedule into JSON format and sends it to the device as an HTTP response. The device analyzes the received data and displays the new schedule in an easy-to-read format for the user. The user can plan and execute daily tasks based on this schedule. In addition, the generative model and emotion engine further learn based on user feedback and actual schedule history, and the learning is reflected in the next schedule generation.

[1102] As a concrete example, consider the case where a user launches a terminal application and inputs their "work hours" as "9:00-18:00," "lunchtime" as "12:00-13:00," and "priority meeting times" as "10:00-11:00, 15:00-16:00." Furthermore, suppose the emotion engine recognizes the user's face and determines their current emotion as "stressed." The server's generative model integrates the input information and the emotion engine's results to generate the following schedule:

[1103] 09:00 - 09:30: Check email

[1104] 09:30 - 10:00: Preparation of materials

[1105] 10:00 - 11:00: Meeting 1

[1106] 11:00 - 12:00: Progress of Task A

[1107] 12:00 - 13:00: Lunch break

[1108] 13:00 - 14:00: Relaxation time

[1109] 14:00 - 15:00: Progress of Task B

[1110] 15:00 - 16:00: Meeting 2

[1111] 16:00 - 17:00: Progress of Task C

[1112] 17:00 - 18:00: Easy stress relief activities

[1113] This schedule takes into account the user's work and meeting times, and is adjusted to reflect the user's stress level using the emotion engine. Based on this schedule, users can carry out their daily tasks efficiently and in a balanced manner.

[1114] As described above, the present invention provides an optimal schedule that takes into account a user's emotional state as well as their patterns and preferences, thereby improving the user's productivity and quality of life.

[1115] The processing flow will be explained below.

[1116] Step 1:

[1117] The user launches a terminal application and enters schedule-related information such as work hours (e.g., 9:00-18:00), lunch time (e.g., 12:00-13:00), and preferred meeting times (e.g., 10:00-11:00, 15:00-16:00) through the terminal UI.

[1118] Step 2:

[1119] The emotion engine recognizes the user's emotions. The device analyzes the user's facial expressions and voice in real time to collect emotional information. For example, it can detect "stress" from the user's facial expressions using camera footage.

[1120] Step 3:

[1121] The device converts the schedule information entered by the user and the emotional information recognized by the emotion engine into JSON format. Specifically, the data is summarized as follows:

[1122] json

[1123] {

[1124] "user_id": "12345",

[1125] "preferences": {

[1126] "work_hours": "9:00-18:00",

[1127] "lunch_break": "12:00-13:00",

[1128] "preferred_meeting_times": ["10:00-11:00", "15:00-16:00"]

[1129] },

[1130] "emotion": "stress",

[1131] "existing_schedule": {}

[1132] }

[1133] Step 4:

[1134] The device sends this compiled JSON data to the server as an HTTP POST request. The endpoint is, for example, / schedule.

[1135] Step 5:

[1136] The server receives the HTTP POST request sent from the device. The server obtains the JSON format data from the request body, parses it, and converts it to the internal data format.

[1137] Step 6:

[1138] The server passes the analyzed data to the generative model and emotion engine. The generative model generates a schedule based on the user's patterns and preferences, and the emotion engine further adjusts the generated schedule using the user's emotion information.

[1139] Step 7:

[1140] The generative model first generates a standard schedule based on user input data. This schedule balances task priority, duration, and break times. For example, the following schedule might be generated:

[1141] 09:00 - 09:30: Check email

[1142] 09:30 - 10:00: Preparation of materials

[1143] 10:00 - 11:00: Meeting 1

[1144] 11:00 - 12:00: Progress of Task A

[1145] 12:00 - 13:00: Lunch break

[1146] 13:00 - 15:00: Progress of Task B

[1147] 15:00 - 16:00: Meeting 2

[1148] 16:00 - 18:00: Progress of Task C

[1149] Step 8:

[1150] The emotion engine adjusts the schedule based on the standard schedule according to the user's emotion information. For example, if the emotion engine determines that the user's emotion is "stress," it adjusts the schedule to increase break time and relaxation time. The adjusted schedule will look like this:

[1151] 09:00 - 09:30: Check email

[1152] 09:30 - 10:00: Preparation of materials

[1153] 10:00 - 11:00: Meeting 1

[1154] 11:00 - 12:00: Progress of Task A

[1155] 12:00 - 13:00: Lunch break

[1156] 13:00 - 14:00: Relaxation time

[1157] 14:00 - 15:00: Progress of Task B

[1158] 15:00 - 16:00: Meeting 2

[1159] 16:00 - 17:00: Progress of Task C

[1160] 17:00 - 18:00: Easy stress relief activities

[1161] Step 9:

[1162] The server converts the schedule generated and adjusted by the generative model and emotion engine into JSON format and sends it to the terminal as an HTTP response.

[1163] Step 10:

[1164] The terminal parses the HTTP response received from the server and converts the JSON data into an internal data format. After obtaining the new schedule information, the terminal displays the schedule in an easy-to-read format for the user.

[1165] Step 11:

[1166] The user can check the new schedule displayed on the terminal and efficiently carry out daily tasks based on the generated schedule.

[1167] Step 12:

[1168] Based on user feedback and actual schedule history, the generative model and emotion engine further learn and reflect this in the next schedule generation, resulting in a more personalized schedule that optimally reflects the user's emotional state.

[1169] Example 2

[1170] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1171] Conventional schedule generation systems only analyze user patterns and preferences, but are unable to consider the user's emotional state. As a result, they may generate schedules that ignore the user's stress and fatigue, making it difficult for the user to complete tasks efficiently. Furthermore, they lacked a learning function that utilizes user feedback and schedule history, making it difficult to generate schedules that are optimized for individual users' needs.

[1172] 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.

[1173] In this invention, the server includes means for analyzing a user's patterns and emotional state using a generative model and an emotion recognition engine to generate an optimal schedule, means for acquiring data entered by the user and emotional information collected by the emotion recognition engine at a terminal and transmitting the data to the server, and means for receiving a schedule generated based on the analyzed data by the server and displaying it to the user. This makes it possible to generate an optimal schedule that reflects the user's emotional state, and furthermore, a learning function based on user feedback and schedule history makes it possible to provide a more personalized schedule for the user.

[1174] A "generative model" is an algorithm that generates an optimal schedule based on a user's patterns and preferences.

[1175] An "emotion recognition engine" is a software component that recognizes and analyzes a user's emotional state in real time.

[1176] A "pattern" is a consistent tendency or habit based on a user's behavior or preferences.

[1177] "Preferences" refer to tasks and time allocations that the user particularly prefers.

[1178] A "schedule" is a plan that arranges a user's daily tasks and events in time.

[1179] A "terminal" is an electronic device that allows a user to input and display information.

[1180] "Server" refers to the central computer system that analyzes data sent from the terminals and generates and adjusts schedules.

[1181] "Data transmission" refers to the process of sending information from a terminal to a server.

[1182] "Data analysis" refers to the process by which the server processes the data it receives to extract useful information.

[1183] "Feedback" refers to opinions and ratings that users provide to a system, which the system uses to learn and improve based on that information.

[1184] "Learning function" refers to the system's ability to improve future performance based on past data and feedback.

[1185] MODE FOR CARRYING OUT THE INVENTION

[1186] This invention is a system that uses a generative model and an emotion recognition engine to analyze a user's patterns, preferences, and emotional state to generate an optimal schedule. This system comprehensively analyzes data entered by the user and emotional information collected by the emotion recognition engine, generates an optimal schedule on the server, and displays it on the terminal.

[1187] First, the user inputs information related to their schedule via their device. Specifically, the user enters information such as "work hours," "lunch time," and "priority meeting times" into an input form on the device. The emotion recognition engine then recognizes the user's emotions in real time and collects that information. For example, the device's camera can be used to analyze facial expressions and extract emotional information from voice data.

[1188] The device converts the information entered by the user and the emotion data collected by the emotion recognition engine into JSON format and sends it to the server using an HTTP request, for example, as a POST request to "https: / / server.url / schedule."

[1189] The server analyzes the received data and integrates the outputs of the generative model and the emotion recognition engine. The generative model generates an initial schedule based on the user's patterns and preferences. The emotion recognition engine then adjusts the generated schedule based on the user's emotional state. For example, if the user is feeling stressed, the engine may add relaxation time or breaks to the generated schedule.

[1190] The server converts the final adjusted schedule into JSON format and sends it to the device as an HTTP response. The device then analyzes the received data and displays the schedule in a user-friendly format, enabling users to plan and complete their daily tasks based on an efficient and balanced schedule.

[1191] Furthermore, user feedback and actual schedule history are sent to the server, and the generative model and emotion recognition engine use this data for training, which is reflected in the next schedule generation, providing a more personalized schedule for the user.

[1192] As a concrete example, suppose a user enters the following information into a terminal:

[1193] Working hours: 9:00-18:00

[1194] Lunchtime: 12:00-13:00

[1195] Preferred meeting times: 10:00-11:00, 15:00-16:00

[1196] If the emotion recognition engine recognizes the user's face and determines that the current emotion is "stress," the generative model on the server will generate the following schedule:

[1197] 09:00 - 09:30: Check email

[1198] 09:30 - 10:00: Preparation of materials

[1199] 10:00 - 11:00: Meeting 1

[1200] 11:00 - 12:00: Progress of Task A

[1201] 12:00 - 13:00: Lunch break

[1202] 13:00 - 14:00: Relaxation time

[1203] 14:00 - 15:00: Progress of Task B

[1204] 15:00 - 16:00: Meeting 2

[1205] 16:00 - 17:00: Progress of Task C

[1206] 17:00 - 18:00: Easy stress relief activities

[1207] An example prompt is:

[1208] "Generate the best schedule for your users based on their current situation. Create a schedule based on the following information:

[1209] Working hours: 9:00-18:00

[1210] Lunchtime: 12:00-13:00

[1211] Preferred meeting times: 10:00-11:00, 15:00-16:00

[1212] Furthermore, the emotion recognition engine determined that the user's emotion was 'stress'.

[1213] In this way, the system provides an optimal schedule that takes into account the user's patterns and preferences as well as their emotional state, improving their productivity and quality of life.

[1214] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1215] Step 1:

[1216] User Data Input

[1217] The user enters schedule-related information such as "work hours," "lunchtime," and "preferred meeting times" into an input form on the terminal. Specifically, the user enters "work hours" as "9:00-18:00," "lunchtime" as "12:00-13:00," and "preferred meeting times" as "10:00-11:00, 15:00-16:00." After entering the information, the user presses the send button. The input in this step is schedule information manually entered by the user, and the output is temporary data stored in the terminal.

[1218] Step 2:

[1219] Emotional Data Collection

[1220] The device collects the user's emotional data using an emotion recognition engine. The device's camera is used to analyze the user's facial expressions in real time, and the emotion recognition engine recognizes "stress" from the facial expressions. If there is voice input, the device extracts emotions from the voice data. The input for this step is the user's facial and voice data, and the output is emotional data analyzed by the emotion recognition engine.

[1221] Step 3:

[1222] Data transmission

[1223] The device combines the schedule information entered by the user with the emotion data collected by the emotion recognition engine and converts it into JSON format. It then sends the data to the server using an HTTP request. For example, the destination is a POST request to "https: / / server.url / schedule." The input of this step is the schedule information and emotion data, and the output is the data converted into JSON format.

[1224] Step 4:

[1225] Data analysis

[1226] The server parses the received JSON data and extracts the user's schedule information and emotional state. This analysis is typically performed using programming languages ​​such as Python or Java. The input for this step is JSON-formatted data, and the output is the parsed schedule information and emotional data.

[1227] Step 5:

[1228] Schedule Generation

[1229] The server's generative model generates an initial schedule based on the analyzed schedule information and user patterns. For example, it arranges tasks such as "09:00-09:30: Check email" and "09:30-10:00: Prepare documents." The input of this step is the analyzed schedule information, and the output is an initial schedule proposal.

[1230] Step 6:

[1231] Schedule adjustment

[1232] The generated initial schedule is adjusted based on the output of the emotion recognition engine. For example, if the user is recognized as "stressed," relaxation time or rest time is added to the schedule. The input of this step is the initial schedule and emotion data, and the output is the adjusted final schedule.

[1233] Step 7:

[1234] Scheduled Sending

[1235] The server converts the adjusted final schedule into JSON format and sends it to the terminal as an HTTP response. The input of this step is the adjusted final schedule, and the output is the transmission of JSON format data.

[1236] Step 8:

[1237] Schedule Display

[1238] The device parses the received JSON data and displays the schedule in a visually easy-to-understand format. For example, it may use the in-app calendar function to display the schedule in a color-coded format. The input of this step is the JSON data received from the server, and the output is a visual schedule display that the user can view.

[1239] Step 9:

[1240] Feedback gathering and learning

[1241] The user enters feedback on the task they performed into a feedback form within the device app. For example, they answer questions such as, "Was today's schedule appropriate?" The device sends this feedback to the server, and the server's generative model and emotion recognition engine use the data for training. The input of this step is the user's feedback data, and the output is the trained generative model and emotion recognition engine.

[1242] As a result, the system improves users' productivity and quality of life by providing an optimal schedule that takes into account their emotional state as well as their patterns and preferences.

[1243] (Application example 2)

[1244] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1245] In modern society, stress and busyness make it difficult for users to efficiently manage their schedules. Furthermore, there is a lack of systems that can recommend optimal content and tasks according to a user's emotional state, which means that users are unable to find appropriate ways to relax or progress with their work according to their emotions.

[1246] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing a user's patterns and preferences using a generative model and generating an optimal schedule, terminal means for transmitting collected data to the server, terminal means for receiving the generated schedule and displaying it to the user, means for analyzing the user's emotional state using an emotion engine, and means for adjusting the schedule based on the emotional state. This allows the user to obtain an optimal schedule based on not only their own patterns and preferences but also their emotional state recognized in real time. Furthermore, appropriate content and relaxation methods are simultaneously suggested based on the user's emotional state, allowing them to perform daily tasks efficiently and comfortably.

[1247] A "generative model" is an algorithm that takes data as input, analyzes user patterns and preferences, and generates output tailored to a specific purpose.

[1248] A "pattern" is a recurring feature that indicates a user's tendencies in behavior or choices.

[1249] "Preferences" are specific activities, content, or options that a user prefers.

[1250] An "optimal schedule" is a timetable or plan that maximizes a user's efficiency and comfort, based on the user's patterns, preferences, and emotional state.

[1251] "Means" refers to a device, system, algorithm, or other technical means used to achieve a specific purpose.

[1252] A "server" is a computer system that provides a set of computing resources for storing, analyzing, and processing data.

[1253] A "terminal" is a device or apparatus that a user directly operates to input, display, and transmit information.

[1254] An "emotion engine" is an algorithm or system that analyzes a user's facial expressions, voice, and behavioral data to identify their emotional state in real time.

[1255] "Collecting" refers to the act or process of gathering necessary data, which in the present invention refers to data relating to the user's emotional state, behavioral patterns, and preferences.

[1256] "Analysis" is the process of examining collected data in detail and deriving meaning and trends from it.

[1257] "Tuning" is the act or process of changing components to optimize them based on specific conditions.

[1258] "Relaxation methods" refer to specific means or activities for reducing the user's stress and resting the mind and body.

[1259] "Content" refers to the information media consumed by users, including, for example, movies, music, videos, etc.

[1260] This invention is a system that uses a generative model and an emotion engine to analyze a user's patterns, preferences, and emotional state to generate an optimal schedule. This system comprehensively analyzes data entered by the user and emotional information collected by the emotion engine, generates an optimal schedule for the user on the server, and displays it on the terminal.

[1261] First, the user inputs information related to their schedule via their device. Specifically, the user enters information such as "work hours," "lunch time," and "priority meeting times" into an input form on the device. The emotion engine then recognizes the user's emotions in real time and collects that information. For example, it can analyze facial expressions using the user's camera or extract emotions from their voice.

[1262] The device converts this information into JSON format and sends it to the server. The server analyzes the data and integrates the output of the generative model and emotion engine. The generative model generates a schedule based on the user's patterns and preferences, and the emotion engine adjusts the schedule according to the user's emotional state.

[1263] The server uses a machine learning algorithm as a generative model to learn the user's past behavioral data and patterns. Specifically, a deep learning model (e.g., TensorFlow) can be used. Furthermore, a library for analyzing the user's emotional state in real time (e.g., OpenCV, Microsoft Azure's Emotion API) can be used as an emotion engine.

[1264] For example, if a user is feeling stressed, the output of the emotion engine is fed back to the generative model, which adjusts the schedule to increase relaxation and rest periods. In this way, a schedule is generated to optimize the user's emotional state. The server converts the generated schedule into JSON format and sends it to the device as an HTTP response. The device analyzes the received data and displays the new schedule in an easy-to-read format for the user. The user can plan and execute daily tasks based on this schedule.

[1265] As a concrete example, consider the case where a user launches a terminal application and inputs their "work hours" as "9:00-18:00," "lunchtime" as "12:00-13:00," and "priority meeting times" as "10:00-11:00, 15:00-16:00." Furthermore, suppose the emotion engine recognizes the user's face and determines their current emotion as "stressed." The server's generative model integrates the input information and the emotion engine's results to generate the following schedule:

[1266] ---

[1267] Example prompt sentence:

[1268] If the user is "stressed", generate a schedule like this:

[1269] 09:00 - 10:00: Relaxation music

[1270] 10:00 - 11:00: Comedy movie

[1271] 11:00 - 12:00: Light fitness videos

[1272] 12:00 - 13:00: Lunch break

[1273] 13:00 - 14:00: Reflection and journaling

[1274] 14:00 - 15:00: Music appreciation (selected songs)

[1275] 15:00 - 16:00: Meditation video

[1276] Based on this schedule, users can take effective actions that are tailored to their own emotions and patterns.

[1277] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1278] Step 1:

[1279] A user inputs information related to his or her schedule (such as "work hours," "lunch time," and "priority meeting times") via a terminal. This information is entered into the terminal using an input form. The input data is used as the initial data required to generate a schedule.

[1280] Input: Schedule-related information (work time, lunch time, meeting time, etc.)

[1281] Output: Structured input data

[1282] Step 2:

[1283] The device uses the user's camera and microphone to analyze the user's facial expressions and voice in real time, and the emotion engine recognizes the user's emotional state. This emotion information is fed back to the generative model.

[1284] Input: Real-time data from camera and microphone

[1285] Output: Parsed emotional state information

[1286] Step 3:

[1287] The device converts the collected schedule information and emotional state information into JSON format and sends it to the server. This data becomes the initial dataset for schedule generation.

[1288] Input: Structured input data and parsed emotional state information

[1289] Output: JSON format data

[1290] Step 4:

[1291] The server analyzes the received data and uses a generative model to analyze the user's patterns and preferences. The generative model uses a deep learning-based model (e.g., TensorFlow). The generative model learns the user's behavioral patterns from past data and generates an optimal schedule.

[1292] Input: JSON format data

[1293] Output: An initial schedule that reflects user patterns and preferences

[1294] Step 5:

[1295] The server then feeds back the analysis results of the emotion engine to the generative model and adjusts the schedule based on the user's emotional state. For example, if the user is feeling stressed, the schedule may be adjusted to increase relaxation time.

[1296] Input: Initial schedule, emotional state information

[1297] Output: An optimized schedule that reflects emotional state

[1298] Step 6:

[1299] The server converts the generated optimized schedule into JSON format and sends it to the terminal as an HTTP response. The optimized schedule is structured in a format that is visually easy for users to understand.

[1300] Input: Optimized schedule reflecting emotional state

[1301] Output: Response data in JSON format

[1302] Step 7:

[1303] The device analyzes the received data and displays the schedule in an easy-to-read format for the user, who can then plan and execute their daily tasks.

[1304] Input: Response data in JSON format

[1305] Output: A visual representation of the schedule

[1306] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1307] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1308] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1309] [Fourth embodiment]

[1310] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1311] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1312] 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).

[1313] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1314] 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.

[1315] 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).

[1316] 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.

[1317] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1318] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1319] 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.

[1320] 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.

[1321] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1322] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1323] The present invention is a system that uses a generative model to analyze user patterns and preferences to generate an optimal schedule. In this system, data entered by the user is sent to a server, which then uses the generative model to generate a schedule and returns the results to the terminal for display to the user.

[1324] First, the user uses the device to input information related to their schedule. For example, the user inputs information such as "work hours," "lunch time," "preferred meeting times," etc. This input data is compiled in JSON format and sent to the server.

[1325] The data received from the device is analyzed by the server and converted into an appropriate format. The server then runs a generative model to generate an optimal schedule based on the user's patterns and preferences. The generative model takes into account the user's input data and creates a schedule by balancing task priorities, durations, break times, etc. The generated schedule is converted into JSON format and sent to the device as an HTTP response.

[1326] The device converts the schedule data received from the server into an internal format and displays it in an easy-to-read format for the user. The user can check this schedule and plan and execute daily tasks based on it. In addition, the generative model can learn more effectively based on user feedback and reflect this in the next schedule generation.

[1327] Next, the operation of the system will be explained using a concrete example.

[1328] As a concrete example, suppose a user starts a terminal application and inputs their "Work Hours" as "9:00-18:00", "Lunch Time" as "12:00-13:00", and "Preferred Meeting Times" as "10:00-11:00, 15:00-16:00". This information is compiled by the terminal in JSON format and sent to the server.

[1329] The server analyzes this data and uses a generative model to generate a schedule like this:

[1330] 09:00 - 09:30: Check email

[1331] 09:30 - 10:00: Preparation of materials

[1332] 10:00 - 11:00: Meeting 1

[1333] 11:00 - 12:00: Progress of Task A

[1334] 12:00 - 13:00: Lunch break

[1335] 13:00 - 15:00: Progress of Task B

[1336] 15:00 - 16:00: Meeting 2

[1337] 16:00 - 18:00: Progress of Task C

[1338] The generated schedule is sent from the server to the device, which receives it and displays it to the user. The user can then use this new schedule to efficiently complete their daily tasks. Initial investments in software development, generative model training, and user experience design can be used to optimize the system, further improving the user's quality of life.

[1339] In this way, the present invention generates an optimal schedule that takes into account the user's patterns and preferences, enabling efficient time management and improved quality of life.

[1340] The processing flow will be explained below.

[1341] Step 1:

[1342] A user launches a terminal application and enters schedule-related information such as work hours, lunch time, and preferred meeting times through the terminal UI.

[1343] Step 2:

[1344] The device collects the information entered by the user and converts it into JSON format. For example, if a user enters their work hours as 9:00-18:00, their lunch time as 12:00-13:00, and their preferred meeting times as 10:00-11:00 and 15:00-16:00, the information is compiled as follows:

[1345] json

[1346] {

[1347] "user_id": "12345",

[1348] "preferences": {

[1349] "work_hours": "9:00-18:00",

[1350] "lunch_break": "12:00-13:00",

[1351] "preferred_meeting_times": ["10:00-11:00", "15:00-16:00"]

[1352] },

[1353] "existing_schedule": {}

[1354] }

[1355] Step 3:

[1356] The device sends this JSON data to the server as an HTTP POST request. The endpoint is specified as / schedule, for example.

[1357] Step 4:

[1358] The server receives the HTTP POST request sent from the device. The server obtains the JSON format data from the request body, parses it, and converts it to the internal data format.

[1359] Step 5:

[1360] The server passes the analyzed data to the generative model, which analyzes the user's patterns and preferences based on the user ID, schedule preference information, and existing schedule information.

[1361] Step 6:

[1362] The generative model takes into account user input data and generates an optimal schedule by balancing task priorities, required times, and break times. For example, the following schedule may be generated:

[1363] 09:00 - 09:30: Check email

[1364] 09:30 - 10:00: Preparation of materials

[1365] 10:00 - 11:00: Meeting 1

[1366] 11:00 - 12:00: Progress of Task A

[1367] 12:00 - 13:00: Lunch break

[1368] 13:00 - 15:00: Progress of Task B

[1369] 15:00 - 16:00: Meeting 2

[1370] 16:00 - 18:00: Progress of Task C

[1371] Step 7:

[1372] The schedule generated by the generative model is converted into JSON format by the server and sent to the terminal as an HTTP response.

[1373] Step 8:

[1374] The terminal parses the HTTP response received from the server and converts the JSON data into an internal data format. After obtaining the new schedule information, the terminal displays the schedule in an easy-to-read format for the user.

[1375] Step 9:

[1376] The user checks the new schedule displayed on the terminal, and can efficiently carry out daily tasks based on the generated schedule.

[1377] Step 10:

[1378] Based on user feedback and actual schedule history, the generative model further learns and reflects this in the next schedule generation, resulting in a more personalized schedule.

[1379] Example 1

[1380] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1381] Conventional scheduling systems struggle to efficiently manage time because they fail to fully reflect users' patterns and preferences. Furthermore, continuous optimization is difficult because there is no mechanism for automatically improving the model based on user feedback. As a result, there are limitations to improving users' quality of life and the accuracy of task management.

[1382] 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.

[1383] In this invention, the server includes: means for analyzing a user's patterns and preferences using a generative model and generating an optimal schedule; terminal means for the user to input information related to the schedule and send it to the server in JSON format; means for the server to analyze the received data, execute the generative model to generate a schedule, and return the result in JSON format to the terminal; terminal means for receiving the generated schedule and visually displaying it to the user; and means for further training the generative model based on feedback from the user. This enables efficient schedule generation that reflects the user's individual patterns and preferences, and by continuously improving the model, more accurate task management and improved quality of life are possible.

[1384] A "generative model" is a machine learning algorithm used to analyze user patterns and preferences and generate optimal schedules.

[1385] "User" refers to a person or organization that inputs schedule-related information and transmits it to the server via a terminal.

[1386] "Terminal" refers to a device such as a computer, tablet, or smartphone that a user uses to input schedule-related information.

[1387] "Server" refers to a networked computer system that receives and analyzes data sent by users, executes generative models to generate optimal schedules, and returns them to the terminals.

[1388] "JSON format" is an abbreviation for JavaScript Object Notation, and is a format for structuring data and expressing it in text format.

[1389] An "HTTP request" refers to a request based on a protocol for a terminal to send and receive data to a server.

[1390] An "HTTP response" refers to data sent by a server in response to an HTTP request received from a terminal.

[1391] "Feedback" refers to opinions and evaluations provided by users regarding the generated schedule, and is used to improve the generative model.

[1392] The present invention is a system that uses a generative model to analyze user patterns and preferences to generate an optimal schedule. In this system, data entered by the user is sent to a server, which then uses the generative model to generate a schedule and returns the results to the terminal for display to the user.

[1393] Specifically, a user uses a terminal to input information related to their schedule. For example, the user inputs information such as "work hours," "lunch time," "preferred meeting times," etc. This input data is compiled in JSON format and sent to the server.

[1394] The server analyzes the data received from the device and converts it into an appropriate format. Python's json module can be used for analysis. The server then runs a generative model built using libraries such as TensorFlow and PyTorch to generate an optimal schedule based on the user's patterns and preferences. The generative model takes into account the user's input data and creates a schedule by balancing task priorities, required times, break times, and other factors.

[1395] The generated schedule is converted back to JSON format and sent to the device as an HTTP response. The device converts the schedule data received from the server into an internal format and displays it in an easy-to-read format for the user. The user can check this schedule and plan and execute daily tasks based on it.

[1396] Users can also provide feedback based on their experience using the schedule. The server uses this feedback to further train the generative model and reflect it in the next schedule generation. This cycle allows the system to be continuously optimized, enabling it to continue providing the best schedule for the user.

[1397] For example, if a user launches a terminal application and enters their "work hours" as "9:00-18:00," "lunchtime" as "12:00-13:00," and "preferred meeting times" as "10:00-11:00, 15:00-16:00," this information is compiled by the terminal in JSON format and sent to the server. The server analyzes this data and uses a generative model to generate the following schedule:

[1398] 09:00 - 09:30: Check email

[1399] 09:30 - 10:00: Preparation of materials

[1400] 10:00 - 11:00: Meeting 1

[1401] 11:00 - 12:00: Progress of Task A

[1402] 12:00 - 13:00: Lunch break

[1403] 13:00 - 15:00: Progress of Task B

[1404] 15:00 - 16:00: Meeting 2

[1405] 16:00 - 18:00: Progress of Task C

[1406] The generated schedule is sent from the server to the device, which receives it and displays it to the user, allowing the user to efficiently complete daily tasks based on this new schedule.

[1407] Below is an example of a prompt sentence to input to the generative AI model.

[1408] "User's schedule data:

[1409] Working hours: 9:00-18:00

[1410] Lunchtime: 12:00-13:00

[1411] Preferred meeting times: 10:00-11:00, 15:00-16:00

[1412] Generate an optimal daily schedule based on the information above.

[1413] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1414] Step 1:

[1415] Users launch the application on their device and enter information related to their schedule, such as "work hours," "lunch time," and "preferred meeting times." This information is formatted in JSON format.

[1416] Input: Schedule information entered by the user (e.g., work hours, lunch times, meeting times, etc.)

[1417] Output: Schedule information formatted in JSON format

[1418] Step 2:

[1419] The device sends the entered JSON format data to the server using an HTTP request. Specifically, the entered schedule information is formatted appropriately and sent to the specified URL.

[1420] Input: Schedule information in JSON format

[1421] Output: HTTP request to the server

[1422] Step 3:

[1423] The server receives the HTTP request sent from the terminal. This process uses server software such as Apache or Nginx. It extracts and analyzes the JSON data contained in the body of the HTTP request.

[1424] Input: HTTP request sent from the terminal

[1425] Output: Parsed schedule information

[1426] Step 4:

[1427] The server decodes the received JSON data using Python's json module and converts it into an internal format, extracts the appropriate fields, and converts them into a data structure for input to the generative model.

[1428] Input: Parsed schedule information (JSON format)

[1429] Output: A data structure to feed into the generative model.

[1430] Step 5:

[1431] The server runs a generative AI model to generate an optimal schedule. The generative model uses TensorFlow and PyTorch. Based on user input data, the model considers the priority, duration, and break times of each task to generate a balanced and appropriate schedule.

[1432] Input: The data structure to input to the model.

[1433] Output: The generated schedule

[1434] Step 6:

[1435] The server converts the generated schedule back into JSON format and sends it back to the terminal as an HTTP response. This conversion is performed using the Python json module. The generated schedule is included in the body of the HTTP response.

[1436] Input: Generated schedule

[1437] Output: JSON formatted schedule, HTTP response

[1438] Step 7:

[1439] The device processes the HTTP response received from the server and parses the JSON-formatted schedule data using JavaScript's fetch API or XMLHttpRequest.

[1440] Input: HTTP response received from the server

[1441] Output: Parsed schedule data

[1442] Step 8:

[1443] The terminal converts the analyzed schedule data into an internal format and processes it for display on the user interface. Specifically, it visually displays the schedule using HTML and CSS.

[1444] Input: Parsed schedule data

[1445] Output: A schedule that is visually displayed to the user

[1446] Step 9:

[1447] The user can then view the displayed schedule, plan and execute their daily tasks based on it, and provide feedback if necessary, which is then formatted into JSON and sent from the device to the server.

[1448] Input: User feedback

[1449] Output: Feedback data formatted in JSON format

[1450] Step 10:

[1451] The server analyzes the received feedback and adds it to the training dataset of the generative model, which then reflects the feedback in the next schedule generation, allowing the system to continuously optimize.

[1452] Input: Feedback data in JSON format

[1453] Output: Updated training dataset, optimized generative model

[1454] (Application example 1)

[1455] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1456] Conventional schedule management systems tend to generate schedules that do not match actual usage conditions because they do not fully consider individual user patterns and preferences. Furthermore, task schedules for factory robots often require manual adjustments, limiting their efficient operation. This leads to problems such as reduced labor productivity and wasted time and effort. Furthermore, efficient task management for users and robots is difficult, and this situation needed to be improved.

[1457] 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.

[1458] In this invention, the server includes means for analyzing user patterns and preferences using a generative model and generating an optimal schedule, terminal means for transmitting collected data to the server, terminal means for receiving the generated schedule and displaying it to the user, and means for generating and optimizing task schedules for factory robots, thereby enabling schedule generation according to individual user needs and efficient task management for factory robots.

[1459] A "generative model" is a type of artificial intelligence used to analyze user patterns and preferences and generate optimal schedules.

[1460] The term "terminal means" refers to a device that allows a user to input information and a device that receives and displays a schedule generated from a server.

[1461] A "factory robot" is a mechanical device that automatically performs tasks within a factory and requires a schedule for efficient operation.

[1462] A "task schedule" is a plan that determines the allocation, order, and time slots of tasks within a specific period of time.

[1463] A "server" is a central processing unit that receives information from multiple terminals, generates a schedule using a generative model, and returns the results to the terminals.

[1464] "Collected data" refers to all information necessary for generating a schedule, such as information entered by users into terminals and operating information of factory robots.

[1465] "Priority" is a criterion that indicates which task is more important than others, and is taken into consideration when generating a schedule.

[1466] "Rest time" refers to a time period set for users or factory robots to take a rest while they are operating.

[1467] "Initial investment" refers to the funds and resources required to deploy the system, including software development, generative model training, and user experience design.

[1468] "User experience design" is a design process that aims to improve the experience users have when using a system.

[1469] The present invention is a system that uses a generative model to analyze user patterns and preferences to generate an optimal schedule. In this system, data entered by the user is sent to a server, which then uses the generative model to generate a schedule and returns the results to the terminal for display to the user.

[1470] First, a user uses a device (e.g., a tablet or PC) to input information related to their schedule. For example, a user might input information such as "work hours," "break times," and "preferred meeting times," or, in the case of a factory robot, "tasks in charge," "priority," and "break times." This input data is compiled in JSON format and sent to the server.

[1471] The server receives the input data, parses it, and converts it into the appropriate format. This data analysis is performed using Python-based scripts. The server then runs a generative AI model (such as GPT-4) to generate an optimal schedule based on the user's patterns and preferences. This generative model takes into account the user's input data and balances task priorities, durations, break times, and other factors to create a schedule.

[1472] The generated schedule is converted back to JSON format and sent to the device as an HTTP response. The device then converts the schedule data received from the server into an internal format and displays it in an easy-to-read format for the user.

[1473] As a concrete example, let's say the user is a factory manager and enters the following information:

[1474] {

[1475] "Operating hours": "08:00-17:00",

[1476] "Task": [

[1477] {"Name": "Welding work", "Priority": "High", "Duration": 60},

[1478] {"Name": "Quality Inspection", "Priority": "Medium", "Time Required": 30},

[1479] {"Name": "Transport", "Priority": "Low", "Duration": 45}

[1480] ],

[1481] "Break Time": "12:00-13:00"

[1482] }

[1483] This information is sent from the device to a server, and a generative AI model generates an optimal schedule that looks like this:

[1484] Generate an optimal schedule for the factory robots based on the following data:

[1485] Operating hours: 08:00-17:00

[1486] task:

[1487] Welding (High Priority, 60 minutes)

[1488] Quality Inspection (Priority: Medium, Time: 30 minutes)

[1489] Transport (Priority: Low, Time: 45 minutes)

[1490] Break time: 12:00-13:00

[1491] The generated schedule looks like this:

[1492] 08:00 - 09:00: Welding work

[1493] 09:00 - 09:30: Quality inspection

[1494] 09:30 - 10:15: Transport

[1495] 10:15 - 11:15: Welding work

[1496] 11:15 - 12:00: Quality inspection

[1497] 12:00 - 13:00: Break

[1498] 13:00 - 14:00: Transport

[1499] 14:00 - 15:00: Welding work

[1500] 15:00 - 15:30: Quality inspection

[1501] 15:30 - 16:15: Transport

[1502] 16:15 - 17:00: Quality inspection

[1503] This schedule is received from the server and displayed on the terminal, allowing users to check it and efficiently manage the operation of factory robots. This is expected to improve factory productivity and work efficiency. In addition, by investing initial funds in software development, generative model training, and user experience design, the system can be optimized to more effectively meet user demands.

[1504] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1505] Step 1:

[1506] Users use devices (e.g., tablets or PCs) to input schedule information, including work hours, break times, preferred meeting times, factory robot tasks, priorities, and required times. The input data is compiled in JSON format and sent to the server.

[1507] Input: Schedule-related information entered by the user into the device

[1508] Output: Data organized in JSON format

[1509] Step 2:

[1510] The server receives JSON-formatted data sent from the device. To receive this data, an HTTP request handler must be set up. The server analyzes the received data and converts it into a format suitable for the generative model. For this purpose, a Python json library or similar is used.

[1511] Input: JSON format data sent from the terminal

[1512] Output: Parsed and transformed schedule-related data

[1513] Step 3:

[1514] The server uses a generative AI model (e.g., GPT-4) to generate an optimal schedule. To do this, a prompt is first generated and sent to the generative model. The generative AI model then takes the input data into account and creates a schedule that balances task priorities, required time, break times, etc.

[1515] Input: Parsed and transformed schedule-related data, and generated prompt statements

[1516] Output: Schedule data generated by the generative AI model

[1517] Step 4:

[1518] The generated schedule is converted back to JSON format and sent to the terminal as an HTTP response. The server uses an HTTP communication library such as Python to generate the HTTP response.

[1519] Input: Generated schedule data

[1520] Output: Generated schedule data converted to JSON format

[1521] Step 5:

[1522] The terminal converts the schedule data received from the server into an internal format and displays it in an easy-to-read format for the user. The GUI application used for display is usually implemented using HTML, CSS, JavaScript, etc. This allows the user to check their schedule and manage tasks efficiently.

[1523] Input: Generated schedule data in JSON format received from the server

[1524] Output: Schedule information displayed on the device screen in a user-friendly format

[1525] 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.

[1526] This invention is a system that uses a generative model and an emotion engine to analyze a user's patterns, preferences, and emotional state to generate an optimal schedule. This system comprehensively analyzes data entered by the user and emotional information collected by the emotion engine, generates an optimal schedule for the user on the server, and displays it on the terminal.

[1527] First, the user inputs information related to their schedule via their device. Specifically, the user enters information such as "work hours," "lunch time," and "priority meeting times" into an input form on the device. The emotion engine then recognizes the user's emotions in real time and collects that information. For example, it can analyze facial expressions using the user's camera or extract emotions from their voice.

[1528] The device converts this information into JSON format and sends it to the server. The server analyzes the data and integrates the output of the generative model and emotion engine. The generative model generates a schedule based on the user's patterns and preferences, and the emotion engine adjusts the schedule according to the user's emotional state.

[1529] For example, if a user is feeling stressed, the emotion engine's output is fed back to the generative model, which adjusts the schedule to increase relaxation and rest time. In this way, a schedule is generated that optimizes the user's emotional state.

[1530] The server converts the generated schedule into JSON format and sends it to the device as an HTTP response. The device analyzes the received data and displays the new schedule in an easy-to-read format for the user. The user can plan and execute daily tasks based on this schedule. In addition, the generative model and emotion engine further learn based on user feedback and actual schedule history, and the learning is reflected in the next schedule generation.

[1531] As a concrete example, consider the case where a user launches a terminal application and inputs their "work hours" as "9:00-18:00," "lunchtime" as "12:00-13:00," and "priority meeting times" as "10:00-11:00, 15:00-16:00." Furthermore, suppose the emotion engine recognizes the user's face and determines their current emotion as "stressed." The server's generative model integrates the input information and the emotion engine's results to generate the following schedule:

[1532] 09:00 - 09:30: Check email

[1533] 09:30 - 10:00: Preparation of materials

[1534] 10:00 - 11:00: Meeting 1

[1535] 11:00 - 12:00: Progress of Task A

[1536] 12:00 - 13:00: Lunch break

[1537] 13:00 - 14:00: Relaxation time

[1538] 14:00 - 15:00: Progress of Task B

[1539] 15:00 - 16:00: Meeting 2

[1540] 16:00 - 17:00: Progress of Task C

[1541] 17:00 - 18:00: Easy stress relief activities

[1542] This schedule takes into account the user's work and meeting times, and is adjusted to reflect the user's stress level using the emotion engine. Based on this schedule, users can carry out their daily tasks efficiently and in a balanced manner.

[1543] As described above, the present invention provides an optimal schedule that takes into account a user's emotional state as well as their patterns and preferences, thereby improving the user's productivity and quality of life.

[1544] The processing flow will be explained below.

[1545] Step 1:

[1546] The user launches a terminal application and enters schedule-related information such as work hours (e.g., 9:00-18:00), lunch time (e.g., 12:00-13:00), and preferred meeting times (e.g., 10:00-11:00, 15:00-16:00) through the terminal UI.

[1547] Step 2:

[1548] The emotion engine recognizes the user's emotions. The device analyzes the user's facial expressions and voice in real time to collect emotional information. For example, it can detect "stress" from the user's facial expressions using camera footage.

[1549] Step 3:

[1550] The device converts the schedule information entered by the user and the emotional information recognized by the emotion engine into JSON format. Specifically, the data is summarized as follows:

[1551] json

[1552] {

[1553] "user_id": "12345",

[1554] "preferences": {

[1555] "work_hours": "9:00-18:00",

[1556] "lunch_break": "12:00-13:00",

[1557] "preferred_meeting_times": ["10:00-11:00", "15:00-16:00"]

[1558] },

[1559] "emotion": "stress",

[1560] "existing_schedule": {}

[1561] }

[1562] Step 4:

[1563] The device sends this compiled JSON data to the server as an HTTP POST request. The endpoint is, for example, / schedule.

[1564] Step 5:

[1565] The server receives the HTTP POST request sent from the device. The server obtains the JSON format data from the request body, parses it, and converts it to the internal data format.

[1566] Step 6:

[1567] The server passes the analyzed data to the generative model and emotion engine. The generative model generates a schedule based on the user's patterns and preferences, and the emotion engine further adjusts the generated schedule using the user's emotion information.

[1568] Step 7:

[1569] The generative model first generates a standard schedule based on user input data. This schedule balances task priority, duration, and break times. For example, the following schedule might be generated:

[1570] 09:00 - 09:30: Check email

[1571] 09:30 - 10:00: Preparation of materials

[1572] 10:00 - 11:00: Meeting 1

[1573] 11:00 - 12:00: Progress of Task A

[1574] 12:00 - 13:00: Lunch break

[1575] 13:00 - 15:00: Progress of Task B

[1576] 15:00 - 16:00: Meeting 2

[1577] 16:00 - 18:00: Progress of Task C

[1578] Step 8:

[1579] The emotion engine adjusts the schedule based on the standard schedule according to the user's emotion information. For example, if the emotion engine determines that the user's emotion is "stress," it adjusts the schedule to increase break time and relaxation time. The adjusted schedule will look like this:

[1580] 09:00 - 09:30: Check email

[1581] 09:30 - 10:00: Preparation of materials

[1582] 10:00 - 11:00: Meeting 1

[1583] 11:00 - 12:00: Progress of Task A

[1584] 12:00 - 13:00: Lunch break

[1585] 13:00 - 14:00: Relaxation time

[1586] 14:00 - 15:00: Progress of Task B

[1587] 15:00 - 16:00: Meeting 2

[1588] 16:00 - 17:00: Progress of Task C

[1589] 17:00 - 18:00: Easy stress relief activities

[1590] Step 9:

[1591] The server converts the schedule generated and adjusted by the generative model and emotion engine into JSON format and sends it to the terminal as an HTTP response.

[1592] Step 10:

[1593] The terminal parses the HTTP response received from the server and converts the JSON data into an internal data format. After obtaining the new schedule information, the terminal displays the schedule in an easy-to-read format for the user.

[1594] Step 11:

[1595] The user can check the new schedule displayed on the terminal and efficiently carry out daily tasks based on the generated schedule.

[1596] Step 12:

[1597] Based on user feedback and actual schedule history, the generative model and emotion engine further learn and reflect this in the next schedule generation, resulting in a more personalized schedule that optimally reflects the user's emotional state.

[1598] Example 2

[1599] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1600] Conventional schedule generation systems only analyze user patterns and preferences, but are unable to consider the user's emotional state. As a result, they may generate schedules that ignore the user's stress and fatigue, making it difficult for the user to complete tasks efficiently. Furthermore, they lacked a learning function that utilizes user feedback and schedule history, making it difficult to generate schedules that are optimized for individual users' needs.

[1601] 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.

[1602] In this invention, the server includes means for analyzing a user's patterns and emotional state using a generative model and an emotion recognition engine to generate an optimal schedule, means for acquiring data entered by the user and emotional information collected by the emotion recognition engine at a terminal and transmitting the data to the server, and means for receiving a schedule generated based on the analyzed data by the server and displaying it to the user. This makes it possible to generate an optimal schedule that reflects the user's emotional state, and furthermore, a learning function based on user feedback and schedule history makes it possible to provide a more personalized schedule for the user.

[1603] A "generative model" is an algorithm that generates an optimal schedule based on a user's patterns and preferences.

[1604] An "emotion recognition engine" is a software component that recognizes and analyzes a user's emotional state in real time.

[1605] A "pattern" is a consistent tendency or habit based on a user's behavior or preferences.

[1606] "Preferences" refer to tasks and time allocations that the user particularly prefers.

[1607] A "schedule" is a plan that arranges a user's daily tasks and events in time.

[1608] A "terminal" is an electronic device that allows a user to input and display information.

[1609] "Server" refers to the central computer system that analyzes data sent from the terminals and generates and adjusts schedules.

[1610] "Data transmission" refers to the process of sending information from a terminal to a server.

[1611] "Data analysis" refers to the process by which the server processes the data it receives to extract useful information.

[1612] "Feedback" refers to opinions and ratings that users provide to a system, which the system uses to learn and improve based on that information.

[1613] "Learning function" refers to the system's ability to improve future performance based on past data and feedback.

[1614] MODE FOR CARRYING OUT THE INVENTION

[1615] This invention is a system that uses a generative model and an emotion recognition engine to analyze a user's patterns, preferences, and emotional state to generate an optimal schedule. This system comprehensively analyzes data entered by the user and emotional information collected by the emotion recognition engine, generates an optimal schedule on the server, and displays it on the terminal.

[1616] First, the user inputs information related to their schedule via their device. Specifically, the user enters information such as "work hours," "lunch time," and "priority meeting times" into an input form on the device. The emotion recognition engine then recognizes the user's emotions in real time and collects that information. For example, the device's camera can be used to analyze facial expressions and extract emotional information from voice data.

[1617] The device converts the information entered by the user and the emotion data collected by the emotion recognition engine into JSON format and sends it to the server using an HTTP request, for example, as a POST request to "https: / / server.url / schedule."

[1618] The server analyzes the received data and integrates the outputs of the generative model and the emotion recognition engine. The generative model generates an initial schedule based on the user's patterns and preferences. The emotion recognition engine then adjusts the generated schedule based on the user's emotional state. For example, if the user is feeling stressed, the engine may add relaxation time or breaks to the generated schedule.

[1619] The server converts the final adjusted schedule into JSON format and sends it to the device as an HTTP response. The device then analyzes the received data and displays the schedule in a user-friendly format, enabling users to plan and complete their daily tasks based on an efficient and balanced schedule.

[1620] Furthermore, user feedback and actual schedule history are sent to the server, and the generative model and emotion recognition engine use this data for training, which is reflected in the next schedule generation, providing a more personalized schedule for the user.

[1621] As a concrete example, suppose a user enters the following information into a terminal:

[1622] Working hours: 9:00-18:00

[1623] Lunchtime: 12:00-13:00

[1624] Preferred meeting times: 10:00-11:00, 15:00-16:00

[1625] If the emotion recognition engine recognizes the user's face and determines that the current emotion is "stress," the generative model on the server will generate the following schedule:

[1626] 09:00 - 09:30: Check email

[1627] 09:30 - 10:00: Preparation of materials

[1628] 10:00 - 11:00: Meeting 1

[1629] 11:00 - 12:00: Progress of Task A

[1630] 12:00 - 13:00: Lunch break

[1631] 13:00 - 14:00: Relaxation time

[1632] 14:00 - 15:00: Progress of Task B

[1633] 15:00 - 16:00: Meeting 2

[1634] 16:00 - 17:00: Progress of Task C

[1635] 17:00 - 18:00: Easy stress relief activities

[1636] An example prompt is:

[1637] "Generate the best schedule for your users based on their current situation. Create a schedule based on the following information:

[1638] Working hours: 9:00-18:00

[1639] Lunchtime: 12:00-13:00

[1640] Preferred meeting times: 10:00-11:00, 15:00-16:00

[1641] Furthermore, the emotion recognition engine determined that the user's emotion was 'stress'.

[1642] In this way, the system provides an optimal schedule that takes into account the user's patterns and preferences as well as their emotional state, improving their productivity and quality of life.

[1643] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1644] Step 1:

[1645] User Data Input

[1646] The user enters schedule-related information such as "work hours," "lunchtime," and "preferred meeting times" into an input form on the terminal. Specifically, the user enters "work hours" as "9:00-18:00," "lunchtime" as "12:00-13:00," and "preferred meeting times" as "10:00-11:00, 15:00-16:00." After entering the information, the user presses the send button. The input in this step is schedule information manually entered by the user, and the output is temporary data stored in the terminal.

[1647] Step 2:

[1648] Emotional Data Collection

[1649] The device collects the user's emotional data using an emotion recognition engine. The device's camera is used to analyze the user's facial expressions in real time, and the emotion recognition engine recognizes "stress" from the facial expressions. If there is voice input, the device extracts emotions from the voice data. The input for this step is the user's facial and voice data, and the output is emotional data analyzed by the emotion recognition engine.

[1650] Step 3:

[1651] Data transmission

[1652] The device combines the schedule information entered by the user with the emotion data collected by the emotion recognition engine and converts it into JSON format. It then sends the data to the server using an HTTP request. For example, the destination is a POST request to "https: / / server.url / schedule." The input of this step is the schedule information and emotion data, and the output is the data converted into JSON format.

[1653] Step 4:

[1654] Data analysis

[1655] The server parses the received JSON data and extracts the user's schedule information and emotional state. This analysis is typically performed using programming languages ​​such as Python or Java. The input for this step is JSON-formatted data, and the output is the parsed schedule information and emotional data.

[1656] Step 5:

[1657] Schedule Generation

[1658] The server's generative model generates an initial schedule based on the analyzed schedule information and user patterns. For example, it arranges tasks such as "09:00-09:30: Check email" and "09:30-10:00: Prepare documents." The input of this step is the analyzed schedule information, and the output is an initial schedule proposal.

[1659] Step 6:

[1660] Schedule adjustment

[1661] The generated initial schedule is adjusted based on the output of the emotion recognition engine. For example, if the user is recognized as "stressed," relaxation time or rest time is added to the schedule. The input of this step is the initial schedule and emotion data, and the output is the adjusted final schedule.

[1662] Step 7:

[1663] Scheduled Sending

[1664] The server converts the adjusted final schedule into JSON format and sends it to the terminal as an HTTP response. The input of this step is the adjusted final schedule, and the output is the transmission of JSON format data.

[1665] Step 8:

[1666] Schedule Display

[1667] The device parses the received JSON data and displays the schedule in a visually easy-to-understand format. For example, it may use the in-app calendar function to display the schedule in a color-coded format. The input of this step is the JSON data received from the server, and the output is a visual schedule display that the user can view.

[1668] Step 9:

[1669] Feedback gathering and learning

[1670] The user enters feedback on the task they performed into a feedback form within the device app. For example, they answer questions such as, "Was today's schedule appropriate?" The device sends this feedback to the server, and the server's generative model and emotion recognition engine use the data for training. The input of this step is the user's feedback data, and the output is the trained generative model and emotion recognition engine.

[1671] As a result, the system improves users' productivity and quality of life by providing an optimal schedule that takes into account their emotional state as well as their patterns and preferences.

[1672] (Application example 2)

[1673] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1674] In modern society, stress and busyness make it difficult for users to efficiently manage their schedules. Furthermore, there is a lack of systems that can recommend optimal content and tasks according to a user's emotional state, which means that users are unable to find appropriate ways to relax or progress with their work according to their emotions.

[1675] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing a user's patterns and preferences using a generative model and generating an optimal schedule, terminal means for transmitting collected data to the server, terminal means for receiving the generated schedule and displaying it to the user, means for analyzing the user's emotional state using an emotion engine, and means for adjusting the schedule based on the emotional state. This allows the user to obtain an optimal schedule based on not only their own patterns and preferences but also their emotional state recognized in real time. Furthermore, appropriate content and relaxation methods are simultaneously suggested based on the user's emotional state, allowing them to perform daily tasks efficiently and comfortably.

[1676] A "generative model" is an algorithm that takes data as input, analyzes user patterns and preferences, and generates output tailored to a specific purpose.

[1677] A "pattern" is a recurring feature that indicates a user's tendencies in behavior or choices.

[1678] "Preferences" are specific activities, content, or options that a user prefers.

[1679] An "optimal schedule" is a timetable or plan that maximizes a user's efficiency and comfort, based on the user's patterns, preferences, and emotional state.

[1680] "Means" refers to a device, system, algorithm, or other technical means used to achieve a specific purpose.

[1681] A "server" is a computer system that provides a set of computing resources for storing, analyzing, and processing data.

[1682] A "terminal" is a device or apparatus that a user directly operates to input, display, and transmit information.

[1683] An "emotion engine" is an algorithm or system that analyzes a user's facial expressions, voice, and behavioral data to identify their emotional state in real time.

[1684] "Collecting" refers to the act or process of gathering necessary data, which in the present invention refers to data relating to the user's emotional state, behavioral patterns, and preferences.

[1685] "Analysis" is the process of examining collected data in detail and deriving meaning and trends from it.

[1686] "Tuning" is the act or process of changing components to optimize them based on specific conditions.

[1687] "Relaxation methods" refer to specific means or activities for reducing the user's stress and resting the mind and body.

[1688] "Content" refers to the information media consumed by users, including, for example, movies, music, videos, etc.

[1689] This invention is a system that uses a generative model and an emotion engine to analyze a user's patterns, preferences, and emotional state to generate an optimal schedule. This system comprehensively analyzes data entered by the user and emotional information collected by the emotion engine, generates an optimal schedule for the user on the server, and displays it on the terminal.

[1690] First, the user inputs information related to their schedule via their device. Specifically, the user enters information such as "work hours," "lunch time," and "priority meeting times" into an input form on the device. The emotion engine then recognizes the user's emotions in real time and collects that information. For example, it can analyze facial expressions using the user's camera or extract emotions from their voice.

[1691] The device converts this information into JSON format and sends it to the server. The server analyzes the data and integrates the output of the generative model and emotion engine. The generative model generates a schedule based on the user's patterns and preferences, and the emotion engine adjusts the schedule according to the user's emotional state.

[1692] The server uses a machine learning algorithm as a generative model to learn the user's past behavioral data and patterns. Specifically, a deep learning model (e.g., TensorFlow) can be used. Furthermore, a library for analyzing the user's emotional state in real time (e.g., OpenCV, Microsoft Azure's Emotion API) can be used as an emotion engine.

[1693] For example, if a user is feeling stressed, the output of the emotion engine is fed back to the generative model, which adjusts the schedule to increase relaxation and rest periods. In this way, a schedule is generated to optimize the user's emotional state. The server converts the generated schedule into JSON format and sends it to the device as an HTTP response. The device analyzes the received data and displays the new schedule in an easy-to-read format for the user. The user can plan and execute daily tasks based on this schedule.

[1694] As a concrete example, consider the case where a user launches a terminal application and inputs their "work hours" as "9:00-18:00," "lunchtime" as "12:00-13:00," and "priority meeting times" as "10:00-11:00, 15:00-16:00." Furthermore, suppose the emotion engine recognizes the user's face and determines their current emotion as "stressed." The server's generative model integrates the input information and the emotion engine's results to generate the following schedule:

[1695] ---

[1696] Example prompt sentence:

[1697] If the user is "stressed", generate a schedule like this:

[1698] 09:00 - 10:00: Relaxation music

[1699] 10:00 - 11:00: Comedy movie

[1700] 11:00 - 12:00: Light fitness videos

[1701] 12:00 - 13:00: Lunch break

[1702] 13:00 - 14:00: Reflection and journaling

[1703] 14:00 - 15:00: Music appreciation (selected songs)

[1704] 15:00 - 16:00: Meditation video

[1705] Based on this schedule, users can take effective actions that are tailored to their own emotions and patterns.

[1706] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1707] Step 1:

[1708] A user inputs information related to his or her schedule (such as "work hours," "lunch time," and "priority meeting times") via a terminal. This information is entered into the terminal using an input form. The input data is used as the initial data required to generate a schedule.

[1709] Input: Schedule-related information (work time, lunch time, meeting time, etc.)

[1710] Output: Structured input data

[1711] Step 2:

[1712] The device uses the user's camera and microphone to analyze the user's facial expressions and voice in real time, and the emotion engine recognizes the user's emotional state. This emotion information is fed back to the generative model.

[1713] Input: Real-time data from camera and microphone

[1714] Output: Parsed emotional state information

[1715] Step 3:

[1716] The device converts the collected schedule information and emotional state information into JSON format and sends it to the server. This data becomes the initial dataset for schedule generation.

[1717] Input: Structured input data and parsed emotional state information

[1718] Output: JSON format data

[1719] Step 4:

[1720] The server analyzes the received data and uses a generative model to analyze the user's patterns and preferences. The generative model uses a deep learning-based model (e.g., TensorFlow). The generative model learns the user's behavioral patterns from past data and generates an optimal schedule.

[1721] Input: JSON format data

[1722] Output: An initial schedule that reflects user patterns and preferences

[1723] Step 5:

[1724] The server then feeds back the analysis results of the emotion engine to the generative model and adjusts the schedule based on the user's emotional state. For example, if the user is feeling stressed, the schedule may be adjusted to increase relaxation time.

[1725] Input: Initial schedule, emotional state information

[1726] Output: An optimized schedule that reflects emotional state

[1727] Step 6:

[1728] The server converts the generated optimized schedule into JSON format and sends it to the terminal as an HTTP response. The optimized schedule is structured in a format that is visually easy for users to understand.

[1729] Input: Optimized schedule reflecting emotional state

[1730] Output: Response data in JSON format

[1731] Step 7:

[1732] The device analyzes the received data and displays the schedule in an easy-to-read format for the user, who can then plan and execute their daily tasks.

[1733] Input: Response data in JSON format

[1734] Output: A visual representation of the schedule

[1735] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1736] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1737] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1738] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1739] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1740] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1741] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1742] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1743] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1744] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1745] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1746] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1747] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1748] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1749] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1750] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1751] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1752] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1753] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1754] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1755] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1756] The following is further disclosed regarding the above embodiment.

[1757] (Claim 1)

[1758] A means for analyzing user patterns and preferences using a generative model to generate an optimal schedule;

[1759] a terminal means for transmitting the collected data to a server;

[1760] a terminal means for receiving the generated schedule and displaying it to a user;

[1761] A system including:

[1762] (Claim 2)

[1763] 10. The system of claim 1, wherein the generated schedule takes into account the user's work hours, break times, and preferred meeting times.

[1764] (Claim 3)

[1765] The system of claim 1, wherein an initial investment is made to develop software, train models, and design user experiences.

[1766] "Example 1"

[1767] (Claim 1)

[1768] A means for analyzing user patterns and preferences using a generative model to generate an optimal schedule;

[1769] A terminal means for a user to input schedule-related information and transmit it to a server in JSON format;

[1770] The server analyzes the received data, executes the generative model to generate a schedule, and returns the results in JSON format to the terminal.

[1771] a terminal means for receiving the generated schedule and visually displaying it to a user;

[1772] a means of further training the generative model based on user feedback; and

[1773] A system including:

[1774] (Claim 2)

[1775] 2. The system according to claim 1, wherein the generated schedule is generated by adjusting task priorities, required times, and break times in a well-balanced manner based on data input by the user.

[1776] (Claim 3)

[1777] The system of claim 1, wherein an initial investment is made to develop software, train models, and design user experiences.

[1778] "Application Example 1"

[1779] New Claims:

[1780] (Claim 1)

[1781] A means for analyzing user patterns and preferences using a generative model to generate an optimal schedule;

[1782] a terminal means for transmitting the collected data to a server;

[1783] a terminal means for receiving the generated schedule and displaying it to a user;

[1784] a means for generating and optimizing a task schedule for a factory robot;

[1785] A system including:

[1786] (Claim 2)

[1787] 2. The system according to claim 1, wherein the generated schedule takes into consideration the user's work hours, break times, preferred meeting times, and the tasks, priorities, and break times of the factory robots.

[1788] (Claim 3)

[1789] The system of claim 1, which provides software development, model training, and user experience design through an initial investment, while supporting efficient operation of factory robots.

[1790] "Example 2: Combining Emotion Engines"

[1791] (Claim 1)

[1792] a means for analyzing a user's patterns and emotional states using a generative model and an emotion recognition engine to generate an optimal schedule;

[1793] A means for acquiring data input by a user and emotion information collected by an emotion recognition engine at a terminal and transmitting the data to a server;

[1794] means for receiving a generated schedule based on the analyzed data at the server and displaying it to a user;

[1795] A system including:

[1796] (Claim 2)

[1797] 10. The system of claim 1, wherein the generated schedule takes into account the user's work hours, break times, preferred meeting times, and the user's emotional state.

[1798] (Claim 3)

[1799] 10. The system of claim 1, wherein the generative model and emotion recognition engine learn from user feedback and actual schedule history.

[1800] "Application example 2 when combining emotion engines"

[1801] (Claim 1)

[1802] A means for analyzing user patterns and preferences using a generative model to generate an optimal schedule;

[1803] a terminal means for transmitting the collected data to a server;

[1804] a terminal means for receiving the generated schedule and displaying it to a user;

[1805] means for analyzing a user's emotional state using an emotion engine;

[1806] a means for adjusting a schedule based on emotional state;

[1807] A system including:

[1808] (Claim 2)

[1809] 10. The system of claim 1, wherein the generated schedule takes into account the user's work hours, break times, preferred meeting times, and is further modified according to the user's emotional state.

[1810] (Claim 3)

[1811] The system of claim 1, wherein an initial investment is made to develop software, train models, and design user experiences to enhance analysis based on the emotion engine. [Explanation of symbols]

[1812] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for analyzing user patterns and preferences using a generative model to generate an optimal schedule; a terminal means for transmitting the collected data to a server; a terminal means for receiving the generated schedule and displaying it to a user; A system including:

2. 2. The system of claim 1, wherein the generated schedule takes into account the user's work hours, break times, and preferred meeting times.

3. The system of claim 1 , wherein an initial investment is made to develop software, train models, and design user experiences.

Images